2658 files changed, 51695 insertions, 20335 deletions

diff --git a/.clang-format b/.clang-format
index 6ec5558b516b..e92e6dd1780d 100644
--- a/.clang-format
+++ b/.clang-format
@@ -142,10 +142,13 @@ ForEachMacros:
   - 'for_each_card_auxs'
   - 'for_each_card_auxs_safe'
   - 'for_each_card_components'
+  - 'for_each_card_dapms'
   - 'for_each_card_pre_auxs'
   - 'for_each_card_prelinks'
   - 'for_each_card_rtds'
   - 'for_each_card_rtds_safe'
+  - 'for_each_card_widgets'
+  - 'for_each_card_widgets_safe'
   - 'for_each_cgroup_storage_type'
   - 'for_each_child_of_node'
   - 'for_each_clear_bit'
@@ -160,6 +163,7 @@ ForEachMacros:
   - 'for_each_cpu_and'
   - 'for_each_cpu_not'
   - 'for_each_cpu_wrap'
+  - 'for_each_dapm_widgets'
   - 'for_each_dev_addr'
   - 'for_each_dev_scope'
   - 'for_each_displayid_db'
@@ -170,7 +174,6 @@ ForEachMacros:
   - 'for_each_dpcm_fe'
   - 'for_each_drhd_unit'
   - 'for_each_dss_dev'
-  - 'for_each_efi_handle'
   - 'for_each_efi_memory_desc'
   - 'for_each_efi_memory_desc_in_map'
   - 'for_each_element'
@@ -191,6 +194,7 @@ ForEachMacros:
   - 'for_each_ip_tunnel_rcu'
   - 'for_each_irq_nr'
   - 'for_each_link_codecs'
+  - 'for_each_link_cpus'
   - 'for_each_link_platforms'
   - 'for_each_lru'
   - 'for_each_matching_node'
@@ -250,6 +254,7 @@ ForEachMacros:
   - 'for_each_pci_bridge'
   - 'for_each_pci_dev'
   - 'for_each_pci_msi_entry'
+  - 'for_each_pcm_streams'
   - 'for_each_populated_zone'
   - 'for_each_possible_cpu'
   - 'for_each_present_cpu'
@@ -260,9 +265,12 @@ ForEachMacros:
   - 'for_each_property_of_node'
   - 'for_each_registered_fb'
   - 'for_each_reserved_mem_region'
-  - 'for_each_rtd_codec_dai'
-  - 'for_each_rtd_codec_dai_rollback'
+  - 'for_each_rtd_codec_dais'
+  - 'for_each_rtd_codec_dais_rollback'
   - 'for_each_rtd_components'
+  - 'for_each_rtd_cpu_dais'
+  - 'for_each_rtd_cpu_dais_rollback'
+  - 'for_each_rtd_dais'
   - 'for_each_set_bit'
   - 'for_each_set_bit_from'
   - 'for_each_set_clump8'
@@ -334,6 +342,7 @@ ForEachMacros:
   - 'klp_for_each_object'
   - 'klp_for_each_object_safe'
   - 'klp_for_each_object_static'
+  - 'kunit_suite_for_each_test_case'
   - 'kvm_for_each_memslot'
   - 'kvm_for_each_vcpu'
   - 'list_for_each'
@@ -387,6 +396,7 @@ ForEachMacros:
   - 'of_property_for_each_string'
   - 'of_property_for_each_u32'
   - 'pci_bus_for_each_resource'
+  - 'pcm_for_each_format'
   - 'ping_portaddr_for_each_entry'
   - 'plist_for_each'
   - 'plist_for_each_continue'
@@ -482,7 +492,7 @@ KeepEmptyLinesAtTheStartOfBlocks: false
 MacroBlockBegin: ''
 MacroBlockEnd: ''
 MaxEmptyLinesToKeep: 1
-NamespaceIndentation: Inner
+NamespaceIndentation: None
 #ObjCBinPackProtocolList: Auto # Unknown to clang-format-5.0
 ObjCBlockIndentWidth: 8
 ObjCSpaceAfterProperty: true
diff --git a/.mailmap b/.mailmap
index 09ae92771030..c69d9c734fb5 100644
--- a/.mailmap
+++ b/.mailmap
@@ -291,6 +291,8 @@ Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
 Takashi YOSHII <takashi.yoshii.zj@renesas.com>
 Will Deacon <will@kernel.org> <will.deacon@arm.com>
+Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de>
+Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de>
 Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>
diff --git a/Documentation/ABI/testing/debugfs-hisi-hpre b/Documentation/ABI/testing/debugfs-hisi-hpre
index ec4a79e3a807..b4be5f1db4b7 100644
--- a/Documentation/ABI/testing/debugfs-hisi-hpre
+++ b/Documentation/ABI/testing/debugfs-hisi-hpre
@@ -33,7 +33,7 @@ Contact:        linux-crypto@vger.kernel.org
 Description:    Dump debug registers from the HPRE.
 		Only available for PF.
 
-What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/qm_regs
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/regs
 Date:           Sep 2019
 Contact:        linux-crypto@vger.kernel.org
 Description:    Dump debug registers from the QM.
@@ -44,14 +44,97 @@ What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/current_q
 Date:           Sep 2019
 Contact:        linux-crypto@vger.kernel.org
 Description:    One QM may contain multiple queues. Select specific queue to
-		show its debug registers in above qm_regs.
+		show its debug registers in above regs.
 		Only available for PF.
 
 What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/clear_enable
 Date:           Sep 2019
 Contact:        linux-crypto@vger.kernel.org
-Description:    QM debug registers(qm_regs) read clear control. 1 means enable
+Description:    QM debug registers(regs) read clear control. 1 means enable
 		register read clear, otherwise 0.
 		Writing to this file has no functional effect, only enable or
 		disable counters clear after reading of these registers.
 		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/err_irq
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of invalid interrupts for
+		QM task completion.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/aeq_irq
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of QM async event queue interrupts.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/abnormal_irq
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of interrupts for QM abnormal event.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/create_qp_err
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of queue allocation errors.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/mb_err
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of failed QM mailbox commands.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/qm/status
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the status of the QM.
+		Four states: initiated, started, stopped and closed.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/hpre_dfx/send_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of sent requests.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/hpre_dfx/recv_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of received requests.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/hpre_dfx/send_busy_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of requests sent
+		with returning busy.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/hpre_dfx/send_fail_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of completed but error requests.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/hpre_dfx/invalid_req_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of invalid requests being received.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/hpre_dfx/overtime_thrhld
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Set the threshold time for counting the request which is
+		processed longer than the threshold.
+		0: disable(default), 1: 1 microsecond.
+		Available for both PF and VF, and take no other effect on HPRE.
+
+What:           /sys/kernel/debug/hisi_hpre/<bdf>/hpre_dfx/over_thrhld_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of time out requests.
+		Available for both PF and VF, and take no other effect on HPRE.
diff --git a/Documentation/ABI/testing/debugfs-hisi-sec b/Documentation/ABI/testing/debugfs-hisi-sec
index 06adb899495e..85feb4408e0f 100644
--- a/Documentation/ABI/testing/debugfs-hisi-sec
+++ b/Documentation/ABI/testing/debugfs-hisi-sec
@@ -1,10 +1,4 @@
-What:           /sys/kernel/debug/hisi_sec/<bdf>/sec_dfx
-Date:           Oct 2019
-Contact:        linux-crypto@vger.kernel.org
-Description:    Dump the debug registers of SEC cores.
-		Only available for PF.
-
-What:           /sys/kernel/debug/hisi_sec/<bdf>/clear_enable
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/clear_enable
 Date:           Oct 2019
 Contact:        linux-crypto@vger.kernel.org
 Description:    Enabling/disabling of clear action after reading
@@ -12,7 +6,7 @@ Description:    Enabling/disabling of clear action after reading
 		0: disable, 1: enable.
 		Only available for PF, and take no other effect on SEC.
 
-What:           /sys/kernel/debug/hisi_sec/<bdf>/current_qm
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/current_qm
 Date:           Oct 2019
 Contact:        linux-crypto@vger.kernel.org
 Description:    One SEC controller has one PF and multiple VFs, each function
@@ -20,24 +14,100 @@ Description:    One SEC controller has one PF and multiple VFs, each function
 		qm refers to.
 		Only available for PF.
 
-What:           /sys/kernel/debug/hisi_sec/<bdf>/qm/qm_regs
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/qm/qm_regs
 Date:           Oct 2019
 Contact:        linux-crypto@vger.kernel.org
 Description:    Dump of QM related debug registers.
 		Available for PF and VF in host. VF in guest currently only
 		has one debug register.
 
-What:           /sys/kernel/debug/hisi_sec/<bdf>/qm/current_q
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/qm/current_q
 Date:           Oct 2019
 Contact:        linux-crypto@vger.kernel.org
 Description:    One QM of SEC may contain multiple queues. Select specific
-		queue to show its debug registers in above 'qm_regs'.
+		queue to show its debug registers in above 'regs'.
 		Only available for PF.
 
-What:           /sys/kernel/debug/hisi_sec/<bdf>/qm/clear_enable
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/qm/clear_enable
 Date:           Oct 2019
 Contact:        linux-crypto@vger.kernel.org
 Description:    Enabling/disabling of clear action after reading
 		the SEC's QM debug registers.
 		0: disable, 1: enable.
 		Only available for PF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/qm/err_irq
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of invalid interrupts for
+		QM task completion.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/qm/aeq_irq
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of QM async event queue interrupts.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/qm/abnormal_irq
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of interrupts for QM abnormal event.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/qm/create_qp_err
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of queue allocation errors.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/qm/mb_err
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of failed QM mailbox commands.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/qm/status
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the status of the QM.
+		Four states: initiated, started, stopped and closed.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/sec_dfx/send_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of sent requests.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/sec_dfx/recv_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of received requests.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/sec_dfx/send_busy_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of requests sent with returning busy.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/sec_dfx/err_bd_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of BD type error requests
+		to be received.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/sec_dfx/invalid_req_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of invalid requests being received.
+		Available for both PF and VF, and take no other effect on SEC.
+
+What:           /sys/kernel/debug/hisi_sec2/<bdf>/sec_dfx/done_flag_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of completed but marked error requests
+		to be received.
+		Available for both PF and VF, and take no other effect on SEC.
diff --git a/Documentation/ABI/testing/debugfs-hisi-zip b/Documentation/ABI/testing/debugfs-hisi-zip
index a7c63e6c4bc3..3034a2bf99ca 100644
--- a/Documentation/ABI/testing/debugfs-hisi-zip
+++ b/Documentation/ABI/testing/debugfs-hisi-zip
@@ -26,7 +26,7 @@ Description:    One ZIP controller has one PF and multiple VFs, each function
 		has a QM. Select the QM which below qm refers to.
 		Only available for PF.
 
-What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/qm_regs
+What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/regs
 Date:           Nov 2018
 Contact:        linux-crypto@vger.kernel.org
 Description:    Dump of QM related debug registers.
@@ -37,14 +37,78 @@ What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/current_q
 Date:           Nov 2018
 Contact:        linux-crypto@vger.kernel.org
 Description:    One QM may contain multiple queues. Select specific queue to
-		show its debug registers in above qm_regs.
+		show its debug registers in above regs.
 		Only available for PF.
 
 What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/clear_enable
 Date:           Nov 2018
 Contact:        linux-crypto@vger.kernel.org
-Description:    QM debug registers(qm_regs) read clear control. 1 means enable
+Description:    QM debug registers(regs) read clear control. 1 means enable
 		register read clear, otherwise 0.
 		Writing to this file has no functional effect, only enable or
 		disable counters clear after reading of these registers.
 		Only available for PF.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/err_irq
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of invalid interrupts for
+		QM task completion.
+		Available for both PF and VF, and take no other effect on ZIP.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/aeq_irq
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of QM async event queue interrupts.
+		Available for both PF and VF, and take no other effect on ZIP.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/abnormal_irq
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of interrupts for QM abnormal event.
+		Available for both PF and VF, and take no other effect on ZIP.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/create_qp_err
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of queue allocation errors.
+		Available for both PF and VF, and take no other effect on ZIP.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/mb_err
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the number of failed QM mailbox commands.
+		Available for both PF and VF, and take no other effect on ZIP.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/qm/status
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the status of the QM.
+		Four states: initiated, started, stopped and closed.
+		Available for both PF and VF, and take no other effect on ZIP.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/zip_dfx/send_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of sent requests.
+		Available for both PF and VF, and take no other effect on ZIP.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/zip_dfx/recv_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of received requests.
+		Available for both PF and VF, and take no other effect on ZIP.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/zip_dfx/send_busy_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of requests received
+		with returning busy.
+		Available for both PF and VF, and take no other effect on ZIP.
+
+What:           /sys/kernel/debug/hisi_zip/<bdf>/zip_dfx/err_bd_cnt
+Date:           Apr 2020
+Contact:        linux-crypto@vger.kernel.org
+Description:    Dump the total number of BD type error requests
+		to be received.
+		Available for both PF and VF, and take no other effect on ZIP.
diff --git a/Documentation/ABI/testing/dev-kmsg b/Documentation/ABI/testing/dev-kmsg
index f307506eb54c..1e6c28b1942b 100644
--- a/Documentation/ABI/testing/dev-kmsg
+++ b/Documentation/ABI/testing/dev-kmsg
@@ -56,6 +56,11 @@ Description:	The /dev/kmsg character device node provides userspace access
 		  seek after the last record available at the time
 		  the last SYSLOG_ACTION_CLEAR was issued.
 
+		Due to the record nature of this interface with a "read all"
+		behavior and the specific positions each seek operation sets,
+		SEEK_CUR is not supported, returning -ESPIPE (invalid seek) to
+		errno whenever requested.
+
 		The output format consists of a prefix carrying the syslog
 		prefix including priority and facility, the 64 bit message
 		sequence number and the monotonic timestamp in microseconds,
diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst
index fd5e2cbc4935..75b8ca007a11 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.rst
+++ b/Documentation/RCU/Design/Requirements/Requirements.rst
@@ -1943,56 +1943,27 @@ invoked from a CPU-hotplug notifier.
 Scheduler and RCU
 ~~~~~~~~~~~~~~~~~
 
-RCU depends on the scheduler, and the scheduler uses RCU to protect some
-of its data structures. The preemptible-RCU ``rcu_read_unlock()``
-implementation must therefore be written carefully to avoid deadlocks
-involving the scheduler's runqueue and priority-inheritance locks. In
-particular, ``rcu_read_unlock()`` must tolerate an interrupt where the
-interrupt handler invokes both ``rcu_read_lock()`` and
-``rcu_read_unlock()``. This possibility requires ``rcu_read_unlock()``
-to use negative nesting levels to avoid destructive recursion via
-interrupt handler's use of RCU.
-
-This scheduler-RCU requirement came as a `complete
-surprise <https://lwn.net/Articles/453002/>`__.
-
-As noted above, RCU makes use of kthreads, and it is necessary to avoid
-excessive CPU-time accumulation by these kthreads. This requirement was
-no surprise, but RCU's violation of it when running context-switch-heavy
-workloads when built with ``CONFIG_NO_HZ_FULL=y`` `did come as a
-surprise
+RCU makes use of kthreads, and it is necessary to avoid excessive CPU-time
+accumulation by these kthreads. This requirement was no surprise, but
+RCU's violation of it when running context-switch-heavy workloads when
+built with ``CONFIG_NO_HZ_FULL=y`` `did come as a surprise
 [PDF] <http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf>`__.
 RCU has made good progress towards meeting this requirement, even for
 context-switch-heavy ``CONFIG_NO_HZ_FULL=y`` workloads, but there is
 room for further improvement.
 
-It is forbidden to hold any of scheduler's runqueue or
-priority-inheritance spinlocks across an ``rcu_read_unlock()`` unless
-interrupts have been disabled across the entire RCU read-side critical
-section, that is, up to and including the matching ``rcu_read_lock()``.
-Violating this restriction can result in deadlocks involving these
-scheduler spinlocks. There was hope that this restriction might be
-lifted when interrupt-disabled calls to ``rcu_read_unlock()`` started
-deferring the reporting of the resulting RCU-preempt quiescent state
-until the end of the corresponding interrupts-disabled region.
-Unfortunately, timely reporting of the corresponding quiescent state to
-expedited grace periods requires a call to ``raise_softirq()``, which
-can acquire these scheduler spinlocks. In addition, real-time systems
-using RCU priority boosting need this restriction to remain in effect
-because deferred quiescent-state reporting would also defer deboosting,
-which in turn would degrade real-time latencies.
-
-In theory, if a given RCU read-side critical section could be guaranteed
-to be less than one second in duration, holding a scheduler spinlock
-across that critical section's ``rcu_read_unlock()`` would require only
-that preemption be disabled across the entire RCU read-side critical
-section, not interrupts. Unfortunately, given the possibility of vCPU
-preemption, long-running interrupts, and so on, it is not possible in
-practice to guarantee that a given RCU read-side critical section will
-complete in less than one second. Therefore, as noted above, if
-scheduler spinlocks are held across a given call to
-``rcu_read_unlock()``, interrupts must be disabled across the entire RCU
-read-side critical section.
+There is no longer any prohibition against holding any of
+scheduler's runqueue or priority-inheritance spinlocks across an
+``rcu_read_unlock()``, even if interrupts and preemption were enabled
+somewhere within the corresponding RCU read-side critical section.
+Therefore, it is now perfectly legal to execute ``rcu_read_lock()``
+with preemption enabled, acquire one of the scheduler locks, and hold
+that lock across the matching ``rcu_read_unlock()``.
+
+Similarly, the RCU flavor consolidation has removed the need for negative
+nesting.  The fact that interrupt-disabled regions of code act as RCU
+read-side critical sections implicitly avoids earlier issues that used
+to result in destructive recursion via interrupt handler's use of RCU.
 
 Tracing and RCU
 ~~~~~~~~~~~~~~~
diff --git a/Documentation/admin-guide/device-mapper/dm-integrity.rst b/Documentation/admin-guide/device-mapper/dm-integrity.rst
index c00f9f11e3f3..8439d2ae689b 100644
--- a/Documentation/admin-guide/device-mapper/dm-integrity.rst
+++ b/Documentation/admin-guide/device-mapper/dm-integrity.rst
@@ -182,12 +182,15 @@ fix_padding
 	space-efficient. If this option is not present, large padding is
 	used - that is for compatibility with older kernels.
 
-
-The journal mode (D/J), buffer_sectors, journal_watermark, commit_time can
-be changed when reloading the target (load an inactive table and swap the
-tables with suspend and resume). The other arguments should not be changed
-when reloading the target because the layout of disk data depend on them
-and the reloaded target would be non-functional.
+allow_discards
+	Allow block discard requests (a.k.a. TRIM) for the integrity device.
+	Discards are only allowed to devices using internal hash.
+
+The journal mode (D/J), buffer_sectors, journal_watermark, commit_time and
+allow_discards can be changed when reloading the target (load an inactive
+table and swap the tables with suspend and resume). The other arguments
+should not be changed when reloading the target because the layout of disk
+data depend on them and the reloaded target would be non-functional.
 
 
 The layout of the formatted block device:
diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst
index 007a6b86e0ee..e4ee8b2db604 100644
--- a/Documentation/admin-guide/kdump/vmcoreinfo.rst
+++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst
@@ -393,6 +393,12 @@ KERNELOFFSET
 The kernel randomization offset. Used to compute the page offset. If
 KASLR is disabled, this value is zero.
 
+KERNELPACMASK
+-------------
+
+The mask to extract the Pointer Authentication Code from a kernel virtual
+address.
+
 arm
 ===
 
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d81d29b5dda7..4379c6ac3265 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1748,6 +1748,13 @@
 
 	initrd=		[BOOT] Specify the location of the initial ramdisk
 
+	initrdmem=	[KNL] Specify a physical address and size from which to
+			load the initrd. If an initrd is compiled in or
+			specified in the bootparams, it takes priority over this
+			setting.
+			Format: ss[KMG],nn[KMG]
+			Default is 0, 0
+
 	init_on_alloc=	[MM] Fill newly allocated pages and heap objects with
 			zeroes.
 			Format: 0 | 1
@@ -4210,12 +4217,24 @@
 			Duration of CPU stall (s) to test RCU CPU stall
 			warnings, zero to disable.
 
+	rcutorture.stall_cpu_block= [KNL]
+			Sleep while stalling if set.  This will result
+			in warnings from preemptible RCU in addition
+			to any other stall-related activity.
+
 	rcutorture.stall_cpu_holdoff= [KNL]
 			Time to wait (s) after boot before inducing stall.
 
 	rcutorture.stall_cpu_irqsoff= [KNL]
 			Disable interrupts while stalling if set.
 
+	rcutorture.stall_gp_kthread= [KNL]
+			Duration (s) of forced sleep within RCU
+			grace-period kthread to test RCU CPU stall
+			warnings, zero to disable.  If both stall_cpu
+			and stall_gp_kthread are specified, the
+			kthread is starved first, then the CPU.
+
 	rcutorture.stat_interval= [KNL]
 			Time (s) between statistics printk()s.
 
@@ -4286,6 +4305,13 @@
 			only normal grace-period primitives.  No effect
 			on CONFIG_TINY_RCU kernels.
 
+	rcupdate.rcu_task_ipi_delay= [KNL]
+			Set time in jiffies during which RCU tasks will
+			avoid sending IPIs, starting with the beginning
+			of a given grace period.  Setting a large
+			number avoids disturbing real-time workloads,
+			but lengthens grace periods.
+
 	rcupdate.rcu_task_stall_timeout= [KNL]
 			Set timeout in jiffies for RCU task stall warning
 			messages.  Disable with a value less than or equal
@@ -5187,8 +5213,7 @@
 
 	usbcore.old_scheme_first=
 			[USB] Start with the old device initialization
-			scheme,  applies only to low and full-speed devices
-			 (default 0 = off).
+			scheme (default 0 = off).
 
 	usbcore.usbfs_memory_mb=
 			[USB] Memory limit (in MB) for buffers allocated by
diff --git a/Documentation/admin-guide/perf-security.rst b/Documentation/admin-guide/perf-security.rst
index 72effa7c23b9..1307b5274a0f 100644
--- a/Documentation/admin-guide/perf-security.rst
+++ b/Documentation/admin-guide/perf-security.rst
@@ -1,6 +1,6 @@
 .. _perf_security:
 
-Perf Events and tool security
+Perf events and tool security
 =============================
 
 Overview
@@ -42,11 +42,11 @@ categories:
 Data that belong to the fourth category can potentially contain
 sensitive process data. If PMUs in some monitoring modes capture values
 of execution context registers or data from process memory then access
-to such monitoring capabilities requires to be ordered and secured
-properly. So, perf_events/Perf performance monitoring is the subject for
-security access control management [5]_ .
+to such monitoring modes requires to be ordered and secured properly.
+So, perf_events performance monitoring and observability operations are
+the subject for security access control management [5]_ .
 
-perf_events/Perf access control
+perf_events access control
 -------------------------------
 
 To perform security checks, the Linux implementation splits processes
@@ -66,11 +66,25 @@ into distinct units, known as capabilities [6]_ , which can be
 independently enabled and disabled on per-thread basis for processes and
 files of unprivileged users.
 
-Unprivileged processes with enabled CAP_SYS_ADMIN capability are treated
+Unprivileged processes with enabled CAP_PERFMON capability are treated
 as privileged processes with respect to perf_events performance
-monitoring and bypass *scope* permissions checks in the kernel.
-
-Unprivileged processes using perf_events system call API is also subject
+monitoring and observability operations, thus, bypass *scope* permissions
+checks in the kernel. CAP_PERFMON implements the principle of least
+privilege [13]_ (POSIX 1003.1e: 2.2.2.39) for performance monitoring and
+observability operations in the kernel and provides a secure approach to
+perfomance monitoring and observability in the system.
+
+For backward compatibility reasons the access to perf_events monitoring and
+observability operations is also open for CAP_SYS_ADMIN privileged
+processes but CAP_SYS_ADMIN usage for secure monitoring and observability
+use cases is discouraged with respect to the CAP_PERFMON capability.
+If system audit records [14]_ for a process using perf_events system call
+API contain denial records of acquiring both CAP_PERFMON and CAP_SYS_ADMIN
+capabilities then providing the process with CAP_PERFMON capability singly
+is recommended as the preferred secure approach to resolve double access
+denial logging related to usage of performance monitoring and observability.
+
+Unprivileged processes using perf_events system call are also subject
 for PTRACE_MODE_READ_REALCREDS ptrace access mode check [7]_ , whose
 outcome determines whether monitoring is permitted. So unprivileged
 processes provided with CAP_SYS_PTRACE capability are effectively
@@ -82,14 +96,14 @@ performance analysis of monitored processes or a system. For example,
 CAP_SYSLOG capability permits reading kernel space memory addresses from
 /proc/kallsyms file.
 
-perf_events/Perf privileged users
+Privileged Perf users groups
 ---------------------------------
 
 Mechanisms of capabilities, privileged capability-dumb files [6]_ and
-file system ACLs [10]_ can be used to create a dedicated group of
-perf_events/Perf privileged users who are permitted to execute
-performance monitoring without scope limits. The following steps can be
-taken to create such a group of privileged Perf users.
+file system ACLs [10]_ can be used to create dedicated groups of
+privileged Perf users who are permitted to execute performance monitoring
+and observability without scope limits. The following steps can be
+taken to create such groups of privileged Perf users.
 
 1. Create perf_users group of privileged Perf users, assign perf_users
    group to Perf tool executable and limit access to the executable for
@@ -108,30 +122,51 @@ taken to create such a group of privileged Perf users.
    -rwxr-x---  2 root perf_users  11M Oct 19 15:12 perf
 
 2. Assign the required capabilities to the Perf tool executable file and
-   enable members of perf_users group with performance monitoring
+   enable members of perf_users group with monitoring and observability
    privileges [6]_ :
 
 ::
 
-   # setcap "cap_sys_admin,cap_sys_ptrace,cap_syslog=ep" perf
-   # setcap -v "cap_sys_admin,cap_sys_ptrace,cap_syslog=ep" perf
+   # setcap "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf
+   # setcap -v "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf
    perf: OK
    # getcap perf
-   perf = cap_sys_ptrace,cap_sys_admin,cap_syslog+ep
+   perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep
+
+If the libcap installed doesn't yet support "cap_perfmon", use "38" instead,
+i.e.:
+
+::
+
+   # setcap "38,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf
+
+Note that you may need to have 'cap_ipc_lock' in the mix for tools such as
+'perf top', alternatively use 'perf top -m N', to reduce the memory that
+it uses for the perf ring buffer, see the memory allocation section below.
+
+Using a libcap without support for CAP_PERFMON will make cap_get_flag(caps, 38,
+CAP_EFFECTIVE, &val) fail, which will lead the default event to be 'cycles:u',
+so as a workaround explicitly ask for the 'cycles' event, i.e.:
+
+::
+
+  # perf top -e cycles
+
+To get kernel and user samples with a perf binary with just CAP_PERFMON.
 
 As a result, members of perf_users group are capable of conducting
-performance monitoring by using functionality of the configured Perf
-tool executable that, when executes, passes perf_events subsystem scope
-checks.
+performance monitoring and observability by using functionality of the
+configured Perf tool executable that, when executes, passes perf_events
+subsystem scope checks.
 
 This specific access control management is only available to superuser
 or root running processes with CAP_SETPCAP, CAP_SETFCAP [6]_
 capabilities.
 
-perf_events/Perf unprivileged users
+Unprivileged users
 -----------------------------------
 
-perf_events/Perf *scope* and *access* control for unprivileged processes
+perf_events *scope* and *access* control for unprivileged processes
 is governed by perf_event_paranoid [2]_ setting:
 
 -1:
@@ -166,7 +201,7 @@ is governed by perf_event_paranoid [2]_ setting:
      perf_event_mlock_kb locking limit is imposed but ignored for
      unprivileged processes with CAP_IPC_LOCK capability.
 
-perf_events/Perf resource control
+Resource control
 ---------------------------------
 
 Open file descriptors
@@ -227,4 +262,5 @@ Bibliography
 .. [10] `<http://man7.org/linux/man-pages/man5/acl.5.html>`_
 .. [11] `<http://man7.org/linux/man-pages/man2/getrlimit.2.html>`_
 .. [12] `<http://man7.org/linux/man-pages/man5/limits.conf.5.html>`_
-
+.. [13] `<https://sites.google.com/site/fullycapable>`_
+.. [14] `<http://man7.org/linux/man-pages/man8/auditd.8.html>`_
diff --git a/Documentation/admin-guide/pstore-blk.rst b/Documentation/admin-guide/pstore-blk.rst
new file mode 100644
index 000000000000..296d5027787a
--- /dev/null
+++ b/Documentation/admin-guide/pstore-blk.rst
@@ -0,0 +1,243 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+pstore block oops/panic logger
+==============================
+
+Introduction
+------------
+
+pstore block (pstore/blk) is an oops/panic logger that writes its logs to a
+block device and non-block device before the system crashes. You can get
+these log files by mounting pstore filesystem like::
+
+    mount -t pstore pstore /sys/fs/pstore
+
+
+pstore block concepts
+---------------------
+
+pstore/blk provides efficient configuration method for pstore/blk, which
+divides all configurations into two parts, configurations for user and
+configurations for driver.
+
+Configurations for user determine how pstore/blk works, such as pmsg_size,
+kmsg_size and so on. All of them support both Kconfig and module parameters,
+but module parameters have priority over Kconfig.
+
+Configurations for driver are all about block device and non-block device,
+such as total_size of block device and read/write operations.
+
+Configurations for user
+-----------------------
+
+All of these configurations support both Kconfig and module parameters, but
+module parameters have priority over Kconfig.
+
+Here is an example for module parameters::
+
+        pstore_blk.blkdev=179:7 pstore_blk.kmsg_size=64
+
+The detail of each configurations may be of interest to you.
+
+blkdev
+~~~~~~
+
+The block device to use. Most of the time, it is a partition of block device.
+It's required for pstore/blk. It is also used for MTD device.
+
+It accepts the following variants for block device:
+
+1. <hex_major><hex_minor> device number in hexadecimal represents itself; no
+   leading 0x, for example b302.
+#. /dev/<disk_name> represents the device number of disk
+#. /dev/<disk_name><decimal> represents the device number of partition - device
+   number of disk plus the partition number
+#. /dev/<disk_name>p<decimal> - same as the above; this form is used when disk
+   name of partitioned disk ends with a digit.
+#. PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF represents the unique id of
+   a partition if the partition table provides it. The UUID may be either an
+   EFI/GPT UUID, or refer to an MSDOS partition using the format SSSSSSSS-PP,
+   where SSSSSSSS is a zero-filled hex representation of the 32-bit
+   "NT disk signature", and PP is a zero-filled hex representation of the
+   1-based partition number.
+#. PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to a
+   partition with a known unique id.
+#. <major>:<minor> major and minor number of the device separated by a colon.
+
+It accepts the following variants for MTD device:
+
+1. <device name> MTD device name. "pstore" is recommended.
+#. <device number> MTD device number.
+
+kmsg_size
+~~~~~~~~~
+
+The chunk size in KB for oops/panic front-end. It **MUST** be a multiple of 4.
+It's optional if you do not care oops/panic log.
+
+There are multiple chunks for oops/panic front-end depending on the remaining
+space except other pstore front-ends.
+
+pstore/blk will log to oops/panic chunks one by one, and always overwrite the
+oldest chunk if there is no more free chunk.
+
+pmsg_size
+~~~~~~~~~
+
+The chunk size in KB for pmsg front-end. It **MUST** be a multiple of 4.
+It's optional if you do not care pmsg log.
+
+Unlike oops/panic front-end, there is only one chunk for pmsg front-end.
+
+Pmsg is a user space accessible pstore object. Writes to */dev/pmsg0* are
+appended to the chunk. On reboot the contents are available in
+*/sys/fs/pstore/pmsg-pstore-blk-0*.
+
+console_size
+~~~~~~~~~~~~
+
+The chunk size in KB for console front-end.  It **MUST** be a multiple of 4.
+It's optional if you do not care console log.
+
+Similar to pmsg front-end, there is only one chunk for console front-end.
+
+All log of console will be appended to the chunk. On reboot the contents are
+available in */sys/fs/pstore/console-pstore-blk-0*.
+
+ftrace_size
+~~~~~~~~~~~
+
+The chunk size in KB for ftrace front-end. It **MUST** be a multiple of 4.
+It's optional if you do not care console log.
+
+Similar to oops front-end, there are multiple chunks for ftrace front-end
+depending on the count of cpu processors. Each chunk size is equal to
+ftrace_size / processors_count.
+
+All log of ftrace will be appended to the chunk. On reboot the contents are
+combined and available in */sys/fs/pstore/ftrace-pstore-blk-0*.
+
+Persistent function tracing might be useful for debugging software or hardware
+related hangs. Here is an example of usage::
+
+ # mount -t pstore pstore /sys/fs/pstore
+ # mount -t debugfs debugfs /sys/kernel/debug/
+ # echo 1 > /sys/kernel/debug/pstore/record_ftrace
+ # reboot -f
+ [...]
+ # mount -t pstore pstore /sys/fs/pstore
+ # tail /sys/fs/pstore/ftrace-pstore-blk-0
+ CPU:0 ts:5914676 c0063828  c0063b94  call_cpuidle <- cpu_startup_entry+0x1b8/0x1e0
+ CPU:0 ts:5914678 c039ecdc  c006385c  cpuidle_enter_state <- call_cpuidle+0x44/0x48
+ CPU:0 ts:5914680 c039e9a0  c039ecf0  cpuidle_enter_freeze <- cpuidle_enter_state+0x304/0x314
+ CPU:0 ts:5914681 c0063870  c039ea30  sched_idle_set_state <- cpuidle_enter_state+0x44/0x314
+ CPU:1 ts:5916720 c0160f59  c015ee04  kernfs_unmap_bin_file <- __kernfs_remove+0x140/0x204
+ CPU:1 ts:5916721 c05ca625  c015ee0c  __mutex_lock_slowpath <- __kernfs_remove+0x148/0x204
+ CPU:1 ts:5916723 c05c813d  c05ca630  yield_to <- __mutex_lock_slowpath+0x314/0x358
+ CPU:1 ts:5916724 c05ca2d1  c05ca638  __ww_mutex_lock <- __mutex_lock_slowpath+0x31c/0x358
+
+max_reason
+~~~~~~~~~~
+
+Limiting which kinds of kmsg dumps are stored can be controlled via
+the ``max_reason`` value, as defined in include/linux/kmsg_dump.h's
+``enum kmsg_dump_reason``. For example, to store both Oopses and Panics,
+``max_reason`` should be set to 2 (KMSG_DUMP_OOPS), to store only Panics
+``max_reason`` should be set to 1 (KMSG_DUMP_PANIC). Setting this to 0
+(KMSG_DUMP_UNDEF), means the reason filtering will be controlled by the
+``printk.always_kmsg_dump`` boot param: if unset, it'll be KMSG_DUMP_OOPS,
+otherwise KMSG_DUMP_MAX.
+
+Configurations for driver
+-------------------------
+
+Only a block device driver cares about these configurations. A block device
+driver uses ``register_pstore_blk`` to register to pstore/blk.
+
+.. kernel-doc:: fs/pstore/blk.c
+   :identifiers: register_pstore_blk
+
+A non-block device driver uses ``register_pstore_device`` with
+``struct pstore_device_info`` to register to pstore/blk.
+
+.. kernel-doc:: fs/pstore/blk.c
+   :identifiers: register_pstore_device
+
+.. kernel-doc:: include/linux/pstore_blk.h
+   :identifiers: pstore_device_info
+
+Compression and header
+----------------------
+
+Block device is large enough for uncompressed oops data. Actually we do not
+recommend data compression because pstore/blk will insert some information into
+the first line of oops/panic data. For example::
+
+        Panic: Total 16 times
+
+It means that it's OOPS|Panic for the 16th time since the first booting.
+Sometimes the number of occurrences of oops|panic since the first booting is
+important to judge whether the system is stable.
+
+The following line is inserted by pstore filesystem. For example::
+
+        Oops#2 Part1
+
+It means that it's OOPS for the 2nd time on the last boot.
+
+Reading the data
+----------------
+
+The dump data can be read from the pstore filesystem. The format for these
+files is ``dmesg-pstore-blk-[N]`` for oops/panic front-end,
+``pmsg-pstore-blk-0`` for pmsg front-end and so on.  The timestamp of the
+dump file records the trigger time. To delete a stored record from block
+device, simply unlink the respective pstore file.
+
+Attentions in panic read/write APIs
+-----------------------------------
+
+If on panic, the kernel is not going to run for much longer, the tasks will not
+be scheduled and most kernel resources will be out of service. It
+looks like a single-threaded program running on a single-core computer.
+
+The following points require special attention for panic read/write APIs:
+
+1. Can **NOT** allocate any memory.
+   If you need memory, just allocate while the block driver is initializing
+   rather than waiting until the panic.
+#. Must be polled, **NOT** interrupt driven.
+   No task schedule any more. The block driver should delay to ensure the write
+   succeeds, but NOT sleep.
+#. Can **NOT** take any lock.
+   There is no other task, nor any shared resource; you are safe to break all
+   locks.
+#. Just use CPU to transfer.
+   Do not use DMA to transfer unless you are sure that DMA will not keep lock.
+#. Control registers directly.
+   Please control registers directly rather than use Linux kernel resources.
+   Do I/O map while initializing rather than wait until a panic occurs.
+#. Reset your block device and controller if necessary.
+   If you are not sure of the state of your block device and controller when
+   a panic occurs, you are safe to stop and reset them.
+
+pstore/blk supports psblk_blkdev_info(), which is defined in
+*linux/pstore_blk.h*, to get information of using block device, such as the
+device number, sector count and start sector of the whole disk.
+
+pstore block internals
+----------------------
+
+For developer reference, here are all the important structures and APIs:
+
+.. kernel-doc:: fs/pstore/zone.c
+   :internal:
+
+.. kernel-doc:: include/linux/pstore_zone.h
+   :internal:
+
+.. kernel-doc:: fs/pstore/blk.c
+   :export:
+
+.. kernel-doc:: include/linux/pstore_blk.h
+   :internal:
diff --git a/Documentation/admin-guide/ramoops.rst b/Documentation/admin-guide/ramoops.rst
index 6dbcc5481000..a60a96218ba9 100644
--- a/Documentation/admin-guide/ramoops.rst
+++ b/Documentation/admin-guide/ramoops.rst
@@ -32,11 +32,17 @@ memory to be mapped strongly ordered, and atomic operations on strongly ordered
 memory are implementation defined, and won't work on many ARMs such as omaps.
 
 The memory area is divided into ``record_size`` chunks (also rounded down to
-power of two) and each oops/panic writes a ``record_size`` chunk of
+power of two) and each kmesg dump writes a ``record_size`` chunk of
 information.
 
-Dumping both oopses and panics can be done by setting 1 in the ``dump_oops``
-variable while setting 0 in that variable dumps only the panics.
+Limiting which kinds of kmsg dumps are stored can be controlled via
+the ``max_reason`` value, as defined in include/linux/kmsg_dump.h's
+``enum kmsg_dump_reason``. For example, to store both Oopses and Panics,
+``max_reason`` should be set to 2 (KMSG_DUMP_OOPS), to store only Panics
+``max_reason`` should be set to 1 (KMSG_DUMP_PANIC). Setting this to 0
+(KMSG_DUMP_UNDEF), means the reason filtering will be controlled by the
+``printk.always_kmsg_dump`` boot param: if unset, it'll be KMSG_DUMP_OOPS,
+otherwise KMSG_DUMP_MAX.
 
 The module uses a counter to record multiple dumps but the counter gets reset
 on restart (i.e. new dumps after the restart will overwrite old ones).
@@ -90,7 +96,7 @@ Setting the ramoops parameters can be done in several different manners:
         .mem_address            = <...>,
         .mem_type               = <...>,
         .record_size            = <...>,
-        .dump_oops              = <...>,
+        .max_reason             = <...>,
         .ecc                    = <...>,
   };
 
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 4752d9a79235..1ebf68d01141 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -807,7 +807,13 @@ perf_event_paranoid
 ===================
 
 Controls use of the performance events system by unprivileged
-users (without CAP_SYS_ADMIN).  The default value is 2.
+users (without CAP_PERFMON).  The default value is 2.
+
+For backward compatibility reasons access to system performance
+monitoring and observability remains open for CAP_SYS_ADMIN
+privileged processes but CAP_SYS_ADMIN usage for secure system
+performance monitoring and observability operations is discouraged
+with respect to CAP_PERFMON use cases.
 
 ===  ==================================================================
  -1  Allow use of (almost) all events by all users.
@@ -816,13 +822,13 @@ users (without CAP_SYS_ADMIN).  The default value is 2.
      ``CAP_IPC_LOCK``.
 
 >=0  Disallow ftrace function tracepoint by users without
-     ``CAP_SYS_ADMIN``.
+     ``CAP_PERFMON``.
 
-     Disallow raw tracepoint access by users without ``CAP_SYS_ADMIN``.
+     Disallow raw tracepoint access by users without ``CAP_PERFMON``.
 
->=1  Disallow CPU event access by users without ``CAP_SYS_ADMIN``.
+>=1  Disallow CPU event access by users without ``CAP_PERFMON``.
 
->=2  Disallow kernel profiling by users without ``CAP_SYS_ADMIN``.
+>=2  Disallow kernel profiling by users without ``CAP_PERFMON``.
 ===  ==================================================================
 
 
diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst
index e50186092948..7552dbc1cc54 100644
--- a/Documentation/arm64/booting.rst
+++ b/Documentation/arm64/booting.rst
@@ -174,7 +174,8 @@ Before jumping into the kernel, the following conditions must be met:
 
   The MMU must be off.
 
-  Instruction cache may be on or off.
+  The instruction cache may be on or off, and must not hold any stale
+  entries corresponding to the loaded kernel image.
 
   The address range corresponding to the loaded kernel image must be
   cleaned to the PoC. In the presence of a system cache or other
diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst
index 41937a8091aa..314fa5bc2655 100644
--- a/Documentation/arm64/cpu-feature-registers.rst
+++ b/Documentation/arm64/cpu-feature-registers.rst
@@ -176,6 +176,8 @@ infrastructure:
      +------------------------------+---------+---------+
      | SSBS                         | [7-4]   |    y    |
      +------------------------------+---------+---------+
+     | BT                           | [3-0]   |    y    |
+     +------------------------------+---------+---------+
 
 
   4) MIDR_EL1 - Main ID Register
diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index 7dfb97dfe416..84a9fd2d41b4 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -236,6 +236,11 @@ HWCAP2_RNG
 
     Functionality implied by ID_AA64ISAR0_EL1.RNDR == 0b0001.
 
+HWCAP2_BTI
+
+    Functionality implied by ID_AA64PFR0_EL1.BT == 0b0001.
+
+
 4. Unused AT_HWCAP bits
 -----------------------
 
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 2c08c628febd..936cf2a59ca4 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -64,6 +64,10 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A53      | #843419         | ARM64_ERRATUM_843419        |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A55      | #1024718        | ARM64_ERRATUM_1024718       |
++----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A55      | #1530923        | ARM64_ERRATUM_1530923       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A57      | #832075         | ARM64_ERRATUM_832075        |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A57      | #852523         | N/A                         |
@@ -78,8 +82,6 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A73      | #858921         | ARM64_ERRATUM_858921        |
 +----------------+-----------------+-----------------+-----------------------------+
-| ARM            | Cortex-A55      | #1024718        | ARM64_ERRATUM_1024718       |
-+----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A76      | #1188873,1418040| ARM64_ERRATUM_1418040       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A76      | #1165522        | ARM64_ERRATUM_1165522       |
@@ -88,8 +90,6 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A76      | #1463225        | ARM64_ERRATUM_1463225       |
 +----------------+-----------------+-----------------+-----------------------------+
-| ARM            | Cortex-A55      | #1530923        | ARM64_ERRATUM_1530923       |
-+----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1188873,1418040| ARM64_ERRATUM_1418040       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst
index 1e3838652348..8c9aba262b1e 100644
--- a/Documentation/core-api/printk-formats.rst
+++ b/Documentation/core-api/printk-formats.rst
@@ -114,6 +114,20 @@ used when printing stack backtraces. The specifier takes into
 consideration the effect of compiler optimisations which may occur
 when tail-calls are used and marked with the noreturn GCC attribute.
 
+Probed Pointers from BPF / tracing
+----------------------------------
+
+::
+
+	%pks	kernel string
+	%pus	user string
+
+The ``k`` and ``u`` specifiers are used for printing prior probed memory from
+either kernel memory (k) or user memory (u). The subsequent ``s`` specifier
+results in printing a string. For direct use in regular vsnprintf() the (k)
+and (u) annotation is ignored, however, when used out of BPF's bpf_trace_printk(),
+for example, it reads the memory it is pointing to without faulting.
+
 Kernel Pointers
 ---------------
 
@@ -470,21 +484,23 @@ Examples (OF)::
 	%pfwf	/ocp@68000000/i2c@48072000/camera@10/port/endpoint - Full name
 	%pfwP	endpoint				- Node name
 
-Time and date (struct rtc_time)
--------------------------------
+Time and date
+-------------
 
 ::
 
-	%ptR		YYYY-mm-ddTHH:MM:SS
-	%ptRd		YYYY-mm-dd
-	%ptRt		HH:MM:SS
-	%ptR[dt][r]
+	%pt[RT]			YYYY-mm-ddTHH:MM:SS
+	%pt[RT]d		YYYY-mm-dd
+	%pt[RT]t		HH:MM:SS
+	%pt[RT][dt][r]
 
-For printing date and time as represented by struct rtc_time structure in
-human readable format.
+For printing date and time as represented by
+	R  struct rtc_time structure
+	T  time64_t type
+in human readable format.
 
-By default year will be incremented by 1900 and month by 1. Use %ptRr (raw)
-to suppress this behaviour.
+By default year will be incremented by 1900 and month by 1.
+Use %pt[RT]r (raw) to suppress this behaviour.
 
 Passed by reference.
 
diff --git a/Documentation/core-api/protection-keys.rst b/Documentation/core-api/protection-keys.rst
index 49d9833af871..ec575e72d0b2 100644
--- a/Documentation/core-api/protection-keys.rst
+++ b/Documentation/core-api/protection-keys.rst
@@ -5,8 +5,9 @@ Memory Protection Keys
 ======================
 
 Memory Protection Keys for Userspace (PKU aka PKEYs) is a feature
-which is found on Intel's Skylake "Scalable Processor" Server CPUs.
-It will be avalable in future non-server parts.
+which is found on Intel's Skylake (and later) "Scalable Processor"
+Server CPUs. It will be available in future non-server Intel parts
+and future AMD processors.
 
 For anyone wishing to test or use this feature, it is available in
 Amazon's EC2 C5 instances and is known to work there using an Ubuntu
diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile
index 1df680d07461..7782d9985082 100644
--- a/Documentation/devicetree/bindings/Makefile
+++ b/Documentation/devicetree/bindings/Makefile
@@ -2,6 +2,7 @@
 DT_DOC_CHECKER ?= dt-doc-validate
 DT_EXTRACT_EX ?= dt-extract-example
 DT_MK_SCHEMA ?= dt-mk-schema
+DT_MK_SCHEMA_USERONLY_FLAG := $(if $(DT_SCHEMA_FILES), -u)
 
 quiet_cmd_chk_binding = CHKDT   $(patsubst $(srctree)/%,%,$<)
       cmd_chk_binding = $(DT_DOC_CHECKER) -u $(srctree)/$(src) $< ; \
@@ -13,16 +14,18 @@ $(obj)/%.example.dts: $(src)/%.yaml FORCE
 # Use full schemas when checking %.example.dts
 DT_TMP_SCHEMA := $(obj)/processed-schema-examples.yaml
 
+find_cmd = find $(srctree)/$(src) \( -name '*.yaml' ! \
+		-name 'processed-schema*' ! \
+		-name '*.example.dt.yaml' \)
+
 quiet_cmd_mk_schema = SCHEMA  $@
-      cmd_mk_schema = $(DT_MK_SCHEMA) $(DT_MK_SCHEMA_FLAGS) -o $@ $(real-prereqs)
+      cmd_mk_schema = rm -f $@ ; \
+                      $(if $(DT_MK_SCHEMA_FLAGS), \
+                           echo $(real-prereqs), \
+                           $(find_cmd)) | \
+                      xargs $(DT_MK_SCHEMA) $(DT_MK_SCHEMA_FLAGS) >> $@
 
-DT_DOCS = $(addprefix $(src)/, \
-	$(shell \
-	cd $(srctree)/$(src) && \
-	find * \( -name '*.yaml' ! \
-		-name 'processed-schema*' ! \
-		-name '*.example.dt.yaml' \) \
-	))
+DT_DOCS = $(shell $(find_cmd) | sed -e 's|^$(srctree)/||')
 
 DT_SCHEMA_FILES ?= $(DT_DOCS)
 
@@ -37,7 +40,7 @@ override DTC_FLAGS := \
 $(obj)/processed-schema-examples.yaml: $(DT_DOCS) FORCE
 	$(call if_changed,mk_schema)
 
-$(obj)/processed-schema.yaml: DT_MK_SCHEMA_FLAGS := -u
+$(obj)/processed-schema.yaml: DT_MK_SCHEMA_FLAGS := $(DT_MK_SCHEMA_USERONLY_FLAG)
 $(obj)/processed-schema.yaml: $(DT_SCHEMA_FILES) FORCE
 	$(call if_changed,mk_schema)
 
diff --git a/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml b/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml
index aa0738b4d534..e713a6fe4cf7 100644
--- a/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml
+++ b/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml
@@ -42,6 +42,10 @@ properties:
     description:
       See section 2.3.9 of the DeviceTree Specification.
 
+  '#address-cells': true
+
+  '#size-cells': true
+
 required:
   - "#interconnect-cells"
   - compatible
@@ -59,6 +63,8 @@ examples:
         compatible = "allwinner,sun5i-a13-mbus";
         reg = <0x01c01000 0x1000>;
         clocks = <&ccu CLK_MBUS>;
+        #address-cells = <1>;
+        #size-cells = <1>;
         dma-ranges = <0x00000000 0x40000000 0x20000000>;
         #interconnect-cells = <1>;
     };
diff --git a/Documentation/devicetree/bindings/clock/arm,syscon-icst.yaml b/Documentation/devicetree/bindings/clock/arm,syscon-icst.yaml
index de9a465096db..444aeea27db8 100644
--- a/Documentation/devicetree/bindings/clock/arm,syscon-icst.yaml
+++ b/Documentation/devicetree/bindings/clock/arm,syscon-icst.yaml
@@ -91,7 +91,7 @@ required:
 
 examples:
   - |
-    vco1: clock@00 {
+    vco1: clock {
       compatible = "arm,impd1-vco1";
       #clock-cells = <0>;
       lock-offset = <0x08>;
diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7123.txt b/Documentation/devicetree/bindings/display/bridge/adi,adv7123.txt
index a6b2b2b8f3d9..d3c2a4914ea2 100644
--- a/Documentation/devicetree/bindings/display/bridge/adi,adv7123.txt
+++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7123.txt
@@ -1,5 +1,5 @@
-Analog Device ADV7123 Video DAC
--------------------------------
+Analog Devices ADV7123 Video DAC
+--------------------------------
 
 The ADV7123 is a digital-to-analog converter that outputs VGA signals from a
 parallel video input.
diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt
index e8ddec5d9d91..659523f538bf 100644
--- a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt
+++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt
@@ -1,5 +1,5 @@
-Analog Device ADV7511(W)/13/33/35 HDMI Encoders
------------------------------------------
+Analog Devices ADV7511(W)/13/33/35 HDMI Encoders
+------------------------------------------------
 
 The ADV7511, ADV7511W, ADV7513, ADV7533 and ADV7535 are HDMI audio and video
 transmitters compatible with HDMI 1.4 and DVI 1.0. They support color space
diff --git a/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml
index fd931b293816..b900973b5f7b 100644
--- a/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml
+++ b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml
@@ -37,7 +37,6 @@ examples:
     dsi {
         #address-cells = <1>;
         #size-cells = <0>;
-        reg = <0xff450000 0x1000>;
 
         panel@0 {
             compatible = "leadtek,ltk500hd1829";
diff --git a/Documentation/devicetree/bindings/display/panel/lvds.yaml b/Documentation/devicetree/bindings/display/panel/lvds.yaml
index d0083301acbe..946dd354256c 100644
--- a/Documentation/devicetree/bindings/display/panel/lvds.yaml
+++ b/Documentation/devicetree/bindings/display/panel/lvds.yaml
@@ -96,12 +96,20 @@ properties:
       If set, reverse the bit order described in the data mappings below on all
       data lanes, transmitting bits for slots 6 to 0 instead of 0 to 6.
 
+  port: true
+  ports: true
+
 required:
   - compatible
   - data-mapping
   - width-mm
   - height-mm
   - panel-timing
-  - port
+
+oneOf:
+  - required:
+      - port
+  - required:
+      - ports
 
 ...
diff --git a/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml
index d9fdb58e06b4..6913923df569 100644
--- a/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml
+++ b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml
@@ -37,7 +37,6 @@ examples:
     dsi {
         #address-cells = <1>;
         #size-cells = <0>;
-        reg = <0xff450000 0x1000>;
 
         panel@0 {
             compatible = "xinpeng,xpp055c272";
diff --git a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt b/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt
index b38ee732efa9..cd17684aaab5 100644
--- a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt
@@ -1,4 +1,4 @@
-Analog Device AXI-DMAC DMA controller
+Analog Devices AXI-DMAC DMA controller
 
 Required properties:
  - compatible: Must be "adi,axi-dmac-1.00.a".
diff --git a/Documentation/devicetree/bindings/dma/fsl-edma.txt b/Documentation/devicetree/bindings/dma/fsl-edma.txt
index e77b08ebcd06..ee1754739b4b 100644
--- a/Documentation/devicetree/bindings/dma/fsl-edma.txt
+++ b/Documentation/devicetree/bindings/dma/fsl-edma.txt
@@ -10,7 +10,8 @@ Required properties:
 - compatible :
 	- "fsl,vf610-edma" for eDMA used similar to that on Vybrid vf610 SoC
 	- "fsl,imx7ulp-edma" for eDMA2 used similar to that on i.mx7ulp
-	- "fsl,fsl,ls1028a-edma" for eDMA used similar to that on Vybrid vf610 SoC
+	- "fsl,ls1028a-edma" followed by "fsl,vf610-edma" for eDMA used on the
+	  LS1028A SoC.
 - reg : Specifies base physical address(s) and size of the eDMA registers.
 	The 1st region is eDMA control register's address and size.
 	The 2nd and the 3rd regions are programmable channel multiplexing
diff --git a/Documentation/devicetree/bindings/dma/socionext,uniphier-xdmac.yaml b/Documentation/devicetree/bindings/dma/socionext,uniphier-xdmac.yaml
index 86cfb599256e..371f18773198 100644
--- a/Documentation/devicetree/bindings/dma/socionext,uniphier-xdmac.yaml
+++ b/Documentation/devicetree/bindings/dma/socionext,uniphier-xdmac.yaml
@@ -22,9 +22,7 @@ properties:
     const: socionext,uniphier-xdmac
 
   reg:
-    items:
-      - description: XDMAC base register region (offset and length)
-      - description: XDMAC extension register region (offset and length)
+    maxItems: 1
 
   interrupts:
     maxItems: 1
@@ -49,12 +47,13 @@ required:
   - reg
   - interrupts
   - "#dma-cells"
+  - dma-channels
 
 examples:
   - |
     xdmac: dma-controller@5fc10000 {
         compatible = "socionext,uniphier-xdmac";
-        reg = <0x5fc10000 0x1000>, <0x5fc20000 0x800>;
+        reg = <0x5fc10000 0x5300>;
         interrupts = <0 188 4>;
         #dma-cells = <2>;
         dma-channels = <16>;
diff --git a/Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml b/Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml
index 57a240d2d026..7db78767c02d 100644
--- a/Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml
+++ b/Documentation/devicetree/bindings/hwmon/adi,axi-fan-control.yaml
@@ -2,7 +2,7 @@
 # Copyright 2019 Analog Devices Inc.
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/hwmon/adi,axi-fan-control.yaml#
+$id: http://devicetree.org/schemas/hwmon/adi,axi-fan-control.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Analog Devices AXI FAN Control Device Tree Bindings
@@ -47,7 +47,7 @@ required:
 
 examples:
   - |
-    fpga_axi: fpga-axi@0 {
+    fpga_axi: fpga-axi {
             #address-cells = <0x2>;
             #size-cells = <0x1>;
 
diff --git a/Documentation/devicetree/bindings/hwmon/adt7475.yaml b/Documentation/devicetree/bindings/hwmon/adt7475.yaml
index 76985034ea73..46c441574f98 100644
--- a/Documentation/devicetree/bindings/hwmon/adt7475.yaml
+++ b/Documentation/devicetree/bindings/hwmon/adt7475.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/adt7475.yaml#
+$id: http://devicetree.org/schemas/hwmon/adt7475.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: ADT7475 hwmon sensor
diff --git a/Documentation/devicetree/bindings/hwmon/baikal,bt1-pvt.yaml b/Documentation/devicetree/bindings/hwmon/baikal,bt1-pvt.yaml
new file mode 100644
index 000000000000..84ae4cdd08ed
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/baikal,bt1-pvt.yaml
@@ -0,0 +1,107 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 BAIKAL ELECTRONICS, JSC
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/hwmon/baikal,bt1-pvt.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Baikal-T1 PVT Sensor
+
+maintainers:
+  - Serge Semin <fancer.lancer@gmail.com>
+
+description: |
+  Baikal-T1 SoC provides an embedded process, voltage and temperature
+  sensor to monitor an internal SoC environment (chip temperature, supply
+  voltage and process monitor) and on time detect critical situations,
+  which may cause the system instability and even damages. The IP-block
+  is based on the Analog Bits PVT sensor, but is equipped with a dedicated
+  control wrapper, which provides a MMIO registers-based access to the
+  sensor core functionality (APB3-bus based) and exposes an additional
+  functions like thresholds/data ready interrupts, its status and masks,
+  measurements timeout. Its internal structure is depicted on the next
+  diagram:
+
+     Analog Bits core                     Bakal-T1 PVT control block
+  +--------------------+                  +------------------------+
+  | Temperature sensor |-+         +------| Sensors control        |
+  |--------------------| |<---En---|      |------------------------|
+  | Voltage sensor     |-|<--Mode--| +--->| Sampled data           |
+  |--------------------| |<--Trim--+ |    |------------------------|
+  | Low-Vt sensor      |-|           | +--| Thresholds comparator  |
+  |--------------------| |---Data----| |  |------------------------|
+  | High-Vt sensor     |-|           | +->| Interrupts status      |
+  |--------------------| |--Valid--+-+ |  |------------------------|
+  | Standard-Vt sensor |-+         +---+--| Interrupts mask        |
+  +--------------------+                  |------------------------|
+           ^                              | Interrupts timeout     |
+           |                              +------------------------+
+           |                                        ^  ^
+  Rclk-----+----------------------------------------+  |
+  APB3-------------------------------------------------+
+
+  This bindings describes the external Baikal-T1 PVT control interfaces
+  like MMIO registers space, interrupt request number and clocks source.
+  These are then used by the corresponding hwmon device driver to
+  implement the sysfs files-based access to the sensors functionality.
+
+properties:
+  compatible:
+    const: baikal,bt1-pvt
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: PVT reference clock
+      - description: APB3 interface clock
+
+  clock-names:
+    items:
+      - const: ref
+      - const: pclk
+
+  "#thermal-sensor-cells":
+    description: Baikal-T1 can be referenced as the CPU thermal-sensor
+    const: 0
+
+  baikal,pvt-temp-offset-millicelsius:
+    description: |
+      Temperature sensor trimming factor. It can be used to manually adjust the
+      temperature measurements within 7.130 degrees Celsius.
+    maxItems: 1
+    items:
+      default: 0
+      minimum: 0
+      maximum: 7130
+
+unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/mips-gic.h>
+
+    pvt@1f200000 {
+      compatible = "baikal,bt1-pvt";
+      reg = <0x1f200000 0x1000>;
+      #thermal-sensor-cells = <0>;
+
+      interrupts = <GIC_SHARED 31 IRQ_TYPE_LEVEL_HIGH>;
+
+      baikal,pvt-temp-trim-millicelsius = <1000>;
+
+      clocks = <&ccu_sys>, <&ccu_sys>;
+      clock-names = "ref", "pclk";
+    };
+...
diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml
index 933ba37944d7..dd8eb15aeb63 100644
--- a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: "http://devicetree.org/schemas/bindings/iio/adc/st,stm32-adc.yaml#"
+$id: "http://devicetree.org/schemas/iio/adc/st,stm32-adc.yaml#"
 $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 
 title: STMicroelectronics STM32 ADC bindings
diff --git a/Documentation/devicetree/bindings/iio/dac/ad5755.txt b/Documentation/devicetree/bindings/iio/dac/ad5755.txt
index f0bbd7e1029b..502e1e55adbd 100644
--- a/Documentation/devicetree/bindings/iio/dac/ad5755.txt
+++ b/Documentation/devicetree/bindings/iio/dac/ad5755.txt
@@ -1,4 +1,4 @@
-* Analog Device AD5755 IIO Multi-Channel DAC Linux Driver
+* Analog Devices AD5755 IIO Multi-Channel DAC Linux Driver
 
 Required properties:
  - compatible: Has to contain one of the following:
diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5770r.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5770r.yaml
index d9c25cf4b92f..58d81ca43460 100644
--- a/Documentation/devicetree/bindings/iio/dac/adi,ad5770r.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5770r.yaml
@@ -2,7 +2,7 @@
 # Copyright 2020 Analog Devices Inc.
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/iio/dac/adi,ad5770r.yaml#
+$id: http://devicetree.org/schemas/iio/dac/adi,ad5770r.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Analog Devices AD5770R DAC device driver
@@ -49,93 +49,86 @@ properties:
       asserted during driver probe.
     maxItems: 1
 
-  channel0:
+  channel@0:
     description: Represents an external channel which are
       connected to the DAC. Channel 0 can act both as a current
       source and sink.
     type: object
 
     properties:
-      num:
+      reg:
         description: This represents the channel number.
-        items:
-          const: 0
+        const: 0
 
       adi,range-microamp:
           description: Output range of the channel.
           oneOf:
-            - $ref: /schemas/types.yaml#/definitions/int32-array
             - items:
-                - enum: [0 300000]
-                - enum: [-60000 0]
-                - enum: [-60000 300000]
+                - const: 0
+                - const: 300000
+            - items:
+                - const: -60000
+                - const: 0
+            - items:
+                - const: -60000
+                - const: 300000
 
-  channel1:
+  channel@1:
     description: Represents an external channel which are
       connected to the DAC.
     type: object
 
     properties:
-      num:
+      reg:
         description: This represents the channel number.
-        items:
-          const: 1
+        const: 1
 
       adi,range-microamp:
           description: Output range of the channel.
-          oneOf:
-            - $ref: /schemas/types.yaml#/definitions/uint32-array
-            - items:
-                - enum: [0 140000]
-                - enum: [0 250000]
+          items:
+            - const: 0
+            - enum: [ 140000, 250000 ]
 
-  channel2:
+  channel@2:
     description: Represents an external channel which are
       connected to the DAC.
     type: object
 
     properties:
-      num:
+      reg:
         description: This represents the channel number.
-        items:
-          const: 2
+        const: 2
 
       adi,range-microamp:
           description: Output range of the channel.
-          oneOf:
-            - $ref: /schemas/types.yaml#/definitions/uint32-array
-            - items:
-                - enum: [0 140000]
-                - enum: [0 250000]
+          items:
+            - const: 0
+            - enum: [ 55000, 150000 ]
 
 patternProperties:
   "^channel@([3-5])$":
     type: object
     description: Represents the external channels which are connected to the DAC.
     properties:
-      num:
+      reg:
         description: This represents the channel number.
-        items:
-          minimum: 3
-          maximum: 5
+        minimum: 3
+        maximum: 5
 
       adi,range-microamp:
           description: Output range of the channel.
-          oneOf:
-            - $ref: /schemas/types.yaml#/definitions/uint32-array
-            - items:
-                - enum: [0 45000]
-                - enum: [0 100000]
+          items:
+            - const: 0
+            - enum: [ 45000, 100000 ]
 
 required:
 - reg
-- diff-channels
-- channel0
-- channel1
-- channel2
-- channel3
-- channel4
-- channel5
+- channel@0
+- channel@1
+- channel@2
+- channel@3
+- channel@4
+- channel@5
 
 examples:
   - |
@@ -144,40 +137,42 @@ examples:
                 #size-cells = <0>;
 
                 ad5770r@0 {
-                        compatible = "ad5770r";
+                        compatible = "adi,ad5770r";
                         reg = <0>;
                         spi-max-frequency = <1000000>;
                         vref-supply = <&vref>;
                         adi,external-resistor;
                         reset-gpios = <&gpio 22 0>;
+                        #address-cells = <1>;
+                        #size-cells = <0>;
 
                         channel@0 {
-                                num = <0>;
-                                adi,range-microamp = <(-60000) 300000>;
+                                reg = <0>;
+                                adi,range-microamp = <0 300000>;
                         };
 
                         channel@1 {
-                                num = <1>;
+                                reg = <1>;
                                 adi,range-microamp = <0 140000>;
                         };
 
                         channel@2 {
-                                num = <2>;
+                                reg = <2>;
                                 adi,range-microamp = <0 55000>;
                         };
 
                         channel@3 {
-                                num = <3>;
+                                reg = <3>;
                                 adi,range-microamp = <0 45000>;
                         };
 
                         channel@4 {
-                                num = <4>;
+                                reg = <4>;
                                 adi,range-microamp = <0 45000>;
                         };
 
                         channel@5 {
-                                num = <5>;
+                                reg = <5>;
                                 adi,range-microamp = <0 45000>;
                         };
                 };
diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
index 8d58709d4b47..383d64a91854 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
@@ -109,7 +109,7 @@ examples:
   - |
     #include <dt-bindings/gpio/gpio.h>
     #include <dt-bindings/interrupt-controller/arm-gic.h>
-    i2c@00000000 {
+    i2c {
       #address-cells = <1>;
       #size-cells = <0>;
       edt-ft5x06@38 {
diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
index 9c6b91fee477..26f1fcf0857a 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,liointc.yaml
@@ -56,9 +56,8 @@ properties:
       cell with zero.
     allOf:
       - $ref: /schemas/types.yaml#/definitions/uint32-array
-      - items:
-          minItems: 4
-          maxItems: 4
+      - minItems: 4
+        maxItems: 4
 
 
 required:
diff --git a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml
index 12516bd89cf9..611bda38d187 100644
--- a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml
+++ b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra186-mc.yaml
@@ -97,30 +97,35 @@ examples:
     #include <dt-bindings/clock/tegra186-clock.h>
     #include <dt-bindings/interrupt-controller/arm-gic.h>
 
-    memory-controller@2c00000 {
-        compatible = "nvidia,tegra186-mc";
-        reg = <0x0 0x02c00000 0x0 0xb0000>;
-        interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_HIGH>;
-
+    bus {
         #address-cells = <2>;
         #size-cells = <2>;
 
-        ranges = <0x0 0x02c00000 0x02c00000 0x0 0xb0000>;
+        memory-controller@2c00000 {
+            compatible = "nvidia,tegra186-mc";
+            reg = <0x0 0x02c00000 0x0 0xb0000>;
+            interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_HIGH>;
+
+            #address-cells = <2>;
+            #size-cells = <2>;
+
+            ranges = <0x0 0x02c00000 0x0 0x02c00000 0x0 0xb0000>;
 
-        /*
-         * Memory clients have access to all 40 bits that the memory
-         * controller can address.
-         */
-        dma-ranges = <0x0 0x0 0x0 0x0 0x100 0x0>;
+            /*
+             * Memory clients have access to all 40 bits that the memory
+             * controller can address.
+             */
+            dma-ranges = <0x0 0x0 0x0 0x0 0x100 0x0>;
 
-        external-memory-controller@2c60000 {
-            compatible = "nvidia,tegra186-emc";
-            reg = <0x0 0x02c60000 0x0 0x50000>;
-            interrupts = <GIC_SPI 224 IRQ_TYPE_LEVEL_HIGH>;
-            clocks = <&bpmp TEGRA186_CLK_EMC>;
-            clock-names = "emc";
+            external-memory-controller@2c60000 {
+                compatible = "nvidia,tegra186-emc";
+                reg = <0x0 0x02c60000 0x0 0x50000>;
+                interrupts = <GIC_SPI 224 IRQ_TYPE_LEVEL_HIGH>;
+                clocks = <&bpmp TEGRA186_CLK_EMC>;
+                clock-names = "emc";
 
-            nvidia,bpmp = <&bpmp>;
+                nvidia,bpmp = <&bpmp>;
+            };
         };
     };
 
diff --git a/Documentation/devicetree/bindings/mfd/gateworks-gsc.yaml b/Documentation/devicetree/bindings/mfd/gateworks-gsc.yaml
new file mode 100644
index 000000000000..487a8445722e
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/gateworks-gsc.yaml
@@ -0,0 +1,196 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mfd/gateworks-gsc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Gateworks System Controller
+
+description: |
+  The Gateworks System Controller (GSC) is a device present across various
+  Gateworks product families that provides a set of system related features
+  such as the following (refer to the board hardware user manuals to see what
+  features are present)
+   - Watchdog Timer
+   - GPIO
+   - Pushbutton controller
+   - Hardware monitor with ADC's for temperature and voltage rails and
+     fan controller
+
+maintainers:
+  - Tim Harvey <tharvey@gateworks.com>
+  - Robert Jones <rjones@gateworks.com>
+
+properties:
+  $nodename:
+    pattern: "gsc@[0-9a-f]{1,2}"
+  compatible:
+    const: gw,gsc
+
+  reg:
+    description: I2C device address
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  interrupt-controller: true
+
+  "#interrupt-cells":
+    const: 1
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+  adc:
+    type: object
+    description: Optional hardware monitoring module
+
+    properties:
+      compatible:
+        const: gw,gsc-adc
+
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+    patternProperties:
+      "^channel@[0-9]+$":
+        type: object
+        description: |
+          Properties for a single ADC which can report cooked values
+          (i.e. temperature sensor based on thermister), raw values
+          (i.e. voltage rail with a pre-scaling resistor divider).
+
+        properties:
+          reg:
+            description: Register of the ADC
+            maxItems: 1
+
+          label:
+            description: Name of the ADC input
+
+          gw,mode:
+            description: |
+              conversion mode:
+                0 - temperature, in C*10
+                1 - pre-scaled voltage value
+                2 - scaled voltage based on an optional resistor divider
+                    and optional offset
+            $ref: /schemas/types.yaml#/definitions/uint32
+            enum: [0, 1, 2]
+
+          gw,voltage-divider-ohms:
+            description: Values of resistors for divider on raw ADC input
+            maxItems: 2
+            items:
+             minimum: 1000
+             maximum: 1000000
+
+          gw,voltage-offset-microvolt:
+            description: |
+              A positive voltage offset to apply to a raw ADC
+              (i.e. to compensate for a diode drop).
+            minimum: 0
+            maximum: 1000000
+
+        required:
+          - gw,mode
+          - reg
+          - label
+
+    required:
+      - compatible
+      - "#address-cells"
+      - "#size-cells"
+
+patternProperties:
+  "^fan-controller@[0-9a-f]+$":
+    type: object
+    description: Optional fan controller
+
+    properties:
+      compatible:
+        const: gw,gsc-fan
+
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      reg:
+        description: The fan controller base address
+        maxItems: 1
+
+    required:
+      - compatible
+      - reg
+      - "#address-cells"
+      - "#size-cells"
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - interrupt-controller
+  - "#interrupt-cells"
+  - "#address-cells"
+  - "#size-cells"
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        gsc@20 {
+            compatible = "gw,gsc";
+            reg = <0x20>;
+            interrupt-parent = <&gpio1>;
+            interrupts = <4 GPIO_ACTIVE_LOW>;
+            interrupt-controller;
+            #interrupt-cells = <1>;
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            adc {
+                compatible = "gw,gsc-adc";
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                channel@0 { /* A0: Board Temperature */
+                    reg = <0x00>;
+                    label = "temp";
+                    gw,mode = <0>;
+                };
+
+                channel@2 { /* A1: Input Voltage (raw ADC) */
+                    reg = <0x02>;
+                    label = "vdd_vin";
+                    gw,mode = <1>;
+                    gw,voltage-divider-ohms = <22100 1000>;
+                    gw,voltage-offset-microvolt = <800000>;
+                };
+
+                channel@b { /* A2: Battery voltage */
+                    reg = <0x0b>;
+                    label = "vdd_bat";
+                    gw,mode = <1>;
+                };
+            };
+
+            fan-controller@2c {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                compatible = "gw,gsc-fan";
+                reg = <0x2c>;
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/mfd/max8998.txt b/Documentation/devicetree/bindings/mfd/max8998.txt
index 5f2f07c09c90..4ed52184d081 100644
--- a/Documentation/devicetree/bindings/mfd/max8998.txt
+++ b/Documentation/devicetree/bindings/mfd/max8998.txt
@@ -73,6 +73,8 @@ number as described in MAX8998 datasheet.
 	- ESAFEOUT1: (ldo19)
 	- ESAFEOUT2: (ld020)
 
+	- CHARGER: main battery charger current control
+
 Standard regulator bindings are used inside regulator subnodes. Check
   Documentation/devicetree/bindings/regulator/regulator.txt
 for more details.
@@ -113,5 +115,11 @@ Example:
 				regulator-always-on;
 				regulator-boot-on;
 			};
+
+			charger_reg: CHARGER {
+				regulator-name = "CHARGER";
+				regulator-min-microamp = <90000>;
+				regulator-max-microamp = <800000>;
+			};
 		};
 	};
diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd71837-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd71837-pmic.yaml
index aa922c560fcc..65018a019e1d 100644
--- a/Documentation/devicetree/bindings/mfd/rohm,bd71837-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/rohm,bd71837-pmic.yaml
@@ -123,7 +123,9 @@ examples:
     #include <dt-bindings/leds/common.h>
 
     i2c {
-      pmic: pmic@4b {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        pmic: pmic@4b {
             compatible = "rohm,bd71837";
             reg = <0x4b>;
             interrupt-parent = <&gpio1>;
diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd71847-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd71847-pmic.yaml
index 402e40dfe0b8..77bcca2d414f 100644
--- a/Documentation/devicetree/bindings/mfd/rohm,bd71847-pmic.yaml
+++ b/Documentation/devicetree/bindings/mfd/rohm,bd71847-pmic.yaml
@@ -128,7 +128,9 @@ examples:
     #include <dt-bindings/leds/common.h>
 
     i2c {
-      pmic: pmic@4b {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        pmic: pmic@4b {
             compatible = "rohm,bd71847";
             reg = <0x4b>;
             interrupt-parent = <&gpio1>;
diff --git a/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml b/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml
index d9ad9260e348..be7faa6dc055 100644
--- a/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml
+++ b/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml
@@ -259,8 +259,6 @@ properties:
 
     additionalProperties: false
 
-  additionalProperties: false
-
 additionalProperties: false
 
 required:
@@ -274,7 +272,7 @@ examples:
   - |
     #include <dt-bindings/mfd/st,stpmic1.h>
     #include <dt-bindings/interrupt-controller/arm-gic.h>
-    i2c@0 {
+    i2c {
       #address-cells = <1>;
       #size-cells = <0>;
       pmic@33 {
diff --git a/Documentation/devicetree/bindings/net/dsa/b53.txt b/Documentation/devicetree/bindings/net/dsa/b53.txt
index 5201bc15fdd6..cfd1afdc6e94 100644
--- a/Documentation/devicetree/bindings/net/dsa/b53.txt
+++ b/Documentation/devicetree/bindings/net/dsa/b53.txt
@@ -110,6 +110,9 @@ Ethernet switch connected via MDIO to the host, CPU port wired to eth0:
 			#size-cells = <0>;
 
 			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
 				port0@0 {
 					reg = <0>;
 					label = "lan1";
diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
index 8927941c74bb..5aa141ccc113 100644
--- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
@@ -45,6 +45,9 @@ properties:
           bits of a vendor specific ID.
       - items:
           - pattern: "^ethernet-phy-id[a-f0-9]{4}\\.[a-f0-9]{4}$"
+          - const: ethernet-phy-ieee802.3-c22
+      - items:
+          - pattern: "^ethernet-phy-id[a-f0-9]{4}\\.[a-f0-9]{4}$"
           - const: ethernet-phy-ieee802.3-c45
 
   reg:
diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt
index 5b88fae0307d..ff8b0f211aa1 100644
--- a/Documentation/devicetree/bindings/net/fsl-fec.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fec.txt
@@ -22,6 +22,8 @@ Optional properties:
 - fsl,err006687-workaround-present: If present indicates that the system has
   the hardware workaround for ERR006687 applied and does not need a software
   workaround.
+- gpr: phandle of SoC general purpose register mode. Required for wake on LAN
+  on some SoCs
  -interrupt-names:  names of the interrupts listed in interrupts property in
   the same order. The defaults if not specified are
   __Number of interrupts__   __Default__
diff --git a/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml b/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml
index b9f90081046f..67df3fe861ee 100644
--- a/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml
+++ b/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml
@@ -48,6 +48,7 @@ examples:
 
         switch@10 {
             compatible = "qca,qca8337";
+            reg = <0x10>;
             /* ... */
         };
     };
diff --git a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml
index 144ae29e7141..f8bd28ff31c1 100644
--- a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml
@@ -97,7 +97,7 @@ then:
         - $ref: /schemas/types.yaml#/definitions/uint32
         - minimum: 0
           maximum: 63
-          default: 0
+          default: 32
 
     qcom,charge-ctrl-value:
      description:
@@ -130,7 +130,7 @@ then:
         - $ref: /schemas/types.yaml#/definitions/uint32
         - minimum: 0
           maximum: 3
-          default: 2
+          default: 0
 
     qcom,preemphasis-width:
       description:
@@ -152,7 +152,7 @@ then:
         - $ref: /schemas/types.yaml#/definitions/uint32
         - minimum: 0
           maximum: 3
-          default: 0
+          default: 1
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/pwm/google,cros-ec-pwm.yaml b/Documentation/devicetree/bindings/pwm/google,cros-ec-pwm.yaml
index 24c217b76580..41ece1d85315 100644
--- a/Documentation/devicetree/bindings/pwm/google,cros-ec-pwm.yaml
+++ b/Documentation/devicetree/bindings/pwm/google,cros-ec-pwm.yaml
@@ -31,10 +31,17 @@ additionalProperties: false
 
 examples:
   - |
-    cros-ec@0 {
-        compatible = "google,cros-ec-spi";
-        cros_ec_pwm: ec-pwm {
-            compatible = "google,cros-ec-pwm";
-            #pwm-cells = <1>;
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        cros-ec@0 {
+            compatible = "google,cros-ec-spi";
+            reg = <0>;
+
+            cros_ec_pwm: ec-pwm {
+                compatible = "google,cros-ec-pwm";
+                #pwm-cells = <1>;
+            };
         };
     };
diff --git a/Documentation/devicetree/bindings/regulator/anatop-regulator.txt b/Documentation/devicetree/bindings/regulator/anatop-regulator.txt
deleted file mode 100644
index a3106c72fbea..000000000000
--- a/Documentation/devicetree/bindings/regulator/anatop-regulator.txt
+++ /dev/null
@@ -1,40 +0,0 @@
-Anatop Voltage regulators
-
-Required properties:
-- compatible: Must be "fsl,anatop-regulator"
-- regulator-name: A string used as a descriptive name for regulator outputs
-- anatop-reg-offset: Anatop MFD register offset
-- anatop-vol-bit-shift: Bit shift for the register
-- anatop-vol-bit-width: Number of bits used in the register
-- anatop-min-bit-val: Minimum value of this register
-- anatop-min-voltage: Minimum voltage of this regulator
-- anatop-max-voltage: Maximum voltage of this regulator
-
-Optional properties:
-- anatop-delay-reg-offset: Anatop MFD step time register offset
-- anatop-delay-bit-shift: Bit shift for the step time register
-- anatop-delay-bit-width: Number of bits used in the step time register
-- vin-supply: The supply for this regulator
-- anatop-enable-bit: Regulator enable bit offset
-
-Any property defined as part of the core regulator
-binding, defined in regulator.txt, can also be used.
-
-Example:
-
-	regulator-vddpu {
-		compatible = "fsl,anatop-regulator";
-		regulator-name = "vddpu";
-		regulator-min-microvolt = <725000>;
-		regulator-max-microvolt = <1300000>;
-		regulator-always-on;
-		anatop-reg-offset = <0x140>;
-		anatop-vol-bit-shift = <9>;
-		anatop-vol-bit-width = <5>;
-		anatop-delay-reg-offset = <0x170>;
-		anatop-delay-bit-shift = <24>;
-		anatop-delay-bit-width = <2>;
-		anatop-min-bit-val = <1>;
-		anatop-min-voltage = <725000>;
-		anatop-max-voltage = <1300000>;
-	};
diff --git a/Documentation/devicetree/bindings/regulator/anatop-regulator.yaml b/Documentation/devicetree/bindings/regulator/anatop-regulator.yaml
new file mode 100644
index 000000000000..e7b3abe30363
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/anatop-regulator.yaml
@@ -0,0 +1,94 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/regulator/anatop-regulator.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale Anatop Voltage Regulators
+
+maintainers:
+  - Ying-Chun Liu (PaulLiu) <paul.liu@linaro.org>
+
+allOf:
+  - $ref: "regulator.yaml#"
+
+properties:
+  compatible:
+    const: fsl,anatop-regulator
+
+  regulator-name: true
+
+  anatop-reg-offset:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing the anatop MFD register offset.
+
+  anatop-vol-bit-shift:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing the bit shift for the register.
+
+  anatop-vol-bit-width:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing the number of bits used in the register.
+
+  anatop-min-bit-val:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing the minimum value of this register.
+
+  anatop-min-voltage:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing the minimum voltage of this regulator.
+
+  anatop-max-voltage:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing the maximum voltage of this regulator.
+
+  anatop-delay-reg-offset:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing the anatop MFD step time register offset.
+
+  anatop-delay-bit-shift:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing the bit shift for the step time register.
+
+  anatop-delay-bit-width:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing the number of bits used in the step time register.
+
+  anatop-enable-bit:
+    $ref: '/schemas/types.yaml#/definitions/uint32'
+    description: u32 value representing regulator enable bit offset.
+
+  vin-supply:
+    $ref: '/schemas/types.yaml#/definitions/phandle'
+    description: input supply phandle.
+
+required:
+  - compatible
+  - regulator-name
+  - anatop-reg-offset
+  - anatop-vol-bit-shift
+  - anatop-vol-bit-width
+  - anatop-min-bit-val
+  - anatop-min-voltage
+  - anatop-max-voltage
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    regulator-vddpu {
+        compatible = "fsl,anatop-regulator";
+        regulator-name = "vddpu";
+        regulator-min-microvolt = <725000>;
+        regulator-max-microvolt = <1300000>;
+        regulator-always-on;
+        anatop-reg-offset = <0x140>;
+        anatop-vol-bit-shift = <9>;
+        anatop-vol-bit-width = <5>;
+        anatop-delay-reg-offset = <0x170>;
+        anatop-delay-bit-shift = <24>;
+        anatop-delay-bit-width = <2>;
+        anatop-min-bit-val = <1>;
+        anatop-min-voltage = <725000>;
+        anatop-max-voltage = <1300000>;
+    };
diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77826.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77826.yaml
new file mode 100644
index 000000000000..19cbd5eb2897
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/maxim,max77826.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/regulator/maxim,max77826.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Maxim Integrated MAX77826 PMIC
+
+maintainers:
+  - Iskren Chernev <iskren.chernev@gmail.com>
+
+properties:
+  $nodename:
+    pattern: "pmic@[0-9a-f]{1,2}"
+  compatible:
+    enum:
+      - maxim,max77826
+
+  reg:
+    maxItems: 1
+
+  regulators:
+    type: object
+    allOf:
+      - $ref: regulator.yaml#
+    description: |
+      list of regulators provided by this controller, must be named
+      after their hardware counterparts LDO[1-15], BUCK and BUCKBOOST
+
+    patternProperties:
+      "^LDO([1-9]|1[0-5])$":
+        type: object
+        allOf:
+          - $ref: regulator.yaml#
+
+      "^BUCK|BUCKBOOST$":
+        type: object
+        allOf:
+          - $ref: regulator.yaml#
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - regulators
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        pmic@69 {
+            compatible = "maxim,max77826";
+            reg = <0x69>;
+
+            regulators {
+                LDO2 {
+                    regulator-min-microvolt = <650000>;
+                    regulator-max-microvolt = <3587500>;
+                };
+            };
+       };
+     };
+...
diff --git a/Documentation/devicetree/bindings/regulator/mps,mp5416.yaml b/Documentation/devicetree/bindings/regulator/mps,mp5416.yaml
index f0acce2029fd..3b019fa6db31 100644
--- a/Documentation/devicetree/bindings/regulator/mps,mp5416.yaml
+++ b/Documentation/devicetree/bindings/regulator/mps,mp5416.yaml
@@ -37,7 +37,6 @@ properties:
         type: object
 
     additionalProperties: false
-  additionalProperties: false
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml b/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml
index a682af0dc67e..ae6e7ab36c58 100644
--- a/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml
+++ b/Documentation/devicetree/bindings/regulator/mps,mpq7920.yaml
@@ -75,7 +75,8 @@ properties:
             description: |
               disables over voltage protection of this buck
 
-      additionalProperties: false
+        unevaluatedProperties: false
+
     additionalProperties: false
 
 required:
diff --git a/Documentation/devicetree/bindings/regulator/rohm,bd71828-regulator.yaml b/Documentation/devicetree/bindings/regulator/rohm,bd71828-regulator.yaml
index 71ce032b8cf8..1e52dafcb5c9 100644
--- a/Documentation/devicetree/bindings/regulator/rohm,bd71828-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/rohm,bd71828-regulator.yaml
@@ -35,6 +35,8 @@ patternProperties:
         description:
           should be "ldo1", ..., "ldo7"
 
+    unevaluatedProperties: false
+
   "^BUCK[1-7]$":
     type: object
     allOf:
@@ -103,5 +105,7 @@ patternProperties:
 
     required:
       - regulator-name
-  additionalProperties: false
+
+    unevaluatedProperties: false
+
 additionalProperties: false
diff --git a/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.yaml b/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.yaml
index a323b1696eee..543d4b52397e 100644
--- a/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.yaml
@@ -41,6 +41,8 @@ patternProperties:
         description:
           should be "ldo1", ..., "ldo7"
 
+    unevaluatedProperties: false
+
   "^BUCK[1-8]$":
     type: object
     allOf:
@@ -99,5 +101,7 @@ patternProperties:
 
     required:
       - regulator-name
-  additionalProperties: false
+
+    unevaluatedProperties: false
+
 additionalProperties: false
diff --git a/Documentation/devicetree/bindings/regulator/rohm,bd71847-regulator.yaml b/Documentation/devicetree/bindings/regulator/rohm,bd71847-regulator.yaml
index 526fd00bcb16..d797cc23406f 100644
--- a/Documentation/devicetree/bindings/regulator/rohm,bd71847-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/rohm,bd71847-regulator.yaml
@@ -40,6 +40,8 @@ patternProperties:
         description:
           should be "ldo1", ..., "ldo6"
 
+    unevaluatedProperties: false
+
   "^BUCK[1-6]$":
     type: object
     allOf:
@@ -93,5 +95,7 @@ patternProperties:
 
     required:
       - regulator-name
-  additionalProperties: false
+
+    unevaluatedProperties: false
+
 additionalProperties: false
diff --git a/Documentation/devicetree/bindings/reserved-memory/ramoops.txt b/Documentation/devicetree/bindings/reserved-memory/ramoops.txt
index 0eba562fe5c6..b7886fea368c 100644
--- a/Documentation/devicetree/bindings/reserved-memory/ramoops.txt
+++ b/Documentation/devicetree/bindings/reserved-memory/ramoops.txt
@@ -30,7 +30,7 @@ Optional properties:
 - ecc-size: enables ECC support and specifies ECC buffer size in bytes
   (defaults to 0: no ECC)
 
-- record-size: maximum size in bytes of each dump done on oops/panic
+- record-size: maximum size in bytes of each kmsg dump.
   (defaults to 0: disabled)
 
 - console-size: size in bytes of log buffer reserved for kernel messages
@@ -45,7 +45,16 @@ Optional properties:
 - unbuffered: if present, use unbuffered mappings to map the reserved region
   (defaults to buffered mappings)
 
-- no-dump-oops: if present, only dump panics (defaults to panics and oops)
+- max-reason: if present, sets maximum type of kmsg dump reasons to store
+  (defaults to 2: log Oopses and Panics). This can be set to INT_MAX to
+  store all kmsg dumps. See include/linux/kmsg_dump.h KMSG_DUMP_* for other
+  kmsg dump reason values. Setting this to 0 (KMSG_DUMP_UNDEF), means the
+  reason filtering will be controlled by the printk.always_kmsg_dump boot
+  param: if unset, it will be KMSG_DUMP_OOPS, otherwise KMSG_DUMP_MAX.
+
+- no-dump-oops: deprecated, use max_reason instead. If present, and
+  max_reason is not specified, it is equivalent to max_reason = 1
+  (KMSG_DUMP_PANIC).
 
 - flags: if present, pass ramoops behavioral flags (defaults to 0,
   see include/linux/pstore_ram.h RAMOOPS_FLAG_* for flag values).
diff --git a/Documentation/devicetree/bindings/rng/arm-cctrng.yaml b/Documentation/devicetree/bindings/rng/arm-cctrng.yaml
new file mode 100644
index 000000000000..ca6aad19b6ba
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/arm-cctrng.yaml
@@ -0,0 +1,54 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rng/arm-cctrng.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Arm TrustZone CryptoCell TRNG engine
+
+maintainers:
+  - Hadar Gat <hadar.gat@arm.com>
+
+description: |+
+  Arm TrustZone CryptoCell TRNG (True Random Number Generator) engine.
+
+properties:
+  compatible:
+    enum:
+      - arm,cryptocell-713-trng
+      - arm,cryptocell-703-trng
+
+  interrupts:
+    maxItems: 1
+
+  reg:
+    maxItems: 1
+
+  arm,rosc-ratio:
+    description:
+      Arm TrustZone CryptoCell TRNG engine has 4 ring oscillators.
+      Sampling ratio values for these 4 ring oscillators. (from calibration)
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/uint32-array
+      - items:
+          maxItems: 4
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - interrupts
+  - reg
+  - arm,rosc-ratio
+
+additionalProperties: false
+
+examples:
+  - |
+    arm_cctrng: rng@60000000 {
+        compatible = "arm,cryptocell-713-trng";
+        interrupts = <0 29 4>;
+        reg = <0x60000000 0x10000>;
+        arm,rosc-ratio = <5000 1000 500 0>;
+    };
diff --git a/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml b/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml
index 89ab67f20a7f..c147900f9041 100644
--- a/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml
+++ b/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml
@@ -39,7 +39,7 @@ additionalProperties: false
 
 examples:
   - |
-    rng {
+    rng@7e104000 {
         compatible = "brcm,bcm2835-rng";
         reg = <0x7e104000 0x10>;
         interrupts = <2 29>;
diff --git a/Documentation/devicetree/bindings/sound/rockchip-i2s.yaml b/Documentation/devicetree/bindings/sound/rockchip-i2s.yaml
index 7cd0e278ed85..a3ba2186d6a1 100644
--- a/Documentation/devicetree/bindings/sound/rockchip-i2s.yaml
+++ b/Documentation/devicetree/bindings/sound/rockchip-i2s.yaml
@@ -56,6 +56,9 @@ properties:
       - const: tx
       - const: rx
 
+  power-domains:
+    maxItems: 1
+
   rockchip,capture-channels:
     allOf:
       - $ref: /schemas/types.yaml#/definitions/uint32
diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.txt b/Documentation/devicetree/bindings/sound/rockchip-spdif.txt
deleted file mode 100644
index ec20c1271e92..000000000000
--- a/Documentation/devicetree/bindings/sound/rockchip-spdif.txt
+++ /dev/null
@@ -1,45 +0,0 @@
-* Rockchip SPDIF transceiver
-
-The S/PDIF audio block is a stereo transceiver that allows the
-processor to receive and transmit digital audio via an coaxial cable or
-a fibre cable.
-
-Required properties:
-
-- compatible: should be one of the following:
-   - "rockchip,rk3066-spdif"
-   - "rockchip,rk3188-spdif"
-   - "rockchip,rk3228-spdif"
-   - "rockchip,rk3288-spdif"
-   - "rockchip,rk3328-spdif"
-   - "rockchip,rk3366-spdif"
-   - "rockchip,rk3368-spdif"
-   - "rockchip,rk3399-spdif"
-- reg: physical base address of the controller and length of memory mapped
-  region.
-- interrupts: should contain the SPDIF interrupt.
-- dmas: DMA specifiers for tx dma. See the DMA client binding,
-  Documentation/devicetree/bindings/dma/dma.txt
-- dma-names: should be "tx"
-- clocks: a list of phandle + clock-specifier pairs, one for each entry
-  in clock-names.
-- clock-names: should contain following:
-   - "hclk": clock for SPDIF controller
-   - "mclk" : clock for SPDIF bus
-
-Required properties on RK3288:
-  - rockchip,grf: the phandle of the syscon node for the general register
-                   file (GRF)
-
-Example for the rk3188 SPDIF controller:
-
-spdif: spdif@1011e000 {
-	compatible = "rockchip,rk3188-spdif", "rockchip,rk3066-spdif";
-	reg = <0x1011e000 0x2000>;
-	interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
-	dmas = <&dmac1_s 8>;
-	dma-names = "tx";
-	clock-names = "hclk", "mclk";
-	clocks = <&cru HCLK_SPDIF>, <&cru SCLK_SPDIF>;
-	#sound-dai-cells = <0>;
-};
diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml
new file mode 100644
index 000000000000..c467152656f7
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml
@@ -0,0 +1,101 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sound/rockchip-spdif.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Rockchip SPDIF transceiver
+
+description:
+  The S/PDIF audio block is a stereo transceiver that allows the
+  processor to receive and transmit digital audio via a coaxial or
+  fibre cable.
+
+maintainers:
+  - Heiko Stuebner <heiko@sntech.de>
+
+properties:
+  compatible:
+    oneOf:
+      - const: rockchip,rk3066-spdif
+      - const: rockchip,rk3228-spdif
+      - const: rockchip,rk3328-spdif
+      - const: rockchip,rk3366-spdif
+      - const: rockchip,rk3368-spdif
+      - const: rockchip,rk3399-spdif
+      - items:
+          - enum:
+            - rockchip,rk3188-spdif
+            - rockchip,rk3288-spdif
+          - const: rockchip,rk3066-spdif
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: clock for SPDIF bus
+      - description: clock for SPDIF controller
+
+  clock-names:
+    items:
+      - const: mclk
+      - const: hclk
+
+  dmas:
+    maxItems: 1
+
+  dma-names:
+    const: tx
+
+  power-domains:
+    maxItems: 1
+
+  rockchip,grf:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      The phandle of the syscon node for the GRF register.
+      Required property on RK3288.
+
+  "#sound-dai-cells":
+    const: 0
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - dmas
+  - dma-names
+  - "#sound-dai-cells"
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: rockchip,rk3288-spdif
+
+then:
+  required:
+    - rockchip,grf
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/rk3188-cru.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    spdif: spdif@1011e000 {
+      compatible = "rockchip,rk3188-spdif", "rockchip,rk3066-spdif";
+      reg = <0x1011e000 0x2000>;
+      interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+      clocks = <&cru SCLK_SPDIF>, <&cru HCLK_SPDIF>;
+      clock-names = "mclk", "hclk";
+      dmas = <&dmac1_s 8>;
+      dma-names = "tx";
+      #sound-dai-cells = <0>;
+    };
diff --git a/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt b/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
index ad7ac80a3841..f5e518d099f2 100644
--- a/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
+++ b/Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.txt
@@ -26,6 +26,16 @@ Required properties:
     "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-qspi" : MSPI+BSPI on BRCMSTB SoCs
     "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
 						   BRCMSTB  SoCs
+    "brcm,spi-bcm7425-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
+    			     			  			    BRCMSTB  SoCs
+    "brcm,spi-bcm7429-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
+    			     			  			    BRCMSTB  SoCs
+    "brcm,spi-bcm7435-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
+    			     			  			    BRCMSTB  SoCs
+    "brcm,spi-bcm7216-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
+    			     			  			    BRCMSTB  SoCs
+    "brcm,spi-bcm7278-qspi", "brcm,spi-bcm-qspi", "brcm,spi-brcmstb-mspi" : Second Instance of MSPI
+    			     			  			    BRCMSTB  SoCs
     "brcm,spi-bcm-qspi", "brcm,spi-nsp-qspi"     : MSPI+BSPI on Cygnus, NSP
     "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi"     : NS2 SoCs
 
diff --git a/Documentation/devicetree/bindings/spi/mikrotik,rb4xx-spi.yaml b/Documentation/devicetree/bindings/spi/mikrotik,rb4xx-spi.yaml
new file mode 100644
index 000000000000..4ddb42a4ae05
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/mikrotik,rb4xx-spi.yaml
@@ -0,0 +1,36 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/mikrotik,rb4xx-spi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MikroTik RB4xx series SPI master
+
+maintainers:
+  - Gabor Juhos <juhosg@openwrt.org>
+  - Bert Vermeulen <bert@biot.com>
+
+allOf:
+  - $ref: "spi-controller.yaml#"
+
+properties:
+  compatible:
+    const: mikrotik,rb4xx-spi
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+
+examples:
+  - |
+    spi: spi@1f000000 {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        compatible = "mikrotik,rb4xx-spi";
+        reg = <0x1f000000 0x10>;
+    };
+
+...
\ No newline at end of file
diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml b/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml
index 0cf470eaf2a0..5c16cf59ca00 100644
--- a/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml
+++ b/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml
@@ -61,7 +61,7 @@ examples:
     #include <dt-bindings/clock/qcom,gcc-sdm845.h>
     #include <dt-bindings/interrupt-controller/arm-gic.h>
 
-    soc: soc@0 {
+    soc: soc {
         #address-cells = <2>;
         #size-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/spi/renesas,rspi.yaml b/Documentation/devicetree/bindings/spi/renesas,rspi.yaml
new file mode 100644
index 000000000000..c54ac059043f
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/renesas,rspi.yaml
@@ -0,0 +1,144 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/renesas,rspi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas (Quad) Serial Peripheral Interface (RSPI/QSPI)
+
+maintainers:
+  - Geert Uytterhoeven <geert+renesas@glider.be>
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - renesas,rspi-sh7757    # SH7757
+          - const: renesas,rspi        # Legacy SH
+
+      - items:
+          - enum:
+              - renesas,rspi-r7s72100  # RZ/A1H
+              - renesas,rspi-r7s9210   # RZ/A2
+          - const: renesas,rspi-rz     # RZ/A
+
+      - items:
+          - enum:
+              - renesas,qspi-r8a7743   # RZ/G1M
+              - renesas,qspi-r8a7744   # RZ/G1N
+              - renesas,qspi-r8a7745   # RZ/G1E
+              - renesas,qspi-r8a77470  # RZ/G1C
+              - renesas,qspi-r8a7790   # R-Car H2
+              - renesas,qspi-r8a7791   # R-Car M2-W
+              - renesas,qspi-r8a7792   # R-Car V2H
+              - renesas,qspi-r8a7793   # R-Car M2-N
+              - renesas,qspi-r8a7794   # R-Car E2
+          - const: renesas,qspi        # R-Car Gen2 and RZ/G1
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    oneOf:
+      - items:
+          - description: A combined interrupt
+      - items:
+          - description: Error interrupt (SPEI)
+          - description: Receive Interrupt (SPRI)
+          - description: Transmit Interrupt (SPTI)
+
+  interrupt-names:
+    oneOf:
+      - items:
+          - const: mux
+      - items:
+          - const: error
+          - const: rx
+          - const: tx
+
+  clocks:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  dmas:
+    description:
+      Must contain a list of pairs of references to DMA specifiers, one for
+      transmission, and one for reception.
+
+  dma-names:
+    minItems: 2
+    maxItems: 4
+    items:
+      enum:
+        - tx
+        - rx
+
+  num-cs:
+    description: |
+      Total number of native chip selects.
+      Hardware limitations related to chip selects:
+        - When using GPIO chip selects, at least one native chip select must
+          be left unused, as it will be driven anyway.
+    minimum: 1
+    maximum: 2
+    default: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - power-domains
+  - '#address-cells'
+  - '#size-cells'
+
+allOf:
+  - $ref: spi-controller.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,rspi-rz
+    then:
+      properties:
+        interrupts:
+          minItems: 3
+      required:
+        - interrupt-names
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,qspi
+    then:
+      required:
+        - resets
+
+examples:
+  - |
+    #include <dt-bindings/clock/r8a7791-cpg-mssr.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/r8a7791-sysc.h>
+
+    qspi: spi@e6b10000 {
+            compatible = "renesas,qspi-r8a7791", "renesas,qspi";
+            reg = <0xe6b10000 0x2c>;
+            interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>;
+            clocks = <&cpg CPG_MOD 917>;
+            dmas = <&dmac0 0x17>, <&dmac0 0x18>, <&dmac1 0x17>, <&dmac1 0x18>;
+            dma-names = "tx", "rx", "tx", "rx";
+            power-domains = <&sysc R8A7791_PD_ALWAYS_ON>;
+            resets = <&cpg 917>;
+            num-cs = <1>;
+            #address-cells = <1>;
+            #size-cells = <0>;
+    };
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
deleted file mode 100644
index 3ed08ee9feba..000000000000
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
+++ /dev/null
@@ -1,41 +0,0 @@
-Synopsys DesignWare AMBA 2.0 Synchronous Serial Interface.
-
-Required properties:
-- compatible : "snps,dw-apb-ssi" or "mscc,<soc>-spi", where soc is "ocelot" or
-  "jaguar2", or "amazon,alpine-dw-apb-ssi"
-- reg : The register base for the controller. For "mscc,<soc>-spi", a second
-  register set is required (named ICPU_CFG:SPI_MST)
-- interrupts : One interrupt, used by the controller.
-- #address-cells : <1>, as required by generic SPI binding.
-- #size-cells : <0>, also as required by generic SPI binding.
-- clocks : phandles for the clocks, see the description of clock-names below.
-   The phandle for the "ssi_clk" is required. The phandle for the "pclk" clock
-   is optional. If a single clock is specified but no clock-name, it is the
-   "ssi_clk" clock. If both clocks are listed, the "ssi_clk" must be first.
-
-Optional properties:
-- clock-names : Contains the names of the clocks:
-    "ssi_clk", for the core clock used to generate the external SPI clock.
-    "pclk", the interface clock, required for register access. If a clock domain
-     used to enable this clock then it should be named "pclk_clkdomain".
-- cs-gpios : Specifies the gpio pins to be used for chipselects.
-- num-cs : The number of chipselects. If omitted, this will default to 4.
-- reg-io-width : The I/O register width (in bytes) implemented by this
-  device.  Supported values are 2 or 4 (the default).
-
-Child nodes as per the generic SPI binding.
-
-Example:
-
-	spi@fff00000 {
-		compatible = "snps,dw-apb-ssi";
-		reg = <0xfff00000 0x1000>;
-		interrupts = <0 154 4>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		clocks = <&spi_m_clk>;
-		num-cs = <2>;
-		cs-gpios = <&gpio0 13 0>,
-			   <&gpio0 14 0>;
-	};
-
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
new file mode 100644
index 000000000000..c62cbe79f00d
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -0,0 +1,133 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/snps,dw-apb-ssi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Synopsys DesignWare AMBA 2.0 Synchronous Serial Interface
+
+maintainers:
+  - Mark Brown <broonie@kernel.org>
+
+allOf:
+  - $ref: "spi-controller.yaml#"
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - mscc,ocelot-spi
+              - mscc,jaguar2-spi
+    then:
+      properties:
+        reg:
+          minItems: 2
+
+properties:
+  compatible:
+    oneOf:
+      - description: Generic DW SPI Controller
+        enum:
+          - snps,dw-apb-ssi
+          - snps,dwc-ssi-1.01a
+      - description: Microsemi Ocelot/Jaguar2 SoC SPI Controller
+        items:
+          - enum:
+              - mscc,ocelot-spi
+              - mscc,jaguar2-spi
+          - const: snps,dw-apb-ssi
+      - description: Amazon Alpine SPI Controller
+        const: amazon,alpine-dw-apb-ssi
+      - description: Renesas RZ/N1 SPI Controller
+        items:
+          - const: renesas,rzn1-spi
+          - const: snps,dw-apb-ssi
+      - description: Intel Keem Bay SPI Controller
+        const: intel,keembay-ssi
+
+  reg:
+    minItems: 1
+    items:
+      - description: DW APB SSI controller memory mapped registers
+      - description: SPI MST region map
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    items:
+      - description: SPI Controller reference clock source
+      - description: APB interface clock source
+
+  clock-names:
+    minItems: 1
+    items:
+      - const: ssi_clk
+      - const: pclk
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    const: spi
+
+  reg-io-width:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: I/O register width (in bytes) implemented by this device
+    default: 4
+    enum: [ 2, 4 ]
+
+  num-cs:
+    default: 4
+    minimum: 1
+    maximum: 4
+
+  dmas:
+    items:
+      - description: TX DMA Channel
+      - description: RX DMA Channel
+
+  dma-names:
+    items:
+      - const: tx
+      - const: rx
+
+patternProperties:
+  "^.*@[0-9a-f]+$":
+    type: object
+    properties:
+      reg:
+        minimum: 0
+        maximum: 3
+
+      spi-rx-bus-width:
+        const: 1
+
+      spi-tx-bus-width:
+        const: 1
+
+unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+  - "#address-cells"
+  - "#size-cells"
+  - interrupts
+  - clocks
+
+examples:
+  - |
+    spi@fff00000 {
+      compatible = "snps,dw-apb-ssi";
+      reg = <0xfff00000 0x1000>;
+      #address-cells = <1>;
+      #size-cells = <0>;
+      interrupts = <0 154 4>;
+      clocks = <&spi_m_clk>;
+      num-cs = <2>;
+      cs-gpios = <&gpio0 13 0>,
+                 <&gpio0 14 0>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/spi/socionext,uniphier-spi.yaml b/Documentation/devicetree/bindings/spi/socionext,uniphier-spi.yaml
new file mode 100644
index 000000000000..c25409298bdf
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/socionext,uniphier-spi.yaml
@@ -0,0 +1,57 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/socionext,uniphier-spi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Socionext UniPhier SPI controller
+
+description: |
+  UniPhier SoCs have SCSSI which supports SPI single channel.
+
+maintainers:
+  - Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
+  - Keiji Hayashibara <hayashibara.keiji@socionext.com>
+
+allOf:
+  - $ref: spi-controller.yaml#
+
+properties:
+  "#address-cells": true
+  "#size-cells": true
+
+  compatible:
+    const: socionext,uniphier-scssi
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - resets
+  - "#address-cells"
+  - "#size-cells"
+
+examples:
+  - |
+    spi0: spi@54006000 {
+        compatible = "socionext,uniphier-scssi";
+        reg = <0x54006000 0x100>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+        interrupts = <0 39 4>;
+        clocks = <&peri_clk 11>;
+        resets = <&peri_rst 11>;
+    };
diff --git a/Documentation/devicetree/bindings/spi/spi-dw.txt b/Documentation/devicetree/bindings/spi/spi-dw.txt
deleted file mode 100644
index 7b63ed601990..000000000000
--- a/Documentation/devicetree/bindings/spi/spi-dw.txt
+++ /dev/null
@@ -1,24 +0,0 @@
-Synopsys DesignWare SPI master
-
-Required properties:
-- compatible: should be "snps,designware-spi"
-- #address-cells: see spi-bus.txt
-- #size-cells: see spi-bus.txt
-- reg: address and length of the spi master registers
-- interrupts: should contain one interrupt
-- clocks: spi clock phandle
-- num-cs: see spi-bus.txt
-
-Optional properties:
-- cs-gpios: see spi-bus.txt
-
-Example:
-
-spi: spi@4020a000 {
-	compatible = "snps,designware-spi";
-	interrupts = <11 1>;
-	reg = <0x4020a000 0x1000>;
-	clocks = <&pclk>;
-	num-cs = <2>;
-	cs-gpios = <&banka 0 0>;
-};
diff --git a/Documentation/devicetree/bindings/spi/spi-rspi.txt b/Documentation/devicetree/bindings/spi/spi-rspi.txt
deleted file mode 100644
index 421722b93992..000000000000
--- a/Documentation/devicetree/bindings/spi/spi-rspi.txt
+++ /dev/null
@@ -1,73 +0,0 @@
-Device tree configuration for Renesas RSPI/QSPI driver
-
-Required properties:
-- compatible       : For Renesas Serial Peripheral Interface on legacy SH:
-		     "renesas,rspi-<soctype>", "renesas,rspi" as fallback.
-		     For Renesas Serial Peripheral Interface on RZ/A:
-		     "renesas,rspi-<soctype>", "renesas,rspi-rz" as fallback.
-		     For Quad Serial Peripheral Interface on R-Car Gen2 and
-		     RZ/G1 devices:
-		     "renesas,qspi-<soctype>", "renesas,qspi" as fallback.
-		     Examples with soctypes are:
-		        - "renesas,rspi-sh7757" (SH)
-			- "renesas,rspi-r7s72100" (RZ/A1H)
-			- "renesas,rspi-r7s9210" (RZ/A2)
-			- "renesas,qspi-r8a7743" (RZ/G1M)
-			- "renesas,qspi-r8a7744" (RZ/G1N)
-			- "renesas,qspi-r8a7745" (RZ/G1E)
-			- "renesas,qspi-r8a77470" (RZ/G1C)
-			- "renesas,qspi-r8a7790" (R-Car H2)
-			- "renesas,qspi-r8a7791" (R-Car M2-W)
-			- "renesas,qspi-r8a7792" (R-Car V2H)
-			- "renesas,qspi-r8a7793" (R-Car M2-N)
-			- "renesas,qspi-r8a7794" (R-Car E2)
-- reg              : Address start and address range size of the device
-- interrupts       : A list of interrupt-specifiers, one for each entry in
-		     interrupt-names.
-		     If interrupt-names is not present, an interrupt specifier
-		     for a single muxed interrupt.
-- interrupt-names  : A list of interrupt names. Should contain (if present):
-		       - "error" for SPEI,
-		       - "rx" for SPRI,
-		       - "tx" to SPTI,
-		       - "mux" for a single muxed interrupt.
-- num-cs	   : Number of chip selects. Some RSPI cores have more than 1.
-- #address-cells   : Must be <1>
-- #size-cells      : Must be <0>
-
-Optional properties:
-- clocks           : Must contain a reference to the functional clock.
-- dmas             : Must contain a list of two references to DMA specifiers,
-		     one for transmission, and one for reception.
-- dma-names        : Must contain a list of two DMA names, "tx" and "rx".
-
-Pinctrl properties might be needed, too.  See
-Documentation/devicetree/bindings/pinctrl/renesas,*.
-
-Examples:
-
-	spi0: spi@e800c800 {
-		compatible = "renesas,rspi-r7s72100", "renesas,rspi-rz";
-		reg = <0xe800c800 0x24>;
-		interrupts = <0 238 IRQ_TYPE_LEVEL_HIGH>,
-			     <0 239 IRQ_TYPE_LEVEL_HIGH>,
-			     <0 240 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "error", "rx", "tx";
-		interrupt-parent = <&gic>;
-		num-cs = <1>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-	};
-
-	spi: spi@e6b10000 {
-		compatible = "renesas,qspi-r8a7791", "renesas,qspi";
-		reg = <0 0xe6b10000 0 0x2c>;
-		interrupt-parent = <&gic>;
-		interrupts = <0 184 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&mstp9_clks R8A7791_CLK_QSPI_MOD>;
-		num-cs = <1>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		dmas = <&dmac0 0x17>, <&dmac0 0x18>;
-		dma-names = "tx", "rx";
-	};
diff --git a/Documentation/devicetree/bindings/spi/spi-uniphier.txt b/Documentation/devicetree/bindings/spi/spi-uniphier.txt
deleted file mode 100644
index e1201573a29a..000000000000
--- a/Documentation/devicetree/bindings/spi/spi-uniphier.txt
+++ /dev/null
@@ -1,28 +0,0 @@
-Socionext UniPhier SPI controller driver
-
-UniPhier SoCs have SCSSI which supports SPI single channel.
-
-Required properties:
- - compatible: should be "socionext,uniphier-scssi"
- - reg: address and length of the spi master registers
- - #address-cells: must be <1>, see spi-bus.txt
- - #size-cells: must be <0>, see spi-bus.txt
- - interrupts: a single interrupt specifier
- - pinctrl-names: should be "default"
- - pinctrl-0: pin control state for the default mode
- - clocks: a phandle to the clock for the device
- - resets: a phandle to the reset control for the device
-
-Example:
-
-spi0: spi@54006000 {
-	compatible = "socionext,uniphier-scssi";
-	reg = <0x54006000 0x100>;
-	#address-cells = <1>;
-	#size-cells = <0>;
-	interrupts = <0 39 4>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_spi0>;
-	clocks = <&peri_clk 11>;
-	resets = <&peri_rst 11>;
-};
diff --git a/Documentation/devicetree/bindings/spi/ti_qspi.txt b/Documentation/devicetree/bindings/spi/ti_qspi.txt
index e65fde4a7388..47b184bce414 100644
--- a/Documentation/devicetree/bindings/spi/ti_qspi.txt
+++ b/Documentation/devicetree/bindings/spi/ti_qspi.txt
@@ -29,7 +29,7 @@ modification to bootloader.
 Example:
 
 For am4372:
-qspi: qspi@4b300000 {
+qspi: qspi@47900000 {
 	compatible = "ti,am4372-qspi";
 	reg = <0x47900000 0x100>, <0x30000000 0x4000000>;
 	reg-names = "qspi_base", "qspi_mmap";
diff --git a/Documentation/devicetree/bindings/usb/ingenic,musb.yaml b/Documentation/devicetree/bindings/usb/ingenic,musb.yaml
index 1d6877875077..c2d2ee43ba67 100644
--- a/Documentation/devicetree/bindings/usb/ingenic,musb.yaml
+++ b/Documentation/devicetree/bindings/usb/ingenic,musb.yaml
@@ -56,7 +56,7 @@ additionalProperties: false
 examples:
   - |
     #include <dt-bindings/clock/jz4740-cgu.h>
-    usb_phy: usb-phy@0 {
+    usb_phy: usb-phy {
       compatible = "usb-nop-xceiv";
       #phy-cells = <0>;
     };
diff --git a/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml b/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml
index 92d8631b9aa6..031452aa25bc 100644
--- a/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml
+++ b/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml
@@ -18,6 +18,7 @@ properties:
           - renesas,r8a774c0-usb3-peri # RZ/G2E
           - renesas,r8a7795-usb3-peri  # R-Car H3
           - renesas,r8a7796-usb3-peri  # R-Car M3-W
+          - renesas,r8a77961-usb3-peri # R-Car M3-W+
           - renesas,r8a77965-usb3-peri # R-Car M3-N
           - renesas,r8a77990-usb3-peri # R-Car E3
       - const: renesas,rcar-gen3-usb3-peri
diff --git a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
index 469affa872d3..a7ae95598ccb 100644
--- a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
+++ b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
@@ -40,6 +40,7 @@ properties:
               - renesas,usbhs-r8a774c0 # RZ/G2E
               - renesas,usbhs-r8a7795  # R-Car H3
               - renesas,usbhs-r8a7796  # R-Car M3-W
+              - renesas,usbhs-r8a77961 # R-Car M3-W+
               - renesas,usbhs-r8a77965 # R-Car M3-N
               - renesas,usbhs-r8a77990 # R-Car E3
               - renesas,usbhs-r8a77995 # R-Car D3
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt
index 3f378951d624..dc025f126d71 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt
@@ -16,7 +16,8 @@ Required properties:
     - "renesas,xhci-r8a7791" for r8a7791 SoC
     - "renesas,xhci-r8a7793" for r8a7793 SoC
     - "renesas,xhci-r8a7795" for r8a7795 SoC
-    - "renesas,xhci-r8a7796" for r8a7796 SoC
+    - "renesas,xhci-r8a7796" for r8a77960 SoC
+    - "renesas,xhci-r8a77961" for r8a77961 SoC
     - "renesas,xhci-r8a77965" for r8a77965 SoC
     - "renesas,xhci-r8a77990" for r8a77990 SoC
     - "renesas,rcar-gen2-xhci" for a generic R-Car Gen2 or RZ/G1 compatible
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index d3891386d671..d3277fe6640b 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -633,6 +633,8 @@ patternProperties:
     description: Microsoft Corporation
   "^mikroe,.*":
     description: MikroElektronika d.o.o.
+  "^mikrotik,.*":
+    description: MikroTik
   "^miniand,.*":
     description: Miniand Tech
   "^minix,.*":
diff --git a/Documentation/fb/efifb.rst b/Documentation/fb/efifb.rst
index 04840331a00e..6badff64756f 100644
--- a/Documentation/fb/efifb.rst
+++ b/Documentation/fb/efifb.rst
@@ -2,8 +2,10 @@
 What is efifb?
 ==============
 
-This is a generic EFI platform driver for Intel based Apple computers.
-efifb is only for EFI booted Intel Macs.
+This is a generic EFI platform driver for systems with UEFI firmware. The
+system must be booted via the EFI stub for this to be usable. efifb supports
+both firmware with Graphics Output Protocol (GOP) displays as well as older
+systems with only Universal Graphics Adapter (UGA) displays.
 
 Supported Hardware
 ==================
@@ -12,11 +14,14 @@ Supported Hardware
 - Macbook
 - Macbook Pro 15"/17"
 - MacMini
+- ARM/ARM64/X86 systems with UEFI firmware
 
 How to use it?
 ==============
 
-efifb does not have any kind of autodetection of your machine.
+For UGA displays, efifb does not have any kind of autodetection of your
+machine.
+
 You have to add the following kernel parameters in your elilo.conf::
 
 	Macbook :
@@ -28,6 +33,9 @@ You have to add the following kernel parameters in your elilo.conf::
 	Macbook Pro 17", iMac 20" :
 		video=efifb:i20
 
+For GOP displays, efifb can autodetect the display's resolution and framebuffer
+address, so these should work out of the box without any special parameters.
+
 Accepted options:
 
 ======= ===========================================================
@@ -36,4 +44,28 @@ nowc	Don't map the framebuffer write combined. This can be used
 	when large amounts of console data are written.
 ======= ===========================================================
 
+Options for GOP displays:
+
+mode=n
+        The EFI stub will set the mode of the display to mode number n if
+        possible.
+
+<xres>x<yres>[-(rgb|bgr|<bpp>)]
+        The EFI stub will search for a display mode that matches the specified
+        horizontal and vertical resolution, and optionally bit depth, and set
+        the mode of the display to it if one is found. The bit depth can either
+        "rgb" or "bgr" to match specifically those pixel formats, or a number
+        for a mode with matching bits per pixel.
+
+auto
+        The EFI stub will choose the mode with the highest resolution (product
+        of horizontal and vertical resolution). If there are multiple modes
+        with the highest resolution, it will choose one with the highest color
+        depth.
+
+list
+        The EFI stub will list out all the display modes that are available. A
+        specific mode can then be chosen using one of the above options for the
+        next boot.
+
 Edgar Hucek <gimli@dark-green.com>
diff --git a/Documentation/filesystems/debugfs.rst b/Documentation/filesystems/debugfs.rst
index 0cfeca376169..1da7a4b7383d 100644
--- a/Documentation/filesystems/debugfs.rst
+++ b/Documentation/filesystems/debugfs.rst
@@ -79,8 +79,8 @@ created with any of::
 			   struct dentry *parent, u8 *value);
     void debugfs_create_u16(const char *name, umode_t mode,
 			    struct dentry *parent, u16 *value);
-    struct dentry *debugfs_create_u32(const char *name, umode_t mode,
-				      struct dentry *parent, u32 *value);
+    void debugfs_create_u32(const char *name, umode_t mode,
+			    struct dentry *parent, u32 *value);
     void debugfs_create_u64(const char *name, umode_t mode,
 			    struct dentry *parent, u64 *value);
 
diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index 87d794bc75a4..4218ac658629 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -225,8 +225,12 @@ fsync_mode=%s          Control the policy of fsync. Currently supports "posix",
                        pass, but the performance will regress. "nobarrier" is
                        based on "posix", but doesn't issue flush command for
                        non-atomic files likewise "nobarrier" mount option.
-test_dummy_encryption  Enable dummy encryption, which provides a fake fscrypt
+test_dummy_encryption
+test_dummy_encryption=%s
+                       Enable dummy encryption, which provides a fake fscrypt
                        context. The fake fscrypt context is used by xfstests.
+                       The argument may be either "v1" or "v2", in order to
+                       select the corresponding fscrypt policy version.
 checkpoint=%s[:%u[%]]  Set to "disable" to turn off checkpointing. Set to "enable"
                        to reenable checkpointing. Is enabled by default. While
                        disabled, any unmounting or unexpected shutdowns will cause
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index aa072112cfff..f517af8ec11c 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -292,8 +292,22 @@ files' data differently, inode numbers are included in the IVs.
 Consequently, shrinking the filesystem may not be allowed.
 
 This format is optimized for use with inline encryption hardware
-compliant with the UFS or eMMC standards, which support only 64 IV
-bits per I/O request and may have only a small number of keyslots.
+compliant with the UFS standard, which supports only 64 IV bits per
+I/O request and may have only a small number of keyslots.
+
+IV_INO_LBLK_32 policies
+-----------------------
+
+IV_INO_LBLK_32 policies work like IV_INO_LBLK_64, except that for
+IV_INO_LBLK_32, the inode number is hashed with SipHash-2-4 (where the
+SipHash key is derived from the master key) and added to the file
+logical block number mod 2^32 to produce a 32-bit IV.
+
+This format is optimized for use with inline encryption hardware
+compliant with the eMMC v5.2 standard, which supports only 32 IV bits
+per I/O request and may have only a small number of keyslots.  This
+format results in some level of IV reuse, so it should only be used
+when necessary due to hardware limitations.
 
 Key identifiers
 ---------------
@@ -369,6 +383,10 @@ a little endian number, except that:
   to 32 bits and is placed in bits 0-31 of the IV.  The inode number
   (which is also limited to 32 bits) is placed in bits 32-63.
 
+- With `IV_INO_LBLK_32 policies`_, the logical block number is limited
+  to 32 bits and is placed in bits 0-31 of the IV.  The inode number
+  is then hashed and added mod 2^32.
+
 Note that because file logical block numbers are included in the IVs,
 filesystems must enforce that blocks are never shifted around within
 encrypted files, e.g. via "collapse range" or "insert range".
@@ -465,8 +483,15 @@ This structure must be initialized as follows:
     (0x3).
   - FSCRYPT_POLICY_FLAG_DIRECT_KEY: See `DIRECT_KEY policies`_.
   - FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64: See `IV_INO_LBLK_64
-    policies`_.  This is mutually exclusive with DIRECT_KEY and is not
-    supported on v1 policies.
+    policies`_.
+  - FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32: See `IV_INO_LBLK_32
+    policies`_.
+
+  v1 encryption policies only support the PAD_* and DIRECT_KEY flags.
+  The other flags are only supported by v2 encryption policies.
+
+  The DIRECT_KEY, IV_INO_LBLK_64, and IV_INO_LBLK_32 flags are
+  mutually exclusive.
 
 - For v2 encryption policies, ``__reserved`` must be zeroed.
 
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index a567bcccbb02..06d41c0b91cc 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -543,6 +543,7 @@ encoded manner. The codes are the following:
     hg    huge page advise flag
     nh    no huge page advise flag
     mg    mergable advise flag
+    bt  - arm64 BTI guarded page
     ==    =======================================
 
 Note that there is no guarantee that every flag and associated mnemonic will
diff --git a/Documentation/hwmon/amd_energy.rst b/Documentation/hwmon/amd_energy.rst
new file mode 100644
index 000000000000..f8288edff664
--- /dev/null
+++ b/Documentation/hwmon/amd_energy.rst
@@ -0,0 +1,109 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Kernel driver amd_energy
+==========================
+
+Supported chips:
+
+* AMD Family 17h Processors
+
+  Prefix: 'amd_energy'
+
+  Addresses used:  RAPL MSRs
+
+  Datasheets:
+
+  - Processor Programming Reference (PPR) for AMD Family 17h Model 01h, Revision B1 Processors
+
+	https://developer.amd.com/wp-content/resources/55570-B1_PUB.zip
+
+  - Preliminary Processor Programming Reference (PPR) for AMD Family 17h Model 31h, Revision B0 Processors
+
+	https://developer.amd.com/wp-content/resources/56176_ppr_Family_17h_Model_71h_B0_pub_Rev_3.06.zip
+
+Author: Naveen Krishna Chatradhi <nchatrad@amd.com>
+
+Description
+-----------
+
+The Energy driver exposes the energy counters that are
+reported via the Running Average Power Limit (RAPL)
+Model-specific Registers (MSRs) via the hardware monitor
+(HWMON) sysfs interface.
+
+1. Power, Energy and Time Units
+   MSR_RAPL_POWER_UNIT/ C001_0299:
+   shared with all cores in the socket
+
+2. Energy consumed by each Core
+   MSR_CORE_ENERGY_STATUS/ C001_029A:
+   32-bitRO, Accumulator, core-level power reporting
+
+3. Energy consumed by Socket
+   MSR_PACKAGE_ENERGY_STATUS/ C001_029B:
+   32-bitRO, Accumulator, socket-level power reporting,
+   shared with all cores in socket
+
+These registers are updated every 1ms and cleared on
+reset of the system.
+
+Note: If SMT is enabled, Linux enumerates all threads as cpus.
+Since, the energy status registers are accessed at core level,
+reading those registers from the sibling threads would result
+in duplicate values. Hence, energy counter entries are not
+populated for the siblings.
+
+Energy Caluclation
+------------------
+
+Energy information (in Joules) is based on the multiplier,
+1/2^ESU; where ESU is an unsigned integer read from
+MSR_RAPL_POWER_UNIT register. Default value is 10000b,
+indicating energy status unit is 15.3 micro-Joules increment.
+
+Reported values are scaled as per the formula
+
+scaled value = ((1/2^ESU) * (Raw value) * 1000000UL) in uJoules
+
+Users calculate power for a given domain by calculating
+	dEnergy/dTime for that domain.
+
+Energy accumulation
+--------------------------
+
+Current, Socket energy status register is 32bit, assuming a 240W
+2P system, the register would wrap around in
+
+	2^32*15.3 e-6/240 * 2 = 547.60833024 secs to wrap(~9 mins)
+
+The Core energy register may wrap around after several days.
+
+To improve the wrap around time, a kernel thread is implemented
+to accumulate the socket energy counters and one core energy counter
+per run to a respective 64-bit counter. The kernel thread starts
+running during probe, wakes up every 100secs and stops running
+when driver is removed.
+
+A socket and core energy read would return the current register
+value added to the respective energy accumulator.
+
+Sysfs attributes
+----------------
+
+=============== ========  =====================================
+Attribute	Label	  Description
+===============	========  =====================================
+
+* For index N between [1] and [nr_cpus]
+
+===============	========  ======================================
+energy[N]_input EcoreX	  Core Energy   X = [0] to [nr_cpus - 1]
+			  Measured input core energy
+===============	========  ======================================
+
+* For N between [nr_cpus] and [nr_cpus + nr_socks]
+
+===============	========  ======================================
+energy[N]_input EsocketX  Socket Energy X = [0] to [nr_socks -1]
+			  Measured input socket energy
+=============== ========  ======================================
diff --git a/Documentation/hwmon/bt1-pvt.rst b/Documentation/hwmon/bt1-pvt.rst
new file mode 100644
index 000000000000..cbb0c0613132
--- /dev/null
+++ b/Documentation/hwmon/bt1-pvt.rst
@@ -0,0 +1,117 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+Kernel driver bt1-pvt
+=====================
+
+Supported chips:
+
+  * Baikal-T1 PVT sensor (in SoC)
+
+    Prefix: 'bt1-pvt'
+
+    Addresses scanned: -
+
+    Datasheet: Provided by BAIKAL ELECTRONICS upon request and under NDA
+
+Authors:
+    Maxim Kaurkin <maxim.kaurkin@baikalelectronics.ru>
+    Serge Semin <Sergey.Semin@baikalelectronics.ru>
+
+Description
+-----------
+
+This driver implements support for the hardware monitoring capabilities of the
+embedded into Baikal-T1 process, voltage and temperature sensors. PVT IP-core
+consists of one temperature and four voltage sensors, which can be used to
+monitor the chip internal environment like heating, supply voltage and
+transistors performance. The driver can optionally provide the hwmon alarms
+for each sensor the PVT controller supports. The alarms functionality is made
+compile-time configurable due to the hardware interface implementation
+peculiarity, which is connected with an ability to convert data from only one
+sensor at a time. Additional limitation is that the controller performs the
+thresholds checking synchronously with the data conversion procedure. Due to
+these in order to have the hwmon alarms automatically detected the driver code
+must switch from one sensor to another, read converted data and manually check
+the threshold status bits. Depending on the measurements timeout settings
+(update_interval sysfs node value) this design may cause additional burden on
+the system performance. So in case if alarms are unnecessary in your system
+design it's recommended to have them disabled to prevent the PVT IRQs being
+periodically raised to get the data cache/alarms status up to date. By default
+in alarm-less configuration the data conversion is performed by the driver
+on demand when read operation is requested via corresponding _input-file.
+
+Temperature Monitoring
+----------------------
+
+Temperature is measured with 10-bit resolution and reported in millidegree
+Celsius. The driver performs all the scaling by itself therefore reports true
+temperatures that don't need any user-space adjustments. While the data
+translation formulae isn't linear, which gives us non-linear discreteness,
+it's close to one, but giving a bit better accuracy for higher temperatures.
+The temperature input is mapped as follows (the last column indicates the input
+ranges)::
+
+	temp1: CPU embedded diode	-48.38C - +147.438C
+
+In case if the alarms kernel config is enabled in the driver the temperature input
+has associated min and max limits which trigger an alarm when crossed.
+
+Voltage Monitoring
+------------------
+
+The voltage inputs are also sampled with 10-bit resolution and reported in
+millivolts. But in this case the data translation formulae is linear, which
+provides a constant measurements discreteness. The data scaling is also
+performed by the driver, so returning true millivolts. The voltage inputs are
+mapped as follows (the last column indicates the input ranges)::
+
+	in0: VDD		(processor core)		0.62V - 1.168V
+	in1: Low-Vt		(low voltage threshold)		0.62V - 1.168V
+	in2: High-Vt		(high voltage threshold)	0.62V - 1.168V
+	in3: Standard-Vt	(standard voltage threshold)	0.62V - 1.168V
+
+In case if the alarms config is enabled in the driver the voltage inputs
+have associated min and max limits which trigger an alarm when crossed.
+
+Sysfs Attributes
+----------------
+
+Following is a list of all sysfs attributes that the driver provides, their
+permissions and a short description:
+
+=============================== ======= =======================================
+Name				Perm	Description
+=============================== ======= =======================================
+update_interval			RW	Measurements update interval per
+					sensor.
+temp1_type			RO	Sensor type (always 1 as CPU embedded
+					diode).
+temp1_label			RO	CPU Core Temperature sensor.
+temp1_input			RO	Measured temperature in millidegree
+					Celsius.
+temp1_min			RW	Low limit for temp input.
+temp1_max			RW	High limit for temp input.
+temp1_min_alarm			RO	Temperature input alarm. Returns 1 if
+					temperature input went below min limit,
+					0 otherwise.
+temp1_max_alarm			RO	Temperature input alarm. Returns 1 if
+					temperature input went above max limit,
+					0 otherwise.
+temp1_offset			RW	Temperature offset in millidegree
+					Celsius which is added to the
+					temperature reading by the chip. It can
+					be used to manually adjust the
+					temperature measurements within 7.130
+					degrees Celsius.
+in[0-3]_label			RO	CPU Voltage sensor (either core or
+					low/high/standard thresholds).
+in[0-3]_input			RO	Measured voltage in millivolts.
+in[0-3]_min			RW	Low limit for voltage input.
+in[0-3]_max			RW	High limit for voltage input.
+in[0-3]_min_alarm		RO	Voltage input alarm. Returns 1 if
+					voltage input went below min limit,
+					0 otherwise.
+in[0-3]_max_alarm		RO	Voltage input alarm. Returns 1 if
+					voltage input went above max limit,
+					0 otherwise.
+=============================== ======= =======================================
diff --git a/Documentation/hwmon/gsc-hwmon.rst b/Documentation/hwmon/gsc-hwmon.rst
new file mode 100644
index 000000000000..ffac392a7129
--- /dev/null
+++ b/Documentation/hwmon/gsc-hwmon.rst
@@ -0,0 +1,53 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Kernel driver gsc-hwmon
+=======================
+
+Supported chips: Gateworks GSC
+Datasheet: http://trac.gateworks.com/wiki/gsc
+Author: Tim Harvey <tharvey@gateworks.com>
+
+Description:
+------------
+
+This driver supports hardware monitoring for the temperature sensor,
+various ADC's connected to the GSC, and optional FAN controller available
+on some boards.
+
+
+Voltage Monitoring
+------------------
+
+The voltage inputs are scaled either internally or by the driver depending
+on the GSC version and firmware. The values returned by the driver do not need
+further scaling. The voltage input labels provide the voltage rail name:
+
+inX_input                  Measured voltage (mV).
+inX_label                  Name of voltage rail.
+
+
+Temperature Monitoring
+----------------------
+
+Temperatures are measured with 12-bit or 10-bit resolution and are scaled
+either internally or by the driver depending on the GSC version and firmware.
+The values returned by the driver reflect millidegree Celcius:
+
+tempX_input                Measured temperature.
+tempX_label                Name of temperature input.
+
+
+PWM Output Control
+------------------
+
+The GSC features 1 PWM output that operates in automatic mode where the
+PWM value will be scalled depending on 6 temperature boundaries.
+The tempeature boundaries are read-write and in millidegree Celcius and the
+read-only PWM values range from 0 (off) to 255 (full speed).
+Fan speed will be set to minimum (off) when the temperature sensor reads
+less than pwm1_auto_point1_temp and maximum when the temperature sensor
+equals or exceeds pwm1_auto_point6_temp.
+
+pwm1_auto_point[1-6]_pwm       PWM value.
+pwm1_auto_point[1-6]_temp      Temperature boundary.
+
diff --git a/Documentation/hwmon/ina2xx.rst b/Documentation/hwmon/ina2xx.rst
index 94b9a260c518..ed81f5416331 100644
--- a/Documentation/hwmon/ina2xx.rst
+++ b/Documentation/hwmon/ina2xx.rst
@@ -99,6 +99,25 @@ Sysfs entries for ina226, ina230 and ina231 only
 ------------------------------------------------
 
 ======================= ====================================================
+in0_lcrit		Critical low shunt voltage
+in0_crit		Critical high shunt voltage
+in0_lcrit_alarm		Shunt voltage critical low alarm
+in0_crit_alarm		Shunt voltage critical high alarm
+in1_lcrit		Critical low bus voltage
+in1_crit		Critical high bus voltage
+in1_lcrit_alarm		Bus voltage critical low alarm
+in1_crit_alarm		Bus voltage critical high alarm
+power1_crit		Critical high power
+power1_crit_alarm	Power critical high alarm
 update_interval		data conversion time; affects number of samples used
 			to average results for shunt and bus voltages.
 ======================= ====================================================
+
+.. note::
+
+   - Configure `shunt_resistor` before configure `power1_crit`, because power
+     value is calculated based on `shunt_resistor` set.
+   - Because of the underlying register implementation, only one `*crit` setting
+     and its `alarm` can be active. Writing to one `*crit` setting clears other
+     `*crit` settings and alarms. Writing 0 to any `*crit` setting clears all
+     `*crit` settings and alarms.
diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst
index 8ef62fd39787..005bf9e124bb 100644
--- a/Documentation/hwmon/index.rst
+++ b/Documentation/hwmon/index.rst
@@ -39,10 +39,12 @@ Hardware Monitoring Kernel Drivers
    adt7470
    adt7475
    amc6821
+   amd_energy
    asb100
    asc7621
    aspeed-pwm-tacho
    bel-pfe
+   bt1-pvt
    coretemp
    da9052
    da9055
@@ -60,6 +62,7 @@ Hardware Monitoring Kernel Drivers
    ftsteutates
    g760a
    g762
+   gsc-hwmon
    gl518sm
    hih6130
    ibmaem
@@ -106,6 +109,7 @@ Hardware Monitoring Kernel Drivers
    max16064
    max16065
    max1619
+   max16601
    max1668
    max197
    max20730
diff --git a/Documentation/hwmon/isl68137.rst b/Documentation/hwmon/isl68137.rst
index cc4b61447b63..0e71b22047f8 100644
--- a/Documentation/hwmon/isl68137.rst
+++ b/Documentation/hwmon/isl68137.rst
@@ -16,7 +16,7 @@ Supported chips:
 
   * Renesas ISL68220
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl68220'
 
     Addresses scanned: -
 
@@ -26,7 +26,7 @@ Supported chips:
 
   * Renesas ISL68221
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl68221'
 
     Addresses scanned: -
 
@@ -36,7 +36,7 @@ Supported chips:
 
   * Renesas ISL68222
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl68222'
 
     Addresses scanned: -
 
@@ -46,7 +46,7 @@ Supported chips:
 
   * Renesas ISL68223
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl68223'
 
     Addresses scanned: -
 
@@ -56,7 +56,7 @@ Supported chips:
 
   * Renesas ISL68224
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl68224'
 
     Addresses scanned: -
 
@@ -66,7 +66,7 @@ Supported chips:
 
   * Renesas ISL68225
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl68225'
 
     Addresses scanned: -
 
@@ -76,7 +76,7 @@ Supported chips:
 
   * Renesas ISL68226
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl68226'
 
     Addresses scanned: -
 
@@ -86,7 +86,7 @@ Supported chips:
 
   * Renesas ISL68227
 
-    Prefix: 'raa_dmpvr2_1rail'
+    Prefix: 'isl68227'
 
     Addresses scanned: -
 
@@ -96,7 +96,7 @@ Supported chips:
 
   * Renesas ISL68229
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl68229'
 
     Addresses scanned: -
 
@@ -106,7 +106,7 @@ Supported chips:
 
   * Renesas ISL68233
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl68233'
 
     Addresses scanned: -
 
@@ -116,7 +116,7 @@ Supported chips:
 
   * Renesas ISL68239
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl68239'
 
     Addresses scanned: -
 
@@ -126,7 +126,7 @@ Supported chips:
 
   * Renesas ISL69222
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69222'
 
     Addresses scanned: -
 
@@ -136,7 +136,7 @@ Supported chips:
 
   * Renesas ISL69223
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl69223'
 
     Addresses scanned: -
 
@@ -146,7 +146,7 @@ Supported chips:
 
   * Renesas ISL69224
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69224'
 
     Addresses scanned: -
 
@@ -156,7 +156,7 @@ Supported chips:
 
   * Renesas ISL69225
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69225'
 
     Addresses scanned: -
 
@@ -166,7 +166,7 @@ Supported chips:
 
   * Renesas ISL69227
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl69227'
 
     Addresses scanned: -
 
@@ -176,7 +176,7 @@ Supported chips:
 
   * Renesas ISL69228
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl69228'
 
     Addresses scanned: -
 
@@ -186,7 +186,7 @@ Supported chips:
 
   * Renesas ISL69234
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69234'
 
     Addresses scanned: -
 
@@ -196,7 +196,7 @@ Supported chips:
 
   * Renesas ISL69236
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69236'
 
     Addresses scanned: -
 
@@ -206,7 +206,7 @@ Supported chips:
 
   * Renesas ISL69239
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl69239'
 
     Addresses scanned: -
 
@@ -216,7 +216,7 @@ Supported chips:
 
   * Renesas ISL69242
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69242'
 
     Addresses scanned: -
 
@@ -226,7 +226,7 @@ Supported chips:
 
   * Renesas ISL69243
 
-    Prefix: 'raa_dmpvr2_1rail'
+    Prefix: 'isl69243'
 
     Addresses scanned: -
 
@@ -236,7 +236,7 @@ Supported chips:
 
   * Renesas ISL69247
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69247'
 
     Addresses scanned: -
 
@@ -246,7 +246,7 @@ Supported chips:
 
   * Renesas ISL69248
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69248'
 
     Addresses scanned: -
 
@@ -256,7 +256,7 @@ Supported chips:
 
   * Renesas ISL69254
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69254'
 
     Addresses scanned: -
 
@@ -266,7 +266,7 @@ Supported chips:
 
   * Renesas ISL69255
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69255'
 
     Addresses scanned: -
 
@@ -276,7 +276,7 @@ Supported chips:
 
   * Renesas ISL69256
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69256'
 
     Addresses scanned: -
 
@@ -286,7 +286,7 @@ Supported chips:
 
   * Renesas ISL69259
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69259'
 
     Addresses scanned: -
 
@@ -296,7 +296,7 @@ Supported chips:
 
   * Renesas ISL69260
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69260'
 
     Addresses scanned: -
 
@@ -306,7 +306,7 @@ Supported chips:
 
   * Renesas ISL69268
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69268'
 
     Addresses scanned: -
 
@@ -316,7 +316,7 @@ Supported chips:
 
   * Renesas ISL69269
 
-    Prefix: 'raa_dmpvr2_3rail'
+    Prefix: 'isl69269'
 
     Addresses scanned: -
 
@@ -326,7 +326,7 @@ Supported chips:
 
   * Renesas ISL69298
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'isl69298'
 
     Addresses scanned: -
 
@@ -336,7 +336,7 @@ Supported chips:
 
   * Renesas RAA228000
 
-    Prefix: 'raa_dmpvr2_hv'
+    Prefix: 'raa228000'
 
     Addresses scanned: -
 
@@ -346,7 +346,7 @@ Supported chips:
 
   * Renesas RAA228004
 
-    Prefix: 'raa_dmpvr2_hv'
+    Prefix: 'raa228004'
 
     Addresses scanned: -
 
@@ -356,7 +356,7 @@ Supported chips:
 
   * Renesas RAA228006
 
-    Prefix: 'raa_dmpvr2_hv'
+    Prefix: 'raa228006'
 
     Addresses scanned: -
 
@@ -366,7 +366,7 @@ Supported chips:
 
   * Renesas RAA228228
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'raa228228'
 
     Addresses scanned: -
 
@@ -376,7 +376,7 @@ Supported chips:
 
   * Renesas RAA229001
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'raa229001'
 
     Addresses scanned: -
 
@@ -386,7 +386,7 @@ Supported chips:
 
   * Renesas RAA229004
 
-    Prefix: 'raa_dmpvr2_2rail'
+    Prefix: 'raa229004'
 
     Addresses scanned: -
 
diff --git a/Documentation/hwmon/lm90.rst b/Documentation/hwmon/lm90.rst
index 953315987c06..78dfc01b47a2 100644
--- a/Documentation/hwmon/lm90.rst
+++ b/Documentation/hwmon/lm90.rst
@@ -123,6 +123,18 @@ Supported chips:
 
 	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
 
+  * Maxim MAX6654
+
+    Prefix: 'max6654'
+
+    Addresses scanned: I2C 0x18, 0x19, 0x1a, 0x29, 0x2a, 0x2b,
+
+			   0x4c, 0x4d and 0x4e
+
+    Datasheet: Publicly available at the Maxim website
+
+	       https://www.maximintegrated.com/en/products/sensors/MAX6654.html
+
   * Maxim MAX6657
 
     Prefix: 'max6657'
@@ -301,6 +313,13 @@ ADT7461, ADT7461A, NCT1008:
   * Extended temperature range (breaks compatibility)
   * Lower resolution for remote temperature
 
+MAX6654:
+  * Better local resolution
+  * Selectable address
+  * Remote sensor type selection
+  * Extended temperature range
+  * Extended resolution only available when conversion rate <= 1 Hz
+
 MAX6657 and MAX6658:
   * Better local resolution
   * Remote sensor type selection
@@ -336,8 +355,8 @@ SA56004X:
 
 All temperature values are given in degrees Celsius. Resolution
 is 1.0 degree for the local temperature, 0.125 degree for the remote
-temperature, except for the MAX6657, MAX6658 and MAX6659 which have a
-resolution of 0.125 degree for both temperatures.
+temperature, except for the MAX6654, MAX6657, MAX6658 and MAX6659 which have
+a resolution of 0.125 degree for both temperatures.
 
 Each sensor has its own high and low limits, plus a critical limit.
 Additionally, there is a relative hysteresis value common to both critical
diff --git a/Documentation/hwmon/max16601.rst b/Documentation/hwmon/max16601.rst
new file mode 100644
index 000000000000..346e74674c51
--- /dev/null
+++ b/Documentation/hwmon/max16601.rst
@@ -0,0 +1,159 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Kernel driver max16601
+======================
+
+Supported chips:
+
+  * Maxim MAX16601
+
+    Prefix: 'max16601'
+
+    Addresses scanned: -
+
+    Datasheet: Not published
+
+Author: Guenter Roeck <linux@roeck-us.net>
+
+
+Description
+-----------
+
+This driver supports the MAX16601 VR13.HC Dual-Output Voltage Regulator
+Chipset.
+
+The driver is a client driver to the core PMBus driver.
+Please see Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
+
+
+Usage Notes
+-----------
+
+This driver does not auto-detect devices. You will have to instantiate the
+devices explicitly. Please see Documentation/i2c/instantiating-devices.rst for
+details.
+
+
+Platform data support
+---------------------
+
+The driver supports standard PMBus driver platform data.
+
+
+Sysfs entries
+-------------
+
+The following attributes are supported.
+
+======================= =======================================================
+in1_label		"vin1"
+in1_input		VCORE input voltage.
+in1_alarm		Input voltage alarm.
+
+in2_label		"vout1"
+in2_input		VCORE output voltage.
+in2_alarm		Output voltage alarm.
+
+curr1_label		"iin1"
+curr1_input		VCORE input current, derived from duty cycle and output
+			current.
+curr1_max		Maximum input current.
+curr1_max_alarm		Current high alarm.
+
+curr2_label		"iin1.0"
+curr2_input		VCORE phase 0 input current.
+
+curr3_label		"iin1.1"
+curr3_input		VCORE phase 1 input current.
+
+curr4_label		"iin1.2"
+curr4_input		VCORE phase 2 input current.
+
+curr5_label		"iin1.3"
+curr5_input		VCORE phase 3 input current.
+
+curr6_label		"iin1.4"
+curr6_input		VCORE phase 4 input current.
+
+curr7_label		"iin1.5"
+curr7_input		VCORE phase 5 input current.
+
+curr8_label		"iin1.6"
+curr8_input		VCORE phase 6 input current.
+
+curr9_label		"iin1.7"
+curr9_input		VCORE phase 7 input current.
+
+curr10_label		"iin2"
+curr10_input		VCORE input current, derived from sensor element.
+
+curr11_label		"iin3"
+curr11_input		VSA input current.
+
+curr12_label		"iout1"
+curr12_input		VCORE output current.
+curr12_crit		Critical output current.
+curr12_crit_alarm	Output current critical alarm.
+curr12_max		Maximum output current.
+curr12_max_alarm	Output current high alarm.
+
+curr13_label		"iout1.0"
+curr13_input		VCORE phase 0 output current.
+
+curr14_label		"iout1.1"
+curr14_input		VCORE phase 1 output current.
+
+curr15_label		"iout1.2"
+curr15_input		VCORE phase 2 output current.
+
+curr16_label		"iout1.3"
+curr16_input		VCORE phase 3 output current.
+
+curr17_label		"iout1.4"
+curr17_input		VCORE phase 4 output current.
+
+curr18_label		"iout1.5"
+curr18_input		VCORE phase 5 output current.
+
+curr19_label		"iout1.6"
+curr19_input		VCORE phase 6 output current.
+
+curr20_label		"iout1.7"
+curr20_input		VCORE phase 7 output current.
+
+curr21_label		"iout3"
+curr21_input		VSA output current.
+curr21_highest		Historical maximum VSA output current.
+curr21_reset_history	Write any value to reset curr21_highest.
+curr21_crit		Critical output current.
+curr21_crit_alarm	Output current critical alarm.
+curr21_max		Maximum output current.
+curr21_max_alarm	Output current high alarm.
+
+power1_label		"pin1"
+power1_input		Input power, derived from duty cycle and output current.
+power1_alarm		Input power alarm.
+
+power2_label		"pin2"
+power2_input		Input power, derived from input current sensor.
+
+power3_label		"pout"
+power3_input		Output power.
+
+temp1_input		VCORE temperature.
+temp1_crit		Critical high temperature.
+temp1_crit_alarm	Chip temperature critical high alarm.
+temp1_max		Maximum temperature.
+temp1_max_alarm		Chip temperature high alarm.
+
+temp2_input		TSENSE_0 temperature
+temp3_input		TSENSE_1 temperature
+temp4_input		TSENSE_2 temperature
+temp5_input		TSENSE_3 temperature
+
+temp6_input		VSA temperature.
+temp6_crit		Critical high temperature.
+temp6_crit_alarm	Chip temperature critical high alarm.
+temp6_max		Maximum temperature.
+temp6_max_alarm		Chip temperature high alarm.
+======================= =======================================================
diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst
index 04d5c01a2e99..b80257a03830 100644
--- a/Documentation/kbuild/makefiles.rst
+++ b/Documentation/kbuild/makefiles.rst
@@ -1241,7 +1241,8 @@ When kbuild executes, the following steps are followed (roughly):
 	will be displayed with "make KBUILD_VERBOSE=0".
 
 
---- 6.9 Preprocessing linker scripts
+6.9 Preprocessing linker scripts
+--------------------------------
 
 	When the vmlinux image is built, the linker script
 	arch/$(ARCH)/kernel/vmlinux.lds is used.
diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst
index 09f45ce38d26..1b577a8bf982 100644
--- a/Documentation/locking/locktypes.rst
+++ b/Documentation/locking/locktypes.rst
@@ -13,6 +13,7 @@ The kernel provides a variety of locking primitives which can be divided
 into two categories:
 
  - Sleeping locks
+ - CPU local locks
  - Spinning locks
 
 This document conceptually describes these lock types and provides rules
@@ -44,9 +45,23 @@ Sleeping lock types:
 
 On PREEMPT_RT kernels, these lock types are converted to sleeping locks:
 
+ - local_lock
  - spinlock_t
  - rwlock_t
 
+
+CPU local locks
+---------------
+
+ - local_lock
+
+On non-PREEMPT_RT kernels, local_lock functions are wrappers around
+preemption and interrupt disabling primitives. Contrary to other locking
+mechanisms, disabling preemption or interrupts are pure CPU local
+concurrency control mechanisms and not suited for inter-CPU concurrency
+control.
+
+
 Spinning locks
 --------------
 
@@ -67,6 +82,7 @@ can have suffixes which apply further protections:
  _irqsave/restore()   Save and disable / restore interrupt disabled state
  ===================  ====================================================
 
+
 Owner semantics
 ===============
 
@@ -139,6 +155,56 @@ implementation, thus changing the fairness:
  writer from starving readers.
 
 
+local_lock
+==========
+
+local_lock provides a named scope to critical sections which are protected
+by disabling preemption or interrupts.
+
+On non-PREEMPT_RT kernels local_lock operations map to the preemption and
+interrupt disabling and enabling primitives:
+
+ =========================== ======================
+ local_lock(&llock)          preempt_disable()
+ local_unlock(&llock)        preempt_enable()
+ local_lock_irq(&llock)      local_irq_disable()
+ local_unlock_irq(&llock)    local_irq_enable()
+ local_lock_save(&llock)     local_irq_save()
+ local_lock_restore(&llock)  local_irq_save()
+ =========================== ======================
+
+The named scope of local_lock has two advantages over the regular
+primitives:
+
+  - The lock name allows static analysis and is also a clear documentation
+    of the protection scope while the regular primitives are scopeless and
+    opaque.
+
+  - If lockdep is enabled the local_lock gains a lockmap which allows to
+    validate the correctness of the protection. This can detect cases where
+    e.g. a function using preempt_disable() as protection mechanism is
+    invoked from interrupt or soft-interrupt context. Aside of that
+    lockdep_assert_held(&llock) works as with any other locking primitive.
+
+local_lock and PREEMPT_RT
+-------------------------
+
+PREEMPT_RT kernels map local_lock to a per-CPU spinlock_t, thus changing
+semantics:
+
+  - All spinlock_t changes also apply to local_lock.
+
+local_lock usage
+----------------
+
+local_lock should be used in situations where disabling preemption or
+interrupts is the appropriate form of concurrency control to protect
+per-CPU data structures on a non PREEMPT_RT kernel.
+
+local_lock is not suitable to protect against preemption or interrupts on a
+PREEMPT_RT kernel due to the PREEMPT_RT specific spinlock_t semantics.
+
+
 raw_spinlock_t and spinlock_t
 =============================
 
@@ -258,10 +324,82 @@ implementation, thus changing semantics:
 PREEMPT_RT caveats
 ==================
 
+local_lock on RT
+----------------
+
+The mapping of local_lock to spinlock_t on PREEMPT_RT kernels has a few
+implications. For example, on a non-PREEMPT_RT kernel the following code
+sequence works as expected::
+
+  local_lock_irq(&local_lock);
+  raw_spin_lock(&lock);
+
+and is fully equivalent to::
+
+   raw_spin_lock_irq(&lock);
+
+On a PREEMPT_RT kernel this code sequence breaks because local_lock_irq()
+is mapped to a per-CPU spinlock_t which neither disables interrupts nor
+preemption. The following code sequence works perfectly correct on both
+PREEMPT_RT and non-PREEMPT_RT kernels::
+
+  local_lock_irq(&local_lock);
+  spin_lock(&lock);
+
+Another caveat with local locks is that each local_lock has a specific
+protection scope. So the following substitution is wrong::
+
+  func1()
+  {
+    local_irq_save(flags);    -> local_lock_irqsave(&local_lock_1, flags);
+    func3();
+    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_1, flags);
+  }
+
+  func2()
+  {
+    local_irq_save(flags);    -> local_lock_irqsave(&local_lock_2, flags);
+    func3();
+    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock_2, flags);
+  }
+
+  func3()
+  {
+    lockdep_assert_irqs_disabled();
+    access_protected_data();
+  }
+
+On a non-PREEMPT_RT kernel this works correctly, but on a PREEMPT_RT kernel
+local_lock_1 and local_lock_2 are distinct and cannot serialize the callers
+of func3(). Also the lockdep assert will trigger on a PREEMPT_RT kernel
+because local_lock_irqsave() does not disable interrupts due to the
+PREEMPT_RT-specific semantics of spinlock_t. The correct substitution is::
+
+  func1()
+  {
+    local_irq_save(flags);    -> local_lock_irqsave(&local_lock, flags);
+    func3();
+    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags);
+  }
+
+  func2()
+  {
+    local_irq_save(flags);    -> local_lock_irqsave(&local_lock, flags);
+    func3();
+    local_irq_restore(flags); -> local_lock_irqrestore(&local_lock, flags);
+  }
+
+  func3()
+  {
+    lockdep_assert_held(&local_lock);
+    access_protected_data();
+  }
+
+
 spinlock_t and rwlock_t
 -----------------------
 
-These changes in spinlock_t and rwlock_t semantics on PREEMPT_RT kernels
+The changes in spinlock_t and rwlock_t semantics on PREEMPT_RT kernels
 have a few implications.  For example, on a non-PREEMPT_RT kernel the
 following code sequence works as expected::
 
@@ -282,9 +420,61 @@ local_lock mechanism.  Acquiring the local_lock pins the task to a CPU,
 allowing things like per-CPU interrupt disabled locks to be acquired.
 However, this approach should be used only where absolutely necessary.
 
+A typical scenario is protection of per-CPU variables in thread context::
 
-raw_spinlock_t
---------------
+  struct foo *p = get_cpu_ptr(&var1);
+
+  spin_lock(&p->lock);
+  p->count += this_cpu_read(var2);
+
+This is correct code on a non-PREEMPT_RT kernel, but on a PREEMPT_RT kernel
+this breaks. The PREEMPT_RT-specific change of spinlock_t semantics does
+not allow to acquire p->lock because get_cpu_ptr() implicitly disables
+preemption. The following substitution works on both kernels::
+
+  struct foo *p;
+
+  migrate_disable();
+  p = this_cpu_ptr(&var1);
+  spin_lock(&p->lock);
+  p->count += this_cpu_read(var2);
+
+On a non-PREEMPT_RT kernel migrate_disable() maps to preempt_disable()
+which makes the above code fully equivalent. On a PREEMPT_RT kernel
+migrate_disable() ensures that the task is pinned on the current CPU which
+in turn guarantees that the per-CPU access to var1 and var2 are staying on
+the same CPU.
+
+The migrate_disable() substitution is not valid for the following
+scenario::
+
+  func()
+  {
+    struct foo *p;
+
+    migrate_disable();
+    p = this_cpu_ptr(&var1);
+    p->val = func2();
+
+While correct on a non-PREEMPT_RT kernel, this breaks on PREEMPT_RT because
+here migrate_disable() does not protect against reentrancy from a
+preempting task. A correct substitution for this case is::
+
+  func()
+  {
+    struct foo *p;
+
+    local_lock(&foo_lock);
+    p = this_cpu_ptr(&var1);
+    p->val = func2();
+
+On a non-PREEMPT_RT kernel this protects against reentrancy by disabling
+preemption. On a PREEMPT_RT kernel this is achieved by acquiring the
+underlying per-CPU spinlock.
+
+
+raw_spinlock_t on RT
+--------------------
 
 Acquiring a raw_spinlock_t disables preemption and possibly also
 interrupts, so the critical section must avoid acquiring a regular
@@ -325,22 +515,25 @@ Lock type nesting rules
 
 The most basic rules are:
 
-  - Lock types of the same lock category (sleeping, spinning) can nest
-    arbitrarily as long as they respect the general lock ordering rules to
-    prevent deadlocks.
+  - Lock types of the same lock category (sleeping, CPU local, spinning)
+    can nest arbitrarily as long as they respect the general lock ordering
+    rules to prevent deadlocks.
+
+  - Sleeping lock types cannot nest inside CPU local and spinning lock types.
 
-  - Sleeping lock types cannot nest inside spinning lock types.
+  - CPU local and spinning lock types can nest inside sleeping lock types.
 
-  - Spinning lock types can nest inside sleeping lock types.
+  - Spinning lock types can nest inside all lock types
 
 These constraints apply both in PREEMPT_RT and otherwise.
 
 The fact that PREEMPT_RT changes the lock category of spinlock_t and
-rwlock_t from spinning to sleeping means that they cannot be acquired while
-holding a raw spinlock.  This results in the following nesting ordering:
+rwlock_t from spinning to sleeping and substitutes local_lock with a
+per-CPU spinlock_t means that they cannot be acquired while holding a raw
+spinlock.  This results in the following nesting ordering:
 
   1) Sleeping locks
-  2) spinlock_t and rwlock_t
+  2) spinlock_t, rwlock_t, local_lock
   3) raw_spinlock_t and bit spinlocks
 
 Lockdep will complain if these constraints are violated, both in
diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst
index a09971c2115c..fe089acb7783 100644
--- a/Documentation/networking/devlink/devlink-trap.rst
+++ b/Documentation/networking/devlink/devlink-trap.rst
@@ -257,6 +257,8 @@ drivers:
   * :doc:`netdevsim`
   * :doc:`mlxsw`
 
+.. _Generic-Packet-Trap-Groups:
+
 Generic Packet Trap Groups
 ==========================
 
diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index 5b58fc4e1268..4574352d6ff4 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -61,8 +61,8 @@ The ``ice`` driver reports the following versions
       - running
       - ICE OS Default Package
       - The name of the DDP package that is active in the device. The DDP
-        package is loaded by the driver during initialization. Each varation
-        of DDP package shall have a unique name.
+        package is loaded by the driver during initialization. Each
+        variation of the DDP package has a unique name.
     * - ``fw.app``
       - running
       - 1.3.1.0
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 50133d9761c9..6538ede29661 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -22,6 +22,7 @@ Contents:
    z8530book
    msg_zerocopy
    failover
+   net_dim
    net_failover
    phy
    sfp-phylink
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ee961d322d93..9375324aa8e1 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -812,7 +812,7 @@ tcp_limit_output_bytes - INTEGER
 tcp_challenge_ack_limit - INTEGER
 	Limits number of Challenge ACK sent per second, as recommended
 	in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
-	Default: 100
+	Default: 1000
 
 tcp_rx_skb_cache - BOOLEAN
 	Controls a per TCP socket cache of one skb, that might help
@@ -983,6 +983,13 @@ ip_early_demux - BOOLEAN
 	reduces overall throughput, in such case you should disable it.
 	Default: 1
 
+ping_group_range - 2 INTEGERS
+	Restrict ICMP_PROTO datagram sockets to users in the group range.
+	The default is "1 0", meaning, that nobody (not even root) may
+	create ping sockets.  Setting it to "100 100" would grant permissions
+	to the single group. "0 4294967295" would enable it for the world, "100
+	4294967295" would enable it for the users, but not daemons.
+
 tcp_early_demux - BOOLEAN
 	Enable early demux for established TCP sockets.
 	Default: 1
diff --git a/Documentation/networking/net_dim.txt b/Documentation/networking/net_dim.rst
index 9bdb7d5a3ba3..3bed9fd95336 100644
--- a/Documentation/networking/net_dim.txt
+++ b/Documentation/networking/net_dim.rst
@@ -1,28 +1,20 @@
+======================================================
 Net DIM - Generic Network Dynamic Interrupt Moderation
 ======================================================
 
-Author:
-	Tal Gilboa <talgi@mellanox.com>
-
-
-Contents
-=========
+:Author: Tal Gilboa <talgi@mellanox.com>
 
-- Assumptions
-- Introduction
-- The Net DIM Algorithm
-- Registering a Network Device to DIM
-- Example
+.. contents:: :depth: 2
 
-Part 0: Assumptions
-======================
+Assumptions
+===========
 
 This document assumes the reader has basic knowledge in network drivers
 and in general interrupt moderation.
 
 
-Part I: Introduction
-======================
+Introduction
+============
 
 Dynamic Interrupt Moderation (DIM) (in networking) refers to changing the
 interrupt moderation configuration of a channel in order to optimize packet
@@ -41,14 +33,15 @@ number of wanted packets per event. The Net DIM algorithm ascribes importance to
 increase bandwidth over reducing interrupt rate.
 
 
-Part II: The Net DIM Algorithm
-===============================
+Net DIM Algorithm
+=================
 
 Each iteration of the Net DIM algorithm follows these steps:
-1. Calculates new data sample.
-2. Compares it to previous sample.
-3. Makes a decision - suggests interrupt moderation configuration fields.
-4. Applies a schedule work function, which applies suggested configuration.
+
+#. Calculates new data sample.
+#. Compares it to previous sample.
+#. Makes a decision - suggests interrupt moderation configuration fields.
+#. Applies a schedule work function, which applies suggested configuration.
 
 The first two steps are straightforward, both the new and the previous data are
 supplied by the driver registered to Net DIM. The previous data is the new data
@@ -89,19 +82,21 @@ manoeuvre as it may provide partial data or ignore the algorithm suggestion
 under some conditions.
 
 
-Part III: Registering a Network Device to DIM
-==============================================
+Registering a Network Device to DIM
+===================================
 
-Net DIM API exposes the main function net_dim(struct dim *dim,
-struct dim_sample end_sample). This function is the entry point to the Net
+Net DIM API exposes the main function net_dim().
+This function is the entry point to the Net
 DIM algorithm and has to be called every time the driver would like to check if
 it should change interrupt moderation parameters. The driver should provide two
-data structures: struct dim and struct dim_sample. Struct dim
+data structures: :c:type:`struct dim <dim>` and
+:c:type:`struct dim_sample <dim_sample>`. :c:type:`struct dim <dim>`
 describes the state of DIM for a specific object (RX queue, TX queue,
 other queues, etc.). This includes the current selected profile, previous data
 samples, the callback function provided by the driver and more.
-Struct dim_sample describes a data sample, which will be compared to the
-data sample stored in struct dim in order to decide on the algorithm's next
+:c:type:`struct dim_sample <dim_sample>` describes a data sample,
+which will be compared to the data sample stored in :c:type:`struct dim <dim>`
+in order to decide on the algorithm's next
 step. The sample should include bytes, packets and interrupts, measured by
 the driver.
 
@@ -110,9 +105,10 @@ main net_dim() function. The recommended method is to call net_dim() on each
 interrupt. Since Net DIM has a built-in moderation and it might decide to skip
 iterations under certain conditions, there is no need to moderate the net_dim()
 calls as well. As mentioned above, the driver needs to provide an object of type
-struct dim to the net_dim() function call. It is advised for each entity
-using Net DIM to hold a struct dim as part of its data structure and use it
-as the main Net DIM API object. The struct dim_sample should hold the latest
+:c:type:`struct dim <dim>` to the net_dim() function call. It is advised for
+each entity using Net DIM to hold a :c:type:`struct dim <dim>` as part of its
+data structure and use it as the main Net DIM API object.
+The :c:type:`struct dim_sample <dim_sample>` should hold the latest
 bytes, packets and interrupts count. No need to perform any calculations, just
 include the raw data.
 
@@ -124,19 +120,19 @@ the data flow. After the work is done, Net DIM algorithm needs to be set to
 the proper state in order to move to the next iteration.
 
 
-Part IV: Example
-=================
+Example
+=======
 
 The following code demonstrates how to register a driver to Net DIM. The actual
 usage is not complete but it should make the outline of the usage clear.
 
-my_driver.c:
+.. code-block:: c
 
-#include <linux/dim.h>
+  #include <linux/dim.h>
 
-/* Callback for net DIM to schedule on a decision to change moderation */
-void my_driver_do_dim_work(struct work_struct *work)
-{
+  /* Callback for net DIM to schedule on a decision to change moderation */
+  void my_driver_do_dim_work(struct work_struct *work)
+  {
 	/* Get struct dim from struct work_struct */
 	struct dim *dim = container_of(work, struct dim,
 				       work);
@@ -145,11 +141,11 @@ void my_driver_do_dim_work(struct work_struct *work)
 
 	/* Signal net DIM work is done and it should move to next iteration */
 	dim->state = DIM_START_MEASURE;
-}
+  }
 
-/* My driver's interrupt handler */
-int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...)
-{
+  /* My driver's interrupt handler */
+  int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...)
+  {
 	...
 	/* A struct to hold current measured data */
 	struct dim_sample dim_sample;
@@ -162,13 +158,19 @@ int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...)
 	/* Call net DIM */
 	net_dim(&my_entity->dim, dim_sample);
 	...
-}
+  }
 
-/* My entity's initialization function (my_entity was already allocated) */
-int my_driver_init_my_entity(struct my_driver_entity *my_entity, ...)
-{
+  /* My entity's initialization function (my_entity was already allocated) */
+  int my_driver_init_my_entity(struct my_driver_entity *my_entity, ...)
+  {
 	...
 	/* Initiate struct work_struct with my driver's callback function */
 	INIT_WORK(&my_entity->dim.work, my_driver_do_dim_work);
 	...
-}
+  }
+
+Dynamic Interrupt Moderation (DIM) library API
+==============================================
+
+.. kernel-doc:: include/linux/dim.h
+    :internal:
diff --git a/Documentation/power/suspend-and-cpuhotplug.rst b/Documentation/power/suspend-and-cpuhotplug.rst
index 572d968c5375..ebedb6c75db9 100644
--- a/Documentation/power/suspend-and-cpuhotplug.rst
+++ b/Documentation/power/suspend-and-cpuhotplug.rst
@@ -48,7 +48,7 @@ More details follow::
                                         |
                                         |
                                         v
-                              disable_nonboot_cpus()
+                              freeze_secondary_cpus()
                                    /* start */
                                         |
                                         v
@@ -83,7 +83,7 @@ More details follow::
                             Release cpu_add_remove_lock
                                         |
                                         v
-                       /* disable_nonboot_cpus() complete */
+                       /* freeze_secondary_cpus() complete */
                                         |
                                         v
                                    Do suspend
@@ -93,7 +93,7 @@ More details follow::
 Resuming back is likewise, with the counterparts being (in the order of
 execution during resume):
 
-* enable_nonboot_cpus() which involves::
+* thaw_secondary_cpus() which involves::
 
    |  Acquire cpu_add_remove_lock
    |  Decrease cpu_hotplug_disabled, thereby enabling regular cpu hotplug
diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index acb2f1b36350..17a8e584f15f 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -84,15 +84,20 @@ Get a decent editor and don't leave whitespace at the end of lines.
 Coding style is all about readability and maintainability using commonly
 available tools.
 
-The limit on the length of lines is 80 columns and this is a strongly
-preferred limit.
-
-Statements longer than 80 columns will be broken into sensible chunks, unless
-exceeding 80 columns significantly increases readability and does not hide
-information. Descendants are always substantially shorter than the parent and
-are placed substantially to the right. The same applies to function headers
-with a long argument list. However, never break user-visible strings such as
-printk messages, because that breaks the ability to grep for them.
+The preferred limit on the length of a single line is 80 columns.
+
+Statements longer than 80 columns should be broken into sensible chunks,
+unless exceeding 80 columns significantly increases readability and does
+not hide information.
+
+Descendants are always substantially shorter than the parent and are
+are placed substantially to the right.  A very commonly used style
+is to align descendants to a function open parenthesis.
+
+These same rules are applied to function headers with a long argument list.
+
+However, never break user-visible strings such as printk messages because
+that breaks the ability to grep for them.
 
 
 3) Placing Braces and Spaces
diff --git a/Documentation/security/siphash.rst b/Documentation/security/siphash.rst
index 4eba68cdf0a1..bd9363025fcb 100644
--- a/Documentation/security/siphash.rst
+++ b/Documentation/security/siphash.rst
@@ -7,7 +7,7 @@ SipHash - a short input PRF
 SipHash is a cryptographically secure PRF -- a keyed hash function -- that
 performs very well for short inputs, hence the name. It was designed by
 cryptographers Daniel J. Bernstein and Jean-Philippe Aumasson. It is intended
-as a replacement for some uses of: `jhash`, `md5_transform`, `sha_transform`,
+as a replacement for some uses of: `jhash`, `md5_transform`, `sha1_transform`,
 and so forth.
 
 SipHash takes a secret key filled with randomly generated numbers and either
diff --git a/Documentation/trace/ftrace-design.rst b/Documentation/trace/ftrace-design.rst
index a8e22e0db63c..6893399157f0 100644
--- a/Documentation/trace/ftrace-design.rst
+++ b/Documentation/trace/ftrace-design.rst
@@ -229,14 +229,6 @@ Adding support for it is easy: just define the macro in asm/ftrace.h and
 pass the return address pointer as the 'retp' argument to
 ftrace_push_return_trace().
 
-HAVE_FTRACE_NMI_ENTER
----------------------
-
-If you can't trace NMI functions, then skip this option.
-
-<details to be filled>
-
-
 HAVE_SYSCALL_TRACEPOINTS
 ------------------------
 
diff --git a/Documentation/usb/raw-gadget.rst b/Documentation/usb/raw-gadget.rst
index 9e78cb858f86..68d879a8009e 100644
--- a/Documentation/usb/raw-gadget.rst
+++ b/Documentation/usb/raw-gadget.rst
@@ -27,9 +27,8 @@ differences are:
 3. Raw Gadget provides a way to select a UDC device/driver to bind to,
    while GadgetFS currently binds to the first available UDC.
 
-4. Raw Gadget uses predictable endpoint names (handles) across different
-   UDCs (as long as UDCs have enough endpoints of each required transfer
-   type).
+4. Raw Gadget explicitly exposes information about endpoints addresses and
+   capabilities allowing a user to write UDC-agnostic gadgets.
 
 5. Raw Gadget has ioctl-based interface instead of a filesystem-based one.
 
@@ -50,12 +49,36 @@ The typical usage of Raw Gadget looks like:
    Raw Gadget and react to those depending on what kind of USB device
    needs to be emulated.
 
+Note, that some UDC drivers have fixed addresses assigned to endpoints, and
+therefore arbitrary endpoint addresses can't be used in the descriptors.
+Nevertheles, Raw Gadget provides a UDC-agnostic way to write USB gadgets.
+Once a USB_RAW_EVENT_CONNECT event is received via USB_RAW_IOCTL_EVENT_FETCH,
+the USB_RAW_IOCTL_EPS_INFO ioctl can be used to find out information about
+endpoints that the UDC driver has. Based on that information, the user must
+chose UDC endpoints that will be used for the gadget being emulated, and
+properly assign addresses in endpoint descriptors.
+
+You can find usage examples (along with a test suite) here:
+
+https://github.com/xairy/raw-gadget
+
+Internal details
+~~~~~~~~~~~~~~~~
+
+Currently every endpoint read/write ioctl submits a USB request and waits until
+its completion. This is the desired mode for coverage-guided fuzzing (as we'd
+like all USB request processing happen during the lifetime of a syscall),
+and must be kept in the implementation. (This might be slow for real world
+applications, thus the O_NONBLOCK improvement suggestion below.)
+
 Potential future improvements
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-- Implement ioctl's for setting/clearing halt status on endpoints.
-
-- Reporting more events (suspend, resume, etc.) through
-  USB_RAW_IOCTL_EVENT_FETCH.
+- Report more events (suspend, resume, etc.) through USB_RAW_IOCTL_EVENT_FETCH.
 
 - Support O_NONBLOCK I/O.
+
+- Support USB 3 features (accept SS endpoint companion descriptor when
+  enabling endpoints; allow providing stream_id for bulk transfers).
+
+- Support ISO transfer features (expose frame_number for completed requests).
diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst
index dcc252634cf9..b6833c7bb474 100644
--- a/Documentation/virt/kvm/index.rst
+++ b/Documentation/virt/kvm/index.rst
@@ -28,3 +28,5 @@ KVM
    arm/index
 
    devices/index
+
+   running-nested-guests
diff --git a/Documentation/virt/kvm/running-nested-guests.rst b/Documentation/virt/kvm/running-nested-guests.rst
new file mode 100644
index 000000000000..d0a1fc754c84
--- /dev/null
+++ b/Documentation/virt/kvm/running-nested-guests.rst
@@ -0,0 +1,276 @@
+==============================
+Running nested guests with KVM
+==============================
+
+A nested guest is the ability to run a guest inside another guest (it
+can be KVM-based or a different hypervisor).  The straightforward
+example is a KVM guest that in turn runs on a KVM guest (the rest of
+this document is built on this example)::
+
+              .----------------.  .----------------.
+              |                |  |                |
+              |      L2        |  |      L2        |
+              | (Nested Guest) |  | (Nested Guest) |
+              |                |  |                |
+              |----------------'--'----------------|
+              |                                    |
+              |       L1 (Guest Hypervisor)        |
+              |          KVM (/dev/kvm)            |
+              |                                    |
+      .------------------------------------------------------.
+      |                 L0 (Host Hypervisor)                 |
+      |                    KVM (/dev/kvm)                    |
+      |------------------------------------------------------|
+      |        Hardware (with virtualization extensions)     |
+      '------------------------------------------------------'
+
+Terminology:
+
+- L0 – level-0; the bare metal host, running KVM
+
+- L1 – level-1 guest; a VM running on L0; also called the "guest
+  hypervisor", as it itself is capable of running KVM.
+
+- L2 – level-2 guest; a VM running on L1, this is the "nested guest"
+
+.. note:: The above diagram is modelled after the x86 architecture;
+          s390x, ppc64 and other architectures are likely to have
+          a different design for nesting.
+
+          For example, s390x always has an LPAR (LogicalPARtition)
+          hypervisor running on bare metal, adding another layer and
+          resulting in at least four levels in a nested setup — L0 (bare
+          metal, running the LPAR hypervisor), L1 (host hypervisor), L2
+          (guest hypervisor), L3 (nested guest).
+
+          This document will stick with the three-level terminology (L0,
+          L1, and L2) for all architectures; and will largely focus on
+          x86.
+
+
+Use Cases
+---------
+
+There are several scenarios where nested KVM can be useful, to name a
+few:
+
+- As a developer, you want to test your software on different operating
+  systems (OSes).  Instead of renting multiple VMs from a Cloud
+  Provider, using nested KVM lets you rent a large enough "guest
+  hypervisor" (level-1 guest).  This in turn allows you to create
+  multiple nested guests (level-2 guests), running different OSes, on
+  which you can develop and test your software.
+
+- Live migration of "guest hypervisors" and their nested guests, for
+  load balancing, disaster recovery, etc.
+
+- VM image creation tools (e.g. ``virt-install``,  etc) often run
+  their own VM, and users expect these to work inside a VM.
+
+- Some OSes use virtualization internally for security (e.g. to let
+  applications run safely in isolation).
+
+
+Enabling "nested" (x86)
+-----------------------
+
+From Linux kernel v4.19 onwards, the ``nested`` KVM parameter is enabled
+by default for Intel and AMD.  (Though your Linux distribution might
+override this default.)
+
+In case you are running a Linux kernel older than v4.19, to enable
+nesting, set the ``nested`` KVM module parameter to ``Y`` or ``1``.  To
+persist this setting across reboots, you can add it in a config file, as
+shown below:
+
+1. On the bare metal host (L0), list the kernel modules and ensure that
+   the KVM modules::
+
+    $ lsmod | grep -i kvm
+    kvm_intel             133627  0
+    kvm                   435079  1 kvm_intel
+
+2. Show information for ``kvm_intel`` module::
+
+    $ modinfo kvm_intel | grep -i nested
+    parm:           nested:bool
+
+3. For the nested KVM configuration to persist across reboots, place the
+   below in ``/etc/modprobed/kvm_intel.conf`` (create the file if it
+   doesn't exist)::
+
+    $ cat /etc/modprobe.d/kvm_intel.conf
+    options kvm-intel nested=y
+
+4. Unload and re-load the KVM Intel module::
+
+    $ sudo rmmod kvm-intel
+    $ sudo modprobe kvm-intel
+
+5. Verify if the ``nested`` parameter for KVM is enabled::
+
+    $ cat /sys/module/kvm_intel/parameters/nested
+    Y
+
+For AMD hosts, the process is the same as above, except that the module
+name is ``kvm-amd``.
+
+
+Additional nested-related kernel parameters (x86)
+-------------------------------------------------
+
+If your hardware is sufficiently advanced (Intel Haswell processor or
+higher, which has newer hardware virt extensions), the following
+additional features will also be enabled by default: "Shadow VMCS
+(Virtual Machine Control Structure)", APIC Virtualization on your bare
+metal host (L0).  Parameters for Intel hosts::
+
+    $ cat /sys/module/kvm_intel/parameters/enable_shadow_vmcs
+    Y
+
+    $ cat /sys/module/kvm_intel/parameters/enable_apicv
+    Y
+
+    $ cat /sys/module/kvm_intel/parameters/ept
+    Y
+
+.. note:: If you suspect your L2 (i.e. nested guest) is running slower,
+          ensure the above are enabled (particularly
+          ``enable_shadow_vmcs`` and ``ept``).
+
+
+Starting a nested guest (x86)
+-----------------------------
+
+Once your bare metal host (L0) is configured for nesting, you should be
+able to start an L1 guest with::
+
+    $ qemu-kvm -cpu host [...]
+
+The above will pass through the host CPU's capabilities as-is to the
+gues); or for better live migration compatibility, use a named CPU
+model supported by QEMU. e.g.::
+
+    $ qemu-kvm -cpu Haswell-noTSX-IBRS,vmx=on
+
+then the guest hypervisor will subsequently be capable of running a
+nested guest with accelerated KVM.
+
+
+Enabling "nested" (s390x)
+-------------------------
+
+1. On the host hypervisor (L0), enable the ``nested`` parameter on
+   s390x::
+
+    $ rmmod kvm
+    $ modprobe kvm nested=1
+
+.. note:: On s390x, the kernel parameter ``hpage`` is mutually exclusive
+          with the ``nested`` paramter — i.e. to be able to enable
+          ``nested``, the ``hpage`` parameter *must* be disabled.
+
+2. The guest hypervisor (L1) must be provided with the ``sie`` CPU
+   feature — with QEMU, this can be done by using "host passthrough"
+   (via the command-line ``-cpu host``).
+
+3. Now the KVM module can be loaded in the L1 (guest hypervisor)::
+
+    $ modprobe kvm
+
+
+Live migration with nested KVM
+------------------------------
+
+Migrating an L1 guest, with a  *live* nested guest in it, to another
+bare metal host, works as of Linux kernel 5.3 and QEMU 4.2.0 for
+Intel x86 systems, and even on older versions for s390x.
+
+On AMD systems, once an L1 guest has started an L2 guest, the L1 guest
+should no longer be migrated or saved (refer to QEMU documentation on
+"savevm"/"loadvm") until the L2 guest shuts down.  Attempting to migrate
+or save-and-load an L1 guest while an L2 guest is running will result in
+undefined behavior.  You might see a ``kernel BUG!`` entry in ``dmesg``, a
+kernel 'oops', or an outright kernel panic.  Such a migrated or loaded L1
+guest can no longer be considered stable or secure, and must be restarted.
+Migrating an L1 guest merely configured to support nesting, while not
+actually running L2 guests, is expected to function normally even on AMD
+systems but may fail once guests are started.
+
+Migrating an L2 guest is always expected to succeed, so all the following
+scenarios should work even on AMD systems:
+
+- Migrating a nested guest (L2) to another L1 guest on the *same* bare
+  metal host.
+
+- Migrating a nested guest (L2) to another L1 guest on a *different*
+  bare metal host.
+
+- Migrating a nested guest (L2) to a bare metal host.
+
+Reporting bugs from nested setups
+-----------------------------------
+
+Debugging "nested" problems can involve sifting through log files across
+L0, L1 and L2; this can result in tedious back-n-forth between the bug
+reporter and the bug fixer.
+
+- Mention that you are in a "nested" setup.  If you are running any kind
+  of "nesting" at all, say so.  Unfortunately, this needs to be called
+  out because when reporting bugs, people tend to forget to even
+  *mention* that they're using nested virtualization.
+
+- Ensure you are actually running KVM on KVM.  Sometimes people do not
+  have KVM enabled for their guest hypervisor (L1), which results in
+  them running with pure emulation or what QEMU calls it as "TCG", but
+  they think they're running nested KVM.  Thus confusing "nested Virt"
+  (which could also mean, QEMU on KVM) with "nested KVM" (KVM on KVM).
+
+Information to collect (generic)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The following is not an exhaustive list, but a very good starting point:
+
+  - Kernel, libvirt, and QEMU version from L0
+
+  - Kernel, libvirt and QEMU version from L1
+
+  - QEMU command-line of L1 -- when using libvirt, you'll find it here:
+    ``/var/log/libvirt/qemu/instance.log``
+
+  - QEMU command-line of L2 -- as above, when using libvirt, get the
+    complete libvirt-generated QEMU command-line
+
+  - ``cat /sys/cpuinfo`` from L0
+
+  - ``cat /sys/cpuinfo`` from L1
+
+  - ``lscpu`` from L0
+
+  - ``lscpu`` from L1
+
+  - Full ``dmesg`` output from L0
+
+  - Full ``dmesg`` output from L1
+
+x86-specific info to collect
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Both the below commands, ``x86info`` and ``dmidecode``, should be
+available on most Linux distributions with the same name:
+
+  - Output of: ``x86info -a`` from L0
+
+  - Output of: ``x86info -a`` from L1
+
+  - Output of: ``dmidecode`` from L0
+
+  - Output of: ``dmidecode`` from L1
+
+s390x-specific info to collect
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Along with the earlier mentioned generic details, the below is
+also recommended:
+
+  - ``/proc/sysinfo`` from L1; this will also include the info from L0
diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst
index fa7ddc0428c8..5325c71ca877 100644
--- a/Documentation/x86/boot.rst
+++ b/Documentation/x86/boot.rst
@@ -1399,8 +1399,8 @@ must have read/write permission; CS must be __BOOT_CS and DS, ES, SS
 must be __BOOT_DS; interrupt must be disabled; %rsi must hold the base
 address of the struct boot_params.
 
-EFI Handover Protocol
-=====================
+EFI Handover Protocol (deprecated)
+==================================
 
 This protocol allows boot loaders to defer initialisation to the EFI
 boot stub. The boot loader is required to load the kernel/initrd(s)
@@ -1408,6 +1408,12 @@ from the boot media and jump to the EFI handover protocol entry point
 which is hdr->handover_offset bytes from the beginning of
 startup_{32,64}.
 
+The boot loader MUST respect the kernel's PE/COFF metadata when it comes
+to section alignment, the memory footprint of the executable image beyond
+the size of the file itself, and any other aspect of the PE/COFF header
+that may affect correct operation of the image as a PE/COFF binary in the
+execution context provided by the EFI firmware.
+
 The function prototype for the handover entry point looks like this::
 
     efi_main(void *handle, efi_system_table_t *table, struct boot_params *bp)
@@ -1419,9 +1425,18 @@ UEFI specification. 'bp' is the boot loader-allocated boot params.
 
 The boot loader *must* fill out the following fields in bp::
 
-  - hdr.code32_start
   - hdr.cmd_line_ptr
   - hdr.ramdisk_image (if applicable)
   - hdr.ramdisk_size  (if applicable)
 
 All other fields should be zero.
+
+NOTE: The EFI Handover Protocol is deprecated in favour of the ordinary PE/COFF
+      entry point, combined with the LINUX_EFI_INITRD_MEDIA_GUID based initrd
+      loading protocol (refer to [0] for an example of the bootloader side of
+      this), which removes the need for any knowledge on the part of the EFI
+      bootloader regarding the internal representation of boot_params or any
+      requirements/limitations regarding the placement of the command line
+      and ramdisk in memory, or the placement of the kernel image itself.
+
+[0] https://github.com/u-boot/u-boot/commit/ec80b4735a593961fe701cc3a5d717d4739b0fd0
diff --git a/MAINTAINERS b/MAINTAINERS
index f967ba816191..ca99126a41c2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -189,7 +189,7 @@ F:	drivers/net/hamradio/6pack.c
 M:	Johannes Berg <johannes@sipsolutions.net>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-W:	http://wireless.kernel.org/
+W:	https://wireless.wiki.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
 F:	Documentation/driver-api/80211/cfg80211.rst
@@ -505,7 +505,7 @@ F:	drivers/hwmon/adm1029.c
 ADM8211 WIRELESS DRIVER
 L:	linux-wireless@vger.kernel.org
 S:	Orphan
-W:	http://wireless.kernel.org/
+W:	https://wireless.wiki.kernel.org/
 F:	drivers/net/wireless/admtek/adm8211.*
 
 ADP1653 FLASH CONTROLLER DRIVER
@@ -570,7 +570,7 @@ F:	Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml
 F:	drivers/input/misc/adxl34x.c
 
 ADXL372 THREE-AXIS DIGITAL ACCELEROMETER DRIVER
-M:	Stefan Popa <stefan.popa@analog.com>
+M:	Michael Hennerich <michael.hennerich@analog.com>
 S:	Supported
 W:	http://ez.analog.com/community/linux-device-drivers
 F:	Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml
@@ -842,6 +842,13 @@ S:	Supported
 T:	git git://people.freedesktop.org/~agd5f/linux
 F:	drivers/gpu/drm/amd/display/
 
+AMD ENERGY DRIVER
+M:	Naveen Krishna Chatradhi <nchatrad@amd.com>
+L:	linux-hwmon@vger.kernel.org
+S:	Maintained
+F:	Documentation/hwmon/amd_energy.rst
+F:	drivers/hwmon/amd_energy.c
+
 AMD FAM15H PROCESSOR POWER MONITORING DRIVER
 M:	Huang Rui <ray.huang@amd.com>
 L:	linux-hwmon@vger.kernel.org
@@ -892,6 +899,11 @@ F:	drivers/gpu/drm/amd/include/v9_structs.h
 F:	drivers/gpu/drm/amd/include/vi_structs.h
 F:	include/uapi/linux/kfd_ioctl.h
 
+AMD SPI DRIVER
+M:	Sanjay R Mehta <sanju.mehta@amd.com>
+S:	Maintained
+F:	drivers/spi/spi-amd.c
+
 AMD MP2 I2C DRIVER
 M:	Elie Morisse <syniurge@gmail.com>
 M:	Nehal Shah <nehal-bakulchandra.shah@amd.com>
@@ -922,7 +934,7 @@ F:	arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi
 F:	drivers/net/ethernet/amd/xgbe/
 
 ANALOG DEVICES INC AD5686 DRIVER
-M:	Stefan Popa <stefan.popa@analog.com>
+M:	Michael Hennerich <Michael.Hennerich@analog.com>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 W:	http://ez.analog.com/community/linux-device-drivers
@@ -930,7 +942,7 @@ F:	drivers/iio/dac/ad5686*
 F:	drivers/iio/dac/ad5696*
 
 ANALOG DEVICES INC AD5758 DRIVER
-M:	Stefan Popa <stefan.popa@analog.com>
+M:	Michael Hennerich <Michael.Hennerich@analog.com>
 L:	linux-iio@vger.kernel.org
 S:	Supported
 W:	http://ez.analog.com/community/linux-device-drivers
@@ -946,7 +958,7 @@ F:	Documentation/devicetree/bindings/iio/adc/adi,ad7091r5.yaml
 F:	drivers/iio/adc/ad7091r5.c
 
 ANALOG DEVICES INC AD7124 DRIVER
-M:	Stefan Popa <stefan.popa@analog.com>
+M:	Michael Hennerich <Michael.Hennerich@analog.com>
 L:	linux-iio@vger.kernel.org
 S:	Supported
 W:	http://ez.analog.com/community/linux-device-drivers
@@ -970,7 +982,7 @@ F:	Documentation/devicetree/bindings/iio/adc/adi,ad7292.yaml
 F:	drivers/iio/adc/ad7292.c
 
 ANALOG DEVICES INC AD7606 DRIVER
-M:	Stefan Popa <stefan.popa@analog.com>
+M:	Michael Hennerich <Michael.Hennerich@analog.com>
 M:	Beniamin Bia <beniamin.bia@analog.com>
 L:	linux-iio@vger.kernel.org
 S:	Supported
@@ -979,7 +991,7 @@ F:	Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml
 F:	drivers/iio/adc/ad7606.c
 
 ANALOG DEVICES INC AD7768-1 DRIVER
-M:	Stefan Popa <stefan.popa@analog.com>
+M:	Michael Hennerich <Michael.Hennerich@analog.com>
 L:	linux-iio@vger.kernel.org
 S:	Supported
 W:	http://ez.analog.com/community/linux-device-drivers
@@ -1040,7 +1052,7 @@ F:	Documentation/devicetree/bindings/hwmon/adi,adm1177.yaml
 F:	drivers/hwmon/adm1177.c
 
 ANALOG DEVICES INC ADP5061 DRIVER
-M:	Stefan Popa <stefan.popa@analog.com>
+M:	Michael Hennerich <Michael.Hennerich@analog.com>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 W:	http://ez.analog.com/community/linux-device-drivers
@@ -1109,7 +1121,6 @@ F:	drivers/iio/amplifiers/hmc425a.c
 ANALOG DEVICES INC IIO DRIVERS
 M:	Lars-Peter Clausen <lars@metafoo.de>
 M:	Michael Hennerich <Michael.Hennerich@analog.com>
-M:	Stefan Popa <stefan.popa@analog.com>
 S:	Supported
 W:	http://wiki.analog.com/
 W:	http://ez.analog.com/community/linux-device-drivers
@@ -2850,14 +2861,14 @@ M:	Nick Kossifidis <mickflemm@gmail.com>
 M:	Luis Chamberlain <mcgrof@kernel.org>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-W:	http://wireless.kernel.org/en/users/Drivers/ath5k
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath5k
 F:	drivers/net/wireless/ath/ath5k/
 
 ATHEROS ATH6KL WIRELESS DRIVER
 M:	Kalle Valo <kvalo@codeaurora.org>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
-W:	http://wireless.kernel.org/en/users/Drivers/ath6kl
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath6kl
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
 F:	drivers/net/wireless/ath/ath6kl/
 
@@ -3020,7 +3031,7 @@ B43 WIRELESS DRIVER
 L:	linux-wireless@vger.kernel.org
 L:	b43-dev@lists.infradead.org
 S:	Odd Fixes
-W:	http://wireless.kernel.org/en/users/Drivers/b43
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/b43
 F:	drivers/net/wireless/broadcom/b43/
 
 B43LEGACY WIRELESS DRIVER
@@ -3028,7 +3039,7 @@ M:	Larry Finger <Larry.Finger@lwfinger.net>
 L:	linux-wireless@vger.kernel.org
 L:	b43-dev@lists.infradead.org
 S:	Maintained
-W:	http://wireless.kernel.org/en/users/Drivers/b43
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/b43
 F:	drivers/net/wireless/broadcom/b43legacy/
 
 BACKLIGHT CLASS/SUBSYSTEM
@@ -3658,7 +3669,7 @@ L:	linux-btrfs@vger.kernel.org
 S:	Maintained
 W:	http://btrfs.wiki.kernel.org/
 Q:	http://patchwork.kernel.org/project/linux-btrfs/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git
 F:	Documentation/filesystems/btrfs.rst
 F:	fs/btrfs/
 F:	include/linux/btrfs*
@@ -3843,7 +3854,7 @@ CARL9170 LINUX COMMUNITY WIRELESS DRIVER
 M:	Christian Lamparter <chunkeey@googlemail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-W:	http://wireless.kernel.org/en/users/Drivers/carl9170
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/carl9170
 F:	drivers/net/wireless/ath/carl9170/
 
 CAVIUM I2C DRIVER
@@ -3897,6 +3908,15 @@ S:	Supported
 W:	https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell-700-family
 F:	drivers/crypto/ccree/
 
+CCTRNG ARM TRUSTZONE CRYPTOCELL TRUE RANDOM NUMBER GENERATOR (TRNG) DRIVER
+M:	Hadar Gat <hadar.gat@arm.com>
+L:	linux-crypto@vger.kernel.org
+S:	Supported
+F:	drivers/char/hw_random/cctrng.c
+F:	drivers/char/hw_random/cctrng.h
+F:	Documentation/devicetree/bindings/rng/arm-cctrng.txt
+W:	https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell-700-family
+
 CEC FRAMEWORK
 M:	Hans Verkuil <hverkuil-cisco@xs4all.nl>
 L:	linux-media@vger.kernel.org
@@ -3937,11 +3957,9 @@ F:	arch/powerpc/platforms/cell/
 CEPH COMMON CODE (LIBCEPH)
 M:	Ilya Dryomov <idryomov@gmail.com>
 M:	Jeff Layton <jlayton@kernel.org>
-M:	Sage Weil <sage@redhat.com>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 T:	git git://github.com/ceph/ceph-client.git
 F:	include/linux/ceph/
 F:	include/linux/crush/
@@ -3949,12 +3967,10 @@ F:	net/ceph/
 
 CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH)
 M:	Jeff Layton <jlayton@kernel.org>
-M:	Sage Weil <sage@redhat.com>
 M:	Ilya Dryomov <idryomov@gmail.com>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 T:	git git://github.com/ceph/ceph-client.git
 F:	Documentation/filesystems/ceph.rst
 F:	fs/ceph/
@@ -5176,6 +5192,7 @@ S:	Maintained
 F:	drivers/soc/fsl/dpio
 
 DPAA2 ETHERNET DRIVER
+M:	Ioana Ciornei <ioana.ciornei@nxp.com>
 M:	Ioana Radulescu <ruxandra.radulescu@nxp.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -5511,10 +5528,10 @@ F:	drivers/gpu/drm/vboxvideo/
 
 DRM DRIVER FOR VMWARE VIRTUAL GPU
 M:	"VMware Graphics" <linux-graphics-maintainer@vmware.com>
-M:	Thomas Hellstrom <thellstrom@vmware.com>
+M:	Roland Scheidegger <sroland@vmware.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Supported
-T:	git git://people.freedesktop.org/~thomash/linux
+T:	git git://people.freedesktop.org/~sroland/linux
 F:	drivers/gpu/drm/vmwgfx/
 F:	include/uapi/drm/vmwgfx_drm.h
 
@@ -5935,6 +5952,7 @@ F:	lib/dynamic_debug.c
 DYNAMIC INTERRUPT MODERATION
 M:	Tal Gilboa <talgi@mellanox.com>
 S:	Maintained
+F:	Documentation/networking/net_dim.rst
 F:	include/linux/dim.h
 F:	lib/dim/
 
@@ -6175,7 +6193,6 @@ M:	Yash Shah <yash.shah@sifive.com>
 L:	linux-edac@vger.kernel.org
 S:	Supported
 F:	drivers/edac/sifive_edac.c
-F:	drivers/soc/sifive_l2_cache.c
 
 EDAC-SKYLAKE
 M:	Tony Luck <tony.luck@intel.com>
@@ -7031,6 +7048,17 @@ F:	kernel/futex.c
 F:	tools/perf/bench/futex*
 F:	Documentation/locking/*futex*
 
+GATEWORKS SYSTEM CONTROLLER (GSC) DRIVER
+M:	Tim Harvey <tharvey@gateworks.com>
+M:	Robert Jones <rjones@gateworks.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/mfd/gateworks-gsc.yaml
+F:	drivers/mfd/gateworks-gsc.c
+F:	include/linux/mfd/gsc.h
+F:	Documentation/hwmon/gsc-hwmon.rst
+F:	drivers/hwmon/gsc-hwmon.c
+F:	include/linux/platform_data/gsc_hwmon.h
+
 GASKET DRIVER FRAMEWORK
 M:	Rob Springer <rspringer@google.com>
 M:	Todd Poynor <toddpoynor@google.com>
@@ -7118,9 +7146,10 @@ F:	include/uapi/asm-generic/
 
 GENERIC PHY FRAMEWORK
 M:	Kishon Vijay Abraham I <kishon@ti.com>
+M:	Vinod Koul <vkoul@kernel.org>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kishon/linux-phy.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git
 F:	Documentation/devicetree/bindings/phy/
 F:	drivers/phy/
 F:	include/linux/phy/
@@ -7745,11 +7774,6 @@ L:	platform-driver-x86@vger.kernel.org
 S:	Orphan
 F:	drivers/platform/x86/tc1100-wmi.c
 
-HP100:	Driver for HP 10/100 Mbit/s Voice Grade Network Adapter Series
-M:	Jaroslav Kysela <perex@perex.cz>
-S:	Obsolete
-F:	drivers/staging/hp/hp100.*
-
 HPET:	High Precision Event Timers driver
 M:	Clemens Ladisch <clemens@ladisch.de>
 S:	Maintained
@@ -7836,7 +7860,7 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/platform/sti/hva
 
 HWPOISON MEMORY FAILURE HANDLING
-M:	Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+M:	Naoya Horiguchi <naoya.horiguchi@nec.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/hwpoison-inject.c
@@ -7948,7 +7972,7 @@ F:	Documentation/i2c/busses/i2c-parport.rst
 F:	drivers/i2c/busses/i2c-parport.c
 
 I2C SUBSYSTEM
-M:	Wolfram Sang <wsa@the-dreams.de>
+M:	Wolfram Sang <wsa@kernel.org>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 W:	https://i2c.wiki.kernel.org/
@@ -9192,6 +9216,11 @@ L:	kexec@lists.infradead.org
 S:	Maintained
 W:	http://lse.sourceforge.net/kdump/
 F:	Documentation/admin-guide/kdump/
+F:	fs/proc/vmcore.c
+F:	include/linux/crash_core.h
+F:	include/linux/crash_dump.h
+F:	include/uapi/linux/vmcore.h
+F:	kernel/crash_*.c
 
 KEENE FM RADIO TRANSMITTER DRIVER
 M:	Hans Verkuil <hverkuil@xs4all.nl>
@@ -9328,6 +9357,7 @@ M:	Christian Borntraeger <borntraeger@de.ibm.com>
 M:	Janosch Frank <frankja@linux.ibm.com>
 R:	David Hildenbrand <david@redhat.com>
 R:	Cornelia Huck <cohuck@redhat.com>
+R:	Claudio Imbrenda <imbrenda@linux.ibm.com>
 L:	kvm@vger.kernel.org
 S:	Supported
 W:	http://www.ibm.com/developerworks/linux/linux390/
@@ -9415,6 +9445,13 @@ F:	include/linux/keyctl.h
 F:	include/uapi/linux/keyctl.h
 F:	security/keys/
 
+KFIFO
+M:	Stefani Seibold <stefani@seibold.net>
+S:	Maintained
+F:	include/linux/kfifo.h
+F:	lib/kfifo.c
+F:	samples/kfifo/
+
 KGDB / KDB /debug_core
 M:	Jason Wessel <jason.wessel@windriver.com>
 M:	Daniel Thompson <daniel.thompson@linaro.org>
@@ -9719,6 +9756,13 @@ F:	drivers/lightnvm/
 F:	include/linux/lightnvm.h
 F:	include/uapi/linux/lightnvm.h
 
+LINEAR RANGES HELPERS
+M:	Mark Brown <broonie@kernel.org>
+R:	Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
+F:	lib/linear_ranges.c
+F:	lib/test_linear_ranges.c
+F:	include/linux/linear_range.h
+
 LINUX FOR POWER MACINTOSH
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
 L:	linuxppc-dev@lists.ozlabs.org
@@ -10066,7 +10110,7 @@ MAC80211
 M:	Johannes Berg <johannes@sipsolutions.net>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-W:	http://wireless.kernel.org/
+W:	https://wireless.wiki.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
 F:	Documentation/networking/mac80211-injection.txt
@@ -10661,6 +10705,13 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/mediatek/
 
+MEDIATEK I2C CONTROLLER DRIVER
+M:	Qii Wang <qii.wang@mediatek.com>
+L:	linux-i2c@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/i2c/i2c-mt65xx.txt
+F:	drivers/i2c/busses/i2c-mt65xx.c
+
 MEDIATEK JPEG DRIVER
 M:	Rick Chang <rick.chang@mediatek.com>
 M:	Bin Liu <bin.liu@mediatek.com>
@@ -10696,7 +10747,6 @@ MEDIATEK MT76 WIRELESS LAN DRIVER
 M:	Felix Fietkau <nbd@nbd.name>
 M:	Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
 R:	Ryder Lee <ryder.lee@mediatek.com>
-R:	Roy Luo <royluo@google.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
 F:	drivers/net/wireless/mediatek/mt76/
@@ -11710,8 +11760,9 @@ F:	net/core/drop_monitor.c
 
 NETWORKING DRIVERS
 M:	"David S. Miller" <davem@davemloft.net>
+M:	Jakub Kicinski <kuba@kernel.org>
 L:	netdev@vger.kernel.org
-S:	Odd Fixes
+S:	Maintained
 W:	http://www.linuxfoundation.org/en/Net
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
@@ -12647,7 +12698,7 @@ F:	fs/orangefs/
 ORINOCO DRIVER
 L:	linux-wireless@vger.kernel.org
 S:	Orphan
-W:	http://wireless.kernel.org/en/users/Drivers/orinoco
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/orinoco
 W:	http://www.nongnu.org/orinoco/
 F:	drivers/net/wireless/intersil/orinoco/
 
@@ -12673,7 +12724,7 @@ P54 WIRELESS DRIVER
 M:	Christian Lamparter <chunkeey@googlemail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-W:	http://wireless.kernel.org/en/users/Drivers/p54
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/p54
 F:	drivers/net/wireless/intersil/p54/
 
 PACKING
@@ -13041,7 +13092,7 @@ F:	drivers/pci/controller/pci-xgene-msi.c
 
 PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
 M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
-R:	Andrew Murray <amurray@thegoodpenguin.co.uk>
+R:	Rob Herring <robh@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
 Q:	http://patchwork.ozlabs.org/project/linux-pci/list/
@@ -13594,7 +13645,7 @@ PRISM54 WIRELESS DRIVER
 M:	Luis Chamberlain <mcgrof@kernel.org>
 L:	linux-wireless@vger.kernel.org
 S:	Obsolete
-W:	http://wireless.kernel.org/en/users/Drivers/p54
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/p54
 F:	drivers/net/wireless/intersil/prism54/
 
 PROC FILESYSTEM
@@ -13663,6 +13714,7 @@ M:	Tony Luck <tony.luck@intel.com>
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/pstore
 F:	Documentation/admin-guide/ramoops.rst
+F:	Documentation/admin-guide/pstore-blk.rst
 F:	Documentation/devicetree/bindings/reserved-memory/ramoops.txt
 F:	drivers/acpi/apei/erst.c
 F:	drivers/firmware/efi/efi-pstore.c
@@ -13856,7 +13908,8 @@ S:	Maintained
 F:	drivers/scsi/qla1280.[ch]
 
 QLOGIC QLA2XXX FC-SCSI DRIVER
-M:	hmadhani@marvell.com
+M:	Nilesh Javali <njavali@marvell.com>
+M:	GR-QLogic-Storage-Upstream@marvell.com
 L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	Documentation/scsi/LICENSE.qla2xxx
@@ -13934,7 +13987,7 @@ QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
 M:	Kalle Valo <kvalo@codeaurora.org>
 L:	ath10k@lists.infradead.org
 S:	Supported
-W:	http://wireless.kernel.org/en/users/Drivers/ath10k
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath10k
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
 F:	drivers/net/wireless/ath/ath10k/
 
@@ -13949,7 +14002,7 @@ QUALCOMM ATHEROS ATH9K WIRELESS DRIVER
 M:	QCA ath9k Development <ath9k-devel@qca.qualcomm.com>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
-W:	http://wireless.kernel.org/en/users/Drivers/ath9k
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath9k
 F:	drivers/net/wireless/ath/ath9k/
 
 QUALCOMM CAMERA SUBSYSTEM DRIVER
@@ -14046,13 +14099,12 @@ QUALCOMM WCN36XX WIRELESS DRIVER
 M:	Kalle Valo <kvalo@codeaurora.org>
 L:	wcn36xx@lists.infradead.org
 S:	Supported
-W:	http://wireless.kernel.org/en/users/Drivers/wcn36xx
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/wcn36xx
 T:	git git://github.com/KrasnikovEugene/wcn36xx.git
 F:	drivers/net/wireless/ath/wcn36xx/
 
 QUANTENNA QTNFMAC WIRELESS DRIVER
 M:	Igor Mitsyanko <imitsyanko@quantenna.com>
-M:	Avinash Patil <avinashp@quantenna.com>
 M:	Sergey Matyukevich <smatyukevich@quantenna.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
@@ -14094,12 +14146,10 @@ F:	drivers/media/radio/radio-tea5777.c
 
 RADOS BLOCK DEVICE (RBD)
 M:	Ilya Dryomov <idryomov@gmail.com>
-M:	Sage Weil <sage@redhat.com>
 R:	Dongsheng Yang <dongsheng.yang@easystack.cn>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 T:	git git://github.com/ceph/ceph-client.git
 F:	Documentation/ABI/testing/sysfs-bus-rbd
 F:	drivers/block/rbd.c
@@ -14219,7 +14269,7 @@ M:	Reinette Chatre <reinette.chatre@intel.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	Documentation/x86/resctrl*
-F:	arch/x86/include/asm/resctrl_sched.h
+F:	arch/x86/include/asm/resctrl.h
 F:	arch/x86/kernel/cpu/resctrl/
 F:	tools/testing/selftests/resctrl/
 
@@ -14274,7 +14324,7 @@ REALTEK WIRELESS DRIVER (rtlwifi family)
 M:	Ping-Ke Shih <pkshih@realtek.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-W:	http://wireless.kernel.org/
+W:	https://wireless.wiki.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 F:	drivers/net/wireless/realtek/rtlwifi/
 
@@ -14409,7 +14459,7 @@ RFKILL
 M:	Johannes Berg <johannes@sipsolutions.net>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-W:	http://wireless.kernel.org/
+W:	https://wireless.wiki.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
 F:	Documentation/ABI/stable/sysfs-class-rfkill
@@ -14558,7 +14608,7 @@ F:	drivers/media/dvb-frontends/rtl2832_sdr*
 RTL8180 WIRELESS DRIVER
 L:	linux-wireless@vger.kernel.org
 S:	Orphan
-W:	http://wireless.kernel.org/
+W:	https://wireless.wiki.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 F:	drivers/net/wireless/realtek/rtl818x/rtl8180/
 
@@ -14568,7 +14618,7 @@ M:	Hin-Tak Leung <htl10@users.sourceforge.net>
 M:	Larry Finger <Larry.Finger@lwfinger.net>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-W:	http://wireless.kernel.org/
+W:	https://wireless.wiki.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 F:	drivers/net/wireless/realtek/rtl818x/rtl8187/
 
@@ -14636,6 +14686,7 @@ F:	drivers/iommu/s390-iommu.c
 
 S390 IUCV NETWORK LAYER
 M:	Julian Wiedmann <jwi@linux.ibm.com>
+M:	Karsten Graul <kgraul@linux.ibm.com>
 M:	Ursula Braun <ubraun@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
@@ -14646,6 +14697,7 @@ F:	net/iucv/
 
 S390 NETWORK DRIVERS
 M:	Julian Wiedmann <jwi@linux.ibm.com>
+M:	Karsten Graul <kgraul@linux.ibm.com>
 M:	Ursula Braun <ubraun@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
@@ -15466,6 +15518,15 @@ M:	Nicolas Pitre <nico@fluxnic.net>
 S:	Odd Fixes
 F:	drivers/net/ethernet/smsc/smc91x.*
 
+SECURE MONITOR CALL(SMC) CALLING CONVENTION (SMCCC)
+M:	Mark Rutland <mark.rutland@arm.com>
+M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+M:	Sudeep Holla <sudeep.holla@arm.com>
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	drivers/firmware/smccc/
+F:	include/linux/arm-smccc.h
+
 SMIA AND SMIA++ IMAGE SENSOR DRIVER
 M:	Sakari Ailus <sakari.ailus@linux.intel.com>
 L:	linux-media@vger.kernel.org
@@ -16923,8 +16984,8 @@ F:	drivers/media/platform/ti-vpe/
 TI WILINK WIRELESS DRIVERS
 L:	linux-wireless@vger.kernel.org
 S:	Orphan
-W:	http://wireless.kernel.org/en/users/Drivers/wl12xx
-W:	http://wireless.kernel.org/en/users/Drivers/wl1251
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/wl12xx
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/wl1251
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/luca/wl12xx.git
 F:	drivers/net/wireless/ti/
 F:	include/linux/wl12xx.h
@@ -18206,7 +18267,7 @@ M:	Maya Erez <merez@codeaurora.org>
 L:	linux-wireless@vger.kernel.org
 L:	wil6210@qti.qualcomm.com
 S:	Supported
-W:	http://wireless.kernel.org/en/users/Drivers/wil6210
+W:	https://wireless.wiki.kernel.org/en/users/Drivers/wil6210
 F:	drivers/net/wireless/ath/wil6210/
 
 WIMAX STACK
diff --git a/Makefile b/Makefile
index 70def4907036..a7bc91cbac8f 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -729,10 +729,6 @@ else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 KBUILD_CFLAGS += -Os
 endif
 
-ifdef CONFIG_CC_DISABLE_WARN_MAYBE_UNINITIALIZED
-KBUILD_CFLAGS   += -Wno-maybe-uninitialized
-endif
-
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
 KBUILD_CFLAGS	+= $(call cc-option,-fno-allow-store-data-races)
@@ -866,6 +862,12 @@ ifdef CONFIG_LIVEPATCH
 KBUILD_CFLAGS += $(call cc-option, -flive-patching=inline-clone)
 endif
 
+ifdef CONFIG_SHADOW_CALL_STACK
+CC_FLAGS_SCS	:= -fsanitize=shadow-call-stack
+KBUILD_CFLAGS	+= $(CC_FLAGS_SCS)
+export CC_FLAGS_SCS
+endif
+
 # arch Makefile may override CC so keep this after arch Makefile is included
 NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include)
 
@@ -881,6 +883,17 @@ KBUILD_CFLAGS += -Wno-pointer-sign
 # disable stringop warnings in gcc 8+
 KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
 
+# We'll want to enable this eventually, but it's not going away for 5.7 at least
+KBUILD_CFLAGS += $(call cc-disable-warning, zero-length-bounds)
+KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds)
+KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow)
+
+# Another good warning that we'll want to enable eventually
+KBUILD_CFLAGS += $(call cc-disable-warning, restrict)
+
+# Enabled with W=2, disabled by default as noisy
+KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized)
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 786a85d4ad40..2e6f843d87c4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -533,6 +533,31 @@ config STACKPROTECTOR_STRONG
 	  about 20% of all kernel functions, which increases the kernel code
 	  size by about 2%.
 
+config ARCH_SUPPORTS_SHADOW_CALL_STACK
+	bool
+	help
+	  An architecture should select this if it supports Clang's Shadow
+	  Call Stack and implements runtime support for shadow stack
+	  switching.
+
+config SHADOW_CALL_STACK
+	bool "Clang Shadow Call Stack"
+	depends on CC_IS_CLANG && ARCH_SUPPORTS_SHADOW_CALL_STACK
+	depends on DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER
+	help
+	  This option enables Clang's Shadow Call Stack, which uses a
+	  shadow stack to protect function return addresses from being
+	  overwritten by an attacker. More information can be found in
+	  Clang's documentation:
+
+	    https://clang.llvm.org/docs/ShadowCallStack.html
+
+	  Note that security guarantees in the kernel differ from the
+	  ones documented for user space. The kernel must store addresses
+	  of shadow stacks in memory, which means an attacker capable of
+	  reading and writing arbitrary memory may be able to locate them
+	  and hijack control flow by modifying the stacks.
+
 config HAVE_ARCH_WITHIN_STACK_FRAMES
 	bool
 	help
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 0974226fab55..aa000075a575 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -65,6 +65,7 @@ CONFIG_DRM_UDL=y
 CONFIG_DRM_ETNAVIV=y
 CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y
diff --git a/arch/arc/include/asm/dsp-impl.h b/arch/arc/include/asm/dsp-impl.h
index e1aa212ca6eb..cd5636dfeb6f 100644
--- a/arch/arc/include/asm/dsp-impl.h
+++ b/arch/arc/include/asm/dsp-impl.h
@@ -15,12 +15,14 @@
 
 /* clobbers r5 register */
 .macro DSP_EARLY_INIT
+#ifdef CONFIG_ISA_ARCV2
 	lr	r5, [ARC_AUX_DSP_BUILD]
 	bmsk	r5, r5, 7
 	breq    r5, 0, 1f
 	mov	r5, DSP_CTRL_DISABLED_ALL
 	sr	r5, [ARC_AUX_DSP_CTRL]
 1:
+#endif
 .endm
 
 /* clobbers r10, r11 registers pair */
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index ae0aa5323be1..0ff4c0610561 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -233,6 +233,8 @@
 
 #ifdef CONFIG_ARC_IRQ_NO_AUTOSAVE
 	__RESTORE_REGFILE_HARD
+
+	; SP points to PC/STAT32: hw restores them despite NO_AUTOSAVE
 	add	sp, sp, SZ_PT_REGS - 8
 #else
 	add	sp, sp, PT_r0
diff --git a/arch/arc/include/asm/module.h b/arch/arc/include/asm/module.h
index 48f13a4ace4b..f534a1fef070 100644
--- a/arch/arc/include/asm/module.h
+++ b/arch/arc/include/asm/module.h
@@ -3,7 +3,6 @@
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  *
  * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
-
  */
 
 #ifndef _ASM_ARC_MODULE_H
@@ -19,8 +18,4 @@ struct mod_arch_specific {
 	const char *secstr;
 };
 
-#define MODULE_PROC_FAMILY "ARC700"
-
-#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
-
 #endif /* _ASM_ARC_MODULE_H */
diff --git a/arch/arc/include/asm/vermagic.h b/arch/arc/include/asm/vermagic.h
new file mode 100644
index 000000000000..a10257d2c62c
--- /dev/null
+++ b/arch/arc/include/asm/vermagic.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#define MODULE_ARCH_VERMAGIC "ARC700"
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile
index 75539670431a..8c4fc4b54c14 100644
--- a/arch/arc/kernel/Makefile
+++ b/arch/arc/kernel/Makefile
@@ -3,9 +3,6 @@
 # Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
 #
 
-# Pass UTS_MACHINE for user_regset definition
-CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
-
 obj-y	:= arcksyms.o setup.o irq.o reset.o ptrace.o process.o devtree.o
 obj-y	+= signal.o traps.o sys.o troubleshoot.o stacktrace.o disasm.o
 obj-$(CONFIG_ISA_ARCOMPACT)		+= entry-compact.o intc-compact.o
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index d5f3fcf273b5..f49a054a1016 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -253,7 +253,7 @@ static const struct user_regset arc_regsets[] = {
 };
 
 static const struct user_regset_view user_arc_view = {
-	.name		= UTS_MACHINE,
+	.name		= "arc",
 	.e_machine	= EM_ARC_INUSE,
 	.regsets	= arc_regsets,
 	.n		= ARRAY_SIZE(arc_regsets)
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index b2b1cb645d9e..dad8a656a2f1 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -11,6 +11,7 @@
 #include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <linux/cpu.h>
 #include <linux/of_clk.h>
 #include <linux/of_fdt.h>
@@ -424,12 +425,12 @@ static void arc_chk_core_config(void)
 	if ((unsigned int)__arc_dccm_base != cpu->dccm.base_addr)
 		panic("Linux built with incorrect DCCM Base address\n");
 
-	if (CONFIG_ARC_DCCM_SZ != cpu->dccm.sz)
+	if (CONFIG_ARC_DCCM_SZ * SZ_1K != cpu->dccm.sz)
 		panic("Linux built with incorrect DCCM Size\n");
 #endif
 
 #ifdef CONFIG_ARC_HAS_ICCM
-	if (CONFIG_ARC_ICCM_SZ != cpu->iccm.sz)
+	if (CONFIG_ARC_ICCM_SZ * SZ_1K != cpu->iccm.sz)
 		panic("Linux built with incorrect ICCM Size\n");
 #endif
 
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index d2999503fb8a..3393558876a9 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -191,10 +191,9 @@ void show_regs(struct pt_regs *regs)
 	if (user_mode(regs))
 		show_faulting_vma(regs->ret); /* faulting code, not data */
 
-	pr_info("ECR: 0x%08lx EFA: 0x%08lx ERET: 0x%08lx\n",
-		regs->event, current->thread.fault_address, regs->ret);
-
-	pr_info("STAT32: 0x%08lx", regs->status32);
+	pr_info("ECR: 0x%08lx EFA: 0x%08lx ERET: 0x%08lx\nSTAT: 0x%08lx",
+		regs->event, current->thread.fault_address, regs->ret,
+		regs->status32);
 
 #define STS_BIT(r, bit)	r->status32 & STATUS_##bit##_MASK ? #bit" " : ""
 
@@ -210,11 +209,10 @@ void show_regs(struct pt_regs *regs)
 			(regs->status32 & STATUS_U_MASK) ? "U " : "K ",
 			STS_BIT(regs, DE), STS_BIT(regs, AE));
 #endif
-	pr_cont("  BTA: 0x%08lx\n", regs->bta);
-	pr_info("BLK: %pS\n SP: 0x%08lx  FP: 0x%08lx\n",
-		(void *)regs->blink, regs->sp, regs->fp);
+	pr_cont("  BTA: 0x%08lx\n  SP: 0x%08lx  FP: 0x%08lx BLK: %pS\n",
+		regs->bta, regs->sp, regs->fp, (void *)regs->blink);
 	pr_info("LPS: 0x%08lx\tLPE: 0x%08lx\tLPC: 0x%08lx\n",
-	       regs->lp_start, regs->lp_end, regs->lp_count);
+		regs->lp_start, regs->lp_end, regs->lp_count);
 
 	/* print regs->r0 thru regs->r12
 	 * Sequential printing was generating horrible code
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 27ea64b1fa33..f87758a6851b 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -1178,11 +1178,9 @@ int arc_unwind(struct unwind_frame_info *frame)
 #endif
 
 	/* update frame */
-#ifndef CONFIG_AS_CFI_SIGNAL_FRAME
 	if (frame->call_frame
 	    && !UNW_DEFAULT_RA(state.regs[retAddrReg], state.dataAlign))
 		frame->call_frame = 0;
-#endif
 	cfa = FRAME_REG(state.cfa.reg, unsigned long) + state.cfa.offs;
 	startLoc = min_t(unsigned long, UNW_SP(frame), cfa);
 	endLoc = max_t(unsigned long, UNW_SP(frame), cfa);
diff --git a/arch/arc/plat-eznps/Kconfig b/arch/arc/plat-eznps/Kconfig
index a931d0a256d0..a645bca5899a 100644
--- a/arch/arc/plat-eznps/Kconfig
+++ b/arch/arc/plat-eznps/Kconfig
@@ -6,6 +6,7 @@
 
 menuconfig ARC_PLAT_EZNPS
 	bool "\"EZchip\" ARC dev platform"
+	depends on ISA_ARCOMPACT
 	select CPU_BIG_ENDIAN
 	select CLKSRC_NPS if !PHYS_ADDR_T_64BIT
 	select EZNPS_GIC
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 66a04f6f4775..16fbf74030fe 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -12,6 +12,7 @@ config ARM
 	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_SETUP_DMA_OPS
@@ -312,6 +313,9 @@ choice
 config ARCH_MULTIPLATFORM
 	bool "Allow multiple platforms to be selected"
 	depends on MMU
+	select ARCH_FLATMEM_ENABLE
+	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_SELECT_MEMORY_MODEL
 	select ARM_HAS_SG_CHAIN
 	select ARM_PATCH_PHYS_VIRT
 	select AUTO_ZRELADDR
@@ -1515,11 +1519,15 @@ config OABI_COMPAT
 config ARCH_HAS_HOLES_MEMORYMODEL
 	bool
 
-config ARCH_SPARSEMEM_ENABLE
+config ARCH_SELECT_MEMORY_MODEL
+	bool
+
+config ARCH_FLATMEM_ENABLE
 	bool
 
-config ARCH_SPARSEMEM_DEFAULT
-	def_bool ARCH_SPARSEMEM_ENABLE
+config ARCH_SPARSEMEM_ENABLE
+	bool
+	select SPARSEMEM_STATIC if SPARSEMEM
 
 config HAVE_ARCH_PFN_VALID
 	def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
@@ -1954,7 +1962,7 @@ config EFI
 	select UCS2_STRING
 	select EFI_PARAMS_FROM_FDT
 	select EFI_STUB
-	select EFI_ARMSTUB
+	select EFI_GENERIC_STUB
 	select EFI_RUNTIME_WRAPPERS
 	---help---
 	  This option provides support for runtime services provided
diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore
index db05c6ef3e31..60606b0f378d 100644
--- a/arch/arm/boot/compressed/.gitignore
+++ b/arch/arm/boot/compressed/.gitignore
@@ -7,12 +7,3 @@ hyp-stub.S
 piggy_data
 vmlinux
 vmlinux.lds
-
-# borrowed libfdt files
-fdt.c
-fdt.h
-fdt_ro.c
-fdt_rw.c
-fdt_wip.c
-libfdt.h
-libfdt_internal.h
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 9c11e7490292..00602a6fba04 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -76,29 +76,30 @@ compress-$(CONFIG_KERNEL_LZMA) = lzma
 compress-$(CONFIG_KERNEL_XZ)   = xzkern
 compress-$(CONFIG_KERNEL_LZ4)  = lz4
 
-# Borrowed libfdt files for the ATAG compatibility mode
-
-libfdt		:= fdt_rw.c fdt_ro.c fdt_wip.c fdt.c
-libfdt_hdrs	:= fdt.h libfdt.h libfdt_internal.h
-
-libfdt_objs	:= $(addsuffix .o, $(basename $(libfdt)))
-
-$(addprefix $(obj)/,$(libfdt) $(libfdt_hdrs)): $(obj)/%: $(srctree)/scripts/dtc/libfdt/%
-	$(call cmd,shipped)
-
-$(addprefix $(obj)/,$(libfdt_objs) atags_to_fdt.o): \
-	$(addprefix $(obj)/,$(libfdt_hdrs))
+libfdt_objs := fdt_rw.o fdt_ro.o fdt_wip.o fdt.o
 
 ifeq ($(CONFIG_ARM_ATAG_DTB_COMPAT),y)
 OBJS	+= $(libfdt_objs) atags_to_fdt.o
 endif
 
+# -fstack-protector-strong triggers protection checks in this code,
+# but it is being used too early to link to meaningful stack_chk logic.
+nossp-flags-$(CONFIG_CC_HAS_STACKPROTECTOR_NONE) := -fno-stack-protector
+$(foreach o, $(libfdt_objs) atags_to_fdt.o, \
+	$(eval CFLAGS_$(o) := -I $(srctree)/scripts/dtc/libfdt $(nossp-flags-y)))
+
+# These were previously generated C files. When you are building the kernel
+# with O=, make sure to remove the stale files in the output tree. Otherwise,
+# the build system wrongly compiles the stale ones.
+ifdef building_out_of_srctree
+$(shell rm -f $(addprefix $(obj)/, fdt_rw.c fdt_ro.c fdt_wip.c fdt.c))
+endif
+
 targets       := vmlinux vmlinux.lds piggy_data piggy.o \
 		 lib1funcs.o ashldi3.o bswapsdi2.o \
 		 head.o $(OBJS)
 
-clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S \
-		$(libfdt) $(libfdt_hdrs) hyp-stub.S
+clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S hyp-stub.S
 
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 
@@ -107,15 +108,6 @@ ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
 endif
 
-# -fstack-protector-strong triggers protection checks in this code,
-# but it is being used too early to link to meaningful stack_chk logic.
-nossp-flags-$(CONFIG_CC_HAS_STACKPROTECTOR_NONE) := -fno-stack-protector
-CFLAGS_atags_to_fdt.o := $(nossp-flags-y)
-CFLAGS_fdt.o := $(nossp-flags-y)
-CFLAGS_fdt_ro.o := $(nossp-flags-y)
-CFLAGS_fdt_rw.o := $(nossp-flags-y)
-CFLAGS_fdt_wip.o := $(nossp-flags-y)
-
 ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \
 	     -I$(obj) $(DISABLE_ARM_SSP_PER_TASK_PLUGIN)
 asflags-y := -DZIMAGE
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
index 64c49747f8a3..8452753efebe 100644
--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/libfdt_env.h>
 #include <asm/setup.h>
 #include <libfdt.h>
 
diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S
index 62286da318e7..c0e7a745103e 100644
--- a/arch/arm/boot/compressed/efi-header.S
+++ b/arch/arm/boot/compressed/efi-header.S
@@ -60,7 +60,7 @@ optional_header:
 		.long	__pecoff_code_size		@ SizeOfCode
 		.long	__pecoff_data_size		@ SizeOfInitializedData
 		.long	0				@ SizeOfUninitializedData
-		.long	efi_entry - start		@ AddressOfEntryPoint
+		.long	efi_pe_entry - start		@ AddressOfEntryPoint
 		.long	start_offset			@ BaseOfCode
 		.long	__pecoff_data_start - start	@ BaseOfData
 
diff --git a/arch/arm/boot/compressed/fdt.c b/arch/arm/boot/compressed/fdt.c
new file mode 100644
index 000000000000..f8ea7a201ab1
--- /dev/null
+++ b/arch/arm/boot/compressed/fdt.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../../../lib/fdt.c"
diff --git a/arch/arm/boot/compressed/fdt_ro.c b/arch/arm/boot/compressed/fdt_ro.c
new file mode 100644
index 000000000000..93970a4ad5ae
--- /dev/null
+++ b/arch/arm/boot/compressed/fdt_ro.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../../../lib/fdt_ro.c"
diff --git a/arch/arm/boot/compressed/fdt_rw.c b/arch/arm/boot/compressed/fdt_rw.c
new file mode 100644
index 000000000000..f7c6b8b7e01c
--- /dev/null
+++ b/arch/arm/boot/compressed/fdt_rw.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../../../lib/fdt_rw.c"
diff --git a/arch/arm/boot/compressed/fdt_wip.c b/arch/arm/boot/compressed/fdt_wip.c
new file mode 100644
index 000000000000..048d2c7a088d
--- /dev/null
+++ b/arch/arm/boot/compressed/fdt_wip.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../../../lib/fdt_wip.c"
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index cabdd8f4a248..c79db44ba128 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -287,28 +287,22 @@ not_angel:
 		 */
 		mov	r0, pc
 		cmp	r0, r4
-		ldrcc	r0, LC0+28
+		ldrcc	r0, .Lheadroom
 		addcc	r0, r0, pc
 		cmpcc	r4, r0
 		orrcc	r4, r4, #1		@ remember we skipped cache_on
 		blcs	cache_on
 
-restart:	adr	r0, LC0
-		ldmia	r0, {r1, r2, r3, r6, r11, r12}
-		ldr	sp, [r0, #24]
-
-		/*
-		 * We might be running at a different address.  We need
-		 * to fix up various pointers.
-		 */
-		sub	r0, r0, r1		@ calculate the delta offset
-		add	r6, r6, r0		@ _edata
+restart:	adr	r0, LC1
+		ldr	sp, [r0]
+		ldr	r6, [r0, #4]
+		add	sp, sp, r0
+		add	r6, r6, r0
 
 		get_inflated_image_size	r9, r10, lr
 
 #ifndef CONFIG_ZBOOT_ROM
 		/* malloc space is above the relocated stack (64k max) */
-		add	sp, sp, r0
 		add	r10, sp, #0x10000
 #else
 		/*
@@ -322,9 +316,6 @@ restart:	adr	r0, LC0
 		mov	r5, #0			@ init dtb size to 0
 #ifdef CONFIG_ARM_APPENDED_DTB
 /*
- *   r0  = delta
- *   r2  = BSS start
- *   r3  = BSS end
  *   r4  = final kernel address (possibly with LSB set)
  *   r5  = appended dtb size (still unknown)
  *   r6  = _edata
@@ -332,8 +323,6 @@ restart:	adr	r0, LC0
  *   r8  = atags/device tree pointer
  *   r9  = size of decompressed image
  *   r10 = end of this image, including  bss/stack/malloc space if non XIP
- *   r11 = GOT start
- *   r12 = GOT end
  *   sp  = stack pointer
  *
  * if there are device trees (dtb) appended to zImage, advance r10 so that the
@@ -381,7 +370,6 @@ restart:	adr	r0, LC0
 		/* temporarily relocate the stack past the DTB work space */
 		add	sp, sp, r5
 
-		stmfd	sp!, {r0-r3, ip, lr}
 		mov	r0, r8
 		mov	r1, r6
 		mov	r2, r5
@@ -400,7 +388,6 @@ restart:	adr	r0, LC0
 		mov	r2, r5
 		bleq	atags_to_fdt
 
-		ldmfd	sp!, {r0-r3, ip, lr}
 		sub	sp, sp, r5
 #endif
 
@@ -537,6 +524,10 @@ dtb_check_done:
 		mov	pc, r0
 
 wont_overwrite:
+		adr	r0, LC0
+		ldmia	r0, {r1, r2, r3, r11, r12}
+		sub	r0, r0, r1		@ calculate the delta offset
+
 /*
  * If delta is zero, we are running at the address we were linked at.
  *   r0  = delta
@@ -660,13 +651,18 @@ not_relocated:	mov	r0, #0
 LC0:		.word	LC0			@ r1
 		.word	__bss_start		@ r2
 		.word	_end			@ r3
-		.word	_edata			@ r6
 		.word	_got_start		@ r11
 		.word	_got_end		@ ip
-		.word	.L_user_stack_end	@ sp
-		.word	_end - restart + 16384 + 1024*1024
 		.size	LC0, . - LC0
 
+		.type	LC1, #object
+LC1:		.word	.L_user_stack_end - LC1	@ sp
+		.word	_edata - LC1		@ r6
+		.size	LC1, . - LC1
+
+.Lheadroom:
+		.word	_end - restart + 16384 + 1024*1024
+
 .Linflated_image_size_offset:
 		.long	(input_data_end - 4) - .
 
@@ -1434,37 +1430,26 @@ reloc_code_end:
 
 #ifdef CONFIG_EFI_STUB
 ENTRY(efi_enter_kernel)
-		mov	r7, r0				@ preserve image base
-		mov	r4, r1				@ preserve DT pointer
+		mov	r4, r0			@ preserve image base
+		mov	r8, r1			@ preserve DT pointer
 
-		mov	r0, r4				@ DT start
-		add	r1, r4, r2			@ DT end
-		bl	cache_clean_flush
+		mrc	p15, 0, r0, c1, c0, 0	@ read SCTLR
+		tst	r0, #0x1		@ MMU enabled?
+		orreq	r4, r4, #1		@ set LSB if not
 
-		mov	r0, r7				@ relocated zImage
-		ldr	r1, =_edata			@ size of zImage
-		add	r1, r1, r0			@ end of zImage
+		mov	r0, r8			@ DT start
+		add	r1, r8, r2		@ DT end
 		bl	cache_clean_flush
 
-		@ The PE/COFF loader might not have cleaned the code we are
-		@ running beyond the PoU, and so calling cache_off below from
-		@ inside the PE/COFF loader allocated region is unsafe unless
-		@ we explicitly clean it to the PoC.
-		adr	r0, call_cache_fn		@ region of code we will
-		adr	r1, 0f				@ run with MMU off
-		bl	cache_clean_flush
-		bl	cache_off
+		adr	r0, 0f			@ switch to our stack
+		ldr	sp, [r0]
+		add	sp, sp, r0
 
-		@ Set parameters for booting zImage according to boot protocol
-		@ put FDT address in r2, it was returned by efi_entry()
-		@ r1 is the machine type, and r0 needs to be 0
-		mov	r0, #0
-		mov	r1, #0xFFFFFFFF
-		mov	r2, r4
-		add	r7, r7, #(__efi_start - start)
-		mov	pc, r7				@ no mode switch
+		mov	r5, #0			@ appended DTB size
+		mov	r7, #0xFFFFFFFF		@ machine ID
+		b	wont_overwrite
 ENDPROC(efi_enter_kernel)
-0:
+0:		.long	.L_user_stack_end - .
 #endif
 
 		.align
diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h
deleted file mode 100644
index 6a0f1f524466..000000000000
--- a/arch/arm/boot/compressed/libfdt_env.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ARM_LIBFDT_ENV_H
-#define _ARM_LIBFDT_ENV_H
-
-#include <linux/limits.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <asm/byteorder.h>
-
-#define INT32_MAX	S32_MAX
-#define UINT32_MAX	U32_MAX
-
-typedef __be16 fdt16_t;
-typedef __be32 fdt32_t;
-typedef __be64 fdt64_t;
-
-#define fdt16_to_cpu(x)		be16_to_cpu(x)
-#define cpu_to_fdt16(x)		cpu_to_be16(x)
-#define fdt32_to_cpu(x)		be32_to_cpu(x)
-#define cpu_to_fdt32(x)		cpu_to_be32(x)
-#define fdt64_to_cpu(x)		be64_to_cpu(x)
-#define cpu_to_fdt64(x)		cpu_to_be64(x)
-
-#endif
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index b247f399de71..09ac33f52814 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -42,7 +42,7 @@ SECTIONS
   }
   .table : ALIGN(4) {
     _table_start = .;
-    LONG(ZIMAGE_MAGIC(2))
+    LONG(ZIMAGE_MAGIC(4))
     LONG(ZIMAGE_MAGIC(0x5a534c4b))
     LONG(ZIMAGE_MAGIC(__piggy_size_addr - _start))
     LONG(ZIMAGE_MAGIC(_kernel_bss_size))
@@ -63,9 +63,11 @@ SECTIONS
   _etext = .;
 
   .got.plt		: { *(.got.plt) }
+#ifndef CONFIG_EFI_STUB
   _got_start = .;
   .got			: { *(.got) }
   _got_end = .;
+#endif
 
   /* ensure the zImage file size is always a multiple of 64 bits */
   /* (without a dummy byte, ld just ignores the empty section) */
@@ -74,11 +76,14 @@ SECTIONS
 #ifdef CONFIG_EFI_STUB
   .data : ALIGN(4096) {
     __pecoff_data_start = .;
+    _got_start = .;
+    *(.got)
+    _got_end = .;
     /*
      * The EFI stub always executes from RAM, and runs strictly before the
      * decompressor, so we can make an exception for its r/w data, and keep it
      */
-    *(.data.efistub)
+    *(.data.efistub .bss.efistub)
     __pecoff_data_end = .;
 
     /*
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index 811c8cae315b..d692e3b2812a 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -943,7 +943,7 @@
 
 &cpsw_emac0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 };
 
 &elm {
diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts
index 9f66f96d09c9..a958f9ee4a5a 100644
--- a/arch/arm/boot/dts/am437x-idk-evm.dts
+++ b/arch/arm/boot/dts/am437x-idk-evm.dts
@@ -504,7 +504,7 @@
 
 &cpsw_emac0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 };
 
 &rtc {
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index 25222497f828..4d5a7ca2e25d 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -833,13 +833,13 @@
 
 &cpsw_emac0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 	dual_emac_res_vlan = <1>;
 };
 
 &cpsw_emac1 {
 	phy-handle = <&ethphy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 	dual_emac_res_vlan = <2>;
 };
 
diff --git a/arch/arm/boot/dts/am571x-idk.dts b/arch/arm/boot/dts/am571x-idk.dts
index 669559c9c95b..c13756fa0f55 100644
--- a/arch/arm/boot/dts/am571x-idk.dts
+++ b/arch/arm/boot/dts/am571x-idk.dts
@@ -190,13 +190,13 @@
 
 &cpsw_port1 {
 	phy-handle = <&ethphy0_sw>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 	ti,dual-emac-pvid = <1>;
 };
 
 &cpsw_port2 {
 	phy-handle = <&ethphy1_sw>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 	ti,dual-emac-pvid = <2>;
 };
 
diff --git a/arch/arm/boot/dts/am574x-idk.dts b/arch/arm/boot/dts/am574x-idk.dts
index fa0088025b2c..85c95cc551dd 100644
--- a/arch/arm/boot/dts/am574x-idk.dts
+++ b/arch/arm/boot/dts/am574x-idk.dts
@@ -40,3 +40,7 @@
 	status = "okay";
 	dual_emac;
 };
+
+&m_can0 {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
index a813a0cf3ff3..565675354de4 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-beagle-x15-common.dtsi
@@ -433,13 +433,13 @@
 
 &cpsw_emac0 {
 	phy-handle = <&phy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 	dual_emac_res_vlan = <1>;
 };
 
 &cpsw_emac1 {
 	phy-handle = <&phy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 	dual_emac_res_vlan = <2>;
 };
 
diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi
index aa5e55f98179..a3ff1237d1fa 100644
--- a/arch/arm/boot/dts/am57xx-idk-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi
@@ -408,13 +408,13 @@
 
 &cpsw_emac0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 	dual_emac_res_vlan = <1>;
 };
 
 &cpsw_emac1 {
 	phy-handle = <&ethphy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 	dual_emac_res_vlan = <2>;
 };
 
diff --git a/arch/arm/boot/dts/bcm-hr2.dtsi b/arch/arm/boot/dts/bcm-hr2.dtsi
index 6142c672811e..5e5f5ca3c86f 100644
--- a/arch/arm/boot/dts/bcm-hr2.dtsi
+++ b/arch/arm/boot/dts/bcm-hr2.dtsi
@@ -75,7 +75,7 @@
 		timer@20200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x20200 0x100>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&periph_clk>;
 		};
 
@@ -83,7 +83,7 @@
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x20600 0x20>;
 			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) |
-						  IRQ_TYPE_LEVEL_HIGH)>;
+						  IRQ_TYPE_EDGE_RISING)>;
 			clocks = <&periph_clk>;
 		};
 
@@ -91,7 +91,7 @@
 			compatible = "arm,cortex-a9-twd-wdt";
 			reg = <0x20620 0x20>;
 			interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) |
-						  IRQ_TYPE_LEVEL_HIGH)>;
+						  IRQ_TYPE_EDGE_RISING)>;
 			clocks = <&periph_clk>;
 		};
 
diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
index 4c3f606e5b8d..f65448c01e31 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
@@ -24,7 +24,7 @@
 
 	leds {
 		act {
-			gpios = <&gpio 47 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpio 47 GPIO_ACTIVE_LOW>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi
index fd2c766e0f71..f7ae5a4530b8 100644
--- a/arch/arm/boot/dts/bcm2835-rpi.dtsi
+++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi
@@ -14,6 +14,9 @@
 	soc {
 		firmware: firmware {
 			compatible = "raspberrypi,bcm2835-firmware", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
 			mboxes = <&mailbox>;
 			dma-ranges;
 		};
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index e1abe8c730ce..b83a864e2e8b 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -372,6 +372,7 @@
 					     "dsi0_ddr2",
 					     "dsi0_ddr";
 
+			status = "disabled";
 		};
 
 		aux: aux@7e215000 {
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index 44ed5a798164..c28ca0540f03 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -693,7 +693,7 @@
 
 					davinci_mdio: mdio@800 {
 						compatible = "ti,cpsw-mdio", "ti,davinci_mdio";
-						clocks = <&alwon_ethernet_clkctrl DM814_ETHERNET_CPGMAC0_CLKCTRL 0>;
+						clocks = <&cpsw_125mhz_gclk>;
 						clock-names = "fck";
 						#address-cells = <1>;
 						#size-cells = <0>;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 4740989ed9c4..7191ee6a1b82 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -172,6 +172,7 @@
 			#address-cells = <1>;
 			ranges = <0x51000000 0x51000000 0x3000
 				  0x0	     0x20000000 0x10000000>;
+			dma-ranges;
 			/**
 			 * To enable PCI endpoint mode, disable the pcie1_rc
 			 * node and enable pcie1_ep mode.
@@ -185,7 +186,6 @@
 				device_type = "pci";
 				ranges = <0x81000000 0 0          0x03000 0 0x00010000
 					  0x82000000 0 0x20013000 0x13000 0 0xffed000>;
-				dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>;
 				bus-range = <0x00 0xff>;
 				#interrupt-cells = <1>;
 				num-lanes = <1>;
@@ -230,6 +230,7 @@
 			#address-cells = <1>;
 			ranges = <0x51800000 0x51800000 0x3000
 				  0x0	     0x30000000 0x10000000>;
+			dma-ranges;
 			status = "disabled";
 			pcie2_rc: pcie@51800000 {
 				reg = <0x51800000 0x2000>, <0x51802000 0x14c>, <0x1000 0x2000>;
@@ -240,7 +241,6 @@
 				device_type = "pci";
 				ranges = <0x81000000 0 0          0x03000 0 0x00010000
 					  0x82000000 0 0x30013000 0x13000 0 0xffed000>;
-				dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>;
 				bus-range = <0x00 0xff>;
 				#interrupt-cells = <1>;
 				num-lanes = <1>;
diff --git a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
index 0cd75dadf292..188639738dc3 100644
--- a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
+++ b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts
@@ -75,8 +75,8 @@
 	imx27-phycard-s-rdk {
 		pinctrl_i2c1: i2c1grp {
 			fsl,pins = <
-				MX27_PAD_I2C2_SDA__I2C2_SDA 0x0
-				MX27_PAD_I2C2_SCL__I2C2_SCL 0x0
+				MX27_PAD_I2C_DATA__I2C_DATA 0x0
+				MX27_PAD_I2C_CLK__I2C_CLK 0x0
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts b/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts
index 0d594e4bd559..a1173bf5bff5 100644
--- a/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts
+++ b/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts
@@ -38,7 +38,7 @@
 };
 
 &switch_ports {
-	/delete-node/ port@2;
+	/delete-node/ port@3;
 };
 
 &touchscreen {
diff --git a/arch/arm/boot/dts/imx6q-b450v3.dts b/arch/arm/boot/dts/imx6q-b450v3.dts
index 95b8f2d71821..fb0980190aa0 100644
--- a/arch/arm/boot/dts/imx6q-b450v3.dts
+++ b/arch/arm/boot/dts/imx6q-b450v3.dts
@@ -65,13 +65,6 @@
 	};
 };
 
-&clks {
-	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
-	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
-				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
-};
-
 &ldb {
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/imx6q-b650v3.dts b/arch/arm/boot/dts/imx6q-b650v3.dts
index 611cb7ae7e55..8f762d9c5ae9 100644
--- a/arch/arm/boot/dts/imx6q-b650v3.dts
+++ b/arch/arm/boot/dts/imx6q-b650v3.dts
@@ -65,13 +65,6 @@
 	};
 };
 
-&clks {
-	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>;
-	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL3_USB_OTG>,
-				 <&clks IMX6QDL_CLK_PLL3_USB_OTG>;
-};
-
 &ldb {
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/imx6q-b850v3.dts b/arch/arm/boot/dts/imx6q-b850v3.dts
index e4cb118f88c6..1ea64ecf4291 100644
--- a/arch/arm/boot/dts/imx6q-b850v3.dts
+++ b/arch/arm/boot/dts/imx6q-b850v3.dts
@@ -53,17 +53,6 @@
 	};
 };
 
-&clks {
-	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
-			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>,
-			  <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>,
-			  <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>;
-	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
-				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
-				 <&clks IMX6QDL_CLK_PLL2_PFD2_396M>,
-				 <&clks IMX6QDL_CLK_PLL2_PFD2_396M>;
-};
-
 &ldb {
 	fsl,dual-channel;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6q-bx50v3.dtsi b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
index fa27dcdf06f1..1938b04199c4 100644
--- a/arch/arm/boot/dts/imx6q-bx50v3.dtsi
+++ b/arch/arm/boot/dts/imx6q-bx50v3.dtsi
@@ -377,3 +377,18 @@
 		#interrupt-cells = <1>;
 	};
 };
+
+&clks {
+	assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>,
+			  <&clks IMX6QDL_CLK_LDB_DI1_SEL>,
+			  <&clks IMX6QDL_CLK_IPU1_DI0_PRE_SEL>,
+			  <&clks IMX6QDL_CLK_IPU1_DI1_PRE_SEL>,
+			  <&clks IMX6QDL_CLK_IPU2_DI0_PRE_SEL>,
+			  <&clks IMX6QDL_CLK_IPU2_DI1_PRE_SEL>;
+	assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
+				 <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>,
+				 <&clks IMX6QDL_CLK_PLL2_PFD0_352M>;
+};
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 47982889d774..98da446aa0f2 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -1039,13 +1039,13 @@
 				compatible = "fsl,imx6q-fec";
 				reg = <0x02188000 0x4000>;
 				interrupt-names = "int0", "pps";
-				interrupts-extended =
-					<&intc 0 118 IRQ_TYPE_LEVEL_HIGH>,
-					<&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>,
+					     <0 119 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6QDL_CLK_ENET>,
 					 <&clks IMX6QDL_CLK_ENET>,
 					 <&clks IMX6QDL_CLK_ENET_REF>;
 				clock-names = "ipg", "ahb", "ptp";
+				gpr = <&gpr>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/imx6qp.dtsi b/arch/arm/boot/dts/imx6qp.dtsi
index 93b89dc1f53b..b310f13a53f2 100644
--- a/arch/arm/boot/dts/imx6qp.dtsi
+++ b/arch/arm/boot/dts/imx6qp.dtsi
@@ -77,7 +77,6 @@
 };
 
 &fec {
-	/delete-property/interrupts-extended;
 	interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>,
 		     <0 119 IRQ_TYPE_LEVEL_HIGH>;
 };
diff --git a/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi b/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi
index ede2e0c999b1..e10f99278c77 100644
--- a/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi
+++ b/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi
@@ -72,8 +72,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/mmp3-dell-ariel.dts b/arch/arm/boot/dts/mmp3-dell-ariel.dts
index 15449c72c042..b0ec14c42164 100644
--- a/arch/arm/boot/dts/mmp3-dell-ariel.dts
+++ b/arch/arm/boot/dts/mmp3-dell-ariel.dts
@@ -98,19 +98,19 @@
 	status = "okay";
 };
 
-&ssp3 {
+&ssp1 {
 	status = "okay";
-	cs-gpios = <&gpio 46 GPIO_ACTIVE_HIGH>;
+	cs-gpios = <&gpio 46 GPIO_ACTIVE_LOW>;
 
 	firmware-flash@0 {
-		compatible = "st,m25p80", "jedec,spi-nor";
+		compatible = "winbond,w25q32", "jedec,spi-nor";
 		reg = <0>;
-		spi-max-frequency = <40000000>;
+		spi-max-frequency = <104000000>;
 		m25p,fast-read;
 	};
 };
 
-&ssp4 {
-	cs-gpios = <&gpio 56 GPIO_ACTIVE_HIGH>;
+&ssp2 {
+	cs-gpios = <&gpio 56 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/mmp3.dtsi b/arch/arm/boot/dts/mmp3.dtsi
index 9b5087a95e73..826f0a577859 100644
--- a/arch/arm/boot/dts/mmp3.dtsi
+++ b/arch/arm/boot/dts/mmp3.dtsi
@@ -202,8 +202,7 @@
 			};
 
 			hsic_phy0: hsic-phy@f0001800 {
-				compatible = "marvell,mmp3-hsic-phy",
-					     "usb-nop-xceiv";
+				compatible = "marvell,mmp3-hsic-phy";
 				reg = <0xf0001800 0x40>;
 				#phy-cells = <0>;
 				status = "disabled";
@@ -224,8 +223,7 @@
 			};
 
 			hsic_phy1: hsic-phy@f0002800 {
-				compatible = "marvell,mmp3-hsic-phy",
-					     "usb-nop-xceiv";
+				compatible = "marvell,mmp3-hsic-phy";
 				reg = <0xf0002800 0x40>;
 				#phy-cells = <0>;
 				status = "disabled";
@@ -531,7 +529,7 @@
 		};
 
 		soc_clocks: clocks@d4050000 {
-			compatible = "marvell,mmp2-clock";
+			compatible = "marvell,mmp3-clock";
 			reg = <0xd4050000 0x1000>,
 			      <0xd4282800 0x400>,
 			      <0xd4015000 0x1000>;
diff --git a/arch/arm/boot/dts/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/motorola-mapphone-common.dtsi
index 9067e0ef4240..06fbffa81636 100644
--- a/arch/arm/boot/dts/motorola-mapphone-common.dtsi
+++ b/arch/arm/boot/dts/motorola-mapphone-common.dtsi
@@ -367,6 +367,8 @@
 };
 
 &mmc3 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc3_pins>;
 	vmmc-supply = <&wl12xx_vmmc>;
 	/* uart2_tx.sdmmc3_dat1 pad as wakeirq */
 	interrupts-extended = <&wakeupgen GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH
@@ -472,6 +474,37 @@
 		>;
 	};
 
+	/*
+	 * Android uses PIN_OFF_INPUT_PULLDOWN | PIN_INPUT_PULLUP | MUX_MODE3
+	 * for gpio_100, but the internal pull makes wlan flakey on some
+	 * devices. Off mode value should be tested if we have off mode working
+	 * later on.
+	 */
+	mmc3_pins: pinmux_mmc3_pins {
+		pinctrl-single,pins = <
+		/* 0x4a10008e gpmc_wait2.gpio_100 d23 */
+		OMAP4_IOPAD(0x08e, PIN_INPUT | MUX_MODE3)
+
+		/* 0x4a100102 abe_mcbsp1_dx.sdmmc3_dat2 ab25 */
+		OMAP4_IOPAD(0x102, PIN_INPUT_PULLUP | MUX_MODE1)
+
+		/* 0x4a100104 abe_mcbsp1_fsx.sdmmc3_dat3 ac27 */
+		OMAP4_IOPAD(0x104, PIN_INPUT_PULLUP | MUX_MODE1)
+
+		/* 0x4a100118 uart2_cts.sdmmc3_clk ab26 */
+		OMAP4_IOPAD(0x118, PIN_INPUT | MUX_MODE1)
+
+		/* 0x4a10011a uart2_rts.sdmmc3_cmd ab27 */
+		OMAP4_IOPAD(0x11a, PIN_INPUT_PULLUP | MUX_MODE1)
+
+		/* 0x4a10011c uart2_rx.sdmmc3_dat0 aa25 */
+		OMAP4_IOPAD(0x11c, PIN_INPUT_PULLUP | MUX_MODE1)
+
+		/* 0x4a10011e uart2_tx.sdmmc3_dat1 aa26 */
+		OMAP4_IOPAD(0x11e, PIN_INPUT_PULLUP | MUX_MODE1)
+		>;
+	};
+
 	/* gpmc_ncs0.gpio_50 */
 	poweroff_gpio: pinmux_poweroff_pins {
 		pinctrl-single,pins = <
@@ -690,14 +723,18 @@
 };
 
 /*
- * As uart1 is wired to mdm6600 with rts and cts, we can use the cts pin for
- * uart1 wakeirq.
+ * The uart1 port is wired to mdm6600 with rts and cts. The modem uses gpio_149
+ * for wake-up events for both the USB PHY and the UART. We can use gpio_149
+ * pad as the shared wakeirq for the UART rather than the RX or CTS pad as we
+ * have gpio_149 trigger before the UART transfer starts.
  */
 &uart1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart1_pins>;
 	interrupts-extended = <&wakeupgen GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH
-			       &omap4_pmx_core 0xfc>;
+			       &omap4_pmx_core 0x110>;
+	uart-has-rtscts;
+	current-speed = <115200>;
 };
 
 &uart3 {
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index a075b63f3087..11d41e86f814 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -341,6 +341,11 @@
 	status = "disabled";
 };
 
+/* RNG not directly accessible on N950/N9. */
+&rng_target {
+	status = "disabled";
+};
+
 &usb_otg_hs {
 	interface-type = <0>;
 	usb-phy = <&usb2_phy>;
diff --git a/arch/arm/boot/dts/r7s9210.dtsi b/arch/arm/boot/dts/r7s9210.dtsi
index 72b79770e336..cace43807497 100644
--- a/arch/arm/boot/dts/r7s9210.dtsi
+++ b/arch/arm/boot/dts/r7s9210.dtsi
@@ -304,7 +304,6 @@
 			reg = <0xe803b000 0x30>;
 			interrupts = <GIC_SPI 56 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&cpg CPG_MOD 36>;
-			clock-names = "ostm0";
 			power-domains = <&cpg>;
 			status = "disabled";
 		};
@@ -314,7 +313,6 @@
 			reg = <0xe803c000 0x30>;
 			interrupts = <GIC_SPI 57 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&cpg CPG_MOD 35>;
-			clock-names = "ostm1";
 			power-domains = <&cpg>;
 			status = "disabled";
 		};
@@ -324,7 +322,6 @@
 			reg = <0xe803d000 0x30>;
 			interrupts = <GIC_SPI 58 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&cpg CPG_MOD 34>;
-			clock-names = "ostm2";
 			power-domains = <&cpg>;
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi
index a5cd31229fbd..a3ba722a9d7f 100644
--- a/arch/arm/boot/dts/r8a73a4.dtsi
+++ b/arch/arm/boot/dts/r8a73a4.dtsi
@@ -131,7 +131,14 @@
 	cmt1: timer@e6130000 {
 		compatible = "renesas,r8a73a4-cmt1", "renesas,rcar-gen2-cmt1";
 		reg = <0 0xe6130000 0 0x1004>;
-		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp3_clks R8A73A4_CLK_CMT1>;
 		clock-names = "fck";
 		power-domains = <&pd_c5>;
diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi
index ebc1ff64f530..90feb2cf9960 100644
--- a/arch/arm/boot/dts/r8a7740.dtsi
+++ b/arch/arm/boot/dts/r8a7740.dtsi
@@ -479,7 +479,7 @@
 		cpg_clocks: cpg_clocks@e6150000 {
 			compatible = "renesas,r8a7740-cpg-clocks";
 			reg = <0xe6150000 0x10000>;
-			clocks = <&extal1_clk>, <&extalr_clk>;
+			clocks = <&extal1_clk>, <&extal2_clk>, <&extalr_clk>;
 			#clock-cells = <1>;
 			clock-output-names = "system", "pllc0", "pllc1",
 					     "pllc2", "r",
diff --git a/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts b/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts
index 92aa26ba423c..b1f679da36b2 100644
--- a/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts
+++ b/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts
@@ -84,8 +84,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7790-lager.dts b/arch/arm/boot/dts/r8a7790-lager.dts
index 69745def44d4..bfe778c4c47b 100644
--- a/arch/arm/boot/dts/r8a7790-lager.dts
+++ b/arch/arm/boot/dts/r8a7790-lager.dts
@@ -364,8 +364,6 @@
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
-			adi,input-style = <1>;
-			adi,input-justification = "evenly";
 
 			ports {
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7790-stout.dts b/arch/arm/boot/dts/r8a7790-stout.dts
index 4138efb2766d..6a457bc9280a 100644
--- a/arch/arm/boot/dts/r8a7790-stout.dts
+++ b/arch/arm/boot/dts/r8a7790-stout.dts
@@ -297,8 +297,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts
index 687167b70cb6..fc74c6cd6def 100644
--- a/arch/arm/boot/dts/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/r8a7791-koelsch.dts
@@ -387,8 +387,6 @@
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
-			adi,input-style = <1>;
-			adi,input-justification = "evenly";
 
 			ports {
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts
index a8e0335148a5..114bf1c4199b 100644
--- a/arch/arm/boot/dts/r8a7791-porter.dts
+++ b/arch/arm/boot/dts/r8a7791-porter.dts
@@ -181,8 +181,6 @@
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
-			adi,input-style = <1>;
-			adi,input-justification = "evenly";
 
 			ports {
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7792-blanche.dts b/arch/arm/boot/dts/r8a7792-blanche.dts
index 248eb717eb35..9368ac2cf508 100644
--- a/arch/arm/boot/dts/r8a7792-blanche.dts
+++ b/arch/arm/boot/dts/r8a7792-blanche.dts
@@ -289,8 +289,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7792-wheat.dts b/arch/arm/boot/dts/r8a7792-wheat.dts
index bd2a63bdab3d..ba2d2a589012 100644
--- a/arch/arm/boot/dts/r8a7792-wheat.dts
+++ b/arch/arm/boot/dts/r8a7792-wheat.dts
@@ -249,14 +249,12 @@
 	 */
 	hdmi@3d {
 		compatible = "adi,adv7513";
-		reg = <0x3d>, <0x2d>, <0x4d>, <0x5d>;
-		reg-names = "main", "cec", "edid", "packet";
+		reg = <0x3d>, <0x4d>, <0x2d>, <0x5d>;
+		reg-names = "main", "edid", "cec", "packet";
 
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
@@ -280,14 +278,12 @@
 
 	hdmi@39 {
 		compatible = "adi,adv7513";
-		reg = <0x39>, <0x29>, <0x49>, <0x59>;
-		reg-names = "main", "cec", "edid", "packet";
+		reg = <0x39>, <0x49>, <0x29>, <0x59>;
+		reg-names = "main", "edid", "cec", "packet";
 
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts
index cfe06a74ce89..79baf06019f5 100644
--- a/arch/arm/boot/dts/r8a7793-gose.dts
+++ b/arch/arm/boot/dts/r8a7793-gose.dts
@@ -366,8 +366,6 @@
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
-			adi,input-style = <1>;
-			adi,input-justification = "evenly";
 
 			ports {
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/r8a7794-silk.dts b/arch/arm/boot/dts/r8a7794-silk.dts
index 9aaa96ea9943..b8b0941f677c 100644
--- a/arch/arm/boot/dts/r8a7794-silk.dts
+++ b/arch/arm/boot/dts/r8a7794-silk.dts
@@ -255,8 +255,6 @@
 			adi,input-depth = <8>;
 			adi,input-colorspace = "rgb";
 			adi,input-clock = "1x";
-			adi,input-style = <1>;
-			adi,input-justification = "evenly";
 
 			ports {
 				#address-cells = <1>;
diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi
index 781ac7583522..d9a0c9a29b68 100644
--- a/arch/arm/boot/dts/rk3036.dtsi
+++ b/arch/arm/boot/dts/rk3036.dtsi
@@ -128,7 +128,7 @@
 		assigned-clocks = <&cru SCLK_GPU>;
 		assigned-clock-rates = <100000000>;
 		clocks = <&cru SCLK_GPU>, <&cru SCLK_GPU>;
-		clock-names = "core", "bus";
+		clock-names = "bus", "core";
 		resets = <&cru SRST_GPU>;
 		status = "disabled";
 	};
diff --git a/arch/arm/boot/dts/rk3228-evb.dts b/arch/arm/boot/dts/rk3228-evb.dts
index 5670b33fd1bd..aed879db6c15 100644
--- a/arch/arm/boot/dts/rk3228-evb.dts
+++ b/arch/arm/boot/dts/rk3228-evb.dts
@@ -46,7 +46,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		phy: phy@0 {
+		phy: ethernet-phy@0 {
 			compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22";
 			reg = <0>;
 			clocks = <&cru SCLK_MAC_PHY>;
diff --git a/arch/arm/boot/dts/rk3229-xms6.dts b/arch/arm/boot/dts/rk3229-xms6.dts
index 679fc2b00e5a..933ef69da32a 100644
--- a/arch/arm/boot/dts/rk3229-xms6.dts
+++ b/arch/arm/boot/dts/rk3229-xms6.dts
@@ -150,7 +150,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		phy: phy@0 {
+		phy: ethernet-phy@0 {
 			compatible = "ethernet-phy-id1234.d400",
 			             "ethernet-phy-ieee802.3-c22";
 			reg = <0>;
diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi
index 06172ebbf0ce..5485a9918da6 100644
--- a/arch/arm/boot/dts/rk322x.dtsi
+++ b/arch/arm/boot/dts/rk322x.dtsi
@@ -555,7 +555,7 @@
 				  "pp1",
 				  "ppmmu1";
 		clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>;
-		clock-names = "core", "bus";
+		clock-names = "bus", "core";
 		resets = <&cru SRST_GPU_A>;
 		status = "disabled";
 	};
@@ -1020,7 +1020,7 @@
 			};
 		};
 
-		spi-0 {
+		spi0 {
 			spi0_clk: spi0-clk {
 				rockchip,pins = <0 RK_PB1 2 &pcfg_pull_up>;
 			};
@@ -1038,7 +1038,7 @@
 			};
 		};
 
-		spi-1 {
+		spi1 {
 			spi1_clk: spi1-clk {
 				rockchip,pins = <0 RK_PC7 2 &pcfg_pull_up>;
 			};
diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi
index f9fcb7e9657b..d929b60517ab 100644
--- a/arch/arm/boot/dts/rk3xxx.dtsi
+++ b/arch/arm/boot/dts/rk3xxx.dtsi
@@ -84,7 +84,7 @@
 		compatible = "arm,mali-400";
 		reg = <0x10090000 0x10000>;
 		clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>;
-		clock-names = "core", "bus";
+		clock-names = "bus", "core";
 		assigned-clocks = <&cru ACLK_GPU>;
 		assigned-clock-rates = <100000000>;
 		resets = <&cru SRST_GPU>;
diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig
index 11e2211f9007..84a3b055f253 100644
--- a/arch/arm/configs/keystone_defconfig
+++ b/arch/arm/configs/keystone_defconfig
@@ -147,6 +147,7 @@ CONFIG_I2C_DAVINCI=y
 CONFIG_SPI=y
 CONFIG_SPI_DAVINCI=y
 CONFIG_SPI_SPIDEV=y
+CONFIG_PTP_1588_CLOCK=y
 CONFIG_PINCTRL_SINGLE=y
 CONFIG_GPIOLIB=y
 CONFIG_GPIO_SYSFS=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 3cc3ca5fa027..8b83d4a5d309 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -274,6 +274,7 @@ CONFIG_SPI_TI_QSPI=m
 CONFIG_HSI=m
 CONFIG_OMAP_SSI=m
 CONFIG_SSI_PROTOCOL=m
+CONFIG_PTP_1588_CLOCK=y
 CONFIG_PINCTRL_SINGLE=y
 CONFIG_DEBUG_GPIO=y
 CONFIG_GPIO_SYSFS=y
diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c
index 6fdb0ac62b3d..59da6c0b63b6 100644
--- a/arch/arm/crypto/chacha-glue.c
+++ b/arch/arm/crypto/chacha-glue.c
@@ -91,9 +91,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
 		return;
 	}
 
-	kernel_neon_begin();
-	chacha_doneon(state, dst, src, bytes, nrounds);
-	kernel_neon_end();
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		kernel_neon_begin();
+		chacha_doneon(state, dst, src, todo, nrounds);
+		kernel_neon_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
 }
 EXPORT_SYMBOL(chacha_crypt_arch);
 
diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c
index ae5aefc44a4d..ffa8d73fe722 100644
--- a/arch/arm/crypto/nhpoly1305-neon-glue.c
+++ b/arch/arm/crypto/nhpoly1305-neon-glue.c
@@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc,
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
-		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_neon_begin();
 		crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon);
diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
index ceec04ec2f40..13cfef4ae22e 100644
--- a/arch/arm/crypto/poly1305-glue.c
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -160,13 +160,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
 		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
 
 		if (static_branch_likely(&have_neon) && do_neon) {
-			kernel_neon_begin();
-			poly1305_blocks_neon(&dctx->h, src, len, 1);
-			kernel_neon_end();
+			do {
+				unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+				kernel_neon_begin();
+				poly1305_blocks_neon(&dctx->h, src, todo, 1);
+				kernel_neon_end();
+
+				len -= todo;
+				src += todo;
+			} while (len);
 		} else {
 			poly1305_blocks_arm(&dctx->h, src, len, 1);
+			src += len;
 		}
-		src += len;
 		nbytes %= POLY1305_BLOCK_SIZE;
 	}
 
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index c80b0ebfd02f..4e954b3f7ecd 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -14,7 +14,6 @@
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
index 2c3627334335..0071e5e4411a 100644
--- a/arch/arm/crypto/sha1_neon_glue.c
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -18,7 +18,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c
index 215497f011f2..b8a4f79020cf 100644
--- a/arch/arm/crypto/sha256_glue.c
+++ b/arch/arm/crypto/sha256_glue.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <crypto/sha.h>
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
index 38645e415196..79820b9e2541 100644
--- a/arch/arm/crypto/sha256_neon_glue.c
+++ b/arch/arm/crypto/sha256_neon_glue.c
@@ -11,7 +11,6 @@
 
 #include <crypto/internal/hash.h>
 #include <crypto/internal/simd.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <crypto/sha.h>
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 99929122dad7..feac2c8b86f2 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -18,11 +18,11 @@
 #endif
 
 #include <asm/ptrace.h>
-#include <asm/domain.h>
 #include <asm/opcodes-virt.h>
 #include <asm/asm-offsets.h>
 #include <asm/page.h>
 #include <asm/thread_info.h>
+#include <asm/uaccess-asm.h>
 
 #define IOMEM(x)	(x)
 
@@ -269,10 +269,9 @@
 	.endif							;\
 	.popsection
 #define ALT_UP_B(label)					\
-	.equ	up_b_offset, label - 9998b			;\
 	.pushsection ".alt.smp.init", "a"			;\
 	.long	9998b						;\
-	W(b)	. + up_b_offset					;\
+	W(b)	. + (label - 9998b)					;\
 	.popsection
 #else
 #define ALT_SMP(instr...)
@@ -446,79 +445,6 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.size \name , . - \name
 	.endm
 
-	.macro	csdb
-#ifdef CONFIG_THUMB2_KERNEL
-	.inst.w	0xf3af8014
-#else
-	.inst	0xe320f014
-#endif
-	.endm
-
-	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
-#ifndef CONFIG_CPU_USE_DOMAINS
-	adds	\tmp, \addr, #\size - 1
-	sbcscc	\tmp, \tmp, \limit
-	bcs	\bad
-#ifdef CONFIG_CPU_SPECTRE
-	movcs	\addr, #0
-	csdb
-#endif
-#endif
-	.endm
-
-	.macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req
-#ifdef CONFIG_CPU_SPECTRE
-	sub	\tmp, \limit, #1
-	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
-	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
-	subshs	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
-	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
-	csdb
-#endif
-	.endm
-
-	.macro	uaccess_disable, tmp, isb=1
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	/*
-	 * Whenever we re-enter userspace, the domains should always be
-	 * set appropriately.
-	 */
-	mov	\tmp, #DACR_UACCESS_DISABLE
-	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
-	.if	\isb
-	instr_sync
-	.endif
-#endif
-	.endm
-
-	.macro	uaccess_enable, tmp, isb=1
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	/*
-	 * Whenever we re-enter userspace, the domains should always be
-	 * set appropriately.
-	 */
-	mov	\tmp, #DACR_UACCESS_ENABLE
-	mcr	p15, 0, \tmp, c3, c0, 0
-	.if	\isb
-	instr_sync
-	.endif
-#endif
-	.endm
-
-	.macro	uaccess_save, tmp
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	mrc	p15, 0, \tmp, c3, c0, 0
-	str	\tmp, [sp, #SVC_DACR]
-#endif
-	.endm
-
-	.macro	uaccess_restore
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	ldr	r0, [sp, #SVC_DACR]
-	mcr	p15, 0, r0, c3, c0, 0
-#endif
-	.endm
-
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 5ac46e2860bc..9383f236e795 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -50,14 +50,6 @@ void efi_virtmap_unload(void);
 
 /* arch specific definitions used by the stub code */
 
-#define efi_bs_call(func, ...)	efi_system_table()->boottime->func(__VA_ARGS__)
-#define efi_rt_call(func, ...)	efi_system_table()->runtime->func(__VA_ARGS__)
-#define efi_is_native()		(true)
-
-#define efi_table_attr(inst, attr)	(inst->attr)
-
-#define efi_call_proto(inst, func, ...) inst->func(inst, ##__VA_ARGS__)
-
 struct screen_info *alloc_screen_info(void);
 void free_screen_info(struct screen_info *si);
 
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index e133da303a98..a9151884bc85 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -165,8 +165,13 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 	preempt_enable();
 #endif
 
-	if (!ret)
-		*oval = oldval;
+	/*
+	 * Store unconditionally. If ret != 0 the extra store is the least
+	 * of the worries but GCC cannot figure out that __futex_atomic_op()
+	 * is either setting ret to -EFAULT or storing the old value in
+	 * oldval which results in a uninitialized warning at the call site.
+	 */
+	*oval = oldval;
 
 	return ret;
 }
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index 182163b55546..4b0df09cbe67 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -37,30 +37,6 @@ struct mod_arch_specific {
 struct module;
 u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val);
 
-/*
- * Add the ARM architecture version to the version magic string
- */
-#define MODULE_ARCH_VERMAGIC_ARMVSN "ARMv" __stringify(__LINUX_ARM_ARCH__) " "
-
-/* Add __virt_to_phys patching state as well */
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
-#define MODULE_ARCH_VERMAGIC_P2V "p2v8 "
-#else
-#define MODULE_ARCH_VERMAGIC_P2V ""
-#endif
-
-/* Add instruction set architecture tag to distinguish ARM/Thumb kernels */
-#ifdef CONFIG_THUMB2_KERNEL
-#define MODULE_ARCH_VERMAGIC_ARMTHUMB "thumb2 "
-#else
-#define MODULE_ARCH_VERMAGIC_ARMTHUMB ""
-#endif
-
-#define MODULE_ARCH_VERMAGIC \
-	MODULE_ARCH_VERMAGIC_ARMVSN \
-	MODULE_ARCH_VERMAGIC_ARMTHUMB \
-	MODULE_ARCH_VERMAGIC_P2V
-
 #ifdef CONFIG_THUMB2_KERNEL
 #define HAVE_ARCH_KALLSYMS_SYMBOL_VALUE
 static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym)
diff --git a/arch/arm/include/asm/uaccess-asm.h b/arch/arm/include/asm/uaccess-asm.h
new file mode 100644
index 000000000000..907571fd05c6
--- /dev/null
+++ b/arch/arm/include/asm/uaccess-asm.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_UACCESS_ASM_H__
+#define __ASM_UACCESS_ASM_H__
+
+#include <asm/asm-offsets.h>
+#include <asm/domain.h>
+#include <asm/memory.h>
+#include <asm/thread_info.h>
+
+	.macro	csdb
+#ifdef CONFIG_THUMB2_KERNEL
+	.inst.w	0xf3af8014
+#else
+	.inst	0xe320f014
+#endif
+	.endm
+
+	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
+#ifndef CONFIG_CPU_USE_DOMAINS
+	adds	\tmp, \addr, #\size - 1
+	sbcscc	\tmp, \tmp, \limit
+	bcs	\bad
+#ifdef CONFIG_CPU_SPECTRE
+	movcs	\addr, #0
+	csdb
+#endif
+#endif
+	.endm
+
+	.macro uaccess_mask_range_ptr, addr:req, size:req, limit:req, tmp:req
+#ifdef CONFIG_CPU_SPECTRE
+	sub	\tmp, \limit, #1
+	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
+	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
+	subshs	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
+	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
+	csdb
+#endif
+	.endm
+
+	.macro	uaccess_disable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_enable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_ENABLE
+	mcr	p15, 0, \tmp, c3, c0, 0
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+#if defined(CONFIG_CPU_SW_DOMAIN_PAN) || defined(CONFIG_CPU_USE_DOMAINS)
+#define DACR(x...)	x
+#else
+#define DACR(x...)
+#endif
+
+	/*
+	 * Save the address limit on entry to a privileged exception.
+	 *
+	 * If we are using the DACR for kernel access by the user accessors
+	 * (CONFIG_CPU_USE_DOMAINS=y), always reset the DACR kernel domain
+	 * back to client mode, whether or not \disable is set.
+	 *
+	 * If we are using SW PAN, set the DACR user domain to no access
+	 * if \disable is set.
+	 */
+	.macro	uaccess_entry, tsk, tmp0, tmp1, tmp2, disable
+	ldr	\tmp1, [\tsk, #TI_ADDR_LIMIT]
+	mov	\tmp2, #TASK_SIZE
+	str	\tmp2, [\tsk, #TI_ADDR_LIMIT]
+ DACR(	mrc	p15, 0, \tmp0, c3, c0, 0)
+ DACR(	str	\tmp0, [sp, #SVC_DACR])
+	str	\tmp1, [sp, #SVC_ADDR_LIMIT]
+	.if \disable && IS_ENABLED(CONFIG_CPU_SW_DOMAIN_PAN)
+	/* kernel=client, user=no access */
+	mov	\tmp2, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp2, c3, c0, 0
+	instr_sync
+	.elseif IS_ENABLED(CONFIG_CPU_USE_DOMAINS)
+	/* kernel=client */
+	bic	\tmp2, \tmp0, #domain_mask(DOMAIN_KERNEL)
+	orr	\tmp2, \tmp2, #domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT)
+	mcr	p15, 0, \tmp2, c3, c0, 0
+	instr_sync
+	.endif
+	.endm
+
+	/* Restore the user access state previously saved by uaccess_entry */
+	.macro	uaccess_exit, tsk, tmp0, tmp1
+	ldr	\tmp1, [sp, #SVC_ADDR_LIMIT]
+ DACR(	ldr	\tmp0, [sp, #SVC_DACR])
+	str	\tmp1, [\tsk, #TI_ADDR_LIMIT]
+ DACR(	mcr	p15, 0, \tmp0, c3, c0, 0)
+	.endm
+
+#undef DACR
+
+#endif /* __ASM_UACCESS_ASM_H__ */
diff --git a/arch/arm/include/asm/vermagic.h b/arch/arm/include/asm/vermagic.h
new file mode 100644
index 000000000000..62ce94e26a63
--- /dev/null
+++ b/arch/arm/include/asm/vermagic.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#include <linux/stringify.h>
+
+/*
+ * Add the ARM architecture version to the version magic string
+ */
+#define MODULE_ARCH_VERMAGIC_ARMVSN "ARMv" __stringify(__LINUX_ARM_ARCH__) " "
+
+/* Add __virt_to_phys patching state as well */
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
+#define MODULE_ARCH_VERMAGIC_P2V "p2v8 "
+#else
+#define MODULE_ARCH_VERMAGIC_P2V ""
+#endif
+
+/* Add instruction set architecture tag to distinguish ARM/Thumb kernels */
+#ifdef CONFIG_THUMB2_KERNEL
+#define MODULE_ARCH_VERMAGIC_ARMTHUMB "thumb2 "
+#else
+#define MODULE_ARCH_VERMAGIC_ARMTHUMB ""
+#endif
+
+#define MODULE_ARCH_VERMAGIC \
+	MODULE_ARCH_VERMAGIC_ARMVSN \
+	MODULE_ARCH_VERMAGIC_ARMTHUMB \
+	MODULE_ARCH_VERMAGIC_P2V
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 98bdea51089d..82e96ac83684 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -7,7 +7,6 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/string.h>
-#include <linux/cryptohash.h>
 #include <linux/delay.h>
 #include <linux/in6.h>
 #include <linux/syscalls.h>
diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c
index 4247ebf4b893..3c2faf2bd124 100644
--- a/arch/arm/kernel/atags_proc.c
+++ b/arch/arm/kernel/atags_proc.c
@@ -42,7 +42,7 @@ static int __init init_atags_procfs(void)
 	size_t size;
 
 	if (tag->hdr.tag != ATAG_CORE) {
-		pr_info("No ATAGs?");
+		pr_info("No ATAGs?\n");
 		return -EINVAL;
 	}
 
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 77f54830554c..55a47df04773 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -27,6 +27,7 @@
 #include <asm/unistd.h>
 #include <asm/tls.h>
 #include <asm/system_info.h>
+#include <asm/uaccess-asm.h>
 
 #include "entry-header.S"
 #include <asm/entry-macro-multi.S>
@@ -179,15 +180,7 @@ ENDPROC(__und_invalid)
 	stmia	r7, {r2 - r6}
 
 	get_thread_info tsk
-	ldr	r0, [tsk, #TI_ADDR_LIMIT]
-	mov	r1, #TASK_SIZE
-	str	r1, [tsk, #TI_ADDR_LIMIT]
-	str	r0, [sp, #SVC_ADDR_LIMIT]
-
-	uaccess_save r0
-	.if \uaccess
-	uaccess_disable r0
-	.endif
+	uaccess_entry tsk, r0, r1, r2, \uaccess
 
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 32051ec5b33f..40db0f9188b6 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -6,6 +6,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/errno.h>
 #include <asm/thread_info.h>
+#include <asm/uaccess-asm.h>
 #include <asm/v7m.h>
 
 @ Bad Abort numbers
@@ -217,9 +218,7 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
-	ldr	r1, [sp, #SVC_ADDR_LIMIT]
-	uaccess_restore
-	str	r1, [tsk, #TI_ADDR_LIMIT]
+	uaccess_exit tsk, r0, r1
 
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode SVC restore
@@ -263,9 +262,7 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
-	ldr	r1, [sp, #SVC_ADDR_LIMIT]
-	uaccess_restore
-	str	r1, [tsk, #TI_ADDR_LIMIT]
+	uaccess_exit tsk, r0, r1
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode restore
 	mov	r0, sp
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index deef17f34bd2..af0a8500a24e 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -55,6 +55,13 @@ void *module_alloc(unsigned long size)
 }
 #endif
 
+bool module_init_section(const char *name)
+{
+	return strstarts(name, ".init") ||
+		strstarts(name, ".ARM.extab.init") ||
+		strstarts(name, ".ARM.exidx.init");
+}
+
 bool module_exit_section(const char *name)
 {
 	return strstarts(name, ".exit") ||
@@ -409,8 +416,17 @@ module_arch_cleanup(struct module *mod)
 #ifdef CONFIG_ARM_UNWIND
 	int i;
 
-	for (i = 0; i < ARM_SEC_MAX; i++)
-		if (mod->arch.unwind[i])
-			unwind_table_del(mod->arch.unwind[i]);
+	for (i = 0; i < ARM_SEC_MAX; i++) {
+		unwind_table_del(mod->arch.unwind[i]);
+		mod->arch.unwind[i] = NULL;
+	}
+#endif
+}
+
+void __weak module_arch_freeing_init(struct module *mod)
+{
+#ifdef CONFIG_ARM_UNWIND
+	unwind_table_del(mod->arch.unwind[ARM_SEC_INIT]);
+	mod->arch.unwind[ARM_SEC_INIT] = NULL;
 #endif
 }
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index b606cded90cd..4cc6a7eff635 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -219,8 +219,8 @@ static struct undef_hook arm_break_hook = {
 };
 
 static struct undef_hook thumb_break_hook = {
-	.instr_mask	= 0xffff,
-	.instr_val	= 0xde01,
+	.instr_mask	= 0xffffffff,
+	.instr_val	= 0x0000de01,
 	.cpsr_mask	= PSR_T_BIT,
 	.cpsr_val	= PSR_T_BIT,
 	.fn		= break_trap,
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 17bd32b22371..0203e545bbc8 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -253,20 +253,15 @@ asmlinkage long sys_oabi_epoll_ctl(int epfd, int op, int fd,
 {
 	struct oabi_epoll_event user;
 	struct epoll_event kernel;
-	mm_segment_t fs;
-	long ret;
 
-	if (op == EPOLL_CTL_DEL)
-		return sys_epoll_ctl(epfd, op, fd, NULL);
-	if (copy_from_user(&user, event, sizeof(user)))
+	if (ep_op_has_event(op) &&
+	    copy_from_user(&user, event, sizeof(user)))
 		return -EFAULT;
+
 	kernel.events = user.events;
 	kernel.data   = user.data;
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-	ret = sys_epoll_ctl(epfd, op, fd, &kernel);
-	set_fs(fs);
-	return ret;
+
+	return do_epoll_ctl(epfd, op, fd, &kernel, false);
 }
 
 asmlinkage long sys_oabi_epoll_wait(int epfd,
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index 03506ce46149..e7364e6c8c6b 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -91,8 +91,10 @@ AFLAGS_suspend-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o
 obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o
 endif
+ifeq ($(CONFIG_ARM_CPU_SUSPEND),y)
 AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += resume-imx6.o
+endif
 obj-$(CONFIG_SOC_IMX6) += pm-imx6.o
 
 obj-$(CONFIG_SOC_IMX1) += mach-imx1.o
diff --git a/arch/arm/mach-oxnas/platsmp.c b/arch/arm/mach-oxnas/platsmp.c
index ab35275b7ee3..f0a50b9e61df 100644
--- a/arch/arm/mach-oxnas/platsmp.c
+++ b/arch/arm/mach-oxnas/platsmp.c
@@ -27,7 +27,8 @@ static void __iomem *gic_cpu_ctrl;
 #define GIC_CPU_CTRL			0x00
 #define GIC_CPU_CTRL_ENABLE		1
 
-int __init ox820_boot_secondary(unsigned int cpu, struct task_struct *idle)
+static int __init ox820_boot_secondary(unsigned int cpu,
+		struct task_struct *idle)
 {
 	/*
 	 * Write the address of secondary startup into the
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 5461d589a1e2..60ac7c5999a9 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -5,6 +5,7 @@
  *  VMA_VM_FLAGS
  *  VM_EXEC
  */
+#include <linux/const.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 
@@ -30,7 +31,7 @@
  * act_mm - get current->active_mm
  */
 	.macro	act_mm, rd
-	bic	\rd, sp, #8128
+	bic	\rd, sp, #(THREAD_SIZE - 1) & ~63
 	bic	\rd, \rd, #63
 	ldr	\rd, [\rd, #TI_TASK]
 	.if (TSK_ACTIVE_MM > IMM12_MASK)
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index cc29869d12a3..bf85d6db4931 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -929,7 +929,11 @@ static inline void emit_a32_rsh_i64(const s8 dst[],
 	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do LSR operation */
-	if (val < 32) {
+	if (val == 0) {
+		/* An immediate value of 0 encodes a shift amount of 32
+		 * for LSR. To shift by 0, don't do anything.
+		 */
+	} else if (val < 32) {
 		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
 		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
 		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_LSR, val), ctx);
@@ -955,7 +959,11 @@ static inline void emit_a32_arsh_i64(const s8 dst[],
 	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do ARSH operation */
-	if (val < 32) {
+	if (val == 0) {
+		/* An immediate value of 0 encodes a shift amount of 32
+		 * for ASR. To shift by 0, don't do anything.
+		 */
+	} else if (val < 32) {
 		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
 		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
 		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, val), ctx);
@@ -992,21 +1000,35 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
 	arm_bpf_put_reg32(dst_hi, rd[0], ctx);
 }
 
+static bool is_ldst_imm(s16 off, const u8 size)
+{
+	s16 off_max = 0;
+
+	switch (size) {
+	case BPF_B:
+	case BPF_W:
+		off_max = 0xfff;
+		break;
+	case BPF_H:
+		off_max = 0xff;
+		break;
+	case BPF_DW:
+		/* Need to make sure off+4 does not overflow. */
+		off_max = 0xfff - 4;
+		break;
+	}
+	return -off_max <= off && off <= off_max;
+}
+
 /* *(size *)(dst + off) = src */
 static inline void emit_str_r(const s8 dst, const s8 src[],
-			      s32 off, struct jit_ctx *ctx, const u8 sz){
+			      s16 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s32 off_max;
 	s8 rd;
 
 	rd = arm_bpf_get_reg32(dst, tmp[1], ctx);
 
-	if (sz == BPF_H)
-		off_max = 0xff;
-	else
-		off_max = 0xfff;
-
-	if (off < 0 || off > off_max) {
+	if (!is_ldst_imm(off, sz)) {
 		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx);
 		rd = tmp[0];
@@ -1035,18 +1057,12 @@ static inline void emit_str_r(const s8 dst, const s8 src[],
 
 /* dst = *(size*)(src + off) */
 static inline void emit_ldx_r(const s8 dst[], const s8 src,
-			      s32 off, struct jit_ctx *ctx, const u8 sz){
+			      s16 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
 	s8 rm = src;
-	s32 off_max;
-
-	if (sz == BPF_H)
-		off_max = 0xff;
-	else
-		off_max = 0xfff;
 
-	if (off < 0 || off > off_max) {
+	if (!is_ldst_imm(off, sz)) {
 		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
 		rm = tmp[0];
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index dd6804a64f1a..fd4e1ce1daf9 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -36,7 +36,7 @@
 
 #include <linux/mm.h>
 
-struct start_info _xen_start_info;
+static struct start_info _xen_start_info;
 struct start_info *xen_start_info = &_xen_start_info;
 EXPORT_SYMBOL(xen_start_info);
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 40fb05d96c60..552d36cacc05 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -9,6 +9,7 @@ config ARM64
 	select ACPI_MCFG if (ACPI && PCI)
 	select ACPI_SPCR_TABLE if ACPI
 	select ACPI_PPTT if ACPI
+	select ARCH_BINFMT_ELF_STATE
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_DMA_PREP_COHERENT
@@ -20,6 +21,7 @@ config ARM64
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SETUP_DMA_OPS
@@ -32,6 +34,7 @@ config ARM64
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAVE_ELF_PROT
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK if !PREEMPTION
 	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
@@ -61,9 +64,12 @@ config ARM64
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
 	select ARCH_KEEP_MEMBLOCK
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_USE_GNU_PROPERTY
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_USE_SYM_ANNOTATIONS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
+	select ARCH_SUPPORTS_SHADOW_CALL_STACK if CC_HAVE_SHADOW_CALL_STACK
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
 	select ARCH_SUPPORTS_NUMA_BALANCING
@@ -524,13 +530,13 @@ config ARM64_ERRATUM_1418040
 
 	  If unsure, say Y.
 
-config ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+config ARM64_WORKAROUND_SPECULATIVE_AT
 	bool
 
 config ARM64_ERRATUM_1165522
-	bool "Cortex-A76: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
+	bool "Cortex-A76: 1165522: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
 	default y
-	select ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+	select ARM64_WORKAROUND_SPECULATIVE_AT
 	help
 	  This option adds a workaround for ARM Cortex-A76 erratum 1165522.
 
@@ -540,10 +546,23 @@ config ARM64_ERRATUM_1165522
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_1319367
+	bool "Cortex-A57/A72: 1319537: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
+	default y
+	select ARM64_WORKAROUND_SPECULATIVE_AT
+	help
+	  This option adds work arounds for ARM Cortex-A57 erratum 1319537
+	  and A72 erratum 1319367
+
+	  Cortex-A57 and A72 cores could end-up with corrupted TLBs by
+	  speculating an AT instruction during a guest context switch.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_1530923
-	bool "Cortex-A55: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
+	bool "Cortex-A55: 1530923: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
 	default y
-	select ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+	select ARM64_WORKAROUND_SPECULATIVE_AT
 	help
 	  This option adds a workaround for ARM Cortex-A55 erratum 1530923.
 
@@ -553,6 +572,9 @@ config ARM64_ERRATUM_1530923
 
 	  If unsure, say Y.
 
+config ARM64_WORKAROUND_REPEAT_TLBI
+	bool
+
 config ARM64_ERRATUM_1286807
 	bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation"
 	default y
@@ -569,22 +591,6 @@ config ARM64_ERRATUM_1286807
 	  invalidated has been observed by other observers. The
 	  workaround repeats the TLBI+DSB operation.
 
-config ARM64_WORKAROUND_SPECULATIVE_AT_NVHE
-	bool
-
-config ARM64_ERRATUM_1319367
-	bool "Cortex-A57/A72: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
-	default y
-	select ARM64_WORKAROUND_SPECULATIVE_AT_NVHE
-	help
-	  This option adds work arounds for ARM Cortex-A57 erratum 1319537
-	  and A72 erratum 1319367
-
-	  Cortex-A57 and A72 cores could end-up with corrupted TLBs by
-	  speculating an AT instruction during a guest context switch.
-
-	  If unsure, say Y.
-
 config ARM64_ERRATUM_1463225
 	bool "Cortex-A76: Software Step might prevent interrupt recognition"
 	default y
@@ -694,6 +700,35 @@ config CAVIUM_TX2_ERRATUM_219
 
 	  If unsure, say Y.
 
+config FUJITSU_ERRATUM_010001
+	bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
+	default y
+	help
+	  This option adds a workaround for Fujitsu-A64FX erratum E#010001.
+	  On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory
+	  accesses may cause undefined fault (Data abort, DFSC=0b111111).
+	  This fault occurs under a specific hardware condition when a
+	  load/store instruction performs an address translation using:
+	  case-1  TTBR0_EL1 with TCR_EL1.NFD0 == 1.
+	  case-2  TTBR0_EL2 with TCR_EL2.NFD0 == 1.
+	  case-3  TTBR1_EL1 with TCR_EL1.NFD1 == 1.
+	  case-4  TTBR1_EL2 with TCR_EL2.NFD1 == 1.
+
+	  The workaround is to ensure these bits are clear in TCR_ELx.
+	  The workaround only affects the Fujitsu-A64FX.
+
+	  If unsure, say Y.
+
+config HISILICON_ERRATUM_161600802
+	bool "Hip07 161600802: Erroneous redistributor VLPI base"
+	default y
+	help
+	  The HiSilicon Hip07 SoC uses the wrong redistributor base
+	  when issued ITS commands such as VMOVP and VMAPP, and requires
+	  a 128kB offset to be applied to the target address in this commands.
+
+	  If unsure, say Y.
+
 config QCOM_FALKOR_ERRATUM_1003
 	bool "Falkor E1003: Incorrect translation due to ASID change"
 	default y
@@ -705,9 +740,6 @@ config QCOM_FALKOR_ERRATUM_1003
 	  is unchanged. Work around the erratum by invalidating the walk cache
 	  entries for the trampoline before entering the kernel proper.
 
-config ARM64_WORKAROUND_REPEAT_TLBI
-	bool
-
 config QCOM_FALKOR_ERRATUM_1009
 	bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
 	default y
@@ -729,25 +761,6 @@ config QCOM_QDF2400_ERRATUM_0065
 
 	  If unsure, say Y.
 
-config SOCIONEXT_SYNQUACER_PREITS
-	bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
-	default y
-	help
-	  Socionext Synquacer SoCs implement a separate h/w block to generate
-	  MSI doorbell writes with non-zero values for the device ID.
-
-	  If unsure, say Y.
-
-config HISILICON_ERRATUM_161600802
-	bool "Hip07 161600802: Erroneous redistributor VLPI base"
-	default y
-	help
-	  The HiSilicon Hip07 SoC uses the wrong redistributor base
-	  when issued ITS commands such as VMOVP and VMAPP, and requires
-	  a 128kB offset to be applied to the target address in this commands.
-
-	  If unsure, say Y.
-
 config QCOM_FALKOR_ERRATUM_E1041
 	bool "Falkor E1041: Speculative instruction fetches might cause errant memory access"
 	default y
@@ -758,22 +771,12 @@ config QCOM_FALKOR_ERRATUM_E1041
 
 	  If unsure, say Y.
 
-config FUJITSU_ERRATUM_010001
-	bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
+config SOCIONEXT_SYNQUACER_PREITS
+	bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
 	default y
 	help
-	  This option adds a workaround for Fujitsu-A64FX erratum E#010001.
-	  On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory
-	  accesses may cause undefined fault (Data abort, DFSC=0b111111).
-	  This fault occurs under a specific hardware condition when a
-	  load/store instruction performs an address translation using:
-	  case-1  TTBR0_EL1 with TCR_EL1.NFD0 == 1.
-	  case-2  TTBR0_EL2 with TCR_EL2.NFD0 == 1.
-	  case-3  TTBR1_EL1 with TCR_EL1.NFD1 == 1.
-	  case-4  TTBR1_EL2 with TCR_EL2.NFD1 == 1.
-
-	  The workaround is to ensure these bits are clear in TCR_ELx.
-	  The workaround only affects the Fujitsu-A64FX.
+	  Socionext Synquacer SoCs implement a separate h/w block to generate
+	  MSI doorbell writes with non-zero values for the device ID.
 
 	  If unsure, say Y.
 
@@ -1025,6 +1028,10 @@ config ARCH_HAS_CACHE_LINE_SIZE
 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	def_bool y if PGTABLE_LEVELS > 2
 
+# Supported by clang >= 7.0
+config CC_HAVE_SHADOW_CALL_STACK
+	def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18)
+
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
 	---help---
@@ -1584,6 +1591,48 @@ endmenu
 
 menu "ARMv8.5 architectural features"
 
+config ARM64_BTI
+	bool "Branch Target Identification support"
+	default y
+	help
+	  Branch Target Identification (part of the ARMv8.5 Extensions)
+	  provides a mechanism to limit the set of locations to which computed
+	  branch instructions such as BR or BLR can jump.
+
+	  To make use of BTI on CPUs that support it, say Y.
+
+	  BTI is intended to provide complementary protection to other control
+	  flow integrity protection mechanisms, such as the Pointer
+	  authentication mechanism provided as part of the ARMv8.3 Extensions.
+	  For this reason, it does not make sense to enable this option without
+	  also enabling support for pointer authentication.  Thus, when
+	  enabling this option you should also select ARM64_PTR_AUTH=y.
+
+	  Userspace binaries must also be specifically compiled to make use of
+	  this mechanism.  If you say N here or the hardware does not support
+	  BTI, such binaries can still run, but you get no additional
+	  enforcement of branch destinations.
+
+config ARM64_BTI_KERNEL
+	bool "Use Branch Target Identification for kernel"
+	default y
+	depends on ARM64_BTI
+	depends on ARM64_PTR_AUTH
+	depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
+	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
+	depends on !CC_IS_GCC || GCC_VERSION >= 100100
+	depends on !(CC_IS_CLANG && GCOV_KERNEL)
+	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
+	help
+	  Build the kernel with Branch Target Identification annotations
+	  and enable enforcement of this for kernel code. When this option
+	  is enabled and the system supports BTI all kernel code including
+	  modular code must have BTI enabled.
+
+config CC_HAS_BRANCH_PROT_PAC_RET_BTI
+	# GCC 9 or later, clang 8 or later
+	def_bool $(cc-option,-mbranch-protection=pac-ret+leaf+bti)
+
 config ARM64_E0PD
 	bool "Enable support for E0PD"
 	default y
@@ -1785,7 +1834,7 @@ config EFI
 	select EFI_PARAMS_FROM_FDT
 	select EFI_RUNTIME_WRAPPERS
 	select EFI_STUB
-	select EFI_ARMSTUB
+	select EFI_GENERIC_STUB
 	default y
 	help
 	  This option provides support for runtime services provided
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 85e4149cc5d5..650e1185c190 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -12,7 +12,6 @@
 
 LDFLAGS_vmlinux	:=--no-undefined -X
 CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
-GZFLAGS		:=-9
 
 ifeq ($(CONFIG_RELOCATABLE), y)
 # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour
@@ -71,7 +70,14 @@ branch-prot-flags-y += $(call cc-option,-mbranch-protection=none)
 
 ifeq ($(CONFIG_ARM64_PTR_AUTH),y)
 branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=all
+# We enable additional protection for leaf functions as there is some
+# narrow potential for ROP protection benefits and no substantial
+# performance impact has been observed.
+ifeq ($(CONFIG_ARM64_BTI_KERNEL),y)
+branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=pac-ret+leaf+bti
+else
 branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pac-ret+leaf
+endif
 # -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
@@ -81,6 +87,10 @@ endif
 
 KBUILD_CFLAGS += $(branch-prot-flags-y)
 
+ifeq ($(CONFIG_SHADOW_CALL_STACK), y)
+KBUILD_CFLAGS	+= -ffixed-x18
+endif
+
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__AARCH64EB__
@@ -118,7 +128,7 @@ TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \
 		 int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \
 		 rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}")
 else
-TEXT_OFFSET := 0x00080000
+TEXT_OFFSET := 0x0
 endif
 
 ifeq ($(CONFIG_KASAN_SW_TAGS), y)
@@ -131,7 +141,7 @@ KBUILD_CFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
 KBUILD_CPPFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
 KBUILD_AFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
 
-export	TEXT_OFFSET GZFLAGS
+export	TEXT_OFFSET
 
 core-y		+= arch/arm64/
 libs-y		:= arch/arm64/lib/ $(libs-y)
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts
index 316e8a443913..dc4ab6b434f9 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts
@@ -98,7 +98,7 @@
 };
 
 &codec_analog {
-	hpvcc-supply = <&reg_eldo1>;
+	cpvdd-supply = <&reg_eldo1>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 31143fe64d91..c26cc1fcaffd 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -154,24 +154,6 @@
 		};
 	};
 
-	sound_spdif {
-		compatible = "simple-audio-card";
-		simple-audio-card,name = "On-board SPDIF";
-
-		simple-audio-card,cpu {
-			sound-dai = <&spdif>;
-		};
-
-		simple-audio-card,codec {
-			sound-dai = <&spdif_out>;
-		};
-	};
-
-	spdif_out: spdif-out {
-		#sound-dai-cells = <0>;
-		compatible = "linux,spdif-dit";
-	};
-
 	timer {
 		compatible = "arm,armv8-timer";
 		allwinner,erratum-unknown1;
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
index 0882ea215b88..c0aef7d69117 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
@@ -2319,7 +2319,7 @@
 				reg = <0x0 0xff400000 0x0 0x40000>;
 				interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clkc CLKID_USB1_DDR_BRIDGE>;
-				clock-names = "ddr";
+				clock-names = "otg";
 				phys = <&usb2_phy1>;
 				phy-names = "usb2-phy";
 				dr_mode = "peripheral";
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12.dtsi
index 783e5a397f86..55d39020ec72 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12.dtsi
@@ -1,4 +1,3 @@
-
 // SPDX-License-Identifier: (GPL-2.0+ OR MIT)
 /*
  * Copyright (c) 2019 BayLibre, SAS
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi
index c33e85fbdaba..c6c8caed8327 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi
@@ -154,6 +154,10 @@
 	clock-latency = <50000>;
 };
 
+&frddr_a {
+	status = "okay";
+};
+
 &frddr_b {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts b/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts
index 325e448eb09c..06c5430eb92d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts
@@ -545,7 +545,7 @@
 &usb {
 	status = "okay";
 	dr_mode = "host";
-	vbus-regulator = <&usb_pwr_en>;
+	vbus-supply = <&usb_pwr_en>;
 };
 
 &usb2_phy0 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index 2a7f70b71149..13d0570c7ed6 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -447,7 +447,7 @@
 
 		edma0: dma-controller@22c0000 {
 			#dma-cells = <2>;
-			compatible = "fsl,ls1028a-edma";
+			compatible = "fsl,ls1028a-edma", "fsl,vf610-edma";
 			reg = <0x0 0x22c0000 0x0 0x10000>,
 			      <0x0 0x22d0000 0x0 0x10000>,
 			      <0x0 0x22e0000 0x0 0x10000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
index cc7152ecedd9..8829628f757a 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
@@ -264,7 +264,7 @@
 
 		aips1: bus@30000000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x301f0000 0x10000>;
+			reg = <0x30000000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x30000000 0x30000000 0x400000>;
@@ -543,7 +543,7 @@
 
 		aips2: bus@30400000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x305f0000 0x10000>;
+			reg = <0x30400000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x30400000 0x30400000 0x400000>;
@@ -603,7 +603,7 @@
 
 		aips3: bus@30800000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x309f0000 0x10000>;
+			reg = <0x30800000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x30800000 0x30800000 0x400000>,
@@ -863,7 +863,7 @@
 
 		aips4: bus@32c00000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x32df0000 0x10000>;
+			reg = <0x32c00000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x32c00000 0x32c00000 0x400000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index fa78f0163270..43971abe218b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -241,7 +241,7 @@
 
 		aips1: bus@30000000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x301f0000 0x10000>;
+			reg = <0x30000000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
@@ -448,7 +448,7 @@
 
 		aips2: bus@30400000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x305f0000 0x10000>;
+			reg = <0x30400000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
@@ -508,7 +508,7 @@
 
 		aips3: bus@30800000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x309f0000 0x10000>;
+			reg = <0x30800000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
@@ -718,7 +718,7 @@
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA1_ROOT>,
-					 <&clk IMX8MN_CLK_SDMA1_ROOT>;
+					 <&clk IMX8MN_CLK_AHB>;
 				clock-names = "ipg", "ahb";
 				#dma-cells = <3>;
 				fsl,sdma-ram-script-name = "imx/sdma/sdma-imx7d.bin";
@@ -754,7 +754,7 @@
 
 		aips4: bus@32c00000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x32df0000 0x10000>;
+			reg = <0x32c00000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mp-pinfunc.h
index da78f89b6c98..319ab34cab3e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-pinfunc.h
+++ b/arch/arm64/boot/dts/freescale/imx8mp-pinfunc.h
@@ -151,26 +151,26 @@
 #define MX8MP_IOMUXC_ENET_TXC__SIM_M_HADDR22                         0x070 0x2D0 0x000 0x7 0x0
 #define MX8MP_IOMUXC_ENET_RX_CTL__ENET_QOS_RGMII_RX_CTL              0x074 0x2D4 0x000 0x0 0x0
 #define MX8MP_IOMUXC_ENET_RX_CTL__AUDIOMIX_SAI7_TX_SYNC              0x074 0x2D4 0x540 0x2 0x0
-#define MX8MP_IOMUXC_ENET_RX_CTL__AUDIOMIX_BIT_STREAM03              0x074 0x2D4 0x4CC 0x3 0x0
+#define MX8MP_IOMUXC_ENET_RX_CTL__AUDIOMIX_BIT_STREAM03              0x074 0x2D4 0x4CC 0x3 0x1
 #define MX8MP_IOMUXC_ENET_RX_CTL__GPIO1_IO24                         0x074 0x2D4 0x000 0x5 0x0
 #define MX8MP_IOMUXC_ENET_RX_CTL__USDHC3_DATA2                       0x074 0x2D4 0x618 0x6 0x0
 #define MX8MP_IOMUXC_ENET_RX_CTL__SIM_M_HADDR23                      0x074 0x2D4 0x000 0x7 0x0
 #define MX8MP_IOMUXC_ENET_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK    0x078 0x2D8 0x000 0x0 0x0
 #define MX8MP_IOMUXC_ENET_RXC__ENET_QOS_RX_ER                        0x078 0x2D8 0x000 0x1 0x0
 #define MX8MP_IOMUXC_ENET_RXC__AUDIOMIX_SAI7_TX_BCLK                 0x078 0x2D8 0x53C 0x2 0x0
-#define MX8MP_IOMUXC_ENET_RXC__AUDIOMIX_BIT_STREAM02                 0x078 0x2D8 0x4C8 0x3 0x0
+#define MX8MP_IOMUXC_ENET_RXC__AUDIOMIX_BIT_STREAM02                 0x078 0x2D8 0x4C8 0x3 0x1
 #define MX8MP_IOMUXC_ENET_RXC__GPIO1_IO25                            0x078 0x2D8 0x000 0x5 0x0
 #define MX8MP_IOMUXC_ENET_RXC__USDHC3_DATA3                          0x078 0x2D8 0x61C 0x6 0x0
 #define MX8MP_IOMUXC_ENET_RXC__SIM_M_HADDR24                         0x078 0x2D8 0x000 0x7 0x0
 #define MX8MP_IOMUXC_ENET_RD0__ENET_QOS_RGMII_RD0                    0x07C 0x2DC 0x000 0x0 0x0
 #define MX8MP_IOMUXC_ENET_RD0__AUDIOMIX_SAI7_RX_DATA00               0x07C 0x2DC 0x534 0x2 0x0
-#define MX8MP_IOMUXC_ENET_RD0__AUDIOMIX_BIT_STREAM01                 0x07C 0x2DC 0x4C4 0x3 0x0
+#define MX8MP_IOMUXC_ENET_RD0__AUDIOMIX_BIT_STREAM01                 0x07C 0x2DC 0x4C4 0x3 0x1
 #define MX8MP_IOMUXC_ENET_RD0__GPIO1_IO26                            0x07C 0x2DC 0x000 0x5 0x0
 #define MX8MP_IOMUXC_ENET_RD0__USDHC3_DATA4                          0x07C 0x2DC 0x620 0x6 0x0
 #define MX8MP_IOMUXC_ENET_RD0__SIM_M_HADDR25                         0x07C 0x2DC 0x000 0x7 0x0
 #define MX8MP_IOMUXC_ENET_RD1__ENET_QOS_RGMII_RD1                    0x080 0x2E0 0x000 0x0 0x0
 #define MX8MP_IOMUXC_ENET_RD1__AUDIOMIX_SAI7_RX_SYNC                 0x080 0x2E0 0x538 0x2 0x0
-#define MX8MP_IOMUXC_ENET_RD1__AUDIOMIX_BIT_STREAM00                 0x080 0x2E0 0x4C0 0x3 0x0
+#define MX8MP_IOMUXC_ENET_RD1__AUDIOMIX_BIT_STREAM00                 0x080 0x2E0 0x4C0 0x3 0x1
 #define MX8MP_IOMUXC_ENET_RD1__GPIO1_IO27                            0x080 0x2E0 0x000 0x5 0x0
 #define MX8MP_IOMUXC_ENET_RD1__USDHC3_RESET_B                        0x080 0x2E0 0x000 0x6 0x0
 #define MX8MP_IOMUXC_ENET_RD1__SIM_M_HADDR26                         0x080 0x2E0 0x000 0x7 0x0
@@ -291,7 +291,7 @@
 #define MX8MP_IOMUXC_SD2_DATA0__I2C4_SDA                             0x0C8 0x328 0x5C0 0x2 0x1
 #define MX8MP_IOMUXC_SD2_DATA0__UART2_DCE_RX                         0x0C8 0x328 0x5F0 0x3 0x2
 #define MX8MP_IOMUXC_SD2_DATA0__UART2_DTE_TX                         0x0C8 0x328 0x000 0x3 0x0
-#define MX8MP_IOMUXC_SD2_DATA0__AUDIOMIX_BIT_STREAM00                0x0C8 0x328 0x4C0 0x4 0x1
+#define MX8MP_IOMUXC_SD2_DATA0__AUDIOMIX_BIT_STREAM00                0x0C8 0x328 0x4C0 0x4 0x2
 #define MX8MP_IOMUXC_SD2_DATA0__GPIO2_IO15                           0x0C8 0x328 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SD2_DATA0__CCMSRCGPCMIX_OBSERVE2                0x0C8 0x328 0x000 0x6 0x0
 #define MX8MP_IOMUXC_SD2_DATA0__OBSERVE_MUX_OUT02                    0x0C8 0x328 0x000 0x7 0x0
@@ -313,7 +313,7 @@
 #define MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3                         0x0D4 0x334 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SD2_DATA3__ECSPI2_MISO                          0x0D4 0x334 0x56C 0x2 0x0
 #define MX8MP_IOMUXC_SD2_DATA3__AUDIOMIX_SPDIF_IN                    0x0D4 0x334 0x544 0x3 0x1
-#define MX8MP_IOMUXC_SD2_DATA3__AUDIOMIX_BIT_STREAM03                0x0D4 0x334 0x4CC 0x4 0x1
+#define MX8MP_IOMUXC_SD2_DATA3__AUDIOMIX_BIT_STREAM03                0x0D4 0x334 0x4CC 0x4 0x2
 #define MX8MP_IOMUXC_SD2_DATA3__GPIO2_IO18                           0x0D4 0x334 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SD2_DATA3__CCMSRCGPCMIX_EARLY_RESET             0x0D4 0x334 0x000 0x6 0x0
 #define MX8MP_IOMUXC_SD2_RESET_B__USDHC2_RESET_B                     0x0D8 0x338 0x000 0x0 0x0
@@ -487,27 +487,27 @@
 #define MX8MP_IOMUXC_SAI5_RXD0__AUDIOMIX_SAI1_TX_DATA02              0x134 0x394 0x000 0x1 0x0
 #define MX8MP_IOMUXC_SAI5_RXD0__PWM2_OUT                             0x134 0x394 0x000 0x2 0x0
 #define MX8MP_IOMUXC_SAI5_RXD0__I2C5_SCL                             0x134 0x394 0x5C4 0x3 0x1
-#define MX8MP_IOMUXC_SAI5_RXD0__AUDIOMIX_BIT_STREAM00                0x134 0x394 0x4C0 0x4 0x2
+#define MX8MP_IOMUXC_SAI5_RXD0__AUDIOMIX_BIT_STREAM00                0x134 0x394 0x4C0 0x4 0x3
 #define MX8MP_IOMUXC_SAI5_RXD0__GPIO3_IO21                           0x134 0x394 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_SAI5_RX_DATA01              0x138 0x398 0x4FC 0x0 0x0
 #define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_SAI1_TX_DATA03              0x138 0x398 0x000 0x1 0x0
 #define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_SAI1_TX_SYNC                0x138 0x398 0x4D8 0x2 0x0
 #define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_SAI5_TX_SYNC                0x138 0x398 0x510 0x3 0x0
-#define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_BIT_STREAM01                0x138 0x398 0x4C4 0x4 0x2
+#define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_BIT_STREAM01                0x138 0x398 0x4C4 0x4 0x3
 #define MX8MP_IOMUXC_SAI5_RXD1__GPIO3_IO22                           0x138 0x398 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SAI5_RXD1__CAN1_TX                              0x138 0x398 0x000 0x6 0x0
 #define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_SAI5_RX_DATA02              0x13C 0x39C 0x500 0x0 0x0
 #define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_SAI1_TX_DATA04              0x13C 0x39C 0x000 0x1 0x0
 #define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_SAI1_TX_SYNC                0x13C 0x39C 0x4D8 0x2 0x1
 #define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_SAI5_TX_BCLK                0x13C 0x39C 0x50C 0x3 0x0
-#define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_BIT_STREAM02                0x13C 0x39C 0x4C8 0x4 0x2
+#define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_BIT_STREAM02                0x13C 0x39C 0x4C8 0x4 0x3
 #define MX8MP_IOMUXC_SAI5_RXD2__GPIO3_IO23                           0x13C 0x39C 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SAI5_RXD2__CAN1_RX                              0x13C 0x39C 0x54C 0x6 0x0
 #define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_SAI5_RX_DATA03              0x140 0x3A0 0x504 0x0 0x0
 #define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_SAI1_TX_DATA05              0x140 0x3A0 0x000 0x1 0x0
 #define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_SAI1_TX_SYNC                0x140 0x3A0 0x4D8 0x2 0x2
 #define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_SAI5_TX_DATA00              0x140 0x3A0 0x000 0x3 0x0
-#define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_BIT_STREAM03                0x140 0x3A0 0x4CC 0x4 0x2
+#define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_BIT_STREAM03                0x140 0x3A0 0x4CC 0x4 0x3
 #define MX8MP_IOMUXC_SAI5_RXD3__GPIO3_IO24                           0x140 0x3A0 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SAI5_RXD3__CAN2_TX                              0x140 0x3A0 0x000 0x6 0x0
 #define MX8MP_IOMUXC_SAI5_MCLK__AUDIOMIX_SAI5_MCLK                   0x144 0x3A4 0x4F0 0x0 0x0
@@ -528,22 +528,22 @@
 #define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_SAI1_RX_DATA00              0x150 0x3B0 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_SAI5_RX_DATA00              0x150 0x3B0 0x4F8 0x1 0x1
 #define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_SAI1_TX_DATA01              0x150 0x3B0 0x000 0x2 0x0
-#define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_BIT_STREAM00                0x150 0x3B0 0x4C0 0x3 0x3
+#define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_BIT_STREAM00                0x150 0x3B0 0x4C0 0x3 0x4
 #define MX8MP_IOMUXC_SAI1_RXD0__ENET1_1588_EVENT1_IN                 0x150 0x3B0 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI1_RXD0__GPIO4_IO02                           0x150 0x3B0 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SAI1_RXD1__AUDIOMIX_SAI1_RX_DATA01              0x154 0x3B4 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI1_RXD1__AUDIOMIX_SAI5_RX_DATA01              0x154 0x3B4 0x4FC 0x1 0x1
-#define MX8MP_IOMUXC_SAI1_RXD1__AUDIOMIX_BIT_STREAM01                0x154 0x3B4 0x4C4 0x3 0x3
+#define MX8MP_IOMUXC_SAI1_RXD1__AUDIOMIX_BIT_STREAM01                0x154 0x3B4 0x4C4 0x3 0x4
 #define MX8MP_IOMUXC_SAI1_RXD1__ENET1_1588_EVENT1_OUT                0x154 0x3B4 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI1_RXD1__GPIO4_IO03                           0x154 0x3B4 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SAI1_RXD2__AUDIOMIX_SAI1_RX_DATA02              0x158 0x3B8 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI1_RXD2__AUDIOMIX_SAI5_RX_DATA02              0x158 0x3B8 0x500 0x1 0x1
-#define MX8MP_IOMUXC_SAI1_RXD2__AUDIOMIX_BIT_STREAM02                0x158 0x3B8 0x4C8 0x3 0x3
+#define MX8MP_IOMUXC_SAI1_RXD2__AUDIOMIX_BIT_STREAM02                0x158 0x3B8 0x4C8 0x3 0x4
 #define MX8MP_IOMUXC_SAI1_RXD2__ENET1_MDC                            0x158 0x3B8 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI1_RXD2__GPIO4_IO04                           0x158 0x3B8 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SAI1_RXD3__AUDIOMIX_SAI1_RX_DATA03              0x15C 0x3BC 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI1_RXD3__AUDIOMIX_SAI5_RX_DATA03              0x15C 0x3BC 0x504 0x1 0x1
-#define MX8MP_IOMUXC_SAI1_RXD3__AUDIOMIX_BIT_STREAM03                0x15C 0x3BC 0x4CC 0x3 0x3
+#define MX8MP_IOMUXC_SAI1_RXD3__AUDIOMIX_BIT_STREAM03                0x15C 0x3BC 0x4CC 0x3 0x4
 #define MX8MP_IOMUXC_SAI1_RXD3__ENET1_MDIO                           0x15C 0x3BC 0x57C 0x4 0x1
 #define MX8MP_IOMUXC_SAI1_RXD3__GPIO4_IO05                           0x15C 0x3BC 0x000 0x5 0x0
 #define MX8MP_IOMUXC_SAI1_RXD4__AUDIOMIX_SAI1_RX_DATA04              0x160 0x3C0 0x000 0x0 0x0
@@ -624,7 +624,7 @@
 #define MX8MP_IOMUXC_SAI2_RXFS__UART1_DCE_TX                         0x19C 0x3FC 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI2_RXFS__UART1_DTE_RX                         0x19C 0x3FC 0x5E8 0x4 0x2
 #define MX8MP_IOMUXC_SAI2_RXFS__GPIO4_IO21                           0x19C 0x3FC 0x000 0x5 0x0
-#define MX8MP_IOMUXC_SAI2_RXFS__AUDIOMIX_BIT_STREAM02                0x19C 0x3FC 0x4C8 0x6 0x4
+#define MX8MP_IOMUXC_SAI2_RXFS__AUDIOMIX_BIT_STREAM02                0x19C 0x3FC 0x4C8 0x6 0x5
 #define MX8MP_IOMUXC_SAI2_RXFS__SIM_M_HSIZE00                        0x19C 0x3FC 0x000 0x7 0x0
 #define MX8MP_IOMUXC_SAI2_RXC__AUDIOMIX_SAI2_RX_BCLK                 0x1A0 0x400 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI2_RXC__AUDIOMIX_SAI5_TX_BCLK                 0x1A0 0x400 0x50C 0x1 0x2
@@ -632,7 +632,7 @@
 #define MX8MP_IOMUXC_SAI2_RXC__UART1_DCE_RX                          0x1A0 0x400 0x5E8 0x4 0x3
 #define MX8MP_IOMUXC_SAI2_RXC__UART1_DTE_TX                          0x1A0 0x400 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI2_RXC__GPIO4_IO22                            0x1A0 0x400 0x000 0x5 0x0
-#define MX8MP_IOMUXC_SAI2_RXC__AUDIOMIX_BIT_STREAM01                 0x1A0 0x400 0x4C4 0x6 0x4
+#define MX8MP_IOMUXC_SAI2_RXC__AUDIOMIX_BIT_STREAM01                 0x1A0 0x400 0x4C4 0x6 0x5
 #define MX8MP_IOMUXC_SAI2_RXC__SIM_M_HSIZE01                         0x1A0 0x400 0x000 0x7 0x0
 #define MX8MP_IOMUXC_SAI2_RXD0__AUDIOMIX_SAI2_RX_DATA00              0x1A4 0x404 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI2_RXD0__AUDIOMIX_SAI5_TX_DATA00              0x1A4 0x404 0x000 0x1 0x0
@@ -641,7 +641,7 @@
 #define MX8MP_IOMUXC_SAI2_RXD0__UART1_DCE_RTS                        0x1A4 0x404 0x5E4 0x4 0x2
 #define MX8MP_IOMUXC_SAI2_RXD0__UART1_DTE_CTS                        0x1A4 0x404 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI2_RXD0__GPIO4_IO23                           0x1A4 0x404 0x000 0x5 0x0
-#define MX8MP_IOMUXC_SAI2_RXD0__AUDIOMIX_BIT_STREAM03                0x1A4 0x404 0x4CC 0x6 0x4
+#define MX8MP_IOMUXC_SAI2_RXD0__AUDIOMIX_BIT_STREAM03                0x1A4 0x404 0x4CC 0x6 0x5
 #define MX8MP_IOMUXC_SAI2_RXD0__SIM_M_HSIZE02                        0x1A4 0x404 0x000 0x7 0x0
 #define MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_SAI2_TX_SYNC                0x1A8 0x408 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_SAI5_TX_DATA01              0x1A8 0x408 0x000 0x1 0x0
@@ -650,13 +650,13 @@
 #define MX8MP_IOMUXC_SAI2_TXFS__UART1_DCE_CTS                        0x1A8 0x408 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI2_TXFS__UART1_DTE_RTS                        0x1A8 0x408 0x5E4 0x4 0x3
 #define MX8MP_IOMUXC_SAI2_TXFS__GPIO4_IO24                           0x1A8 0x408 0x000 0x5 0x0
-#define MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_BIT_STREAM02                0x1A8 0x408 0x4C8 0x6 0x5
+#define MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_BIT_STREAM02                0x1A8 0x408 0x4C8 0x6 0x6
 #define MX8MP_IOMUXC_SAI2_TXFS__SIM_M_HWRITE                         0x1A8 0x408 0x000 0x7 0x0
 #define MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_SAI2_TX_BCLK                 0x1AC 0x40C 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_SAI5_TX_DATA02               0x1AC 0x40C 0x000 0x1 0x0
 #define MX8MP_IOMUXC_SAI2_TXC__CAN1_RX                               0x1AC 0x40C 0x54C 0x3 0x1
 #define MX8MP_IOMUXC_SAI2_TXC__GPIO4_IO25                            0x1AC 0x40C 0x000 0x5 0x0
-#define MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_BIT_STREAM01                 0x1AC 0x40C 0x4C4 0x6 0x5
+#define MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_BIT_STREAM01                 0x1AC 0x40C 0x4C4 0x6 0x6
 #define MX8MP_IOMUXC_SAI2_TXC__SIM_M_HREADYOUT                       0x1AC 0x40C 0x000 0x7 0x0
 #define MX8MP_IOMUXC_SAI2_TXD0__AUDIOMIX_SAI2_TX_DATA00              0x1B0 0x410 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI2_TXD0__AUDIOMIX_SAI5_TX_DATA03              0x1B0 0x410 0x000 0x1 0x0
@@ -680,7 +680,7 @@
 #define MX8MP_IOMUXC_SAI3_RXFS__AUDIOMIX_SAI3_RX_DATA01              0x1B8 0x418 0x000 0x3 0x0
 #define MX8MP_IOMUXC_SAI3_RXFS__AUDIOMIX_SPDIF_IN                    0x1B8 0x418 0x544 0x4 0x2
 #define MX8MP_IOMUXC_SAI3_RXFS__GPIO4_IO28                           0x1B8 0x418 0x000 0x5 0x0
-#define MX8MP_IOMUXC_SAI3_RXFS__AUDIOMIX_BIT_STREAM00                0x1B8 0x418 0x4C0 0x6 0x4
+#define MX8MP_IOMUXC_SAI3_RXFS__AUDIOMIX_BIT_STREAM00                0x1B8 0x418 0x4C0 0x6 0x5
 #define MX8MP_IOMUXC_SAI3_RXFS__TPSMP_HTRANS00                       0x1B8 0x418 0x000 0x7 0x0
 #define MX8MP_IOMUXC_SAI3_RXC__AUDIOMIX_SAI3_RX_BCLK                 0x1BC 0x41C 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI3_RXC__AUDIOMIX_SAI2_RX_DATA02               0x1BC 0x41C 0x000 0x1 0x0
@@ -697,7 +697,7 @@
 #define MX8MP_IOMUXC_SAI3_RXD__UART2_DCE_RTS                         0x1C0 0x420 0x5EC 0x4 0x3
 #define MX8MP_IOMUXC_SAI3_RXD__UART2_DTE_CTS                         0x1C0 0x420 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI3_RXD__GPIO4_IO30                            0x1C0 0x420 0x000 0x5 0x0
-#define MX8MP_IOMUXC_SAI3_RXD__AUDIOMIX_BIT_STREAM01                 0x1C0 0x420 0x4C4 0x6 0x6
+#define MX8MP_IOMUXC_SAI3_RXD__AUDIOMIX_BIT_STREAM01                 0x1C0 0x420 0x4C4 0x6 0x7
 #define MX8MP_IOMUXC_SAI3_RXD__TPSMP_HDATA00                         0x1C0 0x420 0x000 0x7 0x0
 #define MX8MP_IOMUXC_SAI3_TXFS__AUDIOMIX_SAI3_TX_SYNC                0x1C4 0x424 0x4EC 0x0 0x1
 #define MX8MP_IOMUXC_SAI3_TXFS__AUDIOMIX_SAI2_TX_DATA01              0x1C4 0x424 0x000 0x1 0x0
@@ -706,7 +706,7 @@
 #define MX8MP_IOMUXC_SAI3_TXFS__UART2_DCE_RX                         0x1C4 0x424 0x5F0 0x4 0x4
 #define MX8MP_IOMUXC_SAI3_TXFS__UART2_DTE_TX                         0x1C4 0x424 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI3_TXFS__GPIO4_IO31                           0x1C4 0x424 0x000 0x5 0x0
-#define MX8MP_IOMUXC_SAI3_TXFS__AUDIOMIX_BIT_STREAM03                0x1C4 0x424 0x4CC 0x6 0x5
+#define MX8MP_IOMUXC_SAI3_TXFS__AUDIOMIX_BIT_STREAM03                0x1C4 0x424 0x4CC 0x6 0x6
 #define MX8MP_IOMUXC_SAI3_TXFS__TPSMP_HDATA01                        0x1C4 0x424 0x000 0x7 0x0
 #define MX8MP_IOMUXC_SAI3_TXC__AUDIOMIX_SAI3_TX_BCLK                 0x1C8 0x428 0x4E8 0x0 0x1
 #define MX8MP_IOMUXC_SAI3_TXC__AUDIOMIX_SAI2_TX_DATA02               0x1C8 0x428 0x000 0x1 0x0
@@ -715,7 +715,7 @@
 #define MX8MP_IOMUXC_SAI3_TXC__UART2_DCE_TX                          0x1C8 0x428 0x000 0x4 0x0
 #define MX8MP_IOMUXC_SAI3_TXC__UART2_DTE_RX                          0x1C8 0x428 0x5F0 0x4 0x5
 #define MX8MP_IOMUXC_SAI3_TXC__GPIO5_IO00                            0x1C8 0x428 0x000 0x5 0x0
-#define MX8MP_IOMUXC_SAI3_TXC__AUDIOMIX_BIT_STREAM02                 0x1C8 0x428 0x4C8 0x6 0x6
+#define MX8MP_IOMUXC_SAI3_TXC__AUDIOMIX_BIT_STREAM02                 0x1C8 0x428 0x4C8 0x6 0x7
 #define MX8MP_IOMUXC_SAI3_TXC__TPSMP_HDATA02                         0x1C8 0x428 0x000 0x7 0x0
 #define MX8MP_IOMUXC_SAI3_TXD__AUDIOMIX_SAI3_TX_DATA00               0x1CC 0x42C 0x000 0x0 0x0
 #define MX8MP_IOMUXC_SAI3_TXD__AUDIOMIX_SAI2_TX_DATA03               0x1CC 0x42C 0x000 0x1 0x0
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 9b1616e59d58..9f6ba763238d 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -145,7 +145,7 @@
 
 		aips1: bus@30000000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x301f0000 0x10000>;
+			reg = <0x30000000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
@@ -318,7 +318,7 @@
 
 		aips2: bus@30400000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x305f0000 0x400000>;
+			reg = <0x30400000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
@@ -378,7 +378,7 @@
 
 		aips3: bus@30800000 {
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x309f0000 0x400000>;
+			reg = <0x30800000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges;
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index 75b384217a23..bab88369be1b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -291,7 +291,7 @@
 
 		bus@30000000 { /* AIPS1 */
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x301f0000 0x10000>;
+			reg = <0x30000000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x30000000 0x30000000 0x400000>;
@@ -696,7 +696,7 @@
 
 		bus@30400000 { /* AIPS2 */
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x305f0000 0x10000>;
+			reg = <0x30400000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x30400000 0x30400000 0x400000>;
@@ -756,7 +756,7 @@
 
 		bus@30800000 { /* AIPS3 */
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x309f0000 0x10000>;
+			reg = <0x30800000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x30800000 0x30800000 0x400000>,
@@ -1029,7 +1029,7 @@
 
 		bus@32c00000 { /* AIPS4 */
 			compatible = "fsl,aips-bus", "simple-bus";
-			reg = <0x32df0000 0x10000>;
+			reg = <0x32c00000 0x400000>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x32c00000 0x32c00000 0x400000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index ccb8e88a60c5..d819e44d94a8 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -1402,8 +1402,8 @@
 				      "venc_lt_sel";
 			assigned-clocks = <&topckgen CLK_TOP_VENC_SEL>,
 					  <&topckgen CLK_TOP_VENC_LT_SEL>;
-			assigned-clock-parents = <&topckgen CLK_TOP_VENCPLL_D2>,
-						 <&topckgen CLK_TOP_UNIVPLL1_D2>;
+			assigned-clock-parents = <&topckgen CLK_TOP_VCODECPLL>,
+						 <&topckgen CLK_TOP_VCODECPLL_370P5>;
 		};
 
 		jpegdec: jpegdec@18004000 {
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
index af87350b5547..c4abbccf2bed 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
@@ -658,8 +658,8 @@
 	s11 {
 		qcom,saw-leader;
 		regulator-always-on;
-		regulator-min-microvolt = <1230000>;
-		regulator-max-microvolt = <1230000>;
+		regulator-min-microvolt = <980000>;
+		regulator-max-microvolt = <980000>;
 	};
 };
 
@@ -908,10 +908,27 @@
 	status = "okay";
 };
 
+&q6asmdai {
+	dai@0 {
+		reg = <0>;
+	};
+
+	dai@1 {
+		reg = <1>;
+	};
+
+	dai@2 {
+		reg = <2>;
+	};
+};
+
 &sound {
 	compatible = "qcom,apq8096-sndcard";
 	model = "DB820c";
-	audio-routing =	"RX_BIAS", "MCLK";
+	audio-routing =	"RX_BIAS", "MCLK",
+		"MM_DL1",  "MultiMedia1 Playback",
+		"MM_DL2",  "MultiMedia2 Playback",
+		"MultiMedia3 Capture", "MM_UL3";
 
 	mm1-dai-link {
 		link-name = "MultiMedia1";
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 14827adebd94..98634d5c4440 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -2066,6 +2066,8 @@
 						reg = <APR_SVC_ASM>;
 						q6asmdai: dais {
 							compatible = "qcom,q6asm-dais";
+							#address-cells = <1>;
+							#size-cells = <0>;
 							#sound-dai-cells = <1>;
 							iommus = <&lpass_q6_smmu 1>;
 						};
diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
index a2e05926b429..21fd6f8d5799 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
+++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
@@ -442,17 +442,14 @@
 &q6asmdai {
 	dai@0 {
 		reg = <0>;
-		direction = <2>;
 	};
 
 	dai@1 {
 		reg = <1>;
-		direction = <2>;
 	};
 
 	dai@2 {
 		reg = <2>;
-		direction = <1>;
 	};
 
 	dai@3 {
diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
index 3b617a75fafa..51a670ad15b2 100644
--- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
+++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
@@ -359,12 +359,10 @@
 &q6asmdai {
 	dai@0 {
 		reg = <0>;
-		direction = <2>;
 	};
 
 	dai@1 {
 		reg = <1>;
-		direction = <1>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
index 2afb91ec9c8d..ac2156ab3e62 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts
@@ -137,8 +137,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts
index d7c7b9156e08..01c4ba0f7be1 100644
--- a/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts
@@ -150,8 +150,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts
index 3dde028e22a6..ef8350a062af 100644
--- a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts
@@ -174,8 +174,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts b/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts
index adbfd8f07d06..6dff04693223 100644
--- a/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts
@@ -141,8 +141,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77980.dtsi b/arch/arm64/boot/dts/renesas/r8a77980.dtsi
index e01b0508a18f..d672b320bc14 100644
--- a/arch/arm64/boot/dts/renesas/r8a77980.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77980.dtsi
@@ -1318,6 +1318,7 @@
 		ipmmu_vip0: mmu@e7b00000 {
 			compatible = "renesas,ipmmu-r8a77980";
 			reg = <0 0xe7b00000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 4>;
 			power-domains = <&sysc R8A77980_PD_ALWAYS_ON>;
 			#iommu-cells = <1>;
 		};
@@ -1325,6 +1326,7 @@
 		ipmmu_vip1: mmu@e7960000 {
 			compatible = "renesas,ipmmu-r8a77980";
 			reg = <0 0xe7960000 0 0x1000>;
+			renesas,ipmmu-main = <&ipmmu_mm 11>;
 			power-domains = <&sysc R8A77980_PD_ALWAYS_ON>;
 			#iommu-cells = <1>;
 		};
diff --git a/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts b/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts
index 4fd2b14fbb8b..dc24cec46ae1 100644
--- a/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts
@@ -360,8 +360,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/renesas/r8a77995-draak.dts b/arch/arm64/boot/dts/renesas/r8a77995-draak.dts
index 67634cb01d6b..79c73a99d2fe 100644
--- a/arch/arm64/boot/dts/renesas/r8a77995-draak.dts
+++ b/arch/arm64/boot/dts/renesas/r8a77995-draak.dts
@@ -272,8 +272,8 @@
 
 	hdmi-encoder@39 {
 		compatible = "adi,adv7511w";
-		reg = <0x39>, <0x3f>, <0x38>, <0x3c>;
-		reg-names = "main", "edid", "packet", "cec";
+		reg = <0x39>, <0x3f>, <0x3c>, <0x38>;
+		reg-names = "main", "edid", "cec", "packet";
 		interrupt-parent = <&gpio1>;
 		interrupts = <28 IRQ_TYPE_LEVEL_LOW>;
 
@@ -284,8 +284,6 @@
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
 		adi,input-clock = "1x";
-		adi,input-style = <1>;
-		adi,input-justification = "evenly";
 
 		ports {
 			#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi
index f809dd6d5dc3..adc9b8bf5eaa 100644
--- a/arch/arm64/boot/dts/rockchip/px30.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30.dtsi
@@ -143,7 +143,7 @@
 	};
 
 	arm-pmu {
-		compatible = "arm,cortex-a53-pmu";
+		compatible = "arm,cortex-a35-pmu";
 		interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/rockchip/rk3308.dtsi b/arch/arm64/boot/dts/rockchip/rk3308.dtsi
index ac43bc3f7031..ac7f694079d0 100644
--- a/arch/arm64/boot/dts/rockchip/rk3308.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3308.dtsi
@@ -127,7 +127,7 @@
 	};
 
 	arm-pmu {
-		compatible = "arm,cortex-a53-pmu";
+		compatible = "arm,cortex-a35-pmu";
 		interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
index 49c4b96da3d4..ac29c2744d08 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
@@ -82,17 +82,16 @@
 &gmac2phy {
 	phy-supply = <&vcc_phy>;
 	clock_in_out = "output";
-	assigned-clocks = <&cru SCLK_MAC2PHY_SRC>;
 	assigned-clock-rate = <50000000>;
 	assigned-clocks = <&cru SCLK_MAC2PHY>;
 	assigned-clock-parents = <&cru SCLK_MAC2PHY_SRC>;
-
+	status = "okay";
 };
 
 &i2c1 {
 	status = "okay";
 
-	rk805: rk805@18 {
+	rk805: pmic@18 {
 		compatible = "rockchip,rk805";
 		reg = <0x18>;
 		interrupt-parent = <&gpio2>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index bf3e546f5266..ebf3eb222e1f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -170,7 +170,7 @@
 &i2c1 {
 	status = "okay";
 
-	rk805: rk805@18 {
+	rk805: pmic@18 {
 		compatible = "rockchip,rk805";
 		reg = <0x18>;
 		interrupt-parent = <&gpio2>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index 7e88d88aab98..a4d591d91533 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -299,8 +299,6 @@
 	grf: syscon@ff100000 {
 		compatible = "rockchip,rk3328-grf", "syscon", "simple-mfd";
 		reg = <0x0 0xff100000 0x0 0x1000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
 
 		io_domains: io-domains {
 			compatible = "rockchip,rk3328-io-voltage-domain";
@@ -1794,10 +1792,6 @@
 		};
 
 		gmac2phy {
-			fephyled_speed100: fephyled-speed100 {
-				rockchip,pins = <0 RK_PD7 1 &pcfg_pull_none>;
-			};
-
 			fephyled_speed10: fephyled-speed10 {
 				rockchip,pins = <0 RK_PD6 1 &pcfg_pull_none>;
 			};
@@ -1806,18 +1800,6 @@
 				rockchip,pins = <0 RK_PD6 2 &pcfg_pull_none>;
 			};
 
-			fephyled_rxm0: fephyled-rxm0 {
-				rockchip,pins = <0 RK_PD5 1 &pcfg_pull_none>;
-			};
-
-			fephyled_txm0: fephyled-txm0 {
-				rockchip,pins = <0 RK_PD5 2 &pcfg_pull_none>;
-			};
-
-			fephyled_linkm0: fephyled-linkm0 {
-				rockchip,pins = <0 RK_PD4 1 &pcfg_pull_none>;
-			};
-
 			fephyled_rxm1: fephyled-rxm1 {
 				rockchip,pins = <2 RK_PD1 2 &pcfg_pull_none>;
 			};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
index 5ea281b55fe2..c49982dfd8fc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
@@ -147,7 +147,7 @@
 			"Speaker", "Speaker Amplifier OUTL",
 			"Speaker", "Speaker Amplifier OUTR";
 
-		simple-audio-card,hp-det-gpio = <&gpio0 RK_PB0 GPIO_ACTIVE_LOW>;
+		simple-audio-card,hp-det-gpio = <&gpio0 RK_PB0 GPIO_ACTIVE_HIGH>;
 		simple-audio-card,aux-devs = <&speaker_amp>;
 		simple-audio-card,pin-switches = "Speaker";
 
@@ -690,7 +690,8 @@
 	fusb0: fusb30x@22 {
 		compatible = "fcs,fusb302";
 		reg = <0x22>;
-		fcs,int_n = <&gpio1 RK_PA2 GPIO_ACTIVE_HIGH>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <RK_PA2 IRQ_TYPE_LEVEL_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&fusb0_int_gpio>;
 		vbus-supply = <&vbus_typec>;
@@ -788,13 +789,13 @@
 
 	dc-charger {
 		dc_det_gpio: dc-det-gpio {
-			rockchip,pins = <4 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>;
+			rockchip,pins = <4 RK_PD0 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 	};
 
 	es8316 {
 		hp_det_gpio: hp-det-gpio {
-			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_down>;
+			rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 74f2c3d49095..1448f358ed0a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -403,7 +403,7 @@
 		reset-names = "usb3-otg";
 		status = "disabled";
 
-		usbdrd_dwc3_0: dwc3 {
+		usbdrd_dwc3_0: usb@fe800000 {
 			compatible = "snps,dwc3";
 			reg = <0x0 0xfe800000 0x0 0x100000>;
 			interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -439,7 +439,7 @@
 		reset-names = "usb3-otg";
 		status = "disabled";
 
-		usbdrd_dwc3_1: dwc3 {
+		usbdrd_dwc3_1: usb@fe900000 {
 			compatible = "snps,dwc3";
 			reg = <0x0 0xfe900000 0x0 0x100000>;
 			interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH 0>;
@@ -1124,8 +1124,6 @@
 	pmugrf: syscon@ff320000 {
 		compatible = "rockchip,rk3399-pmugrf", "syscon", "simple-mfd";
 		reg = <0x0 0xff320000 0x0 0x1000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
 
 		pmu_io_domains: io-domains {
 			compatible = "rockchip,rk3399-pmu-io-voltage-domain";
@@ -1883,10 +1881,10 @@
 	gpu: gpu@ff9a0000 {
 		compatible = "rockchip,rk3399-mali", "arm,mali-t860";
 		reg = <0x0 0xff9a0000 0x0 0x10000>;
-		interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>;
-		interrupt-names = "gpu", "job", "mmu";
+		interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>,
+			     <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupt-names = "job", "mmu", "gpu";
 		clocks = <&cru ACLK_GPU>;
 		#cooling-cells = <2>;
 		power-domains = <&power RK3399_PD_GPU>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 24e534d85045..03d0189f7d68 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -208,7 +208,7 @@ CONFIG_PCIE_QCOM=y
 CONFIG_PCIE_ARMADA_8K=y
 CONFIG_PCIE_KIRIN=y
 CONFIG_PCIE_HISI_STB=y
-CONFIG_PCIE_TEGRA194=m
+CONFIG_PCIE_TEGRA194_HOST=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_FW_LOADER_USER_HELPER=y
@@ -567,6 +567,7 @@ CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y
 CONFIG_MEDIA_SDR_SUPPORT=y
 CONFIG_MEDIA_CONTROLLER=y
 CONFIG_VIDEO_V4L2_SUBDEV_API=y
+CONFIG_MEDIA_PLATFORM_SUPPORT=y
 # CONFIG_DVB_NET is not set
 CONFIG_MEDIA_USB_SUPPORT=y
 CONFIG_USB_VIDEO_CLASS=m
@@ -610,8 +611,9 @@ CONFIG_DRM_MSM=m
 CONFIG_DRM_TEGRA=m
 CONFIG_DRM_PANEL_LVDS=m
 CONFIG_DRM_PANEL_SIMPLE=m
-CONFIG_DRM_DUMB_VGA_DAC=m
+CONFIG_DRM_SIMPLE_BRIDGE=m
 CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA=m
+CONFIG_DRM_DISPLAY_CONNECTOR=m
 CONFIG_DRM_SII902X=m
 CONFIG_DRM_THINE_THC63LVD1024=m
 CONFIG_DRM_TI_SN65DSI86=m
@@ -848,7 +850,8 @@ CONFIG_QCOM_APR=m
 CONFIG_ARCH_R8A774A1=y
 CONFIG_ARCH_R8A774B1=y
 CONFIG_ARCH_R8A774C0=y
-CONFIG_ARCH_R8A7795=y
+CONFIG_ARCH_R8A77950=y
+CONFIG_ARCH_R8A77951=y
 CONFIG_ARCH_R8A77960=y
 CONFIG_ARCH_R8A77961=y
 CONFIG_ARCH_R8A77965=y
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index ed5409c6abf4..395bbf64b2ab 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -158,7 +158,6 @@ static int __maybe_unused essiv_cbc_set_key(struct crypto_skcipher *tfm,
 					    unsigned int key_len)
 {
 	struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
-	SHASH_DESC_ON_STACK(desc, ctx->hash);
 	u8 digest[SHA256_DIGEST_SIZE];
 	int ret;
 
@@ -166,8 +165,7 @@ static int __maybe_unused essiv_cbc_set_key(struct crypto_skcipher *tfm,
 	if (ret)
 		return ret;
 
-	desc->tfm = ctx->hash;
-	crypto_shash_digest(desc, in_key, key_len, digest);
+	crypto_shash_tfm_digest(ctx->hash, in_key, key_len, digest);
 
 	return aes_expandkey(&ctx->key2, digest, sizeof(digest));
 }
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
index 37ca3e889848..af2bbca38e70 100644
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ b/arch/arm64/crypto/chacha-neon-glue.c
@@ -87,9 +87,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
 	    !crypto_simd_usable())
 		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
 
-	kernel_neon_begin();
-	chacha_doneon(state, dst, src, bytes, nrounds);
-	kernel_neon_end();
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		kernel_neon_begin();
+		chacha_doneon(state, dst, src, todo, nrounds);
+		kernel_neon_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
 }
 EXPORT_SYMBOL(chacha_crypt_arch);
 
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index 5a95c2628fbf..111d9c9abddd 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -66,7 +66,7 @@
 #include <asm/assembler.h>
 
 	.text
-	.cpu		generic+crypto
+	.arch		armv8-a+crypto
 
 	init_crc	.req	w19
 	buf		.req	x20
diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c
index 895d3727c1fb..c5405e6a6db7 100644
--- a/arch/arm64/crypto/nhpoly1305-neon-glue.c
+++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c
@@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc,
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
-		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_neon_begin();
 		crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon);
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
index e97b092f56b8..f33ada70c4ed 100644
--- a/arch/arm64/crypto/poly1305-glue.c
+++ b/arch/arm64/crypto/poly1305-glue.c
@@ -143,13 +143,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
 		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
 
 		if (static_branch_likely(&have_neon) && crypto_simd_usable()) {
-			kernel_neon_begin();
-			poly1305_blocks_neon(&dctx->h, src, len, 1);
-			kernel_neon_end();
+			do {
+				unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+				kernel_neon_begin();
+				poly1305_blocks_neon(&dctx->h, src, todo, 1);
+				kernel_neon_end();
+
+				len -= todo;
+				src += todo;
+			} while (len);
 		} else {
 			poly1305_blocks(&dctx->h, src, len, 1);
+			src += len;
 		}
-		src += len;
 		nbytes %= POLY1305_BLOCK_SIZE;
 	}
 
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index ddf4a0d85c1c..77bc6e72abae 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -12,7 +12,6 @@
 #include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <linux/string.h>
 
diff --git a/arch/arm64/crypto/sha512-glue.c b/arch/arm64/crypto/sha512-glue.c
index 78d3083de6b7..370ccb29602f 100644
--- a/arch/arm64/crypto/sha512-glue.c
+++ b/arch/arm64/crypto/sha512-glue.c
@@ -6,7 +6,6 @@
  */
 
 #include <crypto/internal/hash.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <crypto/sha.h>
diff --git a/arch/arm64/include/asm/asm_pointer_auth.h b/arch/arm64/include/asm/asm_pointer_auth.h
index ce2a8486992b..52dead2a8640 100644
--- a/arch/arm64/include/asm/asm_pointer_auth.h
+++ b/arch/arm64/include/asm/asm_pointer_auth.h
@@ -39,25 +39,58 @@ alternative_if ARM64_HAS_GENERIC_AUTH
 alternative_else_nop_endif
 	.endm
 
-	.macro ptrauth_keys_install_kernel tsk, sync, tmp1, tmp2, tmp3
-alternative_if ARM64_HAS_ADDRESS_AUTH
+	.macro __ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
 	mov	\tmp1, #THREAD_KEYS_KERNEL
 	add	\tmp1, \tsk, \tmp1
 	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_KERNEL_KEY_APIA]
 	msr_s	SYS_APIAKEYLO_EL1, \tmp2
 	msr_s	SYS_APIAKEYHI_EL1, \tmp3
-	.if     \sync == 1
+	.endm
+
+	.macro ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
+alternative_if ARM64_HAS_ADDRESS_AUTH
+	__ptrauth_keys_install_kernel_nosync \tsk, \tmp1, \tmp2, \tmp3
+alternative_else_nop_endif
+	.endm
+
+	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
+alternative_if ARM64_HAS_ADDRESS_AUTH
+	__ptrauth_keys_install_kernel_nosync \tsk, \tmp1, \tmp2, \tmp3
 	isb
-	.endif
 alternative_else_nop_endif
 	.endm
 
+	.macro __ptrauth_keys_init_cpu tsk, tmp1, tmp2, tmp3
+	mrs	\tmp1, id_aa64isar1_el1
+	ubfx	\tmp1, \tmp1, #ID_AA64ISAR1_APA_SHIFT, #8
+	cbz	\tmp1, .Lno_addr_auth\@
+	mov_q	\tmp1, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
+			SCTLR_ELx_ENDA | SCTLR_ELx_ENDB)
+	mrs	\tmp2, sctlr_el1
+	orr	\tmp2, \tmp2, \tmp1
+	msr	sctlr_el1, \tmp2
+	__ptrauth_keys_install_kernel_nosync \tsk, \tmp1, \tmp2, \tmp3
+	isb
+.Lno_addr_auth\@:
+	.endm
+
+	.macro ptrauth_keys_init_cpu tsk, tmp1, tmp2, tmp3
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.Lno_addr_auth\@
+alternative_else_nop_endif
+	__ptrauth_keys_init_cpu \tsk, \tmp1, \tmp2, \tmp3
+.Lno_addr_auth\@:
+	.endm
+
 #else /* CONFIG_ARM64_PTR_AUTH */
 
 	.macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
 	.endm
 
-	.macro ptrauth_keys_install_kernel tsk, sync, tmp1, tmp2, tmp3
+	.macro ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
+	.endm
+
+	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
 	.endm
 
 #endif /* CONFIG_ARM64_PTR_AUTH */
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 0bff325117b4..54d181177656 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -736,4 +736,54 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 .Lyield_out_\@ :
 	.endm
 
+/*
+ * This macro emits a program property note section identifying
+ * architecture features which require special handling, mainly for
+ * use in assembly files included in the VDSO.
+ */
+
+#define NT_GNU_PROPERTY_TYPE_0  5
+#define GNU_PROPERTY_AARCH64_FEATURE_1_AND      0xc0000000
+
+#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI      (1U << 0)
+#define GNU_PROPERTY_AARCH64_FEATURE_1_PAC      (1U << 1)
+
+#ifdef CONFIG_ARM64_BTI_KERNEL
+#define GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT		\
+		((GNU_PROPERTY_AARCH64_FEATURE_1_BTI |	\
+		  GNU_PROPERTY_AARCH64_FEATURE_1_PAC))
+#endif
+
+#ifdef GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT
+.macro emit_aarch64_feature_1_and, feat=GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT
+	.pushsection .note.gnu.property, "a"
+	.align  3
+	.long   2f - 1f
+	.long   6f - 3f
+	.long   NT_GNU_PROPERTY_TYPE_0
+1:      .string "GNU"
+2:
+	.align  3
+3:      .long   GNU_PROPERTY_AARCH64_FEATURE_1_AND
+	.long   5f - 4f
+4:
+	/*
+	 * This is described with an array of char in the Linux API
+	 * spec but the text and all other usage (including binutils,
+	 * clang and GCC) treat this as a 32 bit value so no swizzling
+	 * is required for big endian.
+	 */
+	.long   \feat
+5:
+	.align  3
+6:
+	.popsection
+.endm
+
+#else
+.macro emit_aarch64_feature_1_and, feat=0
+.endm
+
+#endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */
+
 #endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index e6cca3d4acf7..ce50c1f1f1ea 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -79,7 +79,7 @@ static inline void flush_icache_range(unsigned long start, unsigned long end)
 	 * IPI all online CPUs so that they undergo a context synchronization
 	 * event and are forced to refetch the new instructions.
 	 */
-#ifdef CONFIG_KGDB
+
 	/*
 	 * KGDB performs cache maintenance with interrupts disabled, so we
 	 * will deadlock trying to IPI the secondary CPUs. In theory, we can
@@ -89,9 +89,9 @@ static inline void flush_icache_range(unsigned long start, unsigned long end)
 	 * the patching operation, so we don't need extra IPIs here anyway.
 	 * In which case, add a KGDB-specific bodge and return early.
 	 */
-	if (kgdb_connected && irqs_disabled())
+	if (in_dbg_master())
 		return;
-#endif
+
 	kick_all_cpus_sync();
 }
 
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
index eece20d2c55f..51a7ce87cdfe 100644
--- a/arch/arm64/include/asm/compiler.h
+++ b/arch/arm64/include/asm/compiler.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_COMPILER_H
 #define __ASM_COMPILER_H
 
-#if defined(CONFIG_ARM64_PTR_AUTH)
-
 /*
  * The EL0/EL1 pointer bits used by a pointer authentication code.
  * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply.
@@ -19,6 +17,4 @@
 #define __builtin_return_address(val)					\
 	(void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val)))
 
-#endif /* CONFIG_ARM64_PTR_AUTH */
-
 #endif /* __ASM_COMPILER_H */
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index b4a40535a3d8..7faae6ff3ab4 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -33,6 +33,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64zfr0;
 
 	u32		reg_id_dfr0;
+	u32		reg_id_dfr1;
 	u32		reg_id_isar0;
 	u32		reg_id_isar1;
 	u32		reg_id_isar2;
@@ -44,8 +45,11 @@ struct cpuinfo_arm64 {
 	u32		reg_id_mmfr1;
 	u32		reg_id_mmfr2;
 	u32		reg_id_mmfr3;
+	u32		reg_id_mmfr4;
+	u32		reg_id_mmfr5;
 	u32		reg_id_pfr0;
 	u32		reg_id_pfr1;
+	u32		reg_id_pfr2;
 
 	u32		reg_mvfr0;
 	u32		reg_mvfr1;
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 8eb5a088ae65..d7b3bb0cb180 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -44,7 +44,7 @@
 #define ARM64_SSBS				34
 #define ARM64_WORKAROUND_1418040		35
 #define ARM64_HAS_SB				36
-#define ARM64_WORKAROUND_SPECULATIVE_AT_VHE	37
+#define ARM64_WORKAROUND_SPECULATIVE_AT		37
 #define ARM64_HAS_ADDRESS_AUTH_ARCH		38
 #define ARM64_HAS_ADDRESS_AUTH_IMP_DEF		39
 #define ARM64_HAS_GENERIC_AUTH_ARCH		40
@@ -55,13 +55,14 @@
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM	46
 #define ARM64_WORKAROUND_1542419		47
-#define ARM64_WORKAROUND_SPECULATIVE_AT_NVHE	48
-#define ARM64_HAS_E0PD				49
-#define ARM64_HAS_RNG				50
-#define ARM64_HAS_AMU_EXTN			51
-#define ARM64_HAS_ADDRESS_AUTH			52
-#define ARM64_HAS_GENERIC_AUTH			53
+#define ARM64_HAS_E0PD				48
+#define ARM64_HAS_RNG				49
+#define ARM64_HAS_AMU_EXTN			50
+#define ARM64_HAS_ADDRESS_AUTH			51
+#define ARM64_HAS_GENERIC_AUTH			52
+#define ARM64_HAS_32BIT_EL1			53
+#define ARM64_BTI				54
 
-#define ARM64_NCAPS				54
+#define ARM64_NCAPS				55
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index afe08251ff95..5d1f4ae42799 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -551,6 +551,13 @@ static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
 		cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_BIGENDEL0_SHIFT) == 0x1;
 }
 
+static inline bool id_aa64pfr0_32bit_el1(u64 pfr0)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_SHIFT);
+
+	return val == ID_AA64PFR0_EL1_32BIT_64BIT;
+}
+
 static inline bool id_aa64pfr0_32bit_el0(u64 pfr0)
 {
 	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL0_SHIFT);
@@ -680,6 +687,11 @@ static inline bool system_has_prio_mask_debugging(void)
 	       system_uses_irq_prio_masking();
 }
 
+static inline bool system_supports_bti(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
+}
+
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1
@@ -745,6 +757,24 @@ static inline bool cpu_has_hw_af(void)
 extern bool cpu_has_amu_feat(int cpu);
 #endif
 
+static inline unsigned int get_vmid_bits(u64 mmfr1)
+{
+	int vmid_bits;
+
+	vmid_bits = cpuid_feature_extract_unsigned_field(mmfr1,
+						ID_AA64MMFR1_VMIDBITS_SHIFT);
+	if (vmid_bits == ID_AA64MMFR1_VMIDBITS_16)
+		return 16;
+
+	/*
+	 * Return the default here even if any reserved
+	 * value is fetched from the system register.
+	 */
+	return 8;
+}
+
+u32 get_kvm_ipa_limit(void);
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 7619f473155f..e5ceea213e39 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -125,5 +125,7 @@ static inline int reinstall_suspended_bps(struct pt_regs *regs)
 
 int aarch32_break_handler(struct pt_regs *regs);
 
+void debug_traps_init(void);
+
 #endif	/* __ASSEMBLY */
 #endif	/* __ASM_DEBUG_MONITORS_H */
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 45e821222774..d4ab3f73e7a3 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -86,14 +86,6 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
 	return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS_MIN - 1));
 }
 
-#define efi_bs_call(func, ...)	efi_system_table()->boottime->func(__VA_ARGS__)
-#define efi_rt_call(func, ...)	efi_system_table()->runtime->func(__VA_ARGS__)
-#define efi_is_native()		(true)
-
-#define efi_table_attr(inst, attr)	(inst->attr)
-
-#define efi_call_proto(inst, func, ...) inst->func(inst, ##__VA_ARGS__)
-
 #define alloc_screen_info(x...)		&screen_info
 
 static inline void free_screen_info(struct screen_info *si)
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index b618017205a3..4f00d50585a4 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -114,7 +114,11 @@
 
 #ifndef __ASSEMBLY__
 
+#include <uapi/linux/elf.h>
 #include <linux/bug.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/types.h>
 #include <asm/processor.h> /* for signal_minsigstksz, used by ARCH_DLINFO */
 
 typedef unsigned long elf_greg_t;
@@ -224,6 +228,52 @@ extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
 
 #endif /* CONFIG_COMPAT */
 
+struct arch_elf_state {
+	int flags;
+};
+
+#define ARM64_ELF_BTI		(1 << 0)
+
+#define INIT_ARCH_ELF_STATE {			\
+	.flags = 0,				\
+}
+
+static inline int arch_parse_elf_property(u32 type, const void *data,
+					  size_t datasz, bool compat,
+					  struct arch_elf_state *arch)
+{
+	/* No known properties for AArch32 yet */
+	if (IS_ENABLED(CONFIG_COMPAT) && compat)
+		return 0;
+
+	if (type == GNU_PROPERTY_AARCH64_FEATURE_1_AND) {
+		const u32 *p = data;
+
+		if (datasz != sizeof(*p))
+			return -ENOEXEC;
+
+		if (system_supports_bti() &&
+		    (*p & GNU_PROPERTY_AARCH64_FEATURE_1_BTI))
+			arch->flags |= ARM64_ELF_BTI;
+	}
+
+	return 0;
+}
+
+static inline int arch_elf_pt_proc(void *ehdr, void *phdr,
+				   struct file *f, bool is_interp,
+				   struct arch_elf_state *state)
+{
+	return 0;
+}
+
+static inline int arch_check_elf(void *ehdr, bool has_interp,
+				 void *interp_ehdr,
+				 struct arch_elf_state *state)
+{
+	return 0;
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 6a395a7e6707..035003acfa87 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -22,7 +22,7 @@
 #define ESR_ELx_EC_PAC		(0x09)	/* EL2 and above */
 /* Unallocated EC: 0x0A - 0x0B */
 #define ESR_ELx_EC_CP14_64	(0x0C)
-/* Unallocated EC: 0x0d */
+#define ESR_ELx_EC_BTI		(0x0D)
 #define ESR_ELx_EC_ILL		(0x0E)
 /* Unallocated EC: 0x0F - 0x10 */
 #define ESR_ELx_EC_SVC32	(0x11)
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 7a6e81ca23a8..7577a754d443 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -34,6 +34,7 @@ static inline u32 disr_to_esr(u64 disr)
 asmlinkage void enter_from_user_mode(void);
 void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
 void do_undefinstr(struct pt_regs *regs);
+void do_bti(struct pt_regs *regs);
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr);
 void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
 			struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 87ad961f3c97..985493af704b 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -32,30 +32,70 @@ u64 smp_irq_stat_cpu(unsigned int cpu);
 
 struct nmi_ctx {
 	u64 hcr;
+	unsigned int cnt;
 };
 
 DECLARE_PER_CPU(struct nmi_ctx, nmi_contexts);
 
-#define arch_nmi_enter()							\
-	do {									\
-		if (is_kernel_in_hyp_mode()) {					\
-			struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts);	\
-			nmi_ctx->hcr = read_sysreg(hcr_el2);			\
-			if (!(nmi_ctx->hcr & HCR_TGE)) {			\
-				write_sysreg(nmi_ctx->hcr | HCR_TGE, hcr_el2);	\
-				isb();						\
-			}							\
-		}								\
-	} while (0)
+#define arch_nmi_enter()						\
+do {									\
+	struct nmi_ctx *___ctx;						\
+	u64 ___hcr;							\
+									\
+	if (!is_kernel_in_hyp_mode())					\
+		break;							\
+									\
+	___ctx = this_cpu_ptr(&nmi_contexts);				\
+	if (___ctx->cnt) {						\
+		___ctx->cnt++;						\
+		break;							\
+	}								\
+									\
+	___hcr = read_sysreg(hcr_el2);					\
+	if (!(___hcr & HCR_TGE)) {					\
+		write_sysreg(___hcr | HCR_TGE, hcr_el2);		\
+		isb();							\
+	}								\
+	/*								\
+	 * Make sure the sysreg write is performed before ___ctx->cnt	\
+	 * is set to 1. NMIs that see cnt == 1 will rely on us.		\
+	 */								\
+	barrier();							\
+	___ctx->cnt = 1;                                                \
+	/*								\
+	 * Make sure ___ctx->cnt is set before we save ___hcr. We	\
+	 * don't want ___ctx->hcr to be overwritten.			\
+	 */								\
+	barrier();							\
+	___ctx->hcr = ___hcr;						\
+} while (0)
 
-#define arch_nmi_exit()								\
-	do {									\
-		if (is_kernel_in_hyp_mode()) {					\
-			struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts);	\
-			if (!(nmi_ctx->hcr & HCR_TGE))				\
-				write_sysreg(nmi_ctx->hcr, hcr_el2);		\
-		}								\
-	} while (0)
+#define arch_nmi_exit()							\
+do {									\
+	struct nmi_ctx *___ctx;						\
+	u64 ___hcr;							\
+									\
+	if (!is_kernel_in_hyp_mode())					\
+		break;							\
+									\
+	___ctx = this_cpu_ptr(&nmi_contexts);				\
+	___hcr = ___ctx->hcr;						\
+	/*								\
+	 * Make sure we read ___ctx->hcr before we release		\
+	 * ___ctx->cnt as it makes ___ctx->hcr updatable again.		\
+	 */								\
+	barrier();							\
+	___ctx->cnt--;							\
+	/*								\
+	 * Make sure ___ctx->cnt release is visible before we		\
+	 * restore the sysreg. Otherwise a new NMI occurring		\
+	 * right after write_sysreg() can be fooled and think		\
+	 * we secured things for it.					\
+	 */								\
+	barrier();							\
+	if (!___ctx->cnt && !(___hcr & HCR_TGE))			\
+		write_sysreg(___hcr, hcr_el2);				\
+} while (0)
 
 static inline void ack_bad_irq(unsigned int irq)
 {
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 0f00265248b5..d683bcbf1e7c 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -94,6 +94,7 @@
 #define KERNEL_HWCAP_BF16		__khwcap2_feature(BF16)
 #define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
 #define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
+#define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index bb313dde58a4..0bc46149e491 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -39,13 +39,37 @@ enum aarch64_insn_encoding_class {
 					 * system instructions */
 };
 
-enum aarch64_insn_hint_op {
+enum aarch64_insn_hint_cr_op {
 	AARCH64_INSN_HINT_NOP	= 0x0 << 5,
 	AARCH64_INSN_HINT_YIELD	= 0x1 << 5,
 	AARCH64_INSN_HINT_WFE	= 0x2 << 5,
 	AARCH64_INSN_HINT_WFI	= 0x3 << 5,
 	AARCH64_INSN_HINT_SEV	= 0x4 << 5,
 	AARCH64_INSN_HINT_SEVL	= 0x5 << 5,
+
+	AARCH64_INSN_HINT_XPACLRI    = 0x07 << 5,
+	AARCH64_INSN_HINT_PACIA_1716 = 0x08 << 5,
+	AARCH64_INSN_HINT_PACIB_1716 = 0x0A << 5,
+	AARCH64_INSN_HINT_AUTIA_1716 = 0x0C << 5,
+	AARCH64_INSN_HINT_AUTIB_1716 = 0x0E << 5,
+	AARCH64_INSN_HINT_PACIAZ     = 0x18 << 5,
+	AARCH64_INSN_HINT_PACIASP    = 0x19 << 5,
+	AARCH64_INSN_HINT_PACIBZ     = 0x1A << 5,
+	AARCH64_INSN_HINT_PACIBSP    = 0x1B << 5,
+	AARCH64_INSN_HINT_AUTIAZ     = 0x1C << 5,
+	AARCH64_INSN_HINT_AUTIASP    = 0x1D << 5,
+	AARCH64_INSN_HINT_AUTIBZ     = 0x1E << 5,
+	AARCH64_INSN_HINT_AUTIBSP    = 0x1F << 5,
+
+	AARCH64_INSN_HINT_ESB  = 0x10 << 5,
+	AARCH64_INSN_HINT_PSB  = 0x11 << 5,
+	AARCH64_INSN_HINT_TSB  = 0x12 << 5,
+	AARCH64_INSN_HINT_CSDB = 0x14 << 5,
+
+	AARCH64_INSN_HINT_BTI   = 0x20 << 5,
+	AARCH64_INSN_HINT_BTIC  = 0x22 << 5,
+	AARCH64_INSN_HINT_BTIJ  = 0x24 << 5,
+	AARCH64_INSN_HINT_BTIJC = 0x26 << 5,
 };
 
 enum aarch64_insn_imm_type {
@@ -344,7 +368,7 @@ __AARCH64_INSN_FUNCS(msr_reg,	0xFFF00000, 0xD5100000)
 
 #undef	__AARCH64_INSN_FUNCS
 
-bool aarch64_insn_is_nop(u32 insn);
+bool aarch64_insn_is_steppable_hint(u32 insn);
 bool aarch64_insn_is_branch_imm(u32 insn);
 
 static inline bool aarch64_insn_is_adr_adrp(u32 insn)
@@ -370,7 +394,7 @@ u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
 				     enum aarch64_insn_branch_type type);
 u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
 				     enum aarch64_insn_condition cond);
-u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_op op);
+u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op);
 u32 aarch64_insn_gen_nop(void);
 u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
 				enum aarch64_insn_branch_type type);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index a30b4eec7cb4..6ea53e6e8b26 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -507,10 +507,12 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 
 static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
-	if (vcpu_mode_is_32bit(vcpu))
+	if (vcpu_mode_is_32bit(vcpu)) {
 		kvm_skip_instr32(vcpu, is_wide_instr);
-	else
+	} else {
 		*vcpu_pc(vcpu) += 4;
+		*vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK;
+	}
 
 	/* advance the singlestep state machine */
 	*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 32c8a675e5a4..57c0afcf9dcf 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -573,10 +573,6 @@ static inline bool kvm_arch_requires_vhe(void)
 	if (system_supports_sve())
 		return true;
 
-	/* Some implementations have defects that confine them to VHE */
-	if (cpus_have_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE))
-		return true;
-
 	return false;
 }
 
@@ -670,7 +666,7 @@ static inline int kvm_arm_have_ssbd(void)
 void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
 void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
 
-void kvm_set_ipa_limit(void);
+int kvm_set_ipa_limit(void);
 
 #define __KVM_HAVE_ARCH_VM_ALLOC
 struct kvm *kvm_arch_alloc_vm(void);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index fe57f60f06a8..015883671ec3 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -10,10 +10,9 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 #include <asm/alternative.h>
-#include <asm/kvm_mmu.h>
 #include <asm/sysreg.h>
 
-#define __hyp_text __section(.hyp.text) notrace
+#define __hyp_text __section(.hyp.text) notrace __noscs
 
 #define read_sysreg_elx(r,nvh,vh)					\
 	({								\
@@ -88,22 +87,5 @@ void deactivate_traps_vhe_put(void);
 u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
 void __noreturn __hyp_do_panic(unsigned long, ...);
 
-/*
- * Must be called from hyp code running at EL2 with an updated VTTBR
- * and interrupts disabled.
- */
-static __always_inline void __hyp_text __load_guest_stage2(struct kvm *kvm)
-{
-	write_sysreg(kvm->arch.vtcr, vtcr_el2);
-	write_sysreg(kvm_get_vttbr(kvm), vttbr_el2);
-
-	/*
-	 * ARM errata 1165522 and 1530923 require the actual execution of the
-	 * above before we can switch to the EL1/EL0 translation regime used by
-	 * the guest.
-	 */
-	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT_VHE));
-}
-
 #endif /* __ARM64_KVM_HYP_H__ */
 
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 30b0e8d6b895..85da6befe76e 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -416,7 +416,7 @@ static inline unsigned int kvm_get_vmid_bits(void)
 {
 	int reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
 
-	return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
+	return get_vmid_bits(reg);
 }
 
 /*
@@ -604,5 +604,22 @@ static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
 	return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
 }
 
+/*
+ * Must be called from hyp code running at EL2 with an updated VTTBR
+ * and interrupts disabled.
+ */
+static __always_inline void __load_guest_stage2(struct kvm *kvm)
+{
+	write_sysreg(kvm->arch.vtcr, vtcr_el2);
+	write_sysreg(kvm_get_vttbr(kvm), vttbr_el2);
+
+	/*
+	 * ARM errata 1165522 and 1530923 require the actual execution of the
+	 * above before we can switch to the EL1/EL0 translation regime used by
+	 * the guest.
+	 */
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
index ebee3113a62f..81fefd2a1d02 100644
--- a/arch/arm64/include/asm/linkage.h
+++ b/arch/arm64/include/asm/linkage.h
@@ -4,6 +4,52 @@
 #define __ALIGN		.align 2
 #define __ALIGN_STR	".align 2"
 
+#if defined(CONFIG_ARM64_BTI_KERNEL) && defined(__aarch64__)
+
+/*
+ * Since current versions of gas reject the BTI instruction unless we
+ * set the architecture version to v8.5 we use the hint instruction
+ * instead.
+ */
+#define BTI_C hint 34 ;
+#define BTI_J hint 36 ;
+
+/*
+ * When using in-kernel BTI we need to ensure that PCS-conformant assembly
+ * functions have suitable annotations.  Override SYM_FUNC_START to insert
+ * a BTI landing pad at the start of everything.
+ */
+#define SYM_FUNC_START(name)				\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
+	BTI_C
+
+#define SYM_FUNC_START_NOALIGN(name)			\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)	\
+	BTI_C
+
+#define SYM_FUNC_START_LOCAL(name)			\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)	\
+	BTI_C
+
+#define SYM_FUNC_START_LOCAL_NOALIGN(name)		\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)	\
+	BTI_C
+
+#define SYM_FUNC_START_WEAK(name)			\
+	SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)	\
+	BTI_C
+
+#define SYM_FUNC_START_WEAK_NOALIGN(name)		\
+	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
+	BTI_C
+
+#define SYM_INNER_LABEL(name, linkage)			\
+	.type name SYM_T_NONE ASM_NL			\
+	SYM_ENTRY(name, linkage, SYM_A_NONE)		\
+	BTI_J
+
+#endif
+
 /*
  * Annotate a function as position independent, i.e., safe to be called before
  * the kernel virtual mapping is activated.
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
new file mode 100644
index 000000000000..081ec8de9ea6
--- /dev/null
+++ b/arch/arm64/include/asm/mman.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <uapi/asm/mman.h>
+
+static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
+	unsigned long pkey __always_unused)
+{
+	if (system_supports_bti() && (prot & PROT_BTI))
+		return VM_ARM64_BTI;
+
+	return 0;
+}
+#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
+
+static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
+{
+	return (vm_flags & VM_ARM64_BTI) ? __pgprot(PTE_GP) : __pgprot(0);
+}
+#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
+
+static inline bool arch_validate_prot(unsigned long prot,
+	unsigned long addr __always_unused)
+{
+	unsigned long supported = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM;
+
+	if (system_supports_bti())
+		supported |= PROT_BTI;
+
+	return (prot & ~supported) == 0;
+}
+#define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr)
+
+#endif /* ! __ASM_MMAN_H__ */
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 1e93de68c044..4e7fa2623896 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -7,8 +7,6 @@
 
 #include <asm-generic/module.h>
 
-#define MODULE_ARCH_VERMAGIC	"aarch64"
-
 #ifdef CONFIG_ARM64_MODULE_PLTS
 struct mod_plt_sec {
 	int			plt_shndx;
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 6bf5e650da78..9c91a8f93a0e 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -151,6 +151,7 @@
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define PTE_AF			(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_NG			(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_GP			(_AT(pteval_t, 1) << 50)	/* BTI guarded */
 #define PTE_DBM			(_AT(pteval_t, 1) << 51)	/* Dirty Bit Management */
 #define PTE_CONT		(_AT(pteval_t, 1) << 52)	/* Contiguous range */
 #define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
@@ -190,7 +191,6 @@
  * Memory Attribute override for Stage-2 (MemAttr[3:0])
  */
 #define PTE_S2_MEMATTR(t)	(_AT(pteval_t, (t)) << 2)
-#define PTE_S2_MEMATTR_MASK	(_AT(pteval_t, 0xf) << 2)
 
 /*
  * EL2/HYP PTE/PMD definitions
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 1305e28225fc..2e7e0f452301 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -21,6 +21,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/cpufeature.h>
 #include <asm/pgtable-types.h>
 
 extern bool arm64_use_ng_mappings;
@@ -31,6 +32,16 @@ extern bool arm64_use_ng_mappings;
 #define PTE_MAYBE_NG		(arm64_use_ng_mappings ? PTE_NG : 0)
 #define PMD_MAYBE_NG		(arm64_use_ng_mappings ? PMD_SECT_NG : 0)
 
+/*
+ * If we have userspace only BTI we don't want to mark kernel pages
+ * guarded even if the system does support BTI.
+ */
+#ifdef CONFIG_ARM64_BTI_KERNEL
+#define PTE_MAYBE_GP		(system_supports_bti() ? PTE_GP : 0)
+#else
+#define PTE_MAYBE_GP		0
+#endif
+
 #define PROT_DEFAULT		(_PROT_DEFAULT | PTE_MAYBE_NG)
 #define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_MAYBE_NG)
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 538c85e62f86..e50e4dda90c2 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -457,6 +457,7 @@ extern pgd_t init_pg_dir[PTRS_PER_PGD];
 extern pgd_t init_pg_end[];
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t idmap_pg_end[];
 extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
 
 extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd);
@@ -508,7 +509,7 @@ static inline void pte_unmap(pte_t *pte) { }
 #define pte_set_fixmap_offset(pmd, addr)	pte_set_fixmap(pte_offset_phys(pmd, addr))
 #define pte_clear_fixmap()		clear_fixmap(FIX_PTE)
 
-#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(__pmd_to_phys(pmd)))
+#define pmd_page(pmd)			phys_to_page(__pmd_to_phys(pmd))
 
 /* use ONLY for statically allocated translation tables */
 #define pte_offset_kimg(dir,addr)	((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr))))
@@ -566,7 +567,7 @@ static inline phys_addr_t pud_page_paddr(pud_t pud)
 #define pmd_set_fixmap_offset(pud, addr)	pmd_set_fixmap(pmd_offset_phys(pud, addr))
 #define pmd_clear_fixmap()		clear_fixmap(FIX_PMD)
 
-#define pud_page(pud)		pfn_to_page(__phys_to_pfn(__pud_to_phys(pud)))
+#define pud_page(pud)			phys_to_page(__pud_to_phys(pud))
 
 /* use ONLY for statically allocated translation tables */
 #define pmd_offset_kimg(dir,addr)	((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr))))
@@ -624,7 +625,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
 #define pud_set_fixmap_offset(pgd, addr)	pud_set_fixmap(pud_offset_phys(pgd, addr))
 #define pud_clear_fixmap()		clear_fixmap(FIX_PUD)
 
-#define pgd_page(pgd)		pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd)))
+#define pgd_page(pgd)			phys_to_page(__pgd_to_phys(pgd))
 
 /* use ONLY for statically allocated translation tables */
 #define pud_offset_kimg(dir,addr)	((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr))))
@@ -660,7 +661,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
-			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE;
+			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
 		pte = pte_mkdirty(pte);
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 70c47156e54b..c6b4f0603024 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -47,7 +47,7 @@ static inline void ptrauth_keys_init_user(struct ptrauth_keys_user *keys)
 		get_random_bytes(&keys->apga, sizeof(keys->apga));
 }
 
-#define __ptrauth_key_install(k, v)				\
+#define __ptrauth_key_install_nosync(k, v)			\
 do {								\
 	struct ptrauth_key __pki_v = (v);			\
 	write_sysreg_s(__pki_v.lo, SYS_ ## k ## KEYLO_EL1);	\
@@ -62,8 +62,11 @@ static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel
 
 static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kernel *keys)
 {
-	if (system_supports_address_auth())
-		__ptrauth_key_install(APIA, keys->apia);
+	if (!system_supports_address_auth())
+		return;
+
+	__ptrauth_key_install_nosync(APIA, keys->apia);
+	isb();
 }
 
 extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index bf57308fcd63..2172ec7594ba 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -35,6 +35,7 @@
 #define GIC_PRIO_PSR_I_SET		(1 << 4)
 
 /* Additional SPSR bits not exposed in the UABI */
+
 #define PSR_IL_BIT		(1 << 20)
 
 /* AArch32-specific ptrace requests */
diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h
new file mode 100644
index 000000000000..eaa2cd92e4c1
--- /dev/null
+++ b/arch/arm64/include/asm/scs.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SCS_H
+#define _ASM_SCS_H
+
+#ifdef __ASSEMBLY__
+
+#include <asm/asm-offsets.h>
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+	scs_sp	.req	x18
+
+	.macro scs_load tsk, tmp
+	ldr	scs_sp, [\tsk, #TSK_TI_SCS_SP]
+	.endm
+
+	.macro scs_save tsk, tmp
+	str	scs_sp, [\tsk, #TSK_TI_SCS_SP]
+	.endm
+#else
+	.macro scs_load tsk, tmp
+	.endm
+
+	.macro scs_save tsk, tmp
+	.endm
+#endif /* CONFIG_SHADOW_CALL_STACK */
+
+#endif /* __ASSEMBLY __ */
+
+#endif /* _ASM_SCS_H */
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 40d5ba029615..ea268d88b6f7 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -23,14 +23,6 @@
 #define CPU_STUCK_REASON_52_BIT_VA	(UL(1) << CPU_STUCK_REASON_SHIFT)
 #define CPU_STUCK_REASON_NO_GRAN	(UL(2) << CPU_STUCK_REASON_SHIFT)
 
-/* Possible options for __cpu_setup */
-/* Option to setup primary cpu */
-#define ARM64_CPU_BOOT_PRIMARY		(1)
-/* Option to setup secondary cpus */
-#define ARM64_CPU_BOOT_SECONDARY	(2)
-/* Option to setup cpus for different cpu run time services */
-#define ARM64_CPU_RUNTIME		(3)
-
 #ifndef __ASSEMBLY__
 
 #include <asm/percpu.h>
@@ -96,9 +88,6 @@ asmlinkage void secondary_start_kernel(void);
 struct secondary_data {
 	void *stack;
 	struct task_struct *task;
-#ifdef CONFIG_ARM64_PTR_AUTH
-	struct ptrauth_keys_kernel ptrauth_key;
-#endif
 	long status;
 };
 
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 4d9b1f48dc39..5017b531a415 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -68,12 +68,10 @@ extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk);
 
 DECLARE_PER_CPU(unsigned long *, irq_stack_ptr);
 
-static inline bool on_irq_stack(unsigned long sp,
+static inline bool on_stack(unsigned long sp, unsigned long low,
+				unsigned long high, enum stack_type type,
 				struct stack_info *info)
 {
-	unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr);
-	unsigned long high = low + IRQ_STACK_SIZE;
-
 	if (!low)
 		return false;
 
@@ -83,12 +81,20 @@ static inline bool on_irq_stack(unsigned long sp,
 	if (info) {
 		info->low = low;
 		info->high = high;
-		info->type = STACK_TYPE_IRQ;
+		info->type = type;
 	}
-
 	return true;
 }
 
+static inline bool on_irq_stack(unsigned long sp,
+				struct stack_info *info)
+{
+	unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr);
+	unsigned long high = low + IRQ_STACK_SIZE;
+
+	return on_stack(sp, low, high, STACK_TYPE_IRQ, info);
+}
+
 static inline bool on_task_stack(const struct task_struct *tsk,
 				 unsigned long sp,
 				 struct stack_info *info)
@@ -96,16 +102,7 @@ static inline bool on_task_stack(const struct task_struct *tsk,
 	unsigned long low = (unsigned long)task_stack_page(tsk);
 	unsigned long high = low + THREAD_SIZE;
 
-	if (sp < low || sp >= high)
-		return false;
-
-	if (info) {
-		info->low = low;
-		info->high = high;
-		info->type = STACK_TYPE_TASK;
-	}
-
-	return true;
+	return on_stack(sp, low, high, STACK_TYPE_TASK, info);
 }
 
 #ifdef CONFIG_VMAP_STACK
@@ -117,16 +114,7 @@ static inline bool on_overflow_stack(unsigned long sp,
 	unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack);
 	unsigned long high = low + OVERFLOW_STACK_SIZE;
 
-	if (sp < low || sp >= high)
-		return false;
-
-	if (info) {
-		info->low = low;
-		info->high = high;
-		info->type = STACK_TYPE_OVERFLOW;
-	}
-
-	return true;
+	return on_stack(sp, low, high, STACK_TYPE_OVERFLOW, info);
 }
 #else
 static inline bool on_overflow_stack(unsigned long sp,
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index 8939c87c4dce..0cde2f473971 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_SUSPEND_H
 #define __ASM_SUSPEND_H
 
-#define NR_CTX_REGS 12
+#define NR_CTX_REGS 13
 #define NR_CALLEE_SAVED_REGS 12
 
 /*
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index ebc622432831..463175f80341 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -49,7 +49,9 @@
 #ifndef CONFIG_BROKEN_GAS_INST
 
 #ifdef __ASSEMBLY__
-#define __emit_inst(x)			.inst (x)
+// The space separator is omitted so that __emit_inst(x) can be parsed as
+// either an assembler directive or an assembler macro argument.
+#define __emit_inst(x)			.inst(x)
 #else
 #define __emit_inst(x)			".inst " __stringify((x)) "\n\t"
 #endif
@@ -103,6 +105,10 @@
 #define SYS_DC_CSW			sys_insn(1, 0, 7, 10, 2)
 #define SYS_DC_CISW			sys_insn(1, 0, 7, 14, 2)
 
+/*
+ * System registers, organised loosely by encoding but grouped together
+ * where the architected name contains an index. e.g. ID_MMFR<n>_EL1.
+ */
 #define SYS_OSDTRRX_EL1			sys_reg(2, 0, 0, 0, 2)
 #define SYS_MDCCINT_EL1			sys_reg(2, 0, 0, 2, 0)
 #define SYS_MDSCR_EL1			sys_reg(2, 0, 0, 2, 2)
@@ -132,12 +138,16 @@
 
 #define SYS_ID_PFR0_EL1			sys_reg(3, 0, 0, 1, 0)
 #define SYS_ID_PFR1_EL1			sys_reg(3, 0, 0, 1, 1)
+#define SYS_ID_PFR2_EL1			sys_reg(3, 0, 0, 3, 4)
 #define SYS_ID_DFR0_EL1			sys_reg(3, 0, 0, 1, 2)
+#define SYS_ID_DFR1_EL1			sys_reg(3, 0, 0, 3, 5)
 #define SYS_ID_AFR0_EL1			sys_reg(3, 0, 0, 1, 3)
 #define SYS_ID_MMFR0_EL1		sys_reg(3, 0, 0, 1, 4)
 #define SYS_ID_MMFR1_EL1		sys_reg(3, 0, 0, 1, 5)
 #define SYS_ID_MMFR2_EL1		sys_reg(3, 0, 0, 1, 6)
 #define SYS_ID_MMFR3_EL1		sys_reg(3, 0, 0, 1, 7)
+#define SYS_ID_MMFR4_EL1		sys_reg(3, 0, 0, 2, 6)
+#define SYS_ID_MMFR5_EL1		sys_reg(3, 0, 0, 3, 6)
 
 #define SYS_ID_ISAR0_EL1		sys_reg(3, 0, 0, 2, 0)
 #define SYS_ID_ISAR1_EL1		sys_reg(3, 0, 0, 2, 1)
@@ -145,7 +155,6 @@
 #define SYS_ID_ISAR3_EL1		sys_reg(3, 0, 0, 2, 3)
 #define SYS_ID_ISAR4_EL1		sys_reg(3, 0, 0, 2, 4)
 #define SYS_ID_ISAR5_EL1		sys_reg(3, 0, 0, 2, 5)
-#define SYS_ID_MMFR4_EL1		sys_reg(3, 0, 0, 2, 6)
 #define SYS_ID_ISAR6_EL1		sys_reg(3, 0, 0, 2, 7)
 
 #define SYS_MVFR0_EL1			sys_reg(3, 0, 0, 3, 0)
@@ -550,6 +559,8 @@
 #endif
 
 /* SCTLR_EL1 specific flags. */
+#define SCTLR_EL1_BT1		(BIT(36))
+#define SCTLR_EL1_BT0		(BIT(35))
 #define SCTLR_EL1_UCI		(BIT(26))
 #define SCTLR_EL1_E0E		(BIT(24))
 #define SCTLR_EL1_SPAN		(BIT(23))
@@ -592,6 +603,7 @@
 
 /* id_aa64isar0 */
 #define ID_AA64ISAR0_RNDR_SHIFT		60
+#define ID_AA64ISAR0_TLB_SHIFT		56
 #define ID_AA64ISAR0_TS_SHIFT		52
 #define ID_AA64ISAR0_FHM_SHIFT		48
 #define ID_AA64ISAR0_DP_SHIFT		44
@@ -635,6 +647,8 @@
 #define ID_AA64PFR0_CSV2_SHIFT		56
 #define ID_AA64PFR0_DIT_SHIFT		48
 #define ID_AA64PFR0_AMU_SHIFT		44
+#define ID_AA64PFR0_MPAM_SHIFT		40
+#define ID_AA64PFR0_SEL2_SHIFT		36
 #define ID_AA64PFR0_SVE_SHIFT		32
 #define ID_AA64PFR0_RAS_SHIFT		28
 #define ID_AA64PFR0_GIC_SHIFT		24
@@ -653,15 +667,21 @@
 #define ID_AA64PFR0_ASIMD_NI		0xf
 #define ID_AA64PFR0_ASIMD_SUPPORTED	0x0
 #define ID_AA64PFR0_EL1_64BIT_ONLY	0x1
+#define ID_AA64PFR0_EL1_32BIT_64BIT	0x2
 #define ID_AA64PFR0_EL0_64BIT_ONLY	0x1
 #define ID_AA64PFR0_EL0_32BIT_64BIT	0x2
 
 /* id_aa64pfr1 */
+#define ID_AA64PFR1_MPAMFRAC_SHIFT	16
+#define ID_AA64PFR1_RASFRAC_SHIFT	12
+#define ID_AA64PFR1_MTE_SHIFT		8
 #define ID_AA64PFR1_SSBS_SHIFT		4
+#define ID_AA64PFR1_BT_SHIFT		0
 
 #define ID_AA64PFR1_SSBS_PSTATE_NI	0
 #define ID_AA64PFR1_SSBS_PSTATE_ONLY	1
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
+#define ID_AA64PFR1_BT_BTI		0x1
 
 /* id_aa64zfr0 */
 #define ID_AA64ZFR0_F64MM_SHIFT		56
@@ -686,6 +706,9 @@
 #define ID_AA64ZFR0_SVEVER_SVE2		0x1
 
 /* id_aa64mmfr0 */
+#define ID_AA64MMFR0_TGRAN4_2_SHIFT	40
+#define ID_AA64MMFR0_TGRAN64_2_SHIFT	36
+#define ID_AA64MMFR0_TGRAN16_2_SHIFT	32
 #define ID_AA64MMFR0_TGRAN4_SHIFT	28
 #define ID_AA64MMFR0_TGRAN64_SHIFT	24
 #define ID_AA64MMFR0_TGRAN16_SHIFT	20
@@ -750,6 +773,25 @@
 
 #define ID_DFR0_PERFMON_8_1		0x4
 
+#define ID_ISAR4_SWP_FRAC_SHIFT		28
+#define ID_ISAR4_PSR_M_SHIFT		24
+#define ID_ISAR4_SYNCH_PRIM_FRAC_SHIFT	20
+#define ID_ISAR4_BARRIER_SHIFT		16
+#define ID_ISAR4_SMC_SHIFT		12
+#define ID_ISAR4_WRITEBACK_SHIFT	8
+#define ID_ISAR4_WITHSHIFTS_SHIFT	4
+#define ID_ISAR4_UNPRIV_SHIFT		0
+
+#define ID_DFR1_MTPMU_SHIFT		0
+
+#define ID_ISAR0_DIVIDE_SHIFT		24
+#define ID_ISAR0_DEBUG_SHIFT		20
+#define ID_ISAR0_COPROC_SHIFT		16
+#define ID_ISAR0_CMPBRANCH_SHIFT	12
+#define ID_ISAR0_BITFIELD_SHIFT		8
+#define ID_ISAR0_BITCOUNT_SHIFT		4
+#define ID_ISAR0_SWAP_SHIFT		0
+
 #define ID_ISAR5_RDM_SHIFT		24
 #define ID_ISAR5_CRC32_SHIFT		16
 #define ID_ISAR5_SHA2_SHIFT		12
@@ -765,6 +807,22 @@
 #define ID_ISAR6_DP_SHIFT		4
 #define ID_ISAR6_JSCVT_SHIFT		0
 
+#define ID_MMFR4_EVT_SHIFT		28
+#define ID_MMFR4_CCIDX_SHIFT		24
+#define ID_MMFR4_LSM_SHIFT		20
+#define ID_MMFR4_HPDS_SHIFT		16
+#define ID_MMFR4_CNP_SHIFT		12
+#define ID_MMFR4_XNX_SHIFT		8
+#define ID_MMFR4_SPECSEI_SHIFT		0
+
+#define ID_MMFR5_ETS_SHIFT		0
+
+#define ID_PFR0_DIT_SHIFT		24
+#define ID_PFR0_CSV2_SHIFT		16
+
+#define ID_PFR2_SSBS_SHIFT		4
+#define ID_PFR2_CSV3_SHIFT		0
+
 #define MVFR0_FPROUND_SHIFT		28
 #define MVFR0_FPSHVEC_SHIFT		24
 #define MVFR0_FPSQRT_SHIFT		20
@@ -783,17 +841,14 @@
 #define MVFR1_FPDNAN_SHIFT		4
 #define MVFR1_FPFTZ_SHIFT		0
 
-
-#define ID_AA64MMFR0_TGRAN4_SHIFT	28
-#define ID_AA64MMFR0_TGRAN64_SHIFT	24
-#define ID_AA64MMFR0_TGRAN16_SHIFT	20
-
-#define ID_AA64MMFR0_TGRAN4_NI		0xf
-#define ID_AA64MMFR0_TGRAN4_SUPPORTED	0x0
-#define ID_AA64MMFR0_TGRAN64_NI		0xf
-#define ID_AA64MMFR0_TGRAN64_SUPPORTED	0x0
-#define ID_AA64MMFR0_TGRAN16_NI		0x0
-#define ID_AA64MMFR0_TGRAN16_SUPPORTED	0x1
+#define ID_PFR1_GIC_SHIFT		28
+#define ID_PFR1_VIRT_FRAC_SHIFT		24
+#define ID_PFR1_SEC_FRAC_SHIFT		20
+#define ID_PFR1_GENTIMER_SHIFT		16
+#define ID_PFR1_VIRTUALIZATION_SHIFT	12
+#define ID_PFR1_MPROGMOD_SHIFT		8
+#define ID_PFR1_SECURITY_SHIFT		4
+#define ID_PFR1_PROGMOD_SHIFT		0
 
 #if defined(CONFIG_ARM64_4K_PAGES)
 #define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN4_SHIFT
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 512174a8e789..6ea8b6a26ae9 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -41,6 +41,10 @@ struct thread_info {
 #endif
 		} preempt;
 	};
+#ifdef CONFIG_SHADOW_CALL_STACK
+	void			*scs_base;
+	void			*scs_sp;
+#endif
 };
 
 #define thread_saved_pc(tsk)	\
@@ -100,11 +104,20 @@ void arch_release_task_struct(struct task_struct *tsk);
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
 				 _TIF_SYSCALL_EMU)
 
+#ifdef CONFIG_SHADOW_CALL_STACK
+#define INIT_SCS							\
+	.scs_base	= init_shadow_call_stack,			\
+	.scs_sp		= init_shadow_call_stack,
+#else
+#define INIT_SCS
+#endif
+
 #define INIT_THREAD_INFO(tsk)						\
 {									\
 	.flags		= _TIF_FOREIGN_FPSTATE,				\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
+	INIT_SCS							\
 }
 
 #endif /* __ASM_THREAD_INFO_H */
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 32fc8061aa76..bc5c7b091152 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -304,7 +304,7 @@ do {									\
 		__p = uaccess_mask_ptr(__p);				\
 		__raw_get_user((x), __p, (err));			\
 	} else {							\
-		(x) = 0; (err) = -EFAULT;				\
+		(x) = (__force __typeof__(x))0; (err) = -EFAULT;	\
 	}								\
 } while (0)
 
diff --git a/arch/arm64/include/asm/vermagic.h b/arch/arm64/include/asm/vermagic.h
new file mode 100644
index 000000000000..a1eec6a000f1
--- /dev/null
+++ b/arch/arm64/include/asm/vermagic.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#define MODULE_ARCH_VERMAGIC	"aarch64"
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 7752d93bb50f..2d6ba1c2592e 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -73,5 +73,6 @@
 #define HWCAP2_BF16		(1 << 14)
 #define HWCAP2_DGH		(1 << 15)
 #define HWCAP2_RNG		(1 << 16)
+#define HWCAP2_BTI		(1 << 17)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/mman.h b/arch/arm64/include/uapi/asm/mman.h
new file mode 100644
index 000000000000..6fdd71eb644f
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/mman.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__ASM_MMAN_H
+#define _UAPI__ASM_MMAN_H
+
+#include <asm-generic/mman.h>
+
+#define PROT_BTI	0x10		/* BTI guarded page */
+
+#endif /* ! _UAPI__ASM_MMAN_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index d1bb5b69f1ce..42cbe34d95ce 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -46,6 +46,7 @@
 #define PSR_I_BIT	0x00000080
 #define PSR_A_BIT	0x00000100
 #define PSR_D_BIT	0x00000200
+#define PSR_BTYPE_MASK	0x00000c00
 #define PSR_SSBS_BIT	0x00001000
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
@@ -55,6 +56,8 @@
 #define PSR_Z_BIT	0x40000000
 #define PSR_N_BIT	0x80000000
 
+#define PSR_BTYPE_SHIFT		10
+
 /*
  * Groups of PSR bits
  */
@@ -63,6 +66,12 @@
 #define PSR_x		0x0000ff00	/* Extension		*/
 #define PSR_c		0x000000ff	/* Control		*/
 
+/* Convenience names for the values of PSTATE.BTYPE */
+#define PSR_BTYPE_NONE		(0b00 << PSR_BTYPE_SHIFT)
+#define PSR_BTYPE_JC		(0b01 << PSR_BTYPE_SHIFT)
+#define PSR_BTYPE_C		(0b10 << PSR_BTYPE_SHIFT)
+#define PSR_BTYPE_J		(0b11 << PSR_BTYPE_SHIFT)
+
 /* syscall emulation path in ptrace */
 #define PTRACE_SYSEMU		  31
 #define PTRACE_SYSEMU_SINGLESTEP  32
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 4e5b8ee31442..151f28521f1e 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_CRASH_CORE)		+= crash_core.o
 obj-$(CONFIG_ARM_SDE_INTERFACE)		+= sdei.o
 obj-$(CONFIG_ARM64_SSBD)		+= ssbd.o
 obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
+obj-$(CONFIG_SHADOW_CALL_STACK)		+= scs.o
 
 obj-y					+= vdso/ probes/
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32/
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 9981a0a5a87f..3539d7092612 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -34,6 +34,10 @@ int main(void)
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
   DEFINE(TSK_TI_TTBR0,		offsetof(struct task_struct, thread_info.ttbr0));
 #endif
+#ifdef CONFIG_SHADOW_CALL_STACK
+  DEFINE(TSK_TI_SCS_BASE,	offsetof(struct task_struct, thread_info.scs_base));
+  DEFINE(TSK_TI_SCS_SP,		offsetof(struct task_struct, thread_info.scs_sp));
+#endif
   DEFINE(TSK_STACK,		offsetof(struct task_struct, stack));
 #ifdef CONFIG_STACKPROTECTOR
   DEFINE(TSK_STACK_CANARY,	offsetof(struct task_struct, stack_canary));
@@ -92,9 +96,6 @@ int main(void)
   BLANK();
   DEFINE(CPU_BOOT_STACK,	offsetof(struct secondary_data, stack));
   DEFINE(CPU_BOOT_TASK,		offsetof(struct secondary_data, task));
-#ifdef CONFIG_ARM64_PTR_AUTH
-  DEFINE(CPU_BOOT_PTRAUTH_KEY,	offsetof(struct secondary_data, ptrauth_key));
-#endif
   BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
   DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 38087b4c0432..4a18055b2ff9 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -29,7 +29,7 @@
  * branch to what would be the reset vector. It must be executed with the
  * flat identity mapping.
  */
-ENTRY(__cpu_soft_restart)
+SYM_CODE_START(__cpu_soft_restart)
 	/* Clear sctlr_el1 flags. */
 	mrs	x12, sctlr_el1
 	mov_q	x13, SCTLR_ELx_FLAGS
@@ -47,6 +47,6 @@ ENTRY(__cpu_soft_restart)
 	mov	x1, x3				// arg1
 	mov	x2, x4				// arg2
 	br	x8
-ENDPROC(__cpu_soft_restart)
+SYM_CODE_END(__cpu_soft_restart)
 
 .popsection
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index df56d2295d16..b0ce6bf14f6a 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -635,7 +635,7 @@ has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
 	return is_midr_in_range(midr, &range) && has_dic;
 }
 
-#if defined(CONFIG_HARDEN_EL2_VECTORS) || defined(CONFIG_ARM64_ERRATUM_1319367)
+#if defined(CONFIG_HARDEN_EL2_VECTORS)
 
 static const struct midr_range ca57_a72[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
@@ -757,12 +757,16 @@ static const struct arm64_cpu_capabilities erratum_843419_list[] = {
 };
 #endif
 
-#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT_VHE
-static const struct midr_range erratum_speculative_at_vhe_list[] = {
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT
+static const struct midr_range erratum_speculative_at_list[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1165522
 	/* Cortex A76 r0p0 to r2p0 */
 	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_1319367
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_1530923
 	/* Cortex A55 r0p0 to r2p0 */
 	MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 2, 0),
@@ -774,7 +778,7 @@ static const struct midr_range erratum_speculative_at_vhe_list[] = {
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
-		.desc = "ARM errata 826319, 827319, 824069, 819472",
+		.desc = "ARM errata 826319, 827319, 824069, or 819472",
 		.capability = ARM64_WORKAROUND_CLEAN_CACHE,
 		ERRATA_MIDR_RANGE_LIST(workaround_clean_cache),
 		.cpu_enable = cpu_enable_cache_maint_trap,
@@ -856,7 +860,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 #endif
 #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
 	{
-		.desc = "Qualcomm erratum 1009, ARM erratum 1286807",
+		.desc = "Qualcomm erratum 1009, or ARM erratum 1286807",
 		.capability = ARM64_WORKAROUND_REPEAT_TLBI,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = cpucap_multi_entry_cap_matches,
@@ -897,11 +901,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(erratum_1418040_list),
 	},
 #endif
-#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT_VHE
+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT
 	{
-		.desc = "ARM errata 1165522, 1530923",
-		.capability = ARM64_WORKAROUND_SPECULATIVE_AT_VHE,
-		ERRATA_MIDR_RANGE_LIST(erratum_speculative_at_vhe_list),
+		.desc = "ARM errata 1165522, 1319367, or 1530923",
+		.capability = ARM64_WORKAROUND_SPECULATIVE_AT,
+		ERRATA_MIDR_RANGE_LIST(erratum_speculative_at_list),
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_1463225
@@ -935,13 +939,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.cpu_enable = cpu_enable_trap_ctr_access,
 	},
 #endif
-#ifdef CONFIG_ARM64_ERRATUM_1319367
-	{
-		.desc = "ARM erratum 1319367",
-		.capability = ARM64_WORKAROUND_SPECULATIVE_AT_NVHE,
-		ERRATA_MIDR_RANGE_LIST(ca57_a72),
-	},
-#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 9fac745aa7bb..4ae41670c2e6 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -3,6 +3,61 @@
  * Contains CPU feature definitions
  *
  * Copyright (C) 2015 ARM Ltd.
+ *
+ * A note for the weary kernel hacker: the code here is confusing and hard to
+ * follow! That's partly because it's solving a nasty problem, but also because
+ * there's a little bit of over-abstraction that tends to obscure what's going
+ * on behind a maze of helper functions and macros.
+ *
+ * The basic problem is that hardware folks have started gluing together CPUs
+ * with distinct architectural features; in some cases even creating SoCs where
+ * user-visible instructions are available only on a subset of the available
+ * cores. We try to address this by snapshotting the feature registers of the
+ * boot CPU and comparing these with the feature registers of each secondary
+ * CPU when bringing them up. If there is a mismatch, then we update the
+ * snapshot state to indicate the lowest-common denominator of the feature,
+ * known as the "safe" value. This snapshot state can be queried to view the
+ * "sanitised" value of a feature register.
+ *
+ * The sanitised register values are used to decide which capabilities we
+ * have in the system. These may be in the form of traditional "hwcaps"
+ * advertised to userspace or internal "cpucaps" which are used to configure
+ * things like alternative patching and static keys. While a feature mismatch
+ * may result in a TAINT_CPU_OUT_OF_SPEC kernel taint, a capability mismatch
+ * may prevent a CPU from being onlined at all.
+ *
+ * Some implementation details worth remembering:
+ *
+ * - Mismatched features are *always* sanitised to a "safe" value, which
+ *   usually indicates that the feature is not supported.
+ *
+ * - A mismatched feature marked with FTR_STRICT will cause a "SANITY CHECK"
+ *   warning when onlining an offending CPU and the kernel will be tainted
+ *   with TAINT_CPU_OUT_OF_SPEC.
+ *
+ * - Features marked as FTR_VISIBLE have their sanitised value visible to
+ *   userspace. FTR_VISIBLE features in registers that are only visible
+ *   to EL0 by trapping *must* have a corresponding HWCAP so that late
+ *   onlining of CPUs cannot lead to features disappearing at runtime.
+ *
+ * - A "feature" is typically a 4-bit register field. A "capability" is the
+ *   high-level description derived from the sanitised field value.
+ *
+ * - Read the Arm ARM (DDI 0487F.a) section D13.1.3 ("Principles of the ID
+ *   scheme for fields in ID registers") to understand when feature fields
+ *   may be signed or unsigned (FTR_SIGNED and FTR_UNSIGNED accordingly).
+ *
+ * - KVM exposes its own view of the feature registers to guest operating
+ *   systems regardless of FTR_VISIBLE. This is typically driven from the
+ *   sanitised register values to allow virtual CPUs to be migrated between
+ *   arbitrary physical CPUs, but some features not present on the host are
+ *   also advertised and emulated. Look at sys_reg_descs[] for the gory
+ *   details.
+ *
+ * - If the arm64_ftr_bits[] for a register has a missing field, then this
+ *   field is treated as STRICT RES0, including for read_sanitised_ftr_reg().
+ *   This is stronger than FTR_HIDDEN and can be used to hide features from
+ *   KVM guests.
  */
 
 #define pr_fmt(fmt) "CPU features: " fmt
@@ -124,6 +179,7 @@ static bool __system_matches_cap(unsigned int n);
  */
 static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RNDR_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TLB_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0),
@@ -166,22 +222,27 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_DIT_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_AMU_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_MPAM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SEL2_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 				   FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_RAS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
 	S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
-	/* Linux doesn't care about the EL3 */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
 	ARM64_FTR_END,
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_BTI),
+				    FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_BT_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -209,6 +270,24 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	/*
+	 * Page size not being supported at Stage-2 is not fatal. You
+	 * just give up KVM if PAGE_SIZE isn't supported there. Go fix
+	 * your favourite nesting hypervisor.
+	 *
+	 * There is a small corner case where the hypervisor explicitly
+	 * advertises a given granule size at Stage-2 (value 2) on some
+	 * vCPUs, and uses the fallback to Stage-1 (value 0) for other
+	 * vCPUs. Although this is not forbidden by the architecture, it
+	 * indicates that the hypervisor is being silly (or buggy).
+	 *
+	 * We make no effort to cope with this and pretend that if these
+	 * fields are inconsistent across vCPUs, then it isn't worth
+	 * trying to bring KVM up.
+	 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_2_SHIFT, 4, 1),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_2_SHIFT, 4, 1),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_2_SHIFT, 4, 1),
+	/*
 	 * We already refuse to boot CPUs that don't support our configured
 	 * page size, so we can only detect mismatches for a page size other
 	 * than the one we're currently using. Unfortunately, SoCs like this
@@ -247,7 +326,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_UAO_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CNP_SHIFT, 4, 0),
@@ -289,7 +368,7 @@ static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 36, 28, 0),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 36, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64DFR0_PMSVER_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
@@ -316,6 +395,16 @@ static const struct arm64_ftr_bits ftr_dczid[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_id_isar0[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_DIVIDE_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_DEBUG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_COPROC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_CMPBRANCH_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_BITFIELD_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_BITCOUNT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_SWAP_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
 
 static const struct arm64_ftr_bits ftr_id_isar5[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0),
@@ -328,7 +417,37 @@ static const struct arm64_ftr_bits ftr_id_isar5[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EVT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_CCIDX_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_LSM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_HPDS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_CNP_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_XNX_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),	/* ac2 */
+	/*
+	 * SpecSEI = 1 indicates that the PE might generate an SError on an
+	 * external abort on speculative read. It is safe to assume that an
+	 * SError might be generated than it will not be. Hence it has been
+	 * classified as FTR_HIGHER_SAFE.
+	 */
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_MMFR4_SPECSEI_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
+static const struct arm64_ftr_bits ftr_id_isar4[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_SWP_FRAC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_PSR_M_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_SYNCH_PRIM_FRAC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_BARRIER_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_SMC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_WRITEBACK_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_WITHSHIFTS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_UNPRIV_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
+static const struct arm64_ftr_bits ftr_id_mmfr5[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR5_ETS_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -344,6 +463,8 @@ static const struct arm64_ftr_bits ftr_id_isar6[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_pfr0[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_DIT_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR0_CSV2_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0),		/* State3 */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0),		/* State2 */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),		/* State1 */
@@ -351,8 +472,26 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_id_pfr1[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_GIC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_VIRT_FRAC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_SEC_FRAC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_GENTIMER_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_VIRTUALIZATION_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_MPROGMOD_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_SECURITY_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_PROGMOD_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
+static const struct arm64_ftr_bits ftr_id_pfr2[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR2_SSBS_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_CSV3_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_dfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
+	/* [31:28] TraceFilt */
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf),	/* PerfMon */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),
@@ -363,6 +502,11 @@ static const struct arm64_ftr_bits ftr_id_dfr0[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_id_dfr1[] = {
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR1_MTPMU_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_zcr[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
 		ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_SIZE, 0),	/* LEN */
@@ -373,7 +517,7 @@ static const struct arm64_ftr_bits ftr_zcr[] = {
  * Common ftr bits for a 32bit register with all hidden, strict
  * attributes, with 4bit feature fields and a default safe value of
  * 0. Covers the following 32bit registers:
- * id_isar[0-4], id_mmfr[1-3], id_pfr1, mvfr[0-1]
+ * id_isar[1-4], id_mmfr[1-3], id_pfr1, mvfr[0-1]
  */
 static const struct arm64_ftr_bits ftr_generic_32bits[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
@@ -411,7 +555,7 @@ static const struct __ftr_reg_entry {
 
 	/* Op1 = 0, CRn = 0, CRm = 1 */
 	ARM64_FTR_REG(SYS_ID_PFR0_EL1, ftr_id_pfr0),
-	ARM64_FTR_REG(SYS_ID_PFR1_EL1, ftr_generic_32bits),
+	ARM64_FTR_REG(SYS_ID_PFR1_EL1, ftr_id_pfr1),
 	ARM64_FTR_REG(SYS_ID_DFR0_EL1, ftr_id_dfr0),
 	ARM64_FTR_REG(SYS_ID_MMFR0_EL1, ftr_id_mmfr0),
 	ARM64_FTR_REG(SYS_ID_MMFR1_EL1, ftr_generic_32bits),
@@ -419,11 +563,11 @@ static const struct __ftr_reg_entry {
 	ARM64_FTR_REG(SYS_ID_MMFR3_EL1, ftr_generic_32bits),
 
 	/* Op1 = 0, CRn = 0, CRm = 2 */
-	ARM64_FTR_REG(SYS_ID_ISAR0_EL1, ftr_generic_32bits),
+	ARM64_FTR_REG(SYS_ID_ISAR0_EL1, ftr_id_isar0),
 	ARM64_FTR_REG(SYS_ID_ISAR1_EL1, ftr_generic_32bits),
 	ARM64_FTR_REG(SYS_ID_ISAR2_EL1, ftr_generic_32bits),
 	ARM64_FTR_REG(SYS_ID_ISAR3_EL1, ftr_generic_32bits),
-	ARM64_FTR_REG(SYS_ID_ISAR4_EL1, ftr_generic_32bits),
+	ARM64_FTR_REG(SYS_ID_ISAR4_EL1, ftr_id_isar4),
 	ARM64_FTR_REG(SYS_ID_ISAR5_EL1, ftr_id_isar5),
 	ARM64_FTR_REG(SYS_ID_MMFR4_EL1, ftr_id_mmfr4),
 	ARM64_FTR_REG(SYS_ID_ISAR6_EL1, ftr_id_isar6),
@@ -432,6 +576,9 @@ static const struct __ftr_reg_entry {
 	ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits),
 	ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_generic_32bits),
 	ARM64_FTR_REG(SYS_MVFR2_EL1, ftr_mvfr2),
+	ARM64_FTR_REG(SYS_ID_PFR2_EL1, ftr_id_pfr2),
+	ARM64_FTR_REG(SYS_ID_DFR1_EL1, ftr_id_dfr1),
+	ARM64_FTR_REG(SYS_ID_MMFR5_EL1, ftr_id_mmfr5),
 
 	/* Op1 = 0, CRn = 0, CRm = 4 */
 	ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
@@ -468,16 +615,16 @@ static int search_cmp_ftr_reg(const void *id, const void *regp)
 }
 
 /*
- * get_arm64_ftr_reg - Lookup a feature register entry using its
- * sys_reg() encoding. With the array arm64_ftr_regs sorted in the
- * ascending order of sys_id , we use binary search to find a matching
+ * get_arm64_ftr_reg_nowarn - Looks up a feature register entry using
+ * its sys_reg() encoding. With the array arm64_ftr_regs sorted in the
+ * ascending order of sys_id, we use binary search to find a matching
  * entry.
  *
  * returns - Upon success,  matching ftr_reg entry for id.
  *         - NULL on failure. It is upto the caller to decide
  *	     the impact of a failure.
  */
-static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id)
+static struct arm64_ftr_reg *get_arm64_ftr_reg_nowarn(u32 sys_id)
 {
 	const struct __ftr_reg_entry *ret;
 
@@ -491,6 +638,27 @@ static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id)
 	return NULL;
 }
 
+/*
+ * get_arm64_ftr_reg - Looks up a feature register entry using
+ * its sys_reg() encoding. This calls get_arm64_ftr_reg_nowarn().
+ *
+ * returns - Upon success,  matching ftr_reg entry for id.
+ *         - NULL on failure but with an WARN_ON().
+ */
+static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id)
+{
+	struct arm64_ftr_reg *reg;
+
+	reg = get_arm64_ftr_reg_nowarn(sys_id);
+
+	/*
+	 * Requesting a non-existent register search is an error. Warn
+	 * and let the caller handle it.
+	 */
+	WARN_ON(!reg);
+	return reg;
+}
+
 static u64 arm64_ftr_set_value(const struct arm64_ftr_bits *ftrp, s64 reg,
 			       s64 ftr_val)
 {
@@ -552,7 +720,8 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new)
 	const struct arm64_ftr_bits *ftrp;
 	struct arm64_ftr_reg *reg = get_arm64_ftr_reg(sys_reg);
 
-	BUG_ON(!reg);
+	if (!reg)
+		return;
 
 	for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) {
 		u64 ftr_mask = arm64_ftr_mask(ftrp);
@@ -625,6 +794,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
 		init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
+		init_cpu_ftr_reg(SYS_ID_DFR1_EL1, info->reg_id_dfr1);
 		init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0);
 		init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1);
 		init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2);
@@ -636,8 +806,11 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 		init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1);
 		init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2);
 		init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3);
+		init_cpu_ftr_reg(SYS_ID_MMFR4_EL1, info->reg_id_mmfr4);
+		init_cpu_ftr_reg(SYS_ID_MMFR5_EL1, info->reg_id_mmfr5);
 		init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0);
 		init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1);
+		init_cpu_ftr_reg(SYS_ID_PFR2_EL1, info->reg_id_pfr2);
 		init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0);
 		init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1);
 		init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
@@ -682,7 +855,9 @@ static int check_update_ftr_reg(u32 sys_id, int cpu, u64 val, u64 boot)
 {
 	struct arm64_ftr_reg *regp = get_arm64_ftr_reg(sys_id);
 
-	BUG_ON(!regp);
+	if (!regp)
+		return 0;
+
 	update_cpu_ftr_reg(regp, val);
 	if ((boot & regp->strict_mask) == (val & regp->strict_mask))
 		return 0;
@@ -691,6 +866,104 @@ static int check_update_ftr_reg(u32 sys_id, int cpu, u64 val, u64 boot)
 	return 1;
 }
 
+static void relax_cpu_ftr_reg(u32 sys_id, int field)
+{
+	const struct arm64_ftr_bits *ftrp;
+	struct arm64_ftr_reg *regp = get_arm64_ftr_reg(sys_id);
+
+	if (!regp)
+		return;
+
+	for (ftrp = regp->ftr_bits; ftrp->width; ftrp++) {
+		if (ftrp->shift == field) {
+			regp->strict_mask &= ~arm64_ftr_mask(ftrp);
+			break;
+		}
+	}
+
+	/* Bogus field? */
+	WARN_ON(!ftrp->width);
+}
+
+static int update_32bit_cpu_features(int cpu, struct cpuinfo_arm64 *info,
+				     struct cpuinfo_arm64 *boot)
+{
+	int taint = 0;
+	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	/*
+	 * If we don't have AArch32 at all then skip the checks entirely
+	 * as the register values may be UNKNOWN and we're not going to be
+	 * using them for anything.
+	 */
+	if (!id_aa64pfr0_32bit_el0(pfr0))
+		return taint;
+
+	/*
+	 * If we don't have AArch32 at EL1, then relax the strictness of
+	 * EL1-dependent register fields to avoid spurious sanity check fails.
+	 */
+	if (!id_aa64pfr0_32bit_el1(pfr0)) {
+		relax_cpu_ftr_reg(SYS_ID_ISAR4_EL1, ID_ISAR4_SMC_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_VIRT_FRAC_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_SEC_FRAC_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_VIRTUALIZATION_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_SECURITY_SHIFT);
+		relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_PROGMOD_SHIFT);
+	}
+
+	taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu,
+				      info->reg_id_dfr0, boot->reg_id_dfr0);
+	taint |= check_update_ftr_reg(SYS_ID_DFR1_EL1, cpu,
+				      info->reg_id_dfr1, boot->reg_id_dfr1);
+	taint |= check_update_ftr_reg(SYS_ID_ISAR0_EL1, cpu,
+				      info->reg_id_isar0, boot->reg_id_isar0);
+	taint |= check_update_ftr_reg(SYS_ID_ISAR1_EL1, cpu,
+				      info->reg_id_isar1, boot->reg_id_isar1);
+	taint |= check_update_ftr_reg(SYS_ID_ISAR2_EL1, cpu,
+				      info->reg_id_isar2, boot->reg_id_isar2);
+	taint |= check_update_ftr_reg(SYS_ID_ISAR3_EL1, cpu,
+				      info->reg_id_isar3, boot->reg_id_isar3);
+	taint |= check_update_ftr_reg(SYS_ID_ISAR4_EL1, cpu,
+				      info->reg_id_isar4, boot->reg_id_isar4);
+	taint |= check_update_ftr_reg(SYS_ID_ISAR5_EL1, cpu,
+				      info->reg_id_isar5, boot->reg_id_isar5);
+	taint |= check_update_ftr_reg(SYS_ID_ISAR6_EL1, cpu,
+				      info->reg_id_isar6, boot->reg_id_isar6);
+
+	/*
+	 * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and
+	 * ACTLR formats could differ across CPUs and therefore would have to
+	 * be trapped for virtualization anyway.
+	 */
+	taint |= check_update_ftr_reg(SYS_ID_MMFR0_EL1, cpu,
+				      info->reg_id_mmfr0, boot->reg_id_mmfr0);
+	taint |= check_update_ftr_reg(SYS_ID_MMFR1_EL1, cpu,
+				      info->reg_id_mmfr1, boot->reg_id_mmfr1);
+	taint |= check_update_ftr_reg(SYS_ID_MMFR2_EL1, cpu,
+				      info->reg_id_mmfr2, boot->reg_id_mmfr2);
+	taint |= check_update_ftr_reg(SYS_ID_MMFR3_EL1, cpu,
+				      info->reg_id_mmfr3, boot->reg_id_mmfr3);
+	taint |= check_update_ftr_reg(SYS_ID_MMFR4_EL1, cpu,
+				      info->reg_id_mmfr4, boot->reg_id_mmfr4);
+	taint |= check_update_ftr_reg(SYS_ID_MMFR5_EL1, cpu,
+				      info->reg_id_mmfr5, boot->reg_id_mmfr5);
+	taint |= check_update_ftr_reg(SYS_ID_PFR0_EL1, cpu,
+				      info->reg_id_pfr0, boot->reg_id_pfr0);
+	taint |= check_update_ftr_reg(SYS_ID_PFR1_EL1, cpu,
+				      info->reg_id_pfr1, boot->reg_id_pfr1);
+	taint |= check_update_ftr_reg(SYS_ID_PFR2_EL1, cpu,
+				      info->reg_id_pfr2, boot->reg_id_pfr2);
+	taint |= check_update_ftr_reg(SYS_MVFR0_EL1, cpu,
+				      info->reg_mvfr0, boot->reg_mvfr0);
+	taint |= check_update_ftr_reg(SYS_MVFR1_EL1, cpu,
+				      info->reg_mvfr1, boot->reg_mvfr1);
+	taint |= check_update_ftr_reg(SYS_MVFR2_EL1, cpu,
+				      info->reg_mvfr2, boot->reg_mvfr2);
+
+	return taint;
+}
+
 /*
  * Update system wide CPU feature registers with the values from a
  * non-boot CPU. Also performs SANITY checks to make sure that there
@@ -753,9 +1026,6 @@ void update_cpu_features(int cpu,
 	taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu,
 				      info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2);
 
-	/*
-	 * EL3 is not our concern.
-	 */
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu,
 				      info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0);
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu,
@@ -764,55 +1034,6 @@ void update_cpu_features(int cpu,
 	taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu,
 				      info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0);
 
-	/*
-	 * If we have AArch32, we care about 32-bit features for compat.
-	 * If the system doesn't support AArch32, don't update them.
-	 */
-	if (id_aa64pfr0_32bit_el0(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1)) &&
-		id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
-
-		taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu,
-					info->reg_id_dfr0, boot->reg_id_dfr0);
-		taint |= check_update_ftr_reg(SYS_ID_ISAR0_EL1, cpu,
-					info->reg_id_isar0, boot->reg_id_isar0);
-		taint |= check_update_ftr_reg(SYS_ID_ISAR1_EL1, cpu,
-					info->reg_id_isar1, boot->reg_id_isar1);
-		taint |= check_update_ftr_reg(SYS_ID_ISAR2_EL1, cpu,
-					info->reg_id_isar2, boot->reg_id_isar2);
-		taint |= check_update_ftr_reg(SYS_ID_ISAR3_EL1, cpu,
-					info->reg_id_isar3, boot->reg_id_isar3);
-		taint |= check_update_ftr_reg(SYS_ID_ISAR4_EL1, cpu,
-					info->reg_id_isar4, boot->reg_id_isar4);
-		taint |= check_update_ftr_reg(SYS_ID_ISAR5_EL1, cpu,
-					info->reg_id_isar5, boot->reg_id_isar5);
-		taint |= check_update_ftr_reg(SYS_ID_ISAR6_EL1, cpu,
-					info->reg_id_isar6, boot->reg_id_isar6);
-
-		/*
-		 * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and
-		 * ACTLR formats could differ across CPUs and therefore would have to
-		 * be trapped for virtualization anyway.
-		 */
-		taint |= check_update_ftr_reg(SYS_ID_MMFR0_EL1, cpu,
-					info->reg_id_mmfr0, boot->reg_id_mmfr0);
-		taint |= check_update_ftr_reg(SYS_ID_MMFR1_EL1, cpu,
-					info->reg_id_mmfr1, boot->reg_id_mmfr1);
-		taint |= check_update_ftr_reg(SYS_ID_MMFR2_EL1, cpu,
-					info->reg_id_mmfr2, boot->reg_id_mmfr2);
-		taint |= check_update_ftr_reg(SYS_ID_MMFR3_EL1, cpu,
-					info->reg_id_mmfr3, boot->reg_id_mmfr3);
-		taint |= check_update_ftr_reg(SYS_ID_PFR0_EL1, cpu,
-					info->reg_id_pfr0, boot->reg_id_pfr0);
-		taint |= check_update_ftr_reg(SYS_ID_PFR1_EL1, cpu,
-					info->reg_id_pfr1, boot->reg_id_pfr1);
-		taint |= check_update_ftr_reg(SYS_MVFR0_EL1, cpu,
-					info->reg_mvfr0, boot->reg_mvfr0);
-		taint |= check_update_ftr_reg(SYS_MVFR1_EL1, cpu,
-					info->reg_mvfr1, boot->reg_mvfr1);
-		taint |= check_update_ftr_reg(SYS_MVFR2_EL1, cpu,
-					info->reg_mvfr2, boot->reg_mvfr2);
-	}
-
 	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
 		taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu,
 					info->reg_zcr, boot->reg_zcr);
@@ -824,6 +1045,12 @@ void update_cpu_features(int cpu,
 	}
 
 	/*
+	 * This relies on a sanitised view of the AArch64 ID registers
+	 * (e.g. SYS_ID_AA64PFR0_EL1), so we call it last.
+	 */
+	taint |= update_32bit_cpu_features(cpu, info, boot);
+
+	/*
 	 * Mismatched CPU features are a recipe for disaster. Don't even
 	 * pretend to support them.
 	 */
@@ -837,8 +1064,8 @@ u64 read_sanitised_ftr_reg(u32 id)
 {
 	struct arm64_ftr_reg *regp = get_arm64_ftr_reg(id);
 
-	/* We shouldn't get a request for an unsupported register */
-	BUG_ON(!regp);
+	if (!regp)
+		return 0;
 	return regp->sys_val;
 }
 
@@ -854,11 +1081,15 @@ static u64 __read_sysreg_by_encoding(u32 sys_id)
 	switch (sys_id) {
 	read_sysreg_case(SYS_ID_PFR0_EL1);
 	read_sysreg_case(SYS_ID_PFR1_EL1);
+	read_sysreg_case(SYS_ID_PFR2_EL1);
 	read_sysreg_case(SYS_ID_DFR0_EL1);
+	read_sysreg_case(SYS_ID_DFR1_EL1);
 	read_sysreg_case(SYS_ID_MMFR0_EL1);
 	read_sysreg_case(SYS_ID_MMFR1_EL1);
 	read_sysreg_case(SYS_ID_MMFR2_EL1);
 	read_sysreg_case(SYS_ID_MMFR3_EL1);
+	read_sysreg_case(SYS_ID_MMFR4_EL1);
+	read_sysreg_case(SYS_ID_MMFR5_EL1);
 	read_sysreg_case(SYS_ID_ISAR0_EL1);
 	read_sysreg_case(SYS_ID_ISAR1_EL1);
 	read_sysreg_case(SYS_ID_ISAR2_EL1);
@@ -1409,6 +1640,21 @@ static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry,
 }
 #endif
 
+#ifdef CONFIG_ARM64_BTI
+static void bti_enable(const struct arm64_cpu_capabilities *__unused)
+{
+	/*
+	 * Use of X16/X17 for tail-calls and trampolines that jump to
+	 * function entry points using BR is a requirement for
+	 * marking binaries with GNU_PROPERTY_AARCH64_FEATURE_1_BTI.
+	 * So, be strict and forbid other BRs using other registers to
+	 * jump onto a PACIxSP instruction:
+	 */
+	sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_BT0 | SCTLR_EL1_BT1);
+	isb();
+}
+#endif /* CONFIG_ARM64_BTI */
+
 /* Internal helper functions to match cpu capability type */
 static bool
 cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -1511,6 +1757,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64PFR0_EL0_SHIFT,
 		.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
 	},
+#ifdef CONFIG_KVM
+	{
+		.desc = "32-bit EL1 Support",
+		.capability = ARM64_HAS_32BIT_EL1,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64PFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR0_EL1_SHIFT,
+		.min_field_value = ID_AA64PFR0_EL1_32BIT_64BIT,
+	},
+#endif
 	{
 		.desc = "Kernel page table isolation (KPTI)",
 		.capability = ARM64_UNMAP_KERNEL_AT_EL0,
@@ -1779,6 +2037,23 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = 1,
 	},
 #endif
+#ifdef CONFIG_ARM64_BTI
+	{
+		.desc = "Branch Target Identification",
+		.capability = ARM64_BTI,
+#ifdef CONFIG_ARM64_BTI_KERNEL
+		.type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
+#else
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+#endif
+		.matches = has_cpuid_feature,
+		.cpu_enable = bti_enable,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.field_pos = ID_AA64PFR1_BT_SHIFT,
+		.min_field_value = ID_AA64PFR1_BT_BTI,
+		.sign = FTR_UNSIGNED,
+	},
+#endif
 	{},
 };
 
@@ -1888,6 +2163,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F64MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F64MM, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
 #endif
 	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS),
+#ifdef CONFIG_ARM64_BTI
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_BT_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_BT_BTI, CAP_HWCAP, KERNEL_HWCAP_BTI),
+#endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
 	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
@@ -2181,6 +2459,36 @@ static void verify_sve_features(void)
 	/* Add checks on other ZCR bits here if necessary */
 }
 
+static void verify_hyp_capabilities(void)
+{
+	u64 safe_mmfr1, mmfr0, mmfr1;
+	int parange, ipa_max;
+	unsigned int safe_vmid_bits, vmid_bits;
+
+	if (!IS_ENABLED(CONFIG_KVM) || !IS_ENABLED(CONFIG_KVM_ARM_HOST))
+		return;
+
+	safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
+	mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
+	mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
+
+	/* Verify VMID bits */
+	safe_vmid_bits = get_vmid_bits(safe_mmfr1);
+	vmid_bits = get_vmid_bits(mmfr1);
+	if (vmid_bits < safe_vmid_bits) {
+		pr_crit("CPU%d: VMID width mismatch\n", smp_processor_id());
+		cpu_die_early();
+	}
+
+	/* Verify IPA range */
+	parange = cpuid_feature_extract_unsigned_field(mmfr0,
+				ID_AA64MMFR0_PARANGE_SHIFT);
+	ipa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
+	if (ipa_max < get_kvm_ipa_limit()) {
+		pr_crit("CPU%d: IPA range mismatch\n", smp_processor_id());
+		cpu_die_early();
+	}
+}
 
 /*
  * Run through the enabled system capabilities and enable() it on this CPU.
@@ -2206,6 +2514,9 @@ static void verify_local_cpu_capabilities(void)
 
 	if (system_supports_sve())
 		verify_sve_features();
+
+	if (is_hyp_mode_available())
+		verify_hyp_capabilities();
 }
 
 void check_local_cpu_capabilities(void)
@@ -2394,7 +2705,7 @@ static int emulate_sys_reg(u32 id, u64 *valp)
 	if (sys_reg_CRm(id) == 0)
 		return emulate_id_reg(id, valp);
 
-	regp = get_arm64_ftr_reg(id);
+	regp = get_arm64_ftr_reg_nowarn(id);
 	if (regp)
 		*valp = arm64_ftr_reg_user_value(regp);
 	else
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 86136075ae41..86637466daa8 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -92,6 +92,7 @@ static const char *const hwcap_str[] = {
 	"bf16",
 	"dgh",
 	"rng",
+	"bti",
 	NULL
 };
 
@@ -311,6 +312,8 @@ static int __init cpuinfo_regs_init(void)
 	}
 	return 0;
 }
+device_initcall(cpuinfo_regs_init);
+
 static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
 {
 	unsigned int cpu = smp_processor_id();
@@ -362,6 +365,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	/* Update the 32bit ID registers only if AArch32 is implemented */
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
 		info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1);
+		info->reg_id_dfr1 = read_cpuid(ID_DFR1_EL1);
 		info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
 		info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
 		info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
@@ -373,8 +377,11 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 		info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1);
 		info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1);
 		info->reg_id_mmfr3 = read_cpuid(ID_MMFR3_EL1);
+		info->reg_id_mmfr4 = read_cpuid(ID_MMFR4_EL1);
+		info->reg_id_mmfr5 = read_cpuid(ID_MMFR5_EL1);
 		info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
 		info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
+		info->reg_id_pfr2 = read_cpuid(ID_PFR2_EL1);
 
 		info->reg_mvfr0 = read_cpuid(MVFR0_EL1);
 		info->reg_mvfr1 = read_cpuid(MVFR1_EL1);
@@ -403,5 +410,3 @@ void __init cpuinfo_store_boot_cpu(void)
 	boot_cpu_data = *info;
 	init_cpu_features(&boot_cpu_data);
 }
-
-device_initcall(cpuinfo_regs_init);
diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c
index ca4c3e12d8c5..1f646b07e3e9 100644
--- a/arch/arm64/kernel/crash_core.c
+++ b/arch/arm64/kernel/crash_core.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/crash_core.h>
+#include <asm/cpufeature.h>
 #include <asm/memory.h>
 
 void arch_crash_save_vmcoreinfo(void)
@@ -16,4 +17,7 @@ void arch_crash_save_vmcoreinfo(void)
 	vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
 						PHYS_OFFSET);
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+	vmcoreinfo_append_str("NUMBER(KERNELPACMASK)=0x%llx\n",
+						system_supports_address_auth() ?
+						ptrauth_kernel_pac_mask() : 0);
 }
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 48222a4760c2..15e80c876d46 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -376,15 +376,13 @@ int aarch32_break_handler(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(aarch32_break_handler);
 
-static int __init debug_traps_init(void)
+void __init debug_traps_init(void)
 {
 	hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP,
 			      TRAP_TRACE, "single-step handler");
 	hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP,
 			      TRAP_BRKPT, "ptrace BRK handler");
-	return 0;
 }
-arch_initcall(debug_traps_init);
 
 /* Re-enable single step for syscall restarting. */
 void user_rewind_single_step(struct task_struct *task)
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 1a03618df0df..0073b24b5d25 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -14,12 +14,12 @@
 
 SYM_CODE_START(efi_enter_kernel)
 	/*
-	 * efi_entry() will have copied the kernel image if necessary and we
+	 * efi_pe_entry() will have copied the kernel image if necessary and we
 	 * end up here with device tree address in x1 and the kernel entry
 	 * point stored in x0. Save those values in registers which are
 	 * callee preserved.
 	 */
-	ldr	w2, =stext_offset
+	ldr	w2, =primary_entry_offset
 	add	x19, x0, x2		// relocated Image entrypoint
 	mov	x20, x1			// DTB address
 
diff --git a/arch/arm64/kernel/efi-header.S b/arch/arm64/kernel/efi-header.S
index 914999ccaf8a..df67c0f2a077 100644
--- a/arch/arm64/kernel/efi-header.S
+++ b/arch/arm64/kernel/efi-header.S
@@ -27,12 +27,12 @@ optional_header:
 	.long	__initdata_begin - efi_header_end	// SizeOfCode
 	.long	__pecoff_data_size			// SizeOfInitializedData
 	.long	0					// SizeOfUninitializedData
-	.long	__efistub_efi_entry - _head		// AddressOfEntryPoint
+	.long	__efistub_efi_pe_entry - _head		// AddressOfEntryPoint
 	.long	efi_header_end - _head			// BaseOfCode
 
 extra_header_fields:
 	.quad	0					// ImageBase
-	.long	SZ_4K					// SectionAlignment
+	.long	SEGMENT_ALIGN				// SectionAlignment
 	.long	PECOFF_FILE_ALIGNMENT			// FileAlignment
 	.short	0					// MajorOperatingSystemVersion
 	.short	0					// MinorOperatingSystemVersion
diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S
index 3fc71106cb2b..75691a2641c1 100644
--- a/arch/arm64/kernel/efi-rt-wrapper.S
+++ b/arch/arm64/kernel/efi-rt-wrapper.S
@@ -5,7 +5,7 @@
 
 #include <linux/linkage.h>
 
-ENTRY(__efi_rt_asm_wrapper)
+SYM_FUNC_START(__efi_rt_asm_wrapper)
 	stp	x29, x30, [sp, #-32]!
 	mov	x29, sp
 
@@ -34,5 +34,14 @@ ENTRY(__efi_rt_asm_wrapper)
 	ldp	x29, x30, [sp], #32
 	b.ne	0f
 	ret
-0:	b	efi_handle_corrupted_x18	// tail call
-ENDPROC(__efi_rt_asm_wrapper)
+0:
+	/*
+	 * With CONFIG_SHADOW_CALL_STACK, the kernel uses x18 to store a
+	 * shadow stack pointer, which we need to restore before returning to
+	 * potentially instrumented code. This is safe because the wrapper is
+	 * called with preemption disabled and a separate shadow stack is used
+	 * for interrupts.
+	 */
+	mov	x18, x2
+	b	efi_handle_corrupted_x18	// tail call
+SYM_FUNC_END(__efi_rt_asm_wrapper)
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index c839b5bf1904..3dbdf9752b11 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -94,7 +94,7 @@ asmlinkage void notrace el1_sync_handler(struct pt_regs *regs)
 		break;
 	default:
 		el1_inv(regs, esr);
-	};
+	}
 }
 NOKPROBE_SYMBOL(el1_sync_handler);
 
@@ -188,6 +188,14 @@ static void notrace el0_undef(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(el0_undef);
 
+static void notrace el0_bti(struct pt_regs *regs)
+{
+	user_exit_irqoff();
+	local_daif_restore(DAIF_PROCCTX);
+	do_bti(regs);
+}
+NOKPROBE_SYMBOL(el0_bti);
+
 static void notrace el0_inv(struct pt_regs *regs, unsigned long esr)
 {
 	user_exit_irqoff();
@@ -255,6 +263,9 @@ asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
 	case ESR_ELx_EC_UNKNOWN:
 		el0_undef(regs);
 		break;
+	case ESR_ELx_EC_BTI:
+		el0_bti(regs);
+		break;
 	case ESR_ELx_EC_BREAKPT_LOW:
 	case ESR_ELx_EC_SOFTSTP_LOW:
 	case ESR_ELx_EC_WATCHPT_LOW:
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 0f24eae8f3cc..f880dd63ddc3 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -16,34 +16,34 @@
  *
  * x0 - pointer to struct fpsimd_state
  */
-ENTRY(fpsimd_save_state)
+SYM_FUNC_START(fpsimd_save_state)
 	fpsimd_save x0, 8
 	ret
-ENDPROC(fpsimd_save_state)
+SYM_FUNC_END(fpsimd_save_state)
 
 /*
  * Load the FP registers.
  *
  * x0 - pointer to struct fpsimd_state
  */
-ENTRY(fpsimd_load_state)
+SYM_FUNC_START(fpsimd_load_state)
 	fpsimd_restore x0, 8
 	ret
-ENDPROC(fpsimd_load_state)
+SYM_FUNC_END(fpsimd_load_state)
 
 #ifdef CONFIG_ARM64_SVE
-ENTRY(sve_save_state)
+SYM_FUNC_START(sve_save_state)
 	sve_save 0, x1, 2
 	ret
-ENDPROC(sve_save_state)
+SYM_FUNC_END(sve_save_state)
 
-ENTRY(sve_load_state)
+SYM_FUNC_START(sve_load_state)
 	sve_load 0, x1, x2, 3, x4
 	ret
-ENDPROC(sve_load_state)
+SYM_FUNC_END(sve_load_state)
 
-ENTRY(sve_get_vl)
+SYM_FUNC_START(sve_get_vl)
 	_sve_rdvl	0, 1
 	ret
-ENDPROC(sve_get_vl)
+SYM_FUNC_END(sve_get_vl)
 #endif /* CONFIG_ARM64_SVE */
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 833d48c9acb5..a338f40e64d3 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -23,8 +23,9 @@
  *
  * ... where <entry> is either ftrace_caller or ftrace_regs_caller.
  *
- * Each instrumented function follows the AAPCS, so here x0-x8 and x19-x30 are
- * live, and x9-x18 are safe to clobber.
+ * Each instrumented function follows the AAPCS, so here x0-x8 and x18-x30 are
+ * live (x18 holds the Shadow Call Stack pointer), and x9-x17 are safe to
+ * clobber.
  *
  * We save the callsite's context into a pt_regs before invoking any ftrace
  * callbacks. So that we can get a sensible backtrace, we create a stack record
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index ddcde093c433..5304d193c79d 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -23,6 +23,7 @@
 #include <asm/mmu.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
+#include <asm/scs.h>
 #include <asm/thread_info.h>
 #include <asm/asm-uaccess.h>
 #include <asm/unistd.h>
@@ -178,7 +179,9 @@ alternative_cb_end
 
 	apply_ssbd 1, x22, x23
 
-	ptrauth_keys_install_kernel tsk, 1, x20, x22, x23
+	ptrauth_keys_install_kernel tsk, x20, x22, x23
+
+	scs_load tsk, x20
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	get_current_task tsk
@@ -343,6 +346,8 @@ alternative_else_nop_endif
 	msr	cntkctl_el1, x1
 4:
 #endif
+	scs_save tsk, x0
+
 	/* No kernel C function calls after this as user keys are set. */
 	ptrauth_keys_install_user tsk, x0, x1, x2
 
@@ -388,6 +393,9 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 
 	.macro	irq_stack_entry
 	mov	x19, sp			// preserve the original sp
+#ifdef CONFIG_SHADOW_CALL_STACK
+	mov	x24, scs_sp		// preserve the original shadow stack
+#endif
 
 	/*
 	 * Compare sp with the base of the task stack.
@@ -405,15 +413,25 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 
 	/* switch to the irq stack */
 	mov	sp, x26
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+	/* also switch to the irq shadow stack */
+	adr_this_cpu scs_sp, irq_shadow_call_stack, x26
+#endif
+
 9998:
 	.endm
 
 	/*
-	 * x19 should be preserved between irq_stack_entry and
-	 * irq_stack_exit.
+	 * The callee-saved regs (x19-x29) should be preserved between
+	 * irq_stack_entry and irq_stack_exit, but note that kernel_entry
+	 * uses x20-x23 to store data for later use.
 	 */
 	.macro	irq_stack_exit
 	mov	sp, x19
+#ifdef CONFIG_SHADOW_CALL_STACK
+	mov	scs_sp, x24
+#endif
 	.endm
 
 /* GPRs used by entry code */
@@ -728,20 +746,9 @@ el0_error_naked:
 SYM_CODE_END(el0_error)
 
 /*
- * Ok, we need to do extra processing, enter the slow path.
- */
-work_pending:
-	mov	x0, sp				// 'regs'
-	bl	do_notify_resume
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_on		// enabled while in userspace
-#endif
-	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for single-step
-	b	finish_ret_to_user
-/*
  * "slow" syscall return path.
  */
-ret_to_user:
+SYM_CODE_START_LOCAL(ret_to_user)
 	disable_daif
 	gic_prio_kentry_setup tmp=x3
 	ldr	x1, [tsk, #TSK_TI_FLAGS]
@@ -753,7 +760,19 @@ finish_ret_to_user:
 	bl	stackleak_erase
 #endif
 	kernel_exit 0
-ENDPROC(ret_to_user)
+
+/*
+ * Ok, we need to do extra processing, enter the slow path.
+ */
+work_pending:
+	mov	x0, sp				// 'regs'
+	bl	do_notify_resume
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_on		// enabled while in userspace
+#endif
+	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for single-step
+	b	finish_ret_to_user
+SYM_CODE_END(ret_to_user)
 
 	.popsection				// .entry.text
 
@@ -900,7 +919,9 @@ SYM_FUNC_START(cpu_switch_to)
 	ldr	lr, [x8]
 	mov	sp, x9
 	msr	sp_el0, x1
-	ptrauth_keys_install_kernel x1, 1, x8, x9, x10
+	ptrauth_keys_install_kernel x1, x8, x9, x10
+	scs_save x0, x8
+	scs_load x1, x8
 	ret
 SYM_FUNC_END(cpu_switch_to)
 NOKPROBE(cpu_switch_to)
@@ -1029,13 +1050,16 @@ SYM_CODE_START(__sdei_asm_handler)
 
 	mov	x19, x1
 
+#if defined(CONFIG_VMAP_STACK) || defined(CONFIG_SHADOW_CALL_STACK)
+	ldrb	w4, [x19, #SDEI_EVENT_PRIORITY]
+#endif
+
 #ifdef CONFIG_VMAP_STACK
 	/*
 	 * entry.S may have been using sp as a scratch register, find whether
 	 * this is a normal or critical event and switch to the appropriate
 	 * stack for this CPU.
 	 */
-	ldrb	w4, [x19, #SDEI_EVENT_PRIORITY]
 	cbnz	w4, 1f
 	ldr_this_cpu dst=x5, sym=sdei_stack_normal_ptr, tmp=x6
 	b	2f
@@ -1045,6 +1069,15 @@ SYM_CODE_START(__sdei_asm_handler)
 	mov	sp, x5
 #endif
 
+#ifdef CONFIG_SHADOW_CALL_STACK
+	/* Use a separate shadow call stack for normal and critical events */
+	cbnz	w4, 3f
+	adr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_normal, tmp=x6
+	b	4f
+3:	adr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_critical, tmp=x6
+4:
+#endif
+
 	/*
 	 * We may have interrupted userspace, or a guest, or exit-from or
 	 * return-to either of these. We can't trust sp_el0, restore it.
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 57a91032b4c2..632702146813 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/irqchip/arm-gic-v3.h>
 
+#include <asm/asm_pointer_auth.h>
 #include <asm/assembler.h>
 #include <asm/boot.h>
 #include <asm/ptrace.h>
@@ -27,6 +28,7 @@
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
+#include <asm/scs.h>
 #include <asm/smp.h>
 #include <asm/sysreg.h>
 #include <asm/thread_info.h>
@@ -70,9 +72,9 @@ _head:
 	 * its opcode forms the magic "MZ" signature required by UEFI.
 	 */
 	add	x13, x18, #0x16
-	b	stext
+	b	primary_entry
 #else
-	b	stext				// branch to kernel start, magic
+	b	primary_entry			// branch to kernel start, magic
 	.long	0				// reserved
 #endif
 	le64sym	_kernel_offset_le		// Image load offset from start of RAM, little-endian
@@ -98,14 +100,13 @@ pe_header:
 	 * primary lowlevel boot path:
 	 *
 	 *  Register   Scope                      Purpose
-	 *  x21        stext() .. start_kernel()  FDT pointer passed at boot in x0
-	 *  x23        stext() .. start_kernel()  physical misalignment/KASLR offset
-	 *  x28        __create_page_tables()     callee preserved temp register
-	 *  x19/x20    __primary_switch()         callee preserved temp registers
-	 *  x24        __primary_switch() .. relocate_kernel()
-	 *                                        current RELR displacement
+	 *  x21        primary_entry() .. start_kernel()        FDT pointer passed at boot in x0
+	 *  x23        primary_entry() .. start_kernel()        physical misalignment/KASLR offset
+	 *  x28        __create_page_tables()                   callee preserved temp register
+	 *  x19/x20    __primary_switch()                       callee preserved temp registers
+	 *  x24        __primary_switch() .. relocate_kernel()  current RELR displacement
 	 */
-SYM_CODE_START(stext)
+SYM_CODE_START(primary_entry)
 	bl	preserve_boot_args
 	bl	el2_setup			// Drop to EL1, w0=cpu_boot_mode
 	adrp	x23, __PHYS_OFFSET
@@ -118,10 +119,9 @@ SYM_CODE_START(stext)
 	 * On return, the CPU will be ready for the MMU to be turned on and
 	 * the TCR will have been set.
 	 */
-	mov	x0, #ARM64_CPU_BOOT_PRIMARY
 	bl	__cpu_setup			// initialise processor
 	b	__primary_switch
-SYM_CODE_END(stext)
+SYM_CODE_END(primary_entry)
 
 /*
  * Preserve the arguments passed by the bootloader in x0 .. x3
@@ -394,13 +394,19 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 
 	/*
 	 * Since the page tables have been populated with non-cacheable
-	 * accesses (MMU disabled), invalidate the idmap and swapper page
-	 * tables again to remove any speculatively loaded cache lines.
+	 * accesses (MMU disabled), invalidate those tables again to
+	 * remove any speculatively loaded cache lines.
 	 */
+	dmb	sy
+
 	adrp	x0, idmap_pg_dir
+	adrp	x1, idmap_pg_end
+	sub	x1, x1, x0
+	bl	__inval_dcache_area
+
+	adrp	x0, init_pg_dir
 	adrp	x1, init_pg_end
 	sub	x1, x1, x0
-	dmb	sy
 	bl	__inval_dcache_area
 
 	ret	x28
@@ -417,6 +423,10 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 	adr_l	x5, init_task
 	msr	sp_el0, x5			// Save thread_info
 
+#ifdef CONFIG_ARM64_PTR_AUTH
+	__ptrauth_keys_init_cpu	x5, x6, x7, x8
+#endif
+
 	adr_l	x8, vectors			// load VBAR_EL1 with virtual
 	msr	vbar_el1, x8			// vector table address
 	isb
@@ -424,6 +434,10 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 	stp	xzr, x30, [sp, #-16]!
 	mov	x29, sp
 
+#ifdef CONFIG_SHADOW_CALL_STACK
+	adr_l	scs_sp, init_shadow_call_stack	// Set shadow call stack
+#endif
+
 	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
 
 	ldr_l	x4, kimage_vaddr		// Save the offset between
@@ -717,7 +731,6 @@ SYM_FUNC_START_LOCAL(secondary_startup)
 	 * Common entry point for secondary CPUs.
 	 */
 	bl	__cpu_secondary_check52bitva
-	mov	x0, #ARM64_CPU_BOOT_SECONDARY
 	bl	__cpu_setup			// initialise processor
 	adrp	x1, swapper_pg_dir
 	bl	__enable_mmu
@@ -737,8 +750,14 @@ SYM_FUNC_START_LOCAL(__secondary_switched)
 	ldr	x2, [x0, #CPU_BOOT_TASK]
 	cbz	x2, __secondary_too_slow
 	msr	sp_el0, x2
+	scs_load x2, x3
 	mov	x29, #0
 	mov	x30, #0
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+	ptrauth_keys_init_cpu x2, x3, x4, x5
+#endif
+
 	b	secondary_start_kernel
 SYM_FUNC_END(__secondary_switched)
 
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index 6532105b3e32..8ccca660034e 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -65,7 +65,7 @@
  * x5: physical address of a  zero page that remains zero after resume
  */
 .pushsection    ".hibernate_exit.text", "ax"
-ENTRY(swsusp_arch_suspend_exit)
+SYM_CODE_START(swsusp_arch_suspend_exit)
 	/*
 	 * We execute from ttbr0, change ttbr1 to our copied linear map tables
 	 * with a break-before-make via the zero page
@@ -110,7 +110,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	cbz	x24, 3f		/* Do we need to re-initialise EL2? */
 	hvc	#0
 3:	ret
-ENDPROC(swsusp_arch_suspend_exit)
+SYM_CODE_END(swsusp_arch_suspend_exit)
 
 /*
  * Restore the hyp stub.
@@ -119,15 +119,15 @@ ENDPROC(swsusp_arch_suspend_exit)
  *
  * x24: The physical address of __hyp_stub_vectors
  */
-el1_sync:
+SYM_CODE_START_LOCAL(el1_sync)
 	msr	vbar_el2, x24
 	eret
-ENDPROC(el1_sync)
+SYM_CODE_END(el1_sync)
 
 .macro invalid_vector	label
-\label:
+SYM_CODE_START_LOCAL(\label)
 	b \label
-ENDPROC(\label)
+SYM_CODE_END(\label)
 .endm
 
 	invalid_vector	el2_sync_invalid
@@ -141,7 +141,7 @@ ENDPROC(\label)
 
 /* el2 vectors - switch el2 here while we restore the memory image. */
 	.align 11
-ENTRY(hibernate_el2_vectors)
+SYM_CODE_START(hibernate_el2_vectors)
 	ventry	el2_sync_invalid		// Synchronous EL2t
 	ventry	el2_irq_invalid			// IRQ EL2t
 	ventry	el2_fiq_invalid			// FIQ EL2t
@@ -161,6 +161,6 @@ ENTRY(hibernate_el2_vectors)
 	ventry	el1_irq_invalid			// IRQ 32-bit EL1
 	ventry	el1_fiq_invalid			// FIQ 32-bit EL1
 	ventry	el1_error_invalid		// Error 32-bit EL1
-END(hibernate_el2_vectors)
+SYM_CODE_END(hibernate_el2_vectors)
 
 .popsection
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index e473ead806ed..160f5881a0b7 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -21,7 +21,7 @@
 
 	.align 11
 
-ENTRY(__hyp_stub_vectors)
+SYM_CODE_START(__hyp_stub_vectors)
 	ventry	el2_sync_invalid		// Synchronous EL2t
 	ventry	el2_irq_invalid			// IRQ EL2t
 	ventry	el2_fiq_invalid			// FIQ EL2t
@@ -41,11 +41,11 @@ ENTRY(__hyp_stub_vectors)
 	ventry	el1_irq_invalid			// IRQ 32-bit EL1
 	ventry	el1_fiq_invalid			// FIQ 32-bit EL1
 	ventry	el1_error_invalid		// Error 32-bit EL1
-ENDPROC(__hyp_stub_vectors)
+SYM_CODE_END(__hyp_stub_vectors)
 
 	.align 11
 
-el1_sync:
+SYM_CODE_START_LOCAL(el1_sync)
 	cmp	x0, #HVC_SET_VECTORS
 	b.ne	2f
 	msr	vbar_el2, x1
@@ -68,12 +68,12 @@ el1_sync:
 
 9:	mov	x0, xzr
 	eret
-ENDPROC(el1_sync)
+SYM_CODE_END(el1_sync)
 
 .macro invalid_vector	label
-\label:
+SYM_CODE_START_LOCAL(\label)
 	b \label
-ENDPROC(\label)
+SYM_CODE_END(\label)
 .endm
 
 	invalid_vector	el2_sync_invalid
@@ -106,15 +106,15 @@ ENDPROC(\label)
  * initialisation entry point.
  */
 
-ENTRY(__hyp_set_vectors)
+SYM_FUNC_START(__hyp_set_vectors)
 	mov	x1, x0
 	mov	x0, #HVC_SET_VECTORS
 	hvc	#0
 	ret
-ENDPROC(__hyp_set_vectors)
+SYM_FUNC_END(__hyp_set_vectors)
 
-ENTRY(__hyp_reset_vectors)
+SYM_FUNC_START(__hyp_reset_vectors)
 	mov	x0, #HVC_RESET_VECTORS
 	hvc	#0
 	ret
-ENDPROC(__hyp_reset_vectors)
+SYM_FUNC_END(__hyp_reset_vectors)
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 7f06ad93fc95..be0a63ffed23 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -13,7 +13,7 @@
 #ifdef CONFIG_EFI
 
 __efistub_kernel_size		= _edata - _text;
-__efistub_stext_offset		= stext - _text;
+__efistub_primary_entry_offset	= primary_entry - _text;
 
 
 /*
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 4a9e773a177f..684d871ae38d 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -51,21 +51,33 @@ enum aarch64_insn_encoding_class __kprobes aarch64_get_insn_class(u32 insn)
 	return aarch64_insn_encoding_class[(insn >> 25) & 0xf];
 }
 
-/* NOP is an alias of HINT */
-bool __kprobes aarch64_insn_is_nop(u32 insn)
+bool __kprobes aarch64_insn_is_steppable_hint(u32 insn)
 {
 	if (!aarch64_insn_is_hint(insn))
 		return false;
 
 	switch (insn & 0xFE0) {
-	case AARCH64_INSN_HINT_YIELD:
-	case AARCH64_INSN_HINT_WFE:
-	case AARCH64_INSN_HINT_WFI:
-	case AARCH64_INSN_HINT_SEV:
-	case AARCH64_INSN_HINT_SEVL:
-		return false;
-	default:
+	case AARCH64_INSN_HINT_XPACLRI:
+	case AARCH64_INSN_HINT_PACIA_1716:
+	case AARCH64_INSN_HINT_PACIB_1716:
+	case AARCH64_INSN_HINT_AUTIA_1716:
+	case AARCH64_INSN_HINT_AUTIB_1716:
+	case AARCH64_INSN_HINT_PACIAZ:
+	case AARCH64_INSN_HINT_PACIASP:
+	case AARCH64_INSN_HINT_PACIBZ:
+	case AARCH64_INSN_HINT_PACIBSP:
+	case AARCH64_INSN_HINT_AUTIAZ:
+	case AARCH64_INSN_HINT_AUTIASP:
+	case AARCH64_INSN_HINT_AUTIBZ:
+	case AARCH64_INSN_HINT_AUTIBSP:
+	case AARCH64_INSN_HINT_BTI:
+	case AARCH64_INSN_HINT_BTIC:
+	case AARCH64_INSN_HINT_BTIJ:
+	case AARCH64_INSN_HINT_BTIJC:
+	case AARCH64_INSN_HINT_NOP:
 		return true;
+	default:
+		return false;
 	}
 }
 
@@ -574,7 +586,7 @@ u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
 					     offset >> 2);
 }
 
-u32 __kprobes aarch64_insn_gen_hint(enum aarch64_insn_hint_op op)
+u32 __kprobes aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op)
 {
 	return aarch64_insn_get_hint_value() | op;
 }
@@ -1535,16 +1547,10 @@ static u32 aarch64_encode_immediate(u64 imm,
 				    u32 insn)
 {
 	unsigned int immr, imms, n, ones, ror, esz, tmp;
-	u64 mask = ~0UL;
-
-	/* Can't encode full zeroes or full ones */
-	if (!imm || !~imm)
-		return AARCH64_BREAK_FAULT;
+	u64 mask;
 
 	switch (variant) {
 	case AARCH64_INSN_VARIANT_32BIT:
-		if (upper_32_bits(imm))
-			return AARCH64_BREAK_FAULT;
 		esz = 32;
 		break;
 	case AARCH64_INSN_VARIANT_64BIT:
@@ -1556,6 +1562,12 @@ static u32 aarch64_encode_immediate(u64 imm,
 		return AARCH64_BREAK_FAULT;
 	}
 
+	mask = GENMASK(esz - 1, 0);
+
+	/* Can't encode full zeroes, full ones, or value wider than the mask */
+	if (!imm || imm == mask || imm & ~mask)
+		return AARCH64_BREAK_FAULT;
+
 	/*
 	 * Inverse of Replicate(). Try to spot a repeating pattern
 	 * with a pow2 stride.
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 8e9c924423b4..a0b144cfaea7 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -177,6 +177,7 @@ void machine_kexec(struct kimage *kimage)
 	 * the offline CPUs. Therefore, we must use the __* variant here.
 	 */
 	__flush_icache_range((uintptr_t)reboot_code_buffer,
+			     (uintptr_t)reboot_code_buffer +
 			     arm64_relocate_new_kernel_size);
 
 	/* Flush the kimage list and its buffers. */
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index b40c3b0def92..522e6f517ec0 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -138,12 +138,12 @@ static int setup_dtb(struct kimage *image,
 
 	/* add rng-seed */
 	if (rng_is_initialized()) {
-		u8 rng_seed[RNG_SEED_SIZE];
-		get_random_bytes(rng_seed, RNG_SEED_SIZE);
-		ret = fdt_setprop(dtb, off, FDT_PROP_RNG_SEED, rng_seed,
-				RNG_SEED_SIZE);
+		void *rng_seed;
+		ret = fdt_setprop_placeholder(dtb, off, FDT_PROP_RNG_SEED,
+				RNG_SEED_SIZE, &rng_seed);
 		if (ret)
 			goto out;
+		get_random_bytes(rng_seed, RNG_SEED_SIZE);
 	} else {
 		pr_notice("RNG is not initialised: omitting \"%s\" property\n",
 				FDT_PROP_RNG_SEED);
@@ -284,7 +284,7 @@ int load_other_segments(struct kimage *image,
 		image->arch.elf_headers_sz = headers_sz;
 
 		pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-			 image->arch.elf_headers_mem, headers_sz, headers_sz);
+			 image->arch.elf_headers_mem, kbuf.bufsz, kbuf.memsz);
 	}
 
 	/* load initrd */
@@ -305,7 +305,7 @@ int load_other_segments(struct kimage *image,
 		initrd_load_addr = kbuf.mem;
 
 		pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-				initrd_load_addr, initrd_len, initrd_len);
+				initrd_load_addr, kbuf.bufsz, kbuf.memsz);
 	}
 
 	/* load dtb */
@@ -332,7 +332,7 @@ int load_other_segments(struct kimage *image,
 	image->arch.dtb_mem = kbuf.mem;
 
 	pr_debug("Loaded dtb at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-			kbuf.mem, dtb_len, dtb_len);
+			kbuf.mem, kbuf.bufsz, kbuf.memsz);
 
 	return 0;
 
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 1ef702b0be2d..295d66490584 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -120,7 +120,7 @@ static bool has_pv_steal_clock(void)
 	struct arm_smccc_res res;
 
 	/* To detect the presence of PV time support we require SMCCC 1.1+ */
-	if (psci_ops.smccc_version < SMCCC_VERSION_1_1)
+	if (arm_smccc_1_1_get_conduit() == SMCCC_CONDUIT_NONE)
 		return false;
 
 	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
index b78fac9e546c..263d5fba4c8a 100644
--- a/arch/arm64/kernel/probes/decode-insn.c
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -46,7 +46,7 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn)
 		 * except for the NOP case.
 		 */
 		if (aarch64_insn_is_hint(insn))
-			return aarch64_insn_is_nop(insn);
+			return aarch64_insn_is_steppable_hint(insn);
 
 		return true;
 	}
diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S
index 45dce03aaeaf..890ca72c5a51 100644
--- a/arch/arm64/kernel/probes/kprobes_trampoline.S
+++ b/arch/arm64/kernel/probes/kprobes_trampoline.S
@@ -61,7 +61,7 @@
 	ldp x28, x29, [sp, #S_X28]
 	.endm
 
-ENTRY(kretprobe_trampoline)
+SYM_CODE_START(kretprobe_trampoline)
 	sub sp, sp, #S_FRAME_SIZE
 
 	save_all_base_regs
@@ -79,4 +79,4 @@ ENTRY(kretprobe_trampoline)
 	add sp, sp, #S_FRAME_SIZE
 	ret
 
-ENDPROC(kretprobe_trampoline)
+SYM_CODE_END(kretprobe_trampoline)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 56be4cbf771f..eade7807e819 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -11,6 +11,7 @@
 
 #include <linux/compat.h>
 #include <linux/efi.h>
+#include <linux/elf.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
@@ -18,6 +19,7 @@
 #include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
 #include <linux/lockdep.h>
+#include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
@@ -209,6 +211,15 @@ void machine_restart(char *cmd)
 	while (1);
 }
 
+#define bstr(suffix, str) [PSR_BTYPE_ ## suffix >> PSR_BTYPE_SHIFT] = str
+static const char *const btypes[] = {
+	bstr(NONE, "--"),
+	bstr(  JC, "jc"),
+	bstr(   C, "-c"),
+	bstr(  J , "j-")
+};
+#undef bstr
+
 static void print_pstate(struct pt_regs *regs)
 {
 	u64 pstate = regs->pstate;
@@ -227,7 +238,10 @@ static void print_pstate(struct pt_regs *regs)
 			pstate & PSR_AA32_I_BIT ? 'I' : 'i',
 			pstate & PSR_AA32_F_BIT ? 'F' : 'f');
 	} else {
-		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO)\n",
+		const char *btype_str = btypes[(pstate & PSR_BTYPE_MASK) >>
+					       PSR_BTYPE_SHIFT];
+
+		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO BTYPE=%s)\n",
 			pstate,
 			pstate & PSR_N_BIT ? 'N' : 'n',
 			pstate & PSR_Z_BIT ? 'Z' : 'z',
@@ -238,7 +252,8 @@ static void print_pstate(struct pt_regs *regs)
 			pstate & PSR_I_BIT ? 'I' : 'i',
 			pstate & PSR_F_BIT ? 'F' : 'f',
 			pstate & PSR_PAN_BIT ? '+' : '-',
-			pstate & PSR_UAO_BIT ? '+' : '-');
+			pstate & PSR_UAO_BIT ? '+' : '-',
+			btype_str);
 	}
 }
 
@@ -655,3 +670,25 @@ asmlinkage void __sched arm64_preempt_schedule_irq(void)
 	if (system_capabilities_finalized())
 		preempt_schedule_irq();
 }
+
+#ifdef CONFIG_BINFMT_ELF
+int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state,
+			 bool has_interp, bool is_interp)
+{
+	/*
+	 * For dynamically linked executables the interpreter is
+	 * responsible for setting PROT_BTI on everything except
+	 * itself.
+	 */
+	if (is_interp != has_interp)
+		return prot;
+
+	if (!(state->flags & ARM64_ELF_BTI))
+		return prot;
+
+	if (prot & PROT_EXEC)
+		prot |= PROT_BTI;
+
+	return prot;
+}
+#endif
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index b3d3005d9515..76790a5f2a0d 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1829,10 +1829,11 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 
 int syscall_trace_enter(struct pt_regs *regs)
 {
-	if (test_thread_flag(TIF_SYSCALL_TRACE) ||
-		test_thread_flag(TIF_SYSCALL_EMU)) {
+	unsigned long flags = READ_ONCE(current_thread_info()->flags);
+
+	if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) {
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
-		if (!in_syscall(regs) || test_thread_flag(TIF_SYSCALL_EMU))
+		if (!in_syscall(regs) || (flags & _TIF_SYSCALL_EMU))
 			return -1;
 	}
 
@@ -1874,7 +1875,7 @@ void syscall_trace_exit(struct pt_regs *regs)
  */
 #define SPSR_EL1_AARCH64_RES0_BITS \
 	(GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
-	 GENMASK_ULL(20, 13) | GENMASK_ULL(11, 10) | GENMASK_ULL(5, 5))
+	 GENMASK_ULL(20, 13) | GENMASK_ULL(5, 5))
 #define SPSR_EL1_AARCH32_RES0_BITS \
 	(GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20))
 
diff --git a/arch/arm64/kernel/reloc_test_syms.S b/arch/arm64/kernel/reloc_test_syms.S
index 16a34f188f26..c50f45fa29fa 100644
--- a/arch/arm64/kernel/reloc_test_syms.S
+++ b/arch/arm64/kernel/reloc_test_syms.S
@@ -5,81 +5,81 @@
 
 #include <linux/linkage.h>
 
-ENTRY(absolute_data64)
+SYM_FUNC_START(absolute_data64)
 	ldr	x0, 0f
 	ret
 0:	.quad	sym64_abs
-ENDPROC(absolute_data64)
+SYM_FUNC_END(absolute_data64)
 
-ENTRY(absolute_data32)
+SYM_FUNC_START(absolute_data32)
 	ldr	w0, 0f
 	ret
 0:	.long	sym32_abs
-ENDPROC(absolute_data32)
+SYM_FUNC_END(absolute_data32)
 
-ENTRY(absolute_data16)
+SYM_FUNC_START(absolute_data16)
 	adr	x0, 0f
 	ldrh	w0, [x0]
 	ret
 0:	.short	sym16_abs, 0
-ENDPROC(absolute_data16)
+SYM_FUNC_END(absolute_data16)
 
-ENTRY(signed_movw)
+SYM_FUNC_START(signed_movw)
 	movz	x0, #:abs_g2_s:sym64_abs
 	movk	x0, #:abs_g1_nc:sym64_abs
 	movk	x0, #:abs_g0_nc:sym64_abs
 	ret
-ENDPROC(signed_movw)
+SYM_FUNC_END(signed_movw)
 
-ENTRY(unsigned_movw)
+SYM_FUNC_START(unsigned_movw)
 	movz	x0, #:abs_g3:sym64_abs
 	movk	x0, #:abs_g2_nc:sym64_abs
 	movk	x0, #:abs_g1_nc:sym64_abs
 	movk	x0, #:abs_g0_nc:sym64_abs
 	ret
-ENDPROC(unsigned_movw)
+SYM_FUNC_END(unsigned_movw)
 
 	.align	12
 	.space	0xff8
-ENTRY(relative_adrp)
+SYM_FUNC_START(relative_adrp)
 	adrp	x0, sym64_rel
 	add	x0, x0, #:lo12:sym64_rel
 	ret
-ENDPROC(relative_adrp)
+SYM_FUNC_END(relative_adrp)
 
 	.align	12
 	.space	0xffc
-ENTRY(relative_adrp_far)
+SYM_FUNC_START(relative_adrp_far)
 	adrp	x0, memstart_addr
 	add	x0, x0, #:lo12:memstart_addr
 	ret
-ENDPROC(relative_adrp_far)
+SYM_FUNC_END(relative_adrp_far)
 
-ENTRY(relative_adr)
+SYM_FUNC_START(relative_adr)
 	adr	x0, sym64_rel
 	ret
-ENDPROC(relative_adr)
+SYM_FUNC_END(relative_adr)
 
-ENTRY(relative_data64)
+SYM_FUNC_START(relative_data64)
 	adr	x1, 0f
 	ldr	x0, [x1]
 	add	x0, x0, x1
 	ret
 0:	.quad	sym64_rel - .
-ENDPROC(relative_data64)
+SYM_FUNC_END(relative_data64)
 
-ENTRY(relative_data32)
+SYM_FUNC_START(relative_data32)
 	adr	x1, 0f
 	ldr	w0, [x1]
 	add	x0, x0, x1
 	ret
 0:	.long	sym64_rel - .
-ENDPROC(relative_data32)
+SYM_FUNC_END(relative_data32)
 
-ENTRY(relative_data16)
+SYM_FUNC_START(relative_data16)
 	adr	x1, 0f
 	ldrsh	w0, [x1]
 	add	x0, x0, x1
 	ret
 0:	.short	sym64_rel - ., 0
-ENDPROC(relative_data16)
+SYM_FUNC_END(relative_data16)
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index c40ce496c78b..542d6edc6806 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -26,7 +26,7 @@
  * control_code_page, a special page which has been set up to be preserved
  * during the copy operation.
  */
-ENTRY(arm64_relocate_new_kernel)
+SYM_CODE_START(arm64_relocate_new_kernel)
 
 	/* Setup the list loop variables. */
 	mov	x18, x2				/* x18 = dtb address */
@@ -111,7 +111,7 @@ ENTRY(arm64_relocate_new_kernel)
 	mov	x3, xzr
 	br	x17
 
-ENDPROC(arm64_relocate_new_kernel)
+SYM_CODE_END(arm64_relocate_new_kernel)
 
 .align 3	/* To keep the 64-bit values below naturally aligned. */
 
diff --git a/arch/arm64/kernel/scs.c b/arch/arm64/kernel/scs.c
new file mode 100644
index 000000000000..e8f7ff45dd8f
--- /dev/null
+++ b/arch/arm64/kernel/scs.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shadow Call Stack support.
+ *
+ * Copyright (C) 2019 Google LLC
+ */
+
+#include <linux/percpu.h>
+#include <linux/scs.h>
+
+DEFINE_SCS(irq_shadow_call_stack);
+
+#ifdef CONFIG_ARM_SDE_INTERFACE
+DEFINE_SCS(sdei_shadow_call_stack_normal);
+DEFINE_SCS(sdei_shadow_call_stack_critical);
+#endif
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index d6259dac62b6..dab88260b137 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -95,19 +95,7 @@ static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info)
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
 
-	if (!low)
-		return false;
-
-	if (sp < low || sp >= high)
-		return false;
-
-	if (info) {
-		info->low = low;
-		info->high = high;
-		info->type = STACK_TYPE_SDEI_NORMAL;
-	}
-
-	return true;
+	return on_stack(sp, low, high, STACK_TYPE_SDEI_NORMAL, info);
 }
 
 static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info)
@@ -115,19 +103,7 @@ static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info)
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
 
-	if (!low)
-		return false;
-
-	if (sp < low || sp >= high)
-		return false;
-
-	if (info) {
-		info->low = low;
-		info->high = high;
-		info->type = STACK_TYPE_SDEI_CRITICAL;
-	}
-
-	return true;
+	return on_stack(sp, low, high, STACK_TYPE_SDEI_CRITICAL, info);
 }
 
 bool _on_sdei_stack(unsigned long sp, struct stack_info *info)
@@ -251,22 +227,12 @@ asmlinkage __kprobes notrace unsigned long
 __sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
 {
 	unsigned long ret;
-	bool do_nmi_exit = false;
 
-	/*
-	 * nmi_enter() deals with printk() re-entrance and use of RCU when
-	 * RCU believed this CPU was idle. Because critical events can
-	 * interrupt normal events, we may already be in_nmi().
-	 */
-	if (!in_nmi()) {
-		nmi_enter();
-		do_nmi_exit = true;
-	}
+	nmi_enter();
 
 	ret = _sdei_handler(regs, arg);
 
-	if (do_nmi_exit)
-		nmi_exit();
+	nmi_exit();
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 339882db5a91..801d56cdf701 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -732,6 +732,22 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 	regs->regs[29] = (unsigned long)&user->next_frame->fp;
 	regs->pc = (unsigned long)ka->sa.sa_handler;
 
+	/*
+	 * Signal delivery is a (wacky) indirect function call in
+	 * userspace, so simulate the same setting of BTYPE as a BLR
+	 * <register containing the signal handler entry point>.
+	 * Signal delivery to a location in a PROT_BTI guarded page
+	 * that is not a function entry point will now trigger a
+	 * SIGILL in userspace.
+	 *
+	 * If the signal handler entry point is not in a PROT_BTI
+	 * guarded page, this is harmless.
+	 */
+	if (system_supports_bti()) {
+		regs->pstate &= ~PSR_BTYPE_MASK;
+		regs->pstate |= PSR_BTYPE_C;
+	}
+
 	if (ka->sa.sa_flags & SA_RESTORER)
 		sigtramp = ka->sa.sa_restorer;
 	else
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 7b2f2e650c44..ba40d57757d6 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -62,7 +62,7 @@
  *
  *  x0 = struct sleep_stack_data area
  */
-ENTRY(__cpu_suspend_enter)
+SYM_FUNC_START(__cpu_suspend_enter)
 	stp	x29, lr, [x0, #SLEEP_STACK_DATA_CALLEE_REGS]
 	stp	x19, x20, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+16]
 	stp	x21, x22, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+32]
@@ -95,23 +95,22 @@ ENTRY(__cpu_suspend_enter)
 	ldp	x29, lr, [sp], #16
 	mov	x0, #1
 	ret
-ENDPROC(__cpu_suspend_enter)
+SYM_FUNC_END(__cpu_suspend_enter)
 
 	.pushsection ".idmap.text", "awx"
-ENTRY(cpu_resume)
+SYM_CODE_START(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
-	mov	x0, #ARM64_CPU_RUNTIME
 	bl	__cpu_setup
 	/* enable the MMU early - so we can access sleep_save_stash by va */
 	adrp	x1, swapper_pg_dir
 	bl	__enable_mmu
 	ldr	x8, =_cpu_resume
 	br	x8
-ENDPROC(cpu_resume)
+SYM_CODE_END(cpu_resume)
 	.ltorg
 	.popsection
 
-ENTRY(_cpu_resume)
+SYM_FUNC_START(_cpu_resume)
 	mrs	x1, mpidr_el1
 	adr_l	x8, mpidr_hash		// x8 = struct mpidr_hash virt address
 
@@ -147,4 +146,4 @@ ENTRY(_cpu_resume)
 	ldp	x29, lr, [x29]
 	mov	x0, #0
 	ret
-ENDPROC(_cpu_resume)
+SYM_FUNC_END(_cpu_resume)
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
index 54655273d1e0..1f93809528a4 100644
--- a/arch/arm64/kernel/smccc-call.S
+++ b/arch/arm64/kernel/smccc-call.S
@@ -30,9 +30,9 @@
  *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res,
  *		  struct arm_smccc_quirk *quirk)
  */
-ENTRY(__arm_smccc_smc)
+SYM_FUNC_START(__arm_smccc_smc)
 	SMCCC	smc
-ENDPROC(__arm_smccc_smc)
+SYM_FUNC_END(__arm_smccc_smc)
 EXPORT_SYMBOL(__arm_smccc_smc)
 
 /*
@@ -41,7 +41,7 @@ EXPORT_SYMBOL(__arm_smccc_smc)
  *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res,
  *		  struct arm_smccc_quirk *quirk)
  */
-ENTRY(__arm_smccc_hvc)
+SYM_FUNC_START(__arm_smccc_hvc)
 	SMCCC	hvc
-ENDPROC(__arm_smccc_hvc)
+SYM_FUNC_END(__arm_smccc_hvc)
 EXPORT_SYMBOL(__arm_smccc_hvc)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 061f60fe452f..04b1ca0d7aba 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -65,7 +65,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number);
  */
 struct secondary_data secondary_data;
 /* Number of CPUs which aren't online, but looping in kernel text. */
-int cpus_stuck_in_kernel;
+static int cpus_stuck_in_kernel;
 
 enum ipi_msg_type {
 	IPI_RESCHEDULE,
@@ -114,10 +114,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	 */
 	secondary_data.task = idle;
 	secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
-#if defined(CONFIG_ARM64_PTR_AUTH)
-	secondary_data.ptrauth_key.apia.lo = idle->thread.keys_kernel.apia.lo;
-	secondary_data.ptrauth_key.apia.hi = idle->thread.keys_kernel.apia.hi;
-#endif
 	update_cpu_boot_status(CPU_MMU_OFF);
 	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 
@@ -140,10 +136,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	pr_crit("CPU%u: failed to come online\n", cpu);
 	secondary_data.task = NULL;
 	secondary_data.stack = NULL;
-#if defined(CONFIG_ARM64_PTR_AUTH)
-	secondary_data.ptrauth_key.apia.lo = 0;
-	secondary_data.ptrauth_key.apia.hi = 0;
-#endif
 	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	status = READ_ONCE(secondary_data.status);
 	if (status == CPU_MMU_OFF)
@@ -176,7 +168,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 		panic("CPU%u detected unsupported configuration\n", cpu);
 	}
 
-	return ret;
+	return -EIO;
 }
 
 static void init_gic_priority_masking(void)
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index a12c0c88d345..5f5b868292f5 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -98,6 +98,24 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	regs->orig_x0 = regs->regs[0];
 	regs->syscallno = scno;
 
+	/*
+	 * BTI note:
+	 * The architecture does not guarantee that SPSR.BTYPE is zero
+	 * on taking an SVC, so we could return to userspace with a
+	 * non-zero BTYPE after the syscall.
+	 *
+	 * This shouldn't matter except when userspace is explicitly
+	 * doing something stupid, such as setting PROT_BTI on a page
+	 * that lacks conforming BTI/PACIxSP instructions, falling
+	 * through from one executable page to another with differing
+	 * PROT_BTI, or messing with BTYPE via ptrace: in such cases,
+	 * userspace should not be surprised if a SIGILL occurs on
+	 * syscall return.
+	 *
+	 * So, don't touch regs->pstate & PSR_BTYPE_MASK here.
+	 * (Similarly for HVC and SMC elsewhere.)
+	 */
+
 	cortex_a76_erratum_1463225_svc_handler();
 	local_daif_restore(DAIF_PROCCTX);
 	user_exit();
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index cf402be5c573..d332590f5978 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -272,6 +272,61 @@ void arm64_notify_die(const char *str, struct pt_regs *regs,
 	}
 }
 
+#ifdef CONFIG_COMPAT
+#define PSTATE_IT_1_0_SHIFT	25
+#define PSTATE_IT_1_0_MASK	(0x3 << PSTATE_IT_1_0_SHIFT)
+#define PSTATE_IT_7_2_SHIFT	10
+#define PSTATE_IT_7_2_MASK	(0x3f << PSTATE_IT_7_2_SHIFT)
+
+static u32 compat_get_it_state(struct pt_regs *regs)
+{
+	u32 it, pstate = regs->pstate;
+
+	it  = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT;
+	it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2;
+
+	return it;
+}
+
+static void compat_set_it_state(struct pt_regs *regs, u32 it)
+{
+	u32 pstate_it;
+
+	pstate_it  = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK;
+	pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK;
+
+	regs->pstate &= ~PSR_AA32_IT_MASK;
+	regs->pstate |= pstate_it;
+}
+
+static void advance_itstate(struct pt_regs *regs)
+{
+	u32 it;
+
+	/* ARM mode */
+	if (!(regs->pstate & PSR_AA32_T_BIT) ||
+	    !(regs->pstate & PSR_AA32_IT_MASK))
+		return;
+
+	it  = compat_get_it_state(regs);
+
+	/*
+	 * If this is the last instruction of the block, wipe the IT
+	 * state. Otherwise advance it.
+	 */
+	if (!(it & 7))
+		it = 0;
+	else
+		it = (it & 0xe0) | ((it << 1) & 0x1f);
+
+	compat_set_it_state(regs, it);
+}
+#else
+static void advance_itstate(struct pt_regs *regs)
+{
+}
+#endif
+
 void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
 {
 	regs->pc += size;
@@ -282,6 +337,11 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
 	 */
 	if (user_mode(regs))
 		user_fastforward_single_step(current);
+
+	if (compat_user_mode(regs))
+		advance_itstate(regs);
+	else
+		regs->pstate &= ~PSR_BTYPE_MASK;
 }
 
 static LIST_HEAD(undef_hook);
@@ -411,6 +471,13 @@ void do_undefinstr(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(do_undefinstr);
 
+void do_bti(struct pt_regs *regs)
+{
+	BUG_ON(!user_mode(regs));
+	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+}
+NOKPROBE_SYMBOL(do_bti);
+
 #define __user_cache_maint(insn, address, res)			\
 	if (address >= user_addr_max()) {			\
 		res = -EFAULT;					\
@@ -566,34 +633,7 @@ static const struct sys64_hook sys64_hooks[] = {
 	{},
 };
 
-
 #ifdef CONFIG_COMPAT
-#define PSTATE_IT_1_0_SHIFT	25
-#define PSTATE_IT_1_0_MASK	(0x3 << PSTATE_IT_1_0_SHIFT)
-#define PSTATE_IT_7_2_SHIFT	10
-#define PSTATE_IT_7_2_MASK	(0x3f << PSTATE_IT_7_2_SHIFT)
-
-static u32 compat_get_it_state(struct pt_regs *regs)
-{
-	u32 it, pstate = regs->pstate;
-
-	it  = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT;
-	it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2;
-
-	return it;
-}
-
-static void compat_set_it_state(struct pt_regs *regs, u32 it)
-{
-	u32 pstate_it;
-
-	pstate_it  = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK;
-	pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK;
-
-	regs->pstate &= ~PSR_AA32_IT_MASK;
-	regs->pstate |= pstate_it;
-}
-
 static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
 {
 	int cond;
@@ -614,42 +654,12 @@ static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
 	return aarch32_opcode_cond_checks[cond](regs->pstate);
 }
 
-static void advance_itstate(struct pt_regs *regs)
-{
-	u32 it;
-
-	/* ARM mode */
-	if (!(regs->pstate & PSR_AA32_T_BIT) ||
-	    !(regs->pstate & PSR_AA32_IT_MASK))
-		return;
-
-	it  = compat_get_it_state(regs);
-
-	/*
-	 * If this is the last instruction of the block, wipe the IT
-	 * state. Otherwise advance it.
-	 */
-	if (!(it & 7))
-		it = 0;
-	else
-		it = (it & 0xe0) | ((it << 1) & 0x1f);
-
-	compat_set_it_state(regs, it);
-}
-
-static void arm64_compat_skip_faulting_instruction(struct pt_regs *regs,
-						   unsigned int sz)
-{
-	advance_itstate(regs);
-	arm64_skip_faulting_instruction(regs, sz);
-}
-
 static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
 {
 	int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT;
 
 	pt_regs_write_reg(regs, reg, arch_timer_get_rate());
-	arm64_compat_skip_faulting_instruction(regs, 4);
+	arm64_skip_faulting_instruction(regs, 4);
 }
 
 static const struct sys64_hook cp15_32_hooks[] = {
@@ -669,7 +679,7 @@ static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 
 	pt_regs_write_reg(regs, rt, lower_32_bits(val));
 	pt_regs_write_reg(regs, rt2, upper_32_bits(val));
-	arm64_compat_skip_faulting_instruction(regs, 4);
+	arm64_skip_faulting_instruction(regs, 4);
 }
 
 static const struct sys64_hook cp15_64_hooks[] = {
@@ -690,7 +700,7 @@ void do_cp15instr(unsigned int esr, struct pt_regs *regs)
 		 * There is no T16 variant of a CP access, so we
 		 * always advance PC by 4 bytes.
 		 */
-		arm64_compat_skip_faulting_instruction(regs, 4);
+		arm64_skip_faulting_instruction(regs, 4);
 		return;
 	}
 
@@ -753,6 +763,7 @@ static const char *esr_class_str[] = {
 	[ESR_ELx_EC_CP10_ID]		= "CP10 MRC/VMRS",
 	[ESR_ELx_EC_PAC]		= "PAC",
 	[ESR_ELx_EC_CP14_64]		= "CP14 MCRR/MRRC",
+	[ESR_ELx_EC_BTI]		= "BTI",
 	[ESR_ELx_EC_ILL]		= "PSTATE.IL",
 	[ESR_ELx_EC_SVC32]		= "SVC (AArch32)",
 	[ESR_ELx_EC_HVC32]		= "HVC (AArch32)",
@@ -906,17 +917,13 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
 
 asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
 {
-	const bool was_in_nmi = in_nmi();
-
-	if (!was_in_nmi)
-		nmi_enter();
+	nmi_enter();
 
 	/* non-RAS errors are not containable */
 	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
 		arm64_serror_panic(regs, esr);
 
-	if (!was_in_nmi)
-		nmi_exit();
+	nmi_exit();
 }
 
 asmlinkage void enter_from_user_mode(void)
@@ -1047,11 +1054,11 @@ int __init early_brk64(unsigned long addr, unsigned int esr,
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
 }
 
-/* This registration must happen early, before debug_traps_init(). */
 void __init trap_init(void)
 {
 	register_kernel_break_hook(&bug_break_hook);
 #ifdef CONFIG_KASAN_SW_TAGS
 	register_kernel_break_hook(&kasan_break_hook);
 #endif
+	debug_traps_init();
 }
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 354b11e27c07..d51a898fd60f 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -33,20 +33,14 @@ extern char vdso_start[], vdso_end[];
 extern char vdso32_start[], vdso32_end[];
 #endif /* CONFIG_COMPAT_VDSO */
 
-/* vdso_lookup arch_index */
-enum arch_vdso_type {
-	ARM64_VDSO = 0,
+enum vdso_abi {
+	VDSO_ABI_AA64,
 #ifdef CONFIG_COMPAT_VDSO
-	ARM64_VDSO32 = 1,
+	VDSO_ABI_AA32,
 #endif /* CONFIG_COMPAT_VDSO */
 };
-#ifdef CONFIG_COMPAT_VDSO
-#define VDSO_TYPES		(ARM64_VDSO32 + 1)
-#else
-#define VDSO_TYPES		(ARM64_VDSO + 1)
-#endif /* CONFIG_COMPAT_VDSO */
 
-struct __vdso_abi {
+struct vdso_abi_info {
 	const char *name;
 	const char *vdso_code_start;
 	const char *vdso_code_end;
@@ -57,14 +51,14 @@ struct __vdso_abi {
 	struct vm_special_mapping *cm;
 };
 
-static struct __vdso_abi vdso_lookup[VDSO_TYPES] __ro_after_init = {
-	{
+static struct vdso_abi_info vdso_info[] __ro_after_init = {
+	[VDSO_ABI_AA64] = {
 		.name = "vdso",
 		.vdso_code_start = vdso_start,
 		.vdso_code_end = vdso_end,
 	},
 #ifdef CONFIG_COMPAT_VDSO
-	{
+	[VDSO_ABI_AA32] = {
 		.name = "vdso32",
 		.vdso_code_start = vdso32_start,
 		.vdso_code_end = vdso32_end,
@@ -81,13 +75,13 @@ static union {
 } vdso_data_store __page_aligned_data;
 struct vdso_data *vdso_data = vdso_data_store.data;
 
-static int __vdso_remap(enum arch_vdso_type arch_index,
+static int __vdso_remap(enum vdso_abi abi,
 			const struct vm_special_mapping *sm,
 			struct vm_area_struct *new_vma)
 {
 	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
-	unsigned long vdso_size = vdso_lookup[arch_index].vdso_code_end -
-				  vdso_lookup[arch_index].vdso_code_start;
+	unsigned long vdso_size = vdso_info[abi].vdso_code_end -
+				  vdso_info[abi].vdso_code_start;
 
 	if (vdso_size != new_size)
 		return -EINVAL;
@@ -97,24 +91,24 @@ static int __vdso_remap(enum arch_vdso_type arch_index,
 	return 0;
 }
 
-static int __vdso_init(enum arch_vdso_type arch_index)
+static int __vdso_init(enum vdso_abi abi)
 {
 	int i;
 	struct page **vdso_pagelist;
 	unsigned long pfn;
 
-	if (memcmp(vdso_lookup[arch_index].vdso_code_start, "\177ELF", 4)) {
+	if (memcmp(vdso_info[abi].vdso_code_start, "\177ELF", 4)) {
 		pr_err("vDSO is not a valid ELF object!\n");
 		return -EINVAL;
 	}
 
-	vdso_lookup[arch_index].vdso_pages = (
-			vdso_lookup[arch_index].vdso_code_end -
-			vdso_lookup[arch_index].vdso_code_start) >>
+	vdso_info[abi].vdso_pages = (
+			vdso_info[abi].vdso_code_end -
+			vdso_info[abi].vdso_code_start) >>
 			PAGE_SHIFT;
 
 	/* Allocate the vDSO pagelist, plus a page for the data. */
-	vdso_pagelist = kcalloc(vdso_lookup[arch_index].vdso_pages + 1,
+	vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages + 1,
 				sizeof(struct page *),
 				GFP_KERNEL);
 	if (vdso_pagelist == NULL)
@@ -125,26 +119,27 @@ static int __vdso_init(enum arch_vdso_type arch_index)
 
 
 	/* Grab the vDSO code pages. */
-	pfn = sym_to_pfn(vdso_lookup[arch_index].vdso_code_start);
+	pfn = sym_to_pfn(vdso_info[abi].vdso_code_start);
 
-	for (i = 0; i < vdso_lookup[arch_index].vdso_pages; i++)
+	for (i = 0; i < vdso_info[abi].vdso_pages; i++)
 		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
 
-	vdso_lookup[arch_index].dm->pages = &vdso_pagelist[0];
-	vdso_lookup[arch_index].cm->pages = &vdso_pagelist[1];
+	vdso_info[abi].dm->pages = &vdso_pagelist[0];
+	vdso_info[abi].cm->pages = &vdso_pagelist[1];
 
 	return 0;
 }
 
-static int __setup_additional_pages(enum arch_vdso_type arch_index,
+static int __setup_additional_pages(enum vdso_abi abi,
 				    struct mm_struct *mm,
 				    struct linux_binprm *bprm,
 				    int uses_interp)
 {
 	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+	unsigned long gp_flags = 0;
 	void *ret;
 
-	vdso_text_len = vdso_lookup[arch_index].vdso_pages << PAGE_SHIFT;
+	vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
 	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
 
@@ -156,16 +151,19 @@ static int __setup_additional_pages(enum arch_vdso_type arch_index,
 
 	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
 				       VM_READ|VM_MAYREAD,
-				       vdso_lookup[arch_index].dm);
+				       vdso_info[abi].dm);
 	if (IS_ERR(ret))
 		goto up_fail;
 
+	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti())
+		gp_flags = VM_ARM64_BTI;
+
 	vdso_base += PAGE_SIZE;
 	mm->context.vdso = (void *)vdso_base;
 	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
-				       VM_READ|VM_EXEC|
+				       VM_READ|VM_EXEC|gp_flags|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       vdso_lookup[arch_index].cm);
+				       vdso_info[abi].cm);
 	if (IS_ERR(ret))
 		goto up_fail;
 
@@ -184,46 +182,42 @@ up_fail:
 static int aarch32_vdso_mremap(const struct vm_special_mapping *sm,
 		struct vm_area_struct *new_vma)
 {
-	return __vdso_remap(ARM64_VDSO32, sm, new_vma);
+	return __vdso_remap(VDSO_ABI_AA32, sm, new_vma);
 }
 #endif /* CONFIG_COMPAT_VDSO */
 
-/*
- * aarch32_vdso_pages:
- * 0 - kuser helpers
- * 1 - sigreturn code
- * or (CONFIG_COMPAT_VDSO):
- * 0 - kuser helpers
- * 1 - vdso data
- * 2 - vdso code
- */
-#define C_VECTORS	0
+enum aarch32_map {
+	AA32_MAP_VECTORS, /* kuser helpers */
 #ifdef CONFIG_COMPAT_VDSO
-#define C_VVAR		1
-#define C_VDSO		2
-#define C_PAGES		(C_VDSO + 1)
+	AA32_MAP_VVAR,
+	AA32_MAP_VDSO,
 #else
-#define C_SIGPAGE	1
-#define C_PAGES		(C_SIGPAGE + 1)
-#endif /* CONFIG_COMPAT_VDSO */
-static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
-static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
-	{
+	AA32_MAP_SIGPAGE
+#endif
+};
+
+static struct page *aarch32_vectors_page __ro_after_init;
+#ifndef CONFIG_COMPAT_VDSO
+static struct page *aarch32_sig_page __ro_after_init;
+#endif
+
+static struct vm_special_mapping aarch32_vdso_maps[] = {
+	[AA32_MAP_VECTORS] = {
 		.name	= "[vectors]", /* ABI */
-		.pages	= &aarch32_vdso_pages[C_VECTORS],
+		.pages	= &aarch32_vectors_page,
 	},
 #ifdef CONFIG_COMPAT_VDSO
-	{
+	[AA32_MAP_VVAR] = {
 		.name = "[vvar]",
 	},
-	{
+	[AA32_MAP_VDSO] = {
 		.name = "[vdso]",
 		.mremap = aarch32_vdso_mremap,
 	},
 #else
-	{
+	[AA32_MAP_SIGPAGE] = {
 		.name	= "[sigpage]", /* ABI */
-		.pages	= &aarch32_vdso_pages[C_SIGPAGE],
+		.pages	= &aarch32_sig_page,
 	},
 #endif /* CONFIG_COMPAT_VDSO */
 };
@@ -243,8 +237,8 @@ static int aarch32_alloc_kuser_vdso_page(void)
 
 	memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
 	       kuser_sz);
-	aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page);
-	flush_dcache_page(aarch32_vdso_pages[C_VECTORS]);
+	aarch32_vectors_page = virt_to_page(vdso_page);
+	flush_dcache_page(aarch32_vectors_page);
 	return 0;
 }
 
@@ -253,25 +247,14 @@ static int __aarch32_alloc_vdso_pages(void)
 {
 	int ret;
 
-	vdso_lookup[ARM64_VDSO32].dm = &aarch32_vdso_spec[C_VVAR];
-	vdso_lookup[ARM64_VDSO32].cm = &aarch32_vdso_spec[C_VDSO];
+	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
+	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
 
-	ret = __vdso_init(ARM64_VDSO32);
+	ret = __vdso_init(VDSO_ABI_AA32);
 	if (ret)
 		return ret;
 
-	ret = aarch32_alloc_kuser_vdso_page();
-	if (ret) {
-		unsigned long c_vvar =
-			(unsigned long)page_to_virt(aarch32_vdso_pages[C_VVAR]);
-		unsigned long c_vdso =
-			(unsigned long)page_to_virt(aarch32_vdso_pages[C_VDSO]);
-
-		free_page(c_vvar);
-		free_page(c_vdso);
-	}
-
-	return ret;
+	return aarch32_alloc_kuser_vdso_page();
 }
 #else
 static int __aarch32_alloc_vdso_pages(void)
@@ -286,8 +269,8 @@ static int __aarch32_alloc_vdso_pages(void)
 		return -ENOMEM;
 
 	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
-	aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage);
-	flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]);
+	aarch32_sig_page = virt_to_page(sigpage);
+	flush_dcache_page(aarch32_sig_page);
 
 	ret = aarch32_alloc_kuser_vdso_page();
 	if (ret)
@@ -317,7 +300,7 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
 	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
 				       VM_READ | VM_EXEC |
 				       VM_MAYREAD | VM_MAYEXEC,
-				       &aarch32_vdso_spec[C_VECTORS]);
+				       &aarch32_vdso_maps[AA32_MAP_VECTORS]);
 
 	return PTR_ERR_OR_ZERO(ret);
 }
@@ -341,7 +324,7 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm)
 	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
 				       VM_READ | VM_EXEC | VM_MAYREAD |
 				       VM_MAYWRITE | VM_MAYEXEC,
-				       &aarch32_vdso_spec[C_SIGPAGE]);
+				       &aarch32_vdso_maps[AA32_MAP_SIGPAGE]);
 	if (IS_ERR(ret))
 		goto out;
 
@@ -365,7 +348,7 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		goto out;
 
 #ifdef CONFIG_COMPAT_VDSO
-	ret = __setup_additional_pages(ARM64_VDSO32,
+	ret = __setup_additional_pages(VDSO_ABI_AA32,
 				       mm,
 				       bprm,
 				       uses_interp);
@@ -382,22 +365,19 @@ out:
 static int vdso_mremap(const struct vm_special_mapping *sm,
 		struct vm_area_struct *new_vma)
 {
-	return __vdso_remap(ARM64_VDSO, sm, new_vma);
+	return __vdso_remap(VDSO_ABI_AA64, sm, new_vma);
 }
 
-/*
- * aarch64_vdso_pages:
- * 0 - vvar
- * 1 - vdso
- */
-#define A_VVAR		0
-#define A_VDSO		1
-#define A_PAGES		(A_VDSO + 1)
-static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
-	{
+enum aarch64_map {
+	AA64_MAP_VVAR,
+	AA64_MAP_VDSO,
+};
+
+static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = {
+	[AA64_MAP_VVAR] = {
 		.name	= "[vvar]",
 	},
-	{
+	[AA64_MAP_VDSO] = {
 		.name	= "[vdso]",
 		.mremap = vdso_mremap,
 	},
@@ -405,10 +385,10 @@ static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
 
 static int __init vdso_init(void)
 {
-	vdso_lookup[ARM64_VDSO].dm = &vdso_spec[A_VVAR];
-	vdso_lookup[ARM64_VDSO].cm = &vdso_spec[A_VDSO];
+	vdso_info[VDSO_ABI_AA64].dm = &aarch64_vdso_maps[AA64_MAP_VVAR];
+	vdso_info[VDSO_ABI_AA64].cm = &aarch64_vdso_maps[AA64_MAP_VDSO];
 
-	return __vdso_init(ARM64_VDSO);
+	return __vdso_init(VDSO_ABI_AA64);
 }
 arch_initcall(vdso_init);
 
@@ -421,7 +401,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
-	ret = __setup_additional_pages(ARM64_VDSO,
+	ret = __setup_additional_pages(VDSO_ABI_AA64,
 				       mm,
 				       bprm,
 				       uses_interp);
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index dd2514bb1511..556d424c6f52 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -17,22 +17,26 @@ obj-vdso := vgettimeofday.o note.o sigreturn.o
 targets := $(obj-vdso) vdso.so vdso.so.dbg
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
+btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti
+
+# -Bsymbolic has been added for consistency with arm, the compat vDSO and
+# potential future proofing if we end up with internal calls to the exported
+# routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so
+# preparation in build-time C")).
 ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \
-		--build-id -n -T
+		-Bsymbolic --eh-frame-hdr --build-id -n $(btildflags-y) -T
 
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
 ccflags-y += -DDISABLE_BRANCH_PROFILING
 
-VDSO_LDFLAGS := -Bsymbolic
-
-CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS)
 KBUILD_CFLAGS			+= $(DISABLE_LTO)
 KASAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
 OBJECT_FILES_NON_STANDARD	:= y
 KCOV_INSTRUMENT			:= n
 
-CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny
+CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -fasynchronous-unwind-tables
 
 ifneq ($(c-gettimeofday-y),)
   CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
diff --git a/arch/arm64/kernel/vdso/note.S b/arch/arm64/kernel/vdso/note.S
index 0ce6ec75a525..3d4e82290c80 100644
--- a/arch/arm64/kernel/vdso/note.S
+++ b/arch/arm64/kernel/vdso/note.S
@@ -12,9 +12,12 @@
 #include <linux/version.h>
 #include <linux/elfnote.h>
 #include <linux/build-salt.h>
+#include <asm/assembler.h>
 
 ELFNOTE_START(Linux, 0, "a")
 	.long LINUX_VERSION_CODE
 ELFNOTE_END
 
 BUILD_SALT
+
+emit_aarch64_feature_1_and
diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S
index 12324863d5c2..620a3ef837b7 100644
--- a/arch/arm64/kernel/vdso/sigreturn.S
+++ b/arch/arm64/kernel/vdso/sigreturn.S
@@ -1,7 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Sigreturn trampoline for returning from a signal when the SA_RESTORER
- * flag is not set.
+ * flag is not set. It serves primarily as a hall of shame for crappy
+ * unwinders and features an exciting but mysterious NOP instruction.
+ *
+ * It's also fragile as hell, so please think twice before changing anything
+ * in here.
  *
  * Copyright (C) 2012 ARM Limited
  *
@@ -9,18 +13,54 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/unistd.h>
 
 	.text
 
-	nop
-SYM_FUNC_START(__kernel_rt_sigreturn)
+/* Ensure that the mysterious NOP can be associated with a function. */
 	.cfi_startproc
+
+/*
+ * .cfi_signal_frame causes the corresponding Frame Description Entry in the
+ * .eh_frame section to be annotated as a signal frame. This allows DWARF
+ * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo(), which permits
+ * unwinding out of the signal trampoline without the need for the mysterious
+ * NOP.
+ */
 	.cfi_signal_frame
-	.cfi_def_cfa	x29, 0
-	.cfi_offset	x29, 0 * 8
-	.cfi_offset	x30, 1 * 8
+
+/*
+ * Tell the unwinder where to locate the frame record linking back to the
+ * interrupted context. We don't provide unwind info for registers other
+ * than the frame pointer and the link register here; in practice, this
+ * is sufficient for unwinding in C/C++ based runtimes and the values in
+ * the sigcontext may have been modified by this point anyway. Debuggers
+ * already have baked-in strategies for attempting to unwind out of signals.
+ */
+	.cfi_def_cfa    x29, 0
+	.cfi_offset     x29, 0 * 8
+	.cfi_offset     x30, 1 * 8
+
+/*
+ * This mysterious NOP is required for some unwinders (e.g. libc++) that
+ * unconditionally subtract one from the result of _Unwind_GetIP() in order to
+ * identify the calling function.
+ * Hack borrowed from arch/powerpc/kernel/vdso64/sigtramp.S.
+ */
+	nop	// Mysterious NOP
+
+/*
+ * GDB relies on being able to identify the sigreturn instruction sequence to
+ * unwind from signal handlers. We cannot, therefore, use SYM_FUNC_START()
+ * here, as it will emit a BTI C instruction and break the unwinder. Thankfully,
+ * this function is only ever called from a RET and so omitting the landing pad
+ * is perfectly fine.
+ */
+SYM_CODE_START(__kernel_rt_sigreturn)
 	mov	x8, #__NR_rt_sigreturn
 	svc	#0
 	.cfi_endproc
-SYM_FUNC_END(__kernel_rt_sigreturn)
+SYM_CODE_END(__kernel_rt_sigreturn)
+
+emit_aarch64_feature_1_and
diff --git a/arch/arm64/kernel/vdso/vdso.S b/arch/arm64/kernel/vdso/vdso.S
index d1414fee5274..c4b1990bf2be 100644
--- a/arch/arm64/kernel/vdso/vdso.S
+++ b/arch/arm64/kernel/vdso/vdso.S
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/const.h>
+#include <asm/assembler.h>
 #include <asm/page.h>
 
 	.globl vdso_start, vdso_end
@@ -19,3 +20,5 @@ vdso_start:
 vdso_end:
 
 	.previous
+
+emit_aarch64_feature_1_and
diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S
index 620524969696..b0091064c3d6 100644
--- a/arch/arm64/kernel/vdso32/sigreturn.S
+++ b/arch/arm64/kernel/vdso32/sigreturn.S
@@ -3,6 +3,9 @@
  * This file provides both A32 and T32 versions, in accordance with the
  * arm sigreturn code.
  *
+ * Please read the comments in arch/arm64/kernel/vdso/sigreturn.S to
+ * understand some of the craziness in here.
+ *
  * Copyright (C) 2018 ARM Limited
  */
 
@@ -17,39 +20,39 @@
 	.save {r0-r15}
 	.pad #COMPAT_SIGFRAME_REGS_OFFSET
 	nop
-SYM_FUNC_START(__kernel_sigreturn_arm)
+SYM_CODE_START(__kernel_sigreturn_arm)
 	mov r7, #__NR_compat_sigreturn
 	svc #0
 	.fnend
-SYM_FUNC_END(__kernel_sigreturn_arm)
+SYM_CODE_END(__kernel_sigreturn_arm)
 
 	.fnstart
 	.save {r0-r15}
 	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
 	nop
-SYM_FUNC_START(__kernel_rt_sigreturn_arm)
+SYM_CODE_START(__kernel_rt_sigreturn_arm)
 	mov r7, #__NR_compat_rt_sigreturn
 	svc #0
 	.fnend
-SYM_FUNC_END(__kernel_rt_sigreturn_arm)
+SYM_CODE_END(__kernel_rt_sigreturn_arm)
 
 	.thumb
 	.fnstart
 	.save {r0-r15}
 	.pad #COMPAT_SIGFRAME_REGS_OFFSET
 	nop
-SYM_FUNC_START(__kernel_sigreturn_thumb)
+SYM_CODE_START(__kernel_sigreturn_thumb)
 	mov r7, #__NR_compat_sigreturn
 	svc #0
 	.fnend
-SYM_FUNC_END(__kernel_sigreturn_thumb)
+SYM_CODE_END(__kernel_sigreturn_thumb)
 
 	.fnstart
 	.save {r0-r15}
 	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
 	nop
-SYM_FUNC_START(__kernel_rt_sigreturn_thumb)
+SYM_CODE_START(__kernel_rt_sigreturn_thumb)
 	mov r7, #__NR_compat_rt_sigreturn
 	svc #0
 	.fnend
-SYM_FUNC_END(__kernel_rt_sigreturn_thumb)
+SYM_CODE_END(__kernel_rt_sigreturn_thumb)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 497f9675071d..3be632177631 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -17,10 +17,6 @@
 
 #include "image.h"
 
-/* .exit.text needed in case of alternative patching */
-#define ARM_EXIT_KEEP(x)	x
-#define ARM_EXIT_DISCARD(x)
-
 OUTPUT_ARCH(aarch64)
 ENTRY(_text)
 
@@ -72,8 +68,8 @@ jiffies = jiffies_64;
 
 /*
  * The size of the PE/COFF section that covers the kernel image, which
- * runs from stext to _edata, must be a round multiple of the PE/COFF
- * FileAlignment, which we set to its minimum value of 0x200. 'stext'
+ * runs from _stext to _edata, must be a round multiple of the PE/COFF
+ * FileAlignment, which we set to its minimum value of 0x200. '_stext'
  * itself is 4 KB aligned, so padding out _edata to a 0x200 aligned
  * boundary should be sufficient.
  */
@@ -95,8 +91,6 @@ SECTIONS
 	 * order of matching.
 	 */
 	/DISCARD/ : {
-		ARM_EXIT_DISCARD(EXIT_TEXT)
-		ARM_EXIT_DISCARD(EXIT_DATA)
 		EXIT_CALL
 		*(.discard)
 		*(.discard.*)
@@ -139,6 +133,7 @@ SECTIONS
 
 	idmap_pg_dir = .;
 	. += IDMAP_DIR_SIZE;
+	idmap_pg_end = .;
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	tramp_pg_dir = .;
@@ -161,7 +156,7 @@ SECTIONS
 
 	__exittext_begin = .;
 	.exit.text : {
-		ARM_EXIT_KEEP(EXIT_TEXT)
+		EXIT_TEXT
 	}
 	__exittext_end = .;
 
@@ -175,7 +170,7 @@ SECTIONS
 		*(.altinstr_replacement)
 	}
 
-	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(SEGMENT_ALIGN);
 	__inittext_end = .;
 	__initdata_begin = .;
 
@@ -188,7 +183,7 @@ SECTIONS
 		*(.init.rodata.* .init.bss)	/* from the EFI stub */
 	}
 	.exit.data : {
-		ARM_EXIT_KEEP(EXIT_DATA)
+		EXIT_DATA
 	}
 
 	PERCPU_SECTION(L1_CACHE_BYTES)
@@ -246,6 +241,7 @@ SECTIONS
 	. += INIT_DIR_SIZE;
 	init_pg_end = .;
 
+	. = ALIGN(SEGMENT_ALIGN);
 	__pecoff_data_size = ABSOLUTE(. - __initdata_begin);
 	_end = .;
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 23ebe51410f0..50a279d3ddd7 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -200,6 +200,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+
+	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
+		int i;
+
+		for (i = 0; i < 16; i++)
+			*vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i);
+	}
 out:
 	return err;
 }
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index d22d0534dd60..90186cf6473e 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -18,6 +18,7 @@
 
 #define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
 #define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+#define CPU_SP_EL0_OFFSET	(CPU_XREG_OFFSET(30) + 8)
 
 	.text
 	.pushsection	.hyp.text, "ax"
@@ -47,6 +48,16 @@
 	ldp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
 .endm
 
+.macro save_sp_el0 ctxt, tmp
+	mrs	\tmp,	sp_el0
+	str	\tmp,	[\ctxt, #CPU_SP_EL0_OFFSET]
+.endm
+
+.macro restore_sp_el0 ctxt, tmp
+	ldr	\tmp,	  [\ctxt, #CPU_SP_EL0_OFFSET]
+	msr	sp_el0, \tmp
+.endm
+
 /*
  * u64 __guest_enter(struct kvm_vcpu *vcpu,
  *		     struct kvm_cpu_context *host_ctxt);
@@ -60,6 +71,9 @@ SYM_FUNC_START(__guest_enter)
 	// Store the host regs
 	save_callee_saved_regs x1
 
+	// Save the host's sp_el0
+	save_sp_el0	x1, x2
+
 	// Now the host state is stored if we have a pending RAS SError it must
 	// affect the host. If any asynchronous exception is pending we defer
 	// the guest entry. The DSB isn't necessary before v8.2 as any SError
@@ -83,6 +97,9 @@ alternative_else_nop_endif
 	// when this feature is enabled for kernel code.
 	ptrauth_switch_to_guest x29, x0, x1, x2
 
+	// Restore the guest's sp_el0
+	restore_sp_el0 x29, x0
+
 	// Restore guest regs x0-x17
 	ldp	x0, x1,   [x29, #CPU_XREG_OFFSET(0)]
 	ldp	x2, x3,   [x29, #CPU_XREG_OFFSET(2)]
@@ -130,6 +147,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// Store the guest regs x18-x29, lr
 	save_callee_saved_regs x1
 
+	// Store the guest's sp_el0
+	save_sp_el0	x1, x2
+
 	get_host_ctxt	x2, x3
 
 	// Macro ptrauth_switch_to_guest format:
@@ -139,6 +159,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// when this feature is enabled for kernel code.
 	ptrauth_switch_to_host x1, x2, x3, x4, x5
 
+	// Restore the hosts's sp_el0
+	restore_sp_el0 x2, x3
+
 	// Now restore the host regs
 	restore_callee_saved_regs x2
 
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index c2a13ab3c471..9c5cfb04170e 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -198,7 +198,6 @@ SYM_CODE_END(__hyp_panic)
 .macro invalid_vector	label, target = __hyp_panic
 	.align	2
 SYM_CODE_START(\label)
-\label:
 	b \target
 SYM_CODE_END(\label)
 .endm
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 8a1e81a400e0..1336e6f0acdf 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -138,7 +138,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 
 	write_sysreg(val, cptr_el2);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
 
 		isb();
@@ -181,7 +181,7 @@ static void deactivate_traps_vhe(void)
 	 * above before we can switch to the EL2/EL0 translation regime used by
 	 * the host.
 	 */
-	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT_VHE));
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 	write_sysreg(vectors, vbar_el1);
@@ -192,7 +192,7 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	u64 mdcr_el2 = read_sysreg(mdcr_el2);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
 
 		/*
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 75b1925763f1..ea5d22fbdacf 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -15,8 +15,9 @@
 /*
  * Non-VHE: Both host and guest must save everything.
  *
- * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and pstate,
- * which are handled as part of the el2 return state) on every switch.
+ * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
+ * pstate, which are handled as part of the el2 return state) on every
+ * switch (sp_el0 is being dealt with in the assembly code).
  * tpidr_el0 and tpidrro_el0 only need to be switched when going
  * to host userspace or a different VCPU.  EL1 registers only need to be
  * switched when potentially going to run a different VCPU.  The latter two
@@ -26,12 +27,6 @@
 static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
-
-	/*
-	 * The host arm64 Linux uses sp_el0 to point to 'current' and it must
-	 * therefore be saved/restored on every entry/exit to/from the guest.
-	 */
-	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
 }
 
 static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
@@ -99,12 +94,6 @@ NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
 static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
 	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
-
-	/*
-	 * The host arm64 Linux uses sp_el0 to point to 'current' and it must
-	 * therefore be saved/restored on every entry/exit to/from the guest.
-	 */
-	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
 }
 
 static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
@@ -118,7 +107,8 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
 
-	if (!cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (has_vhe() ||
+	    !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
 		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
 	} else	if (!ctxt->__hyp_running_vcpu) {
@@ -149,7 +139,8 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) &&
+	if (!has_vhe() &&
+	    cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) &&
 	    ctxt->__hyp_running_vcpu) {
 		/*
 		 * Must only be done for host registers, hence the context
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index ceaddbe4279f..d063a576d511 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -23,7 +23,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 
 	local_irq_save(cxt->flags);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		/*
 		 * For CPUs that are affected by ARM errata 1165522 or 1530923,
 		 * we cannot trust stage-1 to be in a correct state at that
@@ -63,7 +63,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 						  struct tlb_inv_context *cxt)
 {
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
 
 		/*
@@ -79,8 +79,9 @@ static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 		isb();
 	}
 
+	/* __load_guest_stage2() includes an ISB for the workaround. */
 	__load_guest_stage2(kvm);
-	isb();
+	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
 static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
@@ -103,7 +104,7 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
 	isb();
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		/* Restore the registers to what they were */
 		write_sysreg_el1(cxt->tcr, SYS_TCR);
 		write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
@@ -117,7 +118,7 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 {
 	write_sysreg(0, vttbr_el2);
 
-	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		/* Ensure write of the host VMID */
 		isb();
 		/* Restore the host's TCR_EL1 */
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 30b7ea680f66..70cd7bcca433 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -46,14 +46,6 @@ static const struct kvm_regs default_regs_reset32 = {
 			PSR_AA32_I_BIT | PSR_AA32_F_BIT),
 };
 
-static bool cpu_has_32bit_el1(void)
-{
-	u64 pfr0;
-
-	pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
-	return !!(pfr0 & 0x20);
-}
-
 /**
  * kvm_arch_vm_ioctl_check_extension
  *
@@ -66,7 +58,7 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 
 	switch (ext) {
 	case KVM_CAP_ARM_EL1_32BIT:
-		r = cpu_has_32bit_el1();
+		r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1);
 		break;
 	case KVM_CAP_GUEST_DEBUG_HW_BPS:
 		r = get_num_brps();
@@ -288,7 +280,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpu_has_32bit_el1())
+			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
 				goto out;
 			cpu_reset = &default_regs_reset32;
 		} else {
@@ -340,11 +332,50 @@ out:
 	return ret;
 }
 
-void kvm_set_ipa_limit(void)
+u32 get_kvm_ipa_limit(void)
+{
+	return kvm_ipa_limit;
+}
+
+int kvm_set_ipa_limit(void)
 {
-	unsigned int ipa_max, pa_max, va_max, parange;
+	unsigned int ipa_max, pa_max, va_max, parange, tgran_2;
+	u64 mmfr0;
+
+	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	parange = cpuid_feature_extract_unsigned_field(mmfr0,
+				ID_AA64MMFR0_PARANGE_SHIFT);
+
+	/*
+	 * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at
+	 * Stage-2. If not, things will stop very quickly.
+	 */
+	switch (PAGE_SIZE) {
+	default:
+	case SZ_4K:
+		tgran_2 = ID_AA64MMFR0_TGRAN4_2_SHIFT;
+		break;
+	case SZ_16K:
+		tgran_2 = ID_AA64MMFR0_TGRAN16_2_SHIFT;
+		break;
+	case SZ_64K:
+		tgran_2 = ID_AA64MMFR0_TGRAN64_2_SHIFT;
+		break;
+	}
+
+	switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
+	default:
+	case 1:
+		kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
+		return -EINVAL;
+	case 0:
+		kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
+		break;
+	case 2:
+		kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
+		break;
+	}
 
-	parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 0x7;
 	pa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
 
 	/* Clamp the IPA limit to the PA size supported by the kernel */
@@ -378,6 +409,8 @@ void kvm_set_ipa_limit(void)
 	     "KVM IPA limit (%d bit) is smaller than default size\n", ipa_max);
 	kvm_ipa_limit = ipa_max;
 	kvm_info("IPA Size Limit: %dbits\n", kvm_ipa_limit);
+
+	return 0;
 }
 
 /*
@@ -390,7 +423,7 @@ void kvm_set_ipa_limit(void)
  */
 int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 {
-	u64 vtcr = VTCR_EL2_FLAGS;
+	u64 vtcr = VTCR_EL2_FLAGS, mmfr0;
 	u32 parange, phys_shift;
 	u8 lvls;
 
@@ -406,7 +439,9 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
 		phys_shift = KVM_PHYS_SHIFT;
 	}
 
-	parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 7;
+	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	parange = cpuid_feature_extract_unsigned_field(mmfr0,
+				ID_AA64MMFR0_PARANGE_SHIFT);
 	if (parange > ID_AA64MMFR0_PARANGE_MAX)
 		parange = ID_AA64MMFR0_PARANGE_MAX;
 	vtcr |= parange << VTCR_EL2_PS_SHIFT;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 51db934702b6..7d7a39b01135 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1456,9 +1456,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_SANITISED(MVFR1_EL1),
 	ID_SANITISED(MVFR2_EL1),
 	ID_UNALLOCATED(3,3),
-	ID_UNALLOCATED(3,4),
-	ID_UNALLOCATED(3,5),
-	ID_UNALLOCATED(3,6),
+	ID_SANITISED(ID_PFR2_EL1),
+	ID_HIDDEN(ID_DFR1_EL1),
+	ID_SANITISED(ID_MMFR5_EL1),
 	ID_UNALLOCATED(3,7),
 
 	/* AArch64 ID registers */
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 8e25e89ad01f..0f8a3a9e3795 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -20,36 +20,36 @@
  *	x0 - bytes not copied
  */
 
-	.macro ldrb1 ptr, regB, val
-	uao_user_alternative 9998f, ldrb, ldtrb, \ptr, \regB, \val
+	.macro ldrb1 reg, ptr, val
+	uao_user_alternative 9998f, ldrb, ldtrb, \reg, \ptr, \val
 	.endm
 
-	.macro strb1 ptr, regB, val
-	strb \ptr, [\regB], \val
+	.macro strb1 reg, ptr, val
+	strb \reg, [\ptr], \val
 	.endm
 
-	.macro ldrh1 ptr, regB, val
-	uao_user_alternative 9998f, ldrh, ldtrh, \ptr, \regB, \val
+	.macro ldrh1 reg, ptr, val
+	uao_user_alternative 9998f, ldrh, ldtrh, \reg, \ptr, \val
 	.endm
 
-	.macro strh1 ptr, regB, val
-	strh \ptr, [\regB], \val
+	.macro strh1 reg, ptr, val
+	strh \reg, [\ptr], \val
 	.endm
 
-	.macro ldr1 ptr, regB, val
-	uao_user_alternative 9998f, ldr, ldtr, \ptr, \regB, \val
+	.macro ldr1 reg, ptr, val
+	uao_user_alternative 9998f, ldr, ldtr, \reg, \ptr, \val
 	.endm
 
-	.macro str1 ptr, regB, val
-	str \ptr, [\regB], \val
+	.macro str1 reg, ptr, val
+	str \reg, [\ptr], \val
 	.endm
 
-	.macro ldp1 ptr, regB, regC, val
-	uao_ldp 9998f, \ptr, \regB, \regC, \val
+	.macro ldp1 reg1, reg2, ptr, val
+	uao_ldp 9998f, \reg1, \reg2, \ptr, \val
 	.endm
 
-	.macro stp1 ptr, regB, regC, val
-	stp \ptr, \regB, [\regC], \val
+	.macro stp1 reg1, reg2, ptr, val
+	stp \reg1, \reg2, [\ptr], \val
 	.endm
 
 end	.req	x5
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 667139013ed1..80e37ada0ee1 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -21,36 +21,36 @@
  * Returns:
  *	x0 - bytes not copied
  */
-	.macro ldrb1 ptr, regB, val
-	uao_user_alternative 9998f, ldrb, ldtrb, \ptr, \regB, \val
+	.macro ldrb1 reg, ptr, val
+	uao_user_alternative 9998f, ldrb, ldtrb, \reg, \ptr, \val
 	.endm
 
-	.macro strb1 ptr, regB, val
-	uao_user_alternative 9998f, strb, sttrb, \ptr, \regB, \val
+	.macro strb1 reg, ptr, val
+	uao_user_alternative 9998f, strb, sttrb, \reg, \ptr, \val
 	.endm
 
-	.macro ldrh1 ptr, regB, val
-	uao_user_alternative 9998f, ldrh, ldtrh, \ptr, \regB, \val
+	.macro ldrh1 reg, ptr, val
+	uao_user_alternative 9998f, ldrh, ldtrh, \reg, \ptr, \val
 	.endm
 
-	.macro strh1 ptr, regB, val
-	uao_user_alternative 9998f, strh, sttrh, \ptr, \regB, \val
+	.macro strh1 reg, ptr, val
+	uao_user_alternative 9998f, strh, sttrh, \reg, \ptr, \val
 	.endm
 
-	.macro ldr1 ptr, regB, val
-	uao_user_alternative 9998f, ldr, ldtr, \ptr, \regB, \val
+	.macro ldr1 reg, ptr, val
+	uao_user_alternative 9998f, ldr, ldtr, \reg, \ptr, \val
 	.endm
 
-	.macro str1 ptr, regB, val
-	uao_user_alternative 9998f, str, sttr, \ptr, \regB, \val
+	.macro str1 reg, ptr, val
+	uao_user_alternative 9998f, str, sttr, \reg, \ptr, \val
 	.endm
 
-	.macro ldp1 ptr, regB, regC, val
-	uao_ldp 9998f, \ptr, \regB, \regC, \val
+	.macro ldp1 reg1, reg2, ptr, val
+	uao_ldp 9998f, \reg1, \reg2, \ptr, \val
 	.endm
 
-	.macro stp1 ptr, regB, regC, val
-	uao_stp 9998f, \ptr, \regB, \regC, \val
+	.macro stp1 reg1, reg2, ptr, val
+	uao_stp 9998f, \reg1, \reg2, \ptr, \val
 	.endm
 
 end	.req	x5
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 1a104d0089f3..4ec59704b8f2 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -19,36 +19,36 @@
  * Returns:
  *	x0 - bytes not copied
  */
-	.macro ldrb1 ptr, regB, val
-	ldrb  \ptr, [\regB], \val
+	.macro ldrb1 reg, ptr, val
+	ldrb  \reg, [\ptr], \val
 	.endm
 
-	.macro strb1 ptr, regB, val
-	uao_user_alternative 9998f, strb, sttrb, \ptr, \regB, \val
+	.macro strb1 reg, ptr, val
+	uao_user_alternative 9998f, strb, sttrb, \reg, \ptr, \val
 	.endm
 
-	.macro ldrh1 ptr, regB, val
-	ldrh  \ptr, [\regB], \val
+	.macro ldrh1 reg, ptr, val
+	ldrh  \reg, [\ptr], \val
 	.endm
 
-	.macro strh1 ptr, regB, val
-	uao_user_alternative 9998f, strh, sttrh, \ptr, \regB, \val
+	.macro strh1 reg, ptr, val
+	uao_user_alternative 9998f, strh, sttrh, \reg, \ptr, \val
 	.endm
 
-	.macro ldr1 ptr, regB, val
-	ldr \ptr, [\regB], \val
+	.macro ldr1 reg, ptr, val
+	ldr \reg, [\ptr], \val
 	.endm
 
-	.macro str1 ptr, regB, val
-	uao_user_alternative 9998f, str, sttr, \ptr, \regB, \val
+	.macro str1 reg, ptr, val
+	uao_user_alternative 9998f, str, sttr, \reg, \ptr, \val
 	.endm
 
-	.macro ldp1 ptr, regB, regC, val
-	ldp \ptr, \regB, [\regC], \val
+	.macro ldp1 reg1, reg2, ptr, val
+	ldp \reg1, \reg2, [\ptr], \val
 	.endm
 
-	.macro stp1 ptr, regB, regC, val
-	uao_stp 9998f, \ptr, \regB, \regC, \val
+	.macro stp1 reg1, reg2, ptr, val
+	uao_stp 9998f, \reg1, \reg2, \ptr, \val
 	.endm
 
 end	.req	x5
diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S
index 243e107e9896..0f9e10ecda23 100644
--- a/arch/arm64/lib/crc32.S
+++ b/arch/arm64/lib/crc32.S
@@ -9,7 +9,7 @@
 #include <asm/alternative.h>
 #include <asm/assembler.h>
 
-	.cpu		generic+crc
+	.arch		armv8-a+crc
 
 	.macro		__crc32, c
 	cmp		x2, #16
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index 9f382adfa88a..e0bf83d556f2 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/arch/arm64/lib/memcpy.S
@@ -24,36 +24,36 @@
  * Returns:
  *	x0 - dest
  */
-	.macro ldrb1 ptr, regB, val
-	ldrb  \ptr, [\regB], \val
+	.macro ldrb1 reg, ptr, val
+	ldrb  \reg, [\ptr], \val
 	.endm
 
-	.macro strb1 ptr, regB, val
-	strb \ptr, [\regB], \val
+	.macro strb1 reg, ptr, val
+	strb \reg, [\ptr], \val
 	.endm
 
-	.macro ldrh1 ptr, regB, val
-	ldrh  \ptr, [\regB], \val
+	.macro ldrh1 reg, ptr, val
+	ldrh  \reg, [\ptr], \val
 	.endm
 
-	.macro strh1 ptr, regB, val
-	strh \ptr, [\regB], \val
+	.macro strh1 reg, ptr, val
+	strh \reg, [\ptr], \val
 	.endm
 
-	.macro ldr1 ptr, regB, val
-	ldr \ptr, [\regB], \val
+	.macro ldr1 reg, ptr, val
+	ldr \reg, [\ptr], \val
 	.endm
 
-	.macro str1 ptr, regB, val
-	str \ptr, [\regB], \val
+	.macro str1 reg, ptr, val
+	str \reg, [\ptr], \val
 	.endm
 
-	.macro ldp1 ptr, regB, regC, val
-	ldp \ptr, \regB, [\regC], \val
+	.macro ldp1 reg1, reg2, ptr, val
+	ldp \reg1, \reg2, [\ptr], \val
 	.endm
 
-	.macro stp1 ptr, regB, regC, val
-	stp \ptr, \regB, [\regC], \val
+	.macro stp1 reg1, reg2, ptr, val
+	stp \reg1, \reg2, [\ptr], \val
 	.endm
 
 	.weak memcpy
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 9b26f9a88724..d702d60e64da 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -92,6 +92,9 @@ static void set_reserved_asid_bits(void)
 		bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 }
 
+#define asid_gen_match(asid) \
+	(!(((asid) ^ atomic64_read(&asid_generation)) >> asid_bits))
+
 static void flush_context(void)
 {
 	int i;
@@ -220,8 +223,7 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 	 *   because atomic RmWs are totally ordered for a given location.
 	 */
 	old_active_asid = atomic64_read(&per_cpu(active_asids, cpu));
-	if (old_active_asid &&
-	    !((asid ^ atomic64_read(&asid_generation)) >> asid_bits) &&
+	if (old_active_asid && asid_gen_match(asid) &&
 	    atomic64_cmpxchg_relaxed(&per_cpu(active_asids, cpu),
 				     old_active_asid, asid))
 		goto switch_mm_fastpath;
@@ -229,7 +231,7 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
 	/* Check that our ASID belongs to the current generation. */
 	asid = atomic64_read(&mm->context.id);
-	if ((asid ^ atomic64_read(&asid_generation)) >> asid_bits) {
+	if (!asid_gen_match(asid)) {
 		asid = new_context(mm);
 		atomic64_set(&mm->context.id, asid);
 	}
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 860c00ec8bd3..78163b7a7dde 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -146,6 +146,11 @@ static const struct prot_bits pte_bits[] = {
 		.set	= "UXN",
 		.clear	= "   ",
 	}, {
+		.mask	= PTE_GP,
+		.val	= PTE_GP,
+		.set	= "GP",
+		.clear	= "  ",
+	}, {
 		.mask	= PTE_ATTRINDX_MASK,
 		.val	= PTE_ATTRINDX(MT_DEVICE_nGnRnE),
 		.set	= "DEVICE/nGnRnE",
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index bbeb6a5a6ba6..0be3355e3499 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -230,6 +230,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		ptep = (pte_t *)pudp;
 	} else if (sz == (CONT_PTE_SIZE)) {
 		pmdp = pmd_alloc(mm, pudp, addr);
+		if (!pmdp)
+			return NULL;
 
 		WARN_ON(addr & (sz - 1));
 		/*
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index e42727e3568e..d2df416b840e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -272,7 +272,7 @@ int pfn_valid(unsigned long pfn)
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 
-	if (!valid_section(__nr_to_section(pfn_to_section_nr(pfn))))
+	if (!valid_section(__pfn_to_section(pfn)))
 		return 0;
 #endif
 	return memblock_is_map_memory(addr);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index a374e4f51a62..c299b73dd5e4 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -610,6 +610,22 @@ core_initcall(map_entry_trampoline);
 #endif
 
 /*
+ * Open coded check for BTI, only for use to determine configuration
+ * for early mappings for before the cpufeature code has run.
+ */
+static bool arm64_early_this_cpu_has_bti(void)
+{
+	u64 pfr1;
+
+	if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+		return false;
+
+	pfr1 = read_sysreg_s(SYS_ID_AA64PFR1_EL1);
+	return cpuid_feature_extract_unsigned_field(pfr1,
+						    ID_AA64PFR1_BT_SHIFT);
+}
+
+/*
  * Create fine-grained mappings for the kernel.
  */
 static void __init map_kernel(pgd_t *pgdp)
@@ -625,6 +641,14 @@ static void __init map_kernel(pgd_t *pgdp)
 	pgprot_t text_prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
 
 	/*
+	 * If we have a CPU that supports BTI and a kernel built for
+	 * BTI then mark the kernel executable text as guarded pages
+	 * now so we don't have to rewrite the page tables later.
+	 */
+	if (arm64_early_this_cpu_has_bti())
+		text_prot = __pgprot_modify(text_prot, PTE_GP, PTE_GP);
+
+	/*
 	 * Only rodata will be remapped with different permissions later on,
 	 * all other segments are allowed to use contiguous mappings.
 	 */
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 250c49008d73..bde08090b838 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -126,13 +126,13 @@ int set_memory_nx(unsigned long addr, int numpages)
 {
 	return change_memory_common(addr, numpages,
 					__pgprot(PTE_PXN),
-					__pgprot(0));
+					__pgprot(PTE_MAYBE_GP));
 }
 
 int set_memory_x(unsigned long addr, int numpages)
 {
 	return change_memory_common(addr, numpages,
-					__pgprot(0),
+					__pgprot(PTE_MAYBE_GP),
 					__pgprot(PTE_PXN));
 }
 
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 197a9ba2d5ea..b7bebb12a56d 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -58,6 +58,8 @@
  * cpu_do_suspend - save CPU registers context
  *
  * x0: virtual address of context pointer
+ *
+ * This must be kept in sync with struct cpu_suspend_ctx in <asm/suspend.h>.
  */
 SYM_FUNC_START(cpu_do_suspend)
 	mrs	x2, tpidr_el0
@@ -82,6 +84,11 @@ alternative_endif
 	stp	x8, x9, [x0, #48]
 	stp	x10, x11, [x0, #64]
 	stp	x12, x13, [x0, #80]
+	/*
+	 * Save x18 as it may be used as a platform register, e.g. by shadow
+	 * call stack.
+	 */
+	str	x18, [x0, #96]
 	ret
 SYM_FUNC_END(cpu_do_suspend)
 
@@ -98,6 +105,13 @@ SYM_FUNC_START(cpu_do_resume)
 	ldp	x9, x10, [x0, #48]
 	ldp	x11, x12, [x0, #64]
 	ldp	x13, x14, [x0, #80]
+	/*
+	 * Restore x18, as it may be used as a platform register, and clear
+	 * the buffer to minimize the risk of exposure when used for shadow
+	 * call stack.
+	 */
+	ldr	x18, [x0, #96]
+	str	xzr, [x0, #96]
 	msr	tpidr_el0, x2
 	msr	tpidrro_el0, x3
 	msr	contextidr_el1, x4
@@ -139,7 +153,7 @@ alternative_if ARM64_HAS_RAS_EXTN
 	msr_s	SYS_DISR_EL1, xzr
 alternative_else_nop_endif
 
-	ptrauth_keys_install_kernel x14, 0, x1, x2, x3
+	ptrauth_keys_install_kernel_nosync x14, x1, x2, x3
 	isb
 	ret
 SYM_FUNC_END(cpu_do_resume)
@@ -386,8 +400,6 @@ SYM_FUNC_END(idmap_kpti_install_ng_mappings)
  *
  *	Initialise the processor for turning the MMU on.
  *
- * Input:
- *	x0 with a flag ARM64_CPU_BOOT_PRIMARY/ARM64_CPU_BOOT_SECONDARY/ARM64_CPU_RUNTIME.
  * Output:
  *	Return in x0 the value of the SCTLR_EL1 register.
  */
@@ -446,51 +458,9 @@ SYM_FUNC_START(__cpu_setup)
 1:
 #endif	/* CONFIG_ARM64_HW_AFDBM */
 	msr	tcr_el1, x10
-	mov	x1, x0
 	/*
 	 * Prepare SCTLR
 	 */
 	mov_q	x0, SCTLR_EL1_SET
-
-#ifdef CONFIG_ARM64_PTR_AUTH
-	/* No ptrauth setup for run time cpus */
-	cmp	x1, #ARM64_CPU_RUNTIME
-	b.eq	3f
-
-	/* Check if the CPU supports ptrauth */
-	mrs	x2, id_aa64isar1_el1
-	ubfx	x2, x2, #ID_AA64ISAR1_APA_SHIFT, #8
-	cbz	x2, 3f
-
-	/*
-	 * The primary cpu keys are reset here and can be
-	 * re-initialised with some proper values later.
-	 */
-	msr_s	SYS_APIAKEYLO_EL1, xzr
-	msr_s	SYS_APIAKEYHI_EL1, xzr
-
-	/* Just enable ptrauth for primary cpu */
-	cmp	x1, #ARM64_CPU_BOOT_PRIMARY
-	b.eq	2f
-
-	/* if !system_supports_address_auth() then skip enable */
-alternative_if_not ARM64_HAS_ADDRESS_AUTH
-	b	3f
-alternative_else_nop_endif
-
-	/* Install ptrauth key for secondary cpus */
-	adr_l	x2, secondary_data
-	ldr	x3, [x2, #CPU_BOOT_TASK]	// get secondary_data.task
-	cbz	x3, 2f				// check for slow booting cpus
-	ldp	x3, x4, [x2, #CPU_BOOT_PTRAUTH_KEY]
-	msr_s	SYS_APIAKEYLO_EL1, x3
-	msr_s	SYS_APIAKEYHI_EL1, x4
-
-2:	/* Enable ptrauth instructions */
-	ldr	x2, =SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
-		     SCTLR_ELx_ENDA | SCTLR_ELx_ENDB
-	orr	x0, x0, x2
-3:
-#endif
 	ret					// return to head.S
 SYM_FUNC_END(__cpu_setup)
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index eb73f9f72c46..cc0cf0f5c7c3 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -100,6 +100,14 @@
 /* Rd = Rn OP imm12 */
 #define A64_ADD_I(sf, Rd, Rn, imm12) A64_ADDSUB_IMM(sf, Rd, Rn, imm12, ADD)
 #define A64_SUB_I(sf, Rd, Rn, imm12) A64_ADDSUB_IMM(sf, Rd, Rn, imm12, SUB)
+#define A64_ADDS_I(sf, Rd, Rn, imm12) \
+	A64_ADDSUB_IMM(sf, Rd, Rn, imm12, ADD_SETFLAGS)
+#define A64_SUBS_I(sf, Rd, Rn, imm12) \
+	A64_ADDSUB_IMM(sf, Rd, Rn, imm12, SUB_SETFLAGS)
+/* Rn + imm12; set condition flags */
+#define A64_CMN_I(sf, Rn, imm12) A64_ADDS_I(sf, A64_ZR, Rn, imm12)
+/* Rn - imm12; set condition flags */
+#define A64_CMP_I(sf, Rn, imm12) A64_SUBS_I(sf, A64_ZR, Rn, imm12)
 /* Rd = Rn */
 #define A64_MOV(sf, Rd, Rn) A64_ADD_I(sf, Rd, Rn, 0)
 
@@ -189,4 +197,26 @@
 /* Rn & Rm; set condition flags */
 #define A64_TST(sf, Rn, Rm) A64_ANDS(sf, A64_ZR, Rn, Rm)
 
+/* Logical (immediate) */
+#define A64_LOGIC_IMM(sf, Rd, Rn, imm, type) ({ \
+	u64 imm64 = (sf) ? (u64)imm : (u64)(u32)imm; \
+	aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_##type, \
+		A64_VARIANT(sf), Rn, Rd, imm64); \
+})
+/* Rd = Rn OP imm */
+#define A64_AND_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, AND)
+#define A64_ORR_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, ORR)
+#define A64_EOR_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, EOR)
+#define A64_ANDS_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, AND_SETFLAGS)
+/* Rn & imm; set condition flags */
+#define A64_TST_I(sf, Rn, imm) A64_ANDS_I(sf, A64_ZR, Rn, imm)
+
+/* HINTs */
+#define A64_HINT(x) aarch64_insn_gen_hint(x)
+
+/* BTI */
+#define A64_BTI_C  A64_HINT(AARCH64_INSN_HINT_BTIC)
+#define A64_BTI_J  A64_HINT(AARCH64_INSN_HINT_BTIJ)
+#define A64_BTI_JC A64_HINT(AARCH64_INSN_HINT_BTIJC)
+
 #endif /* _BPF_JIT_H */
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index cdc79de0c794..3cb25b43b368 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -167,11 +167,21 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 	return to - from;
 }
 
+static bool is_addsub_imm(u32 imm)
+{
+	/* Either imm12 or shifted imm12. */
+	return !(imm & ~0xfff) || !(imm & ~0xfff000);
+}
+
 /* Stack must be multiples of 16B */
 #define STACK_ALIGN(sz) (((sz) + 15) & ~15)
 
 /* Tail call offset to jump into */
+#if IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)
+#define PROLOGUE_OFFSET 8
+#else
 #define PROLOGUE_OFFSET 7
+#endif
 
 static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 {
@@ -208,6 +218,10 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	 *
 	 */
 
+	/* BTI landing pad */
+	if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+		emit(A64_BTI_C, ctx);
+
 	/* Save FP and LR registers to stay align with ARM64 AAPCS */
 	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
 	emit(A64_MOV(1, A64_FP, A64_SP), ctx);
@@ -230,6 +244,10 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 				    cur_offset, PROLOGUE_OFFSET);
 			return -1;
 		}
+
+		/* BTI landing pad for the tail call, done with a BR */
+		if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+			emit(A64_BTI_J, ctx);
 	}
 
 	ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth);
@@ -356,6 +374,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	const bool isdw = BPF_SIZE(code) == BPF_DW;
 	u8 jmp_cond, reg;
 	s32 jmp_offset;
+	u32 a64_insn;
 
 #define check_imm(bits, imm) do {				\
 	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
@@ -478,28 +497,55 @@ emit_bswap_uxt:
 	/* dst = dst OP imm */
 	case BPF_ALU | BPF_ADD | BPF_K:
 	case BPF_ALU64 | BPF_ADD | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_ADD(is64, dst, dst, tmp), ctx);
+		if (is_addsub_imm(imm)) {
+			emit(A64_ADD_I(is64, dst, dst, imm), ctx);
+		} else if (is_addsub_imm(-imm)) {
+			emit(A64_SUB_I(is64, dst, dst, -imm), ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_ADD(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_SUB | BPF_K:
 	case BPF_ALU64 | BPF_SUB | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_SUB(is64, dst, dst, tmp), ctx);
+		if (is_addsub_imm(imm)) {
+			emit(A64_SUB_I(is64, dst, dst, imm), ctx);
+		} else if (is_addsub_imm(-imm)) {
+			emit(A64_ADD_I(is64, dst, dst, -imm), ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_SUB(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_AND | BPF_K:
 	case BPF_ALU64 | BPF_AND | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_AND(is64, dst, dst, tmp), ctx);
+		a64_insn = A64_AND_I(is64, dst, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_AND(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_OR | BPF_K:
 	case BPF_ALU64 | BPF_OR | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_ORR(is64, dst, dst, tmp), ctx);
+		a64_insn = A64_ORR_I(is64, dst, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_ORR(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_XOR | BPF_K:
 	case BPF_ALU64 | BPF_XOR | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_EOR(is64, dst, dst, tmp), ctx);
+		a64_insn = A64_EOR_I(is64, dst, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_EOR(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_MUL | BPF_K:
 	case BPF_ALU64 | BPF_MUL | BPF_K:
@@ -623,13 +669,24 @@ emit_cond_jmp:
 	case BPF_JMP32 | BPF_JSLT | BPF_K:
 	case BPF_JMP32 | BPF_JSGE | BPF_K:
 	case BPF_JMP32 | BPF_JSLE | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_CMP(is64, dst, tmp), ctx);
+		if (is_addsub_imm(imm)) {
+			emit(A64_CMP_I(is64, dst, imm), ctx);
+		} else if (is_addsub_imm(-imm)) {
+			emit(A64_CMN_I(is64, dst, -imm), ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_CMP(is64, dst, tmp), ctx);
+		}
 		goto emit_cond_jmp;
 	case BPF_JMP | BPF_JSET | BPF_K:
 	case BPF_JMP32 | BPF_JSET | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_TST(is64, dst, tmp), ctx);
+		a64_insn = A64_TST_I(is64, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_TST(is64, dst, tmp), ctx);
+		}
 		goto emit_cond_jmp;
 	/* function call */
 	case BPF_JMP | BPF_CALL:
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 94545d50d40f..bd31ab12f77d 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -8,6 +8,7 @@ config CSKY
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS if NR_CPUS>2
+	select ARCH_WANT_FRAME_POINTERS if !CPU_CK610
 	select COMMON_CLK
 	select CLKSRC_MMIO
 	select CSKY_MPINTC if CPU_CK860
@@ -38,6 +39,7 @@ config CSKY
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_COPY_THREAD_TLS
+	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_FUNCTION_TRACER
diff --git a/arch/csky/Makefile b/arch/csky/Makefile
index fb1bbbd91954..37f593a4bf53 100644
--- a/arch/csky/Makefile
+++ b/arch/csky/Makefile
@@ -47,7 +47,7 @@ ifeq ($(CSKYABI),abiv2)
 KBUILD_CFLAGS += -mno-stack-size
 endif
 
-ifdef CONFIG_STACKTRACE
+ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS += -mbacktrace
 endif
 
diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h
index 5056ebb902d1..13c23e2c707c 100644
--- a/arch/csky/abiv1/inc/abi/entry.h
+++ b/arch/csky/abiv1/inc/abi/entry.h
@@ -80,7 +80,6 @@
 .endm
 
 .macro	RESTORE_ALL
-	psrclr  ie
 	ldw	lr, (sp, 4)
 	ldw     a0, (sp, 8)
 	mtcr    a0, epc
@@ -167,17 +166,12 @@
 	 *   BA     Reserved  C   D   V
 	 */
 	cprcr	r6, cpcr30
-	lsri	r6, 28
-	lsli	r6, 28
+	lsri	r6, 29
+	lsli	r6, 29
 	addi	r6, 0xe
 	cpwcr	r6, cpcr30
 
 	movi	r6, 0
 	cpwcr	r6, cpcr31
 .endm
-
-.macro ANDI_R3 rx, imm
-	lsri	\rx, 3
-	andi	\rx, (\imm >> 3)
-.endm
 #endif /* __ASM_CSKY_ENTRY_H */
diff --git a/arch/csky/abiv2/inc/abi/entry.h b/arch/csky/abiv2/inc/abi/entry.h
index a99aff555a0a..4fdd6c12e7ff 100644
--- a/arch/csky/abiv2/inc/abi/entry.h
+++ b/arch/csky/abiv2/inc/abi/entry.h
@@ -13,6 +13,8 @@
 #define LSAVE_A1	28
 #define LSAVE_A2	32
 #define LSAVE_A3	36
+#define LSAVE_A4	40
+#define LSAVE_A5	44
 
 #define KSPTOUSP
 #define USPTOKSP
@@ -63,7 +65,6 @@
 .endm
 
 .macro	RESTORE_ALL
-	psrclr  ie
 	ldw	tls, (sp, 0)
 	ldw	lr, (sp, 4)
 	ldw	a0, (sp, 8)
@@ -285,8 +286,8 @@
 	 */
 	mfcr	r6, cr<30, 15> /* Get MSA0 */
 2:
-	lsri	r6, 28
-	lsli	r6, 28
+	lsri	r6, 29
+	lsli	r6, 29
 	addi	r6, 0x1ce
 	mtcr	r6, cr<30, 15> /* Set MSA0 */
 
@@ -301,9 +302,4 @@
 	jmpi	3f /* jump to va */
 3:
 .endm
-
-.macro ANDI_R3 rx, imm
-	lsri	\rx, 3
-	andi	\rx, (\imm >> 3)
-.endm
 #endif /* __ASM_CSKY_ENTRY_H */
diff --git a/arch/csky/abiv2/mcount.S b/arch/csky/abiv2/mcount.S
index 9331c7ed5958..911512bf480f 100644
--- a/arch/csky/abiv2/mcount.S
+++ b/arch/csky/abiv2/mcount.S
@@ -103,6 +103,8 @@ ENTRY(_mcount)
 	mov	a0, lr
 	subi	a0, 4
 	ldw	a1, (sp, 24)
+	lrw	a2, function_trace_op
+	ldw	a2, (a2, 0)
 
 	jsr	r26
 
diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h
index c6bcd7f7c720..24442d8e86f9 100644
--- a/arch/csky/include/asm/processor.h
+++ b/arch/csky/include/asm/processor.h
@@ -41,8 +41,7 @@ extern struct cpuinfo_csky cpu_data[];
 #define TASK_UNMAPPED_BASE      (TASK_SIZE / 3)
 
 struct thread_struct {
-	unsigned long  ksp;       /* kernel stack pointer */
-	unsigned long  sr;        /* saved status register */
+	unsigned long  sp;        /* kernel stack pointer */
 	unsigned long  trap_no;   /* saved status register */
 
 	/* FPU regs */
@@ -50,8 +49,7 @@ struct thread_struct {
 };
 
 #define INIT_THREAD  { \
-	.ksp = sizeof(init_stack) + (unsigned long) &init_stack, \
-	.sr = DEFAULT_PSR_VALUE, \
+	.sp = sizeof(init_stack) + (unsigned long) &init_stack, \
 }
 
 /*
diff --git a/arch/csky/include/asm/ptrace.h b/arch/csky/include/asm/ptrace.h
index aae5aa96cf54..bcfb7070e48d 100644
--- a/arch/csky/include/asm/ptrace.h
+++ b/arch/csky/include/asm/ptrace.h
@@ -58,6 +58,16 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 	return regs->usp;
 }
 
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+	return regs->regs[4];
+}
+static inline void frame_pointer_set(struct pt_regs *regs,
+				     unsigned long val)
+{
+	regs->regs[4] = val;
+}
+
 extern int regs_query_register_offset(const char *name);
 extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 						unsigned int n);
diff --git a/arch/csky/include/asm/thread_info.h b/arch/csky/include/asm/thread_info.h
index 442fedad0260..8980e4e64391 100644
--- a/arch/csky/include/asm/thread_info.h
+++ b/arch/csky/include/asm/thread_info.h
@@ -38,7 +38,13 @@ struct thread_info {
 #define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT)
 
 #define thread_saved_fp(tsk) \
-	((unsigned long)(((struct switch_stack *)(tsk->thread.ksp))->r8))
+	((unsigned long)(((struct switch_stack *)(tsk->thread.sp))->r8))
+
+#define thread_saved_sp(tsk) \
+	((unsigned long)(tsk->thread.sp))
+
+#define thread_saved_lr(tsk) \
+	((unsigned long)(((struct switch_stack *)(tsk->thread.sp))->r15))
 
 static inline struct thread_info *current_thread_info(void)
 {
@@ -54,10 +60,10 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SIGPENDING		0	/* signal pending */
 #define TIF_NOTIFY_RESUME	1       /* callback before returning to user */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_SYSCALL_TRACE	3	/* syscall trace active */
-#define TIF_SYSCALL_TRACEPOINT	4       /* syscall tracepoint instrumentation */
-#define TIF_SYSCALL_AUDIT	5	/* syscall auditing */
-#define TIF_UPROBE		6	/* uprobe breakpoint or singlestep */
+#define TIF_UPROBE		3	/* uprobe breakpoint or singlestep */
+#define TIF_SYSCALL_TRACE	4	/* syscall trace active */
+#define TIF_SYSCALL_TRACEPOINT	5       /* syscall tracepoint instrumentation */
+#define TIF_SYSCALL_AUDIT	6	/* syscall auditing */
 #define TIF_POLLING_NRFLAG	16	/* poll_idle() is TIF_NEED_RESCHED */
 #define TIF_MEMDIE		18      /* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	20	/* restore signal mask in do_signal() */
@@ -75,4 +81,10 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 
+#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+
+#define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+				 _TIF_SYSCALL_TRACEPOINT)
+
 #endif	/* _ASM_CSKY_THREAD_INFO_H */
diff --git a/arch/csky/include/asm/uaccess.h b/arch/csky/include/asm/uaccess.h
index abefa125b93c..1633ffe5ae15 100644
--- a/arch/csky/include/asm/uaccess.h
+++ b/arch/csky/include/asm/uaccess.h
@@ -253,7 +253,7 @@ do {								\
 
 extern int __get_user_bad(void);
 
-#define __copy_user(to, from, n)			\
+#define ___copy_to_user(to, from, n)			\
 do {							\
 	int w0, w1, w2, w3;				\
 	asm volatile(					\
@@ -288,31 +288,34 @@ do {							\
 	"       subi    %0, 4           \n"		\
 	"       br      3b              \n"		\
 	"5:     cmpnei  %0, 0           \n"  /* 1B */   \
-	"       bf      8f              \n"		\
+	"       bf      13f             \n"		\
 	"       ldb     %3, (%2, 0)     \n"		\
 	"6:     stb     %3, (%1, 0)     \n"		\
 	"       addi    %2,  1          \n"		\
 	"       addi    %1,  1          \n"		\
 	"       subi    %0,  1          \n"		\
 	"       br      5b              \n"		\
-	"7:     br      8f              \n"		\
+	"7:     subi	%0,  4          \n"		\
+	"8:     subi	%0,  4          \n"		\
+	"12:    subi	%0,  4          \n"		\
+	"       br      13f             \n"		\
 	".section __ex_table, \"a\"     \n"		\
 	".align   2                     \n"		\
-	".long    2b, 7b                \n"		\
-	".long    9b, 7b                \n"		\
-	".long   10b, 7b                \n"		\
+	".long    2b, 13f               \n"		\
+	".long    4b, 13f               \n"		\
+	".long    6b, 13f               \n"		\
+	".long    9b, 12b               \n"		\
+	".long   10b, 8b                \n"		\
 	".long   11b, 7b                \n"		\
-	".long    4b, 7b                \n"		\
-	".long    6b, 7b                \n"		\
 	".previous                      \n"		\
-	"8:                             \n"		\
+	"13:                            \n"		\
 	: "=r"(n), "=r"(to), "=r"(from), "=r"(w0),	\
 	  "=r"(w1), "=r"(w2), "=r"(w3)			\
 	: "0"(n), "1"(to), "2"(from)			\
 	: "memory");					\
 } while (0)
 
-#define __copy_user_zeroing(to, from, n)		\
+#define ___copy_from_user(to, from, n)			\
 do {							\
 	int tmp;					\
 	int nsave;					\
@@ -355,22 +358,22 @@ do {							\
 	"       addi    %1,  1          \n"		\
 	"       subi    %0,  1          \n"		\
 	"       br      5b              \n"		\
-	"8:     mov     %3, %0          \n"		\
-	"       movi    %4, 0           \n"		\
-	"9:     stb     %4, (%1, 0)     \n"		\
-	"       addi    %1, 1           \n"		\
-	"       subi    %3, 1           \n"		\
-	"       cmpnei  %3, 0           \n"		\
-	"       bt      9b              \n"		\
-	"       br      7f              \n"		\
+	"8:     stw     %3, (%1, 0)     \n"		\
+	"       subi    %0, 4           \n"		\
+	"       bf      7f              \n"		\
+	"9:     subi    %0, 8           \n"		\
+	"       bf      7f              \n"		\
+	"13:    stw     %3, (%1, 8)     \n"		\
+	"       subi    %0, 12          \n"		\
+	"       bf      7f              \n"		\
 	".section __ex_table, \"a\"     \n"		\
 	".align   2                     \n"		\
-	".long    2b, 8b                \n"		\
+	".long    2b, 7f                \n"		\
+	".long    4b, 7f                \n"		\
+	".long    6b, 7f                \n"		\
 	".long   10b, 8b                \n"		\
-	".long   11b, 8b                \n"		\
-	".long   12b, 8b                \n"		\
-	".long    4b, 8b                \n"		\
-	".long    6b, 8b                \n"		\
+	".long   11b, 9b                \n"		\
+	".long   12b,13b                \n"		\
 	".previous                      \n"		\
 	"7:                             \n"		\
 	: "=r"(n), "=r"(to), "=r"(from), "=r"(nsave),	\
diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile
index fd6d9dc8b7f3..37f37c0e934a 100644
--- a/arch/csky/kernel/Makefile
+++ b/arch/csky/kernel/Makefile
@@ -3,7 +3,7 @@ extra-y := head.o vmlinux.lds
 
 obj-y += entry.o atomic.o signal.o traps.o irq.o time.o vdso.o
 obj-y += power.o syscall.o syscall_table.o setup.o
-obj-y += process.o cpu-probe.o ptrace.o dumpstack.o
+obj-y += process.o cpu-probe.o ptrace.o stacktrace.o
 obj-y += probes/
 
 obj-$(CONFIG_MODULES)			+= module.o
diff --git a/arch/csky/kernel/asm-offsets.c b/arch/csky/kernel/asm-offsets.c
index f8be348df9e4..17479860d43d 100644
--- a/arch/csky/kernel/asm-offsets.c
+++ b/arch/csky/kernel/asm-offsets.c
@@ -18,8 +18,7 @@ int main(void)
 	DEFINE(TASK_ACTIVE_MM,    offsetof(struct task_struct, active_mm));
 
 	/* offsets into the thread struct */
-	DEFINE(THREAD_KSP,        offsetof(struct thread_struct, ksp));
-	DEFINE(THREAD_SR,         offsetof(struct thread_struct, sr));
+	DEFINE(THREAD_KSP,        offsetof(struct thread_struct, sp));
 	DEFINE(THREAD_FESR,       offsetof(struct thread_struct, user_fp.fesr));
 	DEFINE(THREAD_FCR,        offsetof(struct thread_struct, user_fp.fcr));
 	DEFINE(THREAD_FPREG,      offsetof(struct thread_struct, user_fp.vr));
diff --git a/arch/csky/kernel/dumpstack.c b/arch/csky/kernel/dumpstack.c
deleted file mode 100644
index d67f9777cfd9..000000000000
--- a/arch/csky/kernel/dumpstack.c
+++ /dev/null
@@ -1,49 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
-
-#include <linux/ptrace.h>
-
-int kstack_depth_to_print = 48;
-
-void show_trace(unsigned long *stack)
-{
-	unsigned long *stack_end;
-	unsigned long *stack_start;
-	unsigned long *fp;
-	unsigned long addr;
-
-	addr = (unsigned long) stack & THREAD_MASK;
-	stack_start = (unsigned long *) addr;
-	stack_end = (unsigned long *) (addr + THREAD_SIZE);
-
-	fp = stack;
-	pr_info("\nCall Trace:");
-
-	while (fp > stack_start && fp < stack_end) {
-#ifdef CONFIG_STACKTRACE
-		addr	= fp[1];
-		fp	= (unsigned long *) fp[0];
-#else
-		addr	= *fp++;
-#endif
-		if (__kernel_text_address(addr))
-			pr_cont("\n[<%08lx>] %pS", addr, (void *)addr);
-	}
-	pr_cont("\n");
-}
-
-void show_stack(struct task_struct *task, unsigned long *stack)
-{
-	if (!stack) {
-		if (task)
-			stack = (unsigned long *)thread_saved_fp(task);
-		else
-#ifdef CONFIG_STACKTRACE
-			asm volatile("mov %0, r8\n":"=r"(stack)::"memory");
-#else
-			stack = (unsigned long *)&stack;
-#endif
-	}
-
-	show_trace(stack);
-}
diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
index 364819536f2e..f13800383a19 100644
--- a/arch/csky/kernel/entry.S
+++ b/arch/csky/kernel/entry.S
@@ -128,39 +128,41 @@ tlbop_end 1
 ENTRY(csky_systemcall)
 	SAVE_ALL TRAP0_SIZE
 	zero_fp
-#ifdef CONFIG_RSEQ_DEBUG
-	mov	a0, sp
-	jbsr	rseq_syscall
-#endif
 	psrset  ee, ie
 
-	lrw     r11, __NR_syscalls
-	cmphs   syscallid, r11		/* Check nr of syscall */
-	bt      ret_from_exception
+	lrw     r9, __NR_syscalls
+	cmphs   syscallid, r9		/* Check nr of syscall */
+	bt      1f
 
-	lrw     r13, sys_call_table
-	ixw     r13, syscallid
-	ldw     r11, (r13)
-	cmpnei  r11, 0
+	lrw     r9, sys_call_table
+	ixw     r9, syscallid
+	ldw     syscallid, (r9)
+	cmpnei  syscallid, 0
 	bf      ret_from_exception
 
 	mov     r9, sp
 	bmaski  r10, THREAD_SHIFT
 	andn    r9, r10
-	ldw     r12, (r9, TINFO_FLAGS)
-	ANDI_R3	r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
-	cmpnei	r12, 0
+	ldw     r10, (r9, TINFO_FLAGS)
+	lrw	r9, _TIF_SYSCALL_WORK
+	and	r10, r9
+	cmpnei	r10, 0
 	bt      csky_syscall_trace
 #if defined(__CSKYABIV2__)
 	subi    sp, 8
 	stw  	r5, (sp, 0x4)
 	stw  	r4, (sp, 0x0)
-	jsr     r11                      /* Do system call */
+	jsr     syscallid                      /* Do system call */
 	addi 	sp, 8
 #else
-	jsr     r11
+	jsr     syscallid
 #endif
 	stw     a0, (sp, LSAVE_A0)      /* Save return value */
+1:
+#ifdef CONFIG_DEBUG_RSEQ
+	mov	a0, sp
+	jbsr	rseq_syscall
+#endif
 	jmpi    ret_from_exception
 
 csky_syscall_trace:
@@ -173,18 +175,23 @@ csky_syscall_trace:
 	ldw	a3, (sp, LSAVE_A3)
 #if defined(__CSKYABIV2__)
 	subi	sp, 8
-	stw	r5, (sp, 0x4)
-	stw	r4, (sp, 0x0)
+	ldw	r9, (sp, LSAVE_A4)
+	stw	r9, (sp, 0x0)
+	ldw	r9, (sp, LSAVE_A5)
+	stw	r9, (sp, 0x4)
+	jsr	syscallid                     /* Do system call */
+	addi	sp, 8
 #else
 	ldw	r6, (sp, LSAVE_A4)
 	ldw	r7, (sp, LSAVE_A5)
-#endif
-	jsr	r11                     /* Do system call */
-#if defined(__CSKYABIV2__)
-	addi	sp, 8
+	jsr	syscallid                     /* Do system call */
 #endif
 	stw	a0, (sp, LSAVE_A0)	/* Save return value */
 
+#ifdef CONFIG_DEBUG_RSEQ
+	mov	a0, sp
+	jbsr	rseq_syscall
+#endif
 	mov     a0, sp                  /* right now, sp --> pt_regs */
 	jbsr    syscall_trace_exit
 	br	ret_from_exception
@@ -200,18 +207,20 @@ ENTRY(ret_from_fork)
 	mov	r9, sp
 	bmaski	r10, THREAD_SHIFT
 	andn	r9, r10
-	ldw	r12, (r9, TINFO_FLAGS)
-	ANDI_R3	r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
-	cmpnei	r12, 0
+	ldw	r10, (r9, TINFO_FLAGS)
+	lrw	r9, _TIF_SYSCALL_WORK
+	and	r10, r9
+	cmpnei	r10, 0
 	bf	ret_from_exception
 	mov	a0, sp			/* sp = pt_regs pointer */
 	jbsr	syscall_trace_exit
 
 ret_from_exception:
-	ld	syscallid, (sp, LSAVE_PSR)
-	btsti	syscallid, 31
-	bt	1f
+	psrclr	ie
+	ld	r9, (sp, LSAVE_PSR)
+	btsti	r9, 31
 
+	bt	1f
 	/*
 	 * Load address of current->thread_info, Then get address of task_struct
 	 * Get task_needreshed in task_struct
@@ -220,11 +229,24 @@ ret_from_exception:
 	bmaski	r10, THREAD_SHIFT
 	andn	r9, r10
 
-	ldw	r12, (r9, TINFO_FLAGS)
-	andi	r12, (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | _TIF_UPROBE)
-	cmpnei	r12, 0
+	ldw	r10, (r9, TINFO_FLAGS)
+	lrw	r9, _TIF_WORK_MASK
+	and	r10, r9
+	cmpnei	r10, 0
 	bt	exit_work
 1:
+#ifdef CONFIG_PREEMPTION
+	mov	r9, sp
+	bmaski	r10, THREAD_SHIFT
+	andn	r9, r10
+
+	ldw	r10, (r9, TINFO_PREEMPT)
+	cmpnei	r10, 0
+	bt	2f
+	jbsr	preempt_schedule_irq	/* irq en/disable is done inside */
+2:
+#endif
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 	ld	r10, (sp, LSAVE_PSR)
 	btsti	r10, 6
@@ -235,14 +257,15 @@ ret_from_exception:
 	RESTORE_ALL
 
 exit_work:
-	lrw	syscallid, ret_from_exception
-	mov	lr, syscallid
+	lrw	r9, ret_from_exception
+	mov	lr, r9
 
-	btsti	r12, TIF_NEED_RESCHED
+	btsti	r10, TIF_NEED_RESCHED
 	bt	work_resched
 
+	psrset	ie
 	mov	a0, sp
-	mov	a1, r12
+	mov	a1, r10
 	jmpi	do_notify_resume
 
 work_resched:
@@ -291,34 +314,10 @@ ENTRY(csky_irq)
 	jbsr	trace_hardirqs_off
 #endif
 
-#ifdef CONFIG_PREEMPTION
-	mov	r9, sp			/* Get current stack  pointer */
-	bmaski	r10, THREAD_SHIFT
-	andn	r9, r10			/* Get thread_info */
-
-	/*
-	 * Get task_struct->stack.preempt_count for current,
-	 * and increase 1.
-	 */
-	ldw	r12, (r9, TINFO_PREEMPT)
-	addi	r12, 1
-	stw	r12, (r9, TINFO_PREEMPT)
-#endif
 
 	mov	a0, sp
 	jbsr	csky_do_IRQ
 
-#ifdef CONFIG_PREEMPTION
-	subi	r12, 1
-	stw	r12, (r9, TINFO_PREEMPT)
-	cmpnei	r12, 0
-	bt	2f
-	ldw	r12, (r9, TINFO_FLAGS)
-	btsti	r12, TIF_NEED_RESCHED
-	bf	2f
-	jbsr	preempt_schedule_irq	/* irq en/disable is done inside */
-#endif
-2:
 	jmpi	ret_from_exception
 
 /*
@@ -330,11 +329,6 @@ ENTRY(__switch_to)
 	lrw	a3, TASK_THREAD
 	addu	a3, a0
 
-	mfcr	a2, psr			/* Save PSR value */
-	stw	a2, (a3, THREAD_SR)	/* Save PSR in task struct */
-	bclri	a2, 6			/* Disable interrupts */
-	mtcr	a2, psr
-
 	SAVE_SWITCH_STACK
 
 	stw	sp, (a3, THREAD_KSP)
@@ -345,12 +339,9 @@ ENTRY(__switch_to)
 
 	ldw	sp, (a3, THREAD_KSP)	/* Set next kernel sp */
 
-	ldw	a2, (a3, THREAD_SR)	/* Set next PSR */
-	mtcr	a2, psr
-
 #if  defined(__CSKYABIV2__)
-	addi	r7, a1, TASK_THREAD_INFO
-	ldw	tls, (r7, TINFO_TP_VALUE)
+	addi	a3, a1, TASK_THREAD_INFO
+	ldw	tls, (a3, TINFO_TP_VALUE)
 #endif
 
 	RESTORE_SWITCH_STACK
diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c
index 44628e3f7fa6..3c425b84e3be 100644
--- a/arch/csky/kernel/ftrace.c
+++ b/arch/csky/kernel/ftrace.c
@@ -202,6 +202,7 @@ int ftrace_disable_ftrace_graph_caller(void)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
+#ifdef CONFIG_DYNAMIC_FTRACE
 #ifndef CONFIG_CPU_HAS_ICACHE_INS
 struct ftrace_modify_param {
 	int command;
@@ -231,6 +232,7 @@ void arch_ftrace_update_code(int command)
 	stop_machine(__ftrace_modify_code, &param, cpu_online_mask);
 }
 #endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* _mcount is defined in abi's mcount.S */
 EXPORT_SYMBOL(_mcount);
diff --git a/arch/csky/kernel/perf_callchain.c b/arch/csky/kernel/perf_callchain.c
index e68ff375c8f8..ab55e98ee8f6 100644
--- a/arch/csky/kernel/perf_callchain.c
+++ b/arch/csky/kernel/perf_callchain.c
@@ -12,12 +12,17 @@ struct stackframe {
 
 static int unwind_frame_kernel(struct stackframe *frame)
 {
-	if (kstack_end((void *)frame->fp))
+	unsigned long low = (unsigned long)task_stack_page(current);
+	unsigned long high = low + THREAD_SIZE;
+
+	if (unlikely(frame->fp < low || frame->fp > high))
 		return -EPERM;
-	if (frame->fp & 0x3 || frame->fp < TASK_SIZE)
+
+	if (kstack_end((void *)frame->fp) || frame->fp & 0x3)
 		return -EPERM;
 
 	*frame = *(struct stackframe *)frame->fp;
+
 	if (__kernel_text_address(frame->lr)) {
 		int graph = 0;
 
diff --git a/arch/csky/kernel/probes/uprobes.c b/arch/csky/kernel/probes/uprobes.c
index b3a56c260e3e..1a9e0961b2b5 100644
--- a/arch/csky/kernel/probes/uprobes.c
+++ b/arch/csky/kernel/probes/uprobes.c
@@ -11,6 +11,11 @@
 
 #define UPROBE_TRAP_NR	UINT_MAX
 
+bool is_swbp_insn(uprobe_opcode_t *insn)
+{
+	return (*insn & 0xffff) == UPROBE_SWBP_INSN;
+}
+
 unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
 {
 	return instruction_pointer(regs);
diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c
index f7b231ca269a..8b3fad062ab2 100644
--- a/arch/csky/kernel/process.c
+++ b/arch/csky/kernel/process.c
@@ -35,7 +35,7 @@ void flush_thread(void){}
  */
 unsigned long thread_saved_pc(struct task_struct *tsk)
 {
-	struct switch_stack *sw = (struct switch_stack *)tsk->thread.ksp;
+	struct switch_stack *sw = (struct switch_stack *)tsk->thread.sp;
 
 	return sw->r15;
 }
@@ -56,8 +56,8 @@ int copy_thread_tls(unsigned long clone_flags,
 	childstack = ((struct switch_stack *) childregs) - 1;
 	memset(childstack, 0, sizeof(struct switch_stack));
 
-	/* setup ksp for switch_to !!! */
-	p->thread.ksp = (unsigned long)childstack;
+	/* setup thread.sp for switch_to !!! */
+	p->thread.sp = (unsigned long)childstack;
 
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
@@ -98,37 +98,6 @@ int dump_task_regs(struct task_struct *tsk, elf_gregset_t *pr_regs)
 	return 1;
 }
 
-unsigned long get_wchan(struct task_struct *p)
-{
-	unsigned long lr;
-	unsigned long *fp, *stack_start, *stack_end;
-	int count = 0;
-
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-
-	stack_start = (unsigned long *)end_of_stack(p);
-	stack_end = (unsigned long *)(task_stack_page(p) + THREAD_SIZE);
-
-	fp = (unsigned long *) thread_saved_fp(p);
-	do {
-		if (fp < stack_start || fp > stack_end)
-			return 0;
-#ifdef CONFIG_STACKTRACE
-		lr = fp[1];
-		fp = (unsigned long *)fp[0];
-#else
-		lr = *fp++;
-#endif
-		if (!in_sched_functions(lr) &&
-		    __kernel_text_address(lr))
-			return lr;
-	} while (count++ < 16);
-
-	return 0;
-}
-EXPORT_SYMBOL(get_wchan);
-
 #ifndef CONFIG_CPU_PM_NONE
 void arch_cpu_idle(void)
 {
diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c
index 21ac2608f205..5a82230bddf9 100644
--- a/arch/csky/kernel/ptrace.c
+++ b/arch/csky/kernel/ptrace.c
@@ -41,6 +41,9 @@ static void singlestep_disable(struct task_struct *tsk)
 
 	regs = task_pt_regs(tsk);
 	regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_RUN;
+
+	/* Enable irq */
+	regs->sr |= BIT(6);
 }
 
 static void singlestep_enable(struct task_struct *tsk)
@@ -49,6 +52,9 @@ static void singlestep_enable(struct task_struct *tsk)
 
 	regs = task_pt_regs(tsk);
 	regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_SI;
+
+	/* Disable irq */
+	regs->sr &= ~BIT(6);
 }
 
 /*
diff --git a/arch/csky/kernel/stacktrace.c b/arch/csky/kernel/stacktrace.c
index fec777a643f1..92809e1da723 100644
--- a/arch/csky/kernel/stacktrace.c
+++ b/arch/csky/kernel/stacktrace.c
@@ -1,57 +1,159 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. */
 
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
 #include <linux/ftrace.h>
+#include <linux/ptrace.h>
 
-void save_stack_trace(struct stack_trace *trace)
+#ifdef CONFIG_FRAME_POINTER
+
+struct stackframe {
+	unsigned long fp;
+	unsigned long ra;
+};
+
+void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
+			     bool (*fn)(unsigned long, void *), void *arg)
 {
-	save_stack_trace_tsk(current, trace);
+	unsigned long fp, sp, pc;
+
+	if (regs) {
+		fp = frame_pointer(regs);
+		sp = user_stack_pointer(regs);
+		pc = instruction_pointer(regs);
+	} else if (task == NULL || task == current) {
+		const register unsigned long current_sp __asm__ ("sp");
+		const register unsigned long current_fp __asm__ ("r8");
+		fp = current_fp;
+		sp = current_sp;
+		pc = (unsigned long)walk_stackframe;
+	} else {
+		/* task blocked in __switch_to */
+		fp = thread_saved_fp(task);
+		sp = thread_saved_sp(task);
+		pc = thread_saved_lr(task);
+	}
+
+	for (;;) {
+		unsigned long low, high;
+		struct stackframe *frame;
+
+		if (unlikely(!__kernel_text_address(pc) || fn(pc, arg)))
+			break;
+
+		/* Validate frame pointer */
+		low = sp;
+		high = ALIGN(sp, THREAD_SIZE);
+		if (unlikely(fp < low || fp > high || fp & 0x3))
+			break;
+		/* Unwind stack frame */
+		frame = (struct stackframe *)fp;
+		sp = fp;
+		fp = frame->fp;
+		pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
+					   (unsigned long *)(fp - 8));
+	}
 }
-EXPORT_SYMBOL_GPL(save_stack_trace);
 
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+#else /* !CONFIG_FRAME_POINTER */
+
+static void notrace walk_stackframe(struct task_struct *task,
+	struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
 {
-	unsigned long *fp, *stack_start, *stack_end;
-	unsigned long addr;
-	int skip = trace->skip;
-	int savesched;
-	int graph_idx = 0;
+	unsigned long sp, pc;
+	unsigned long *ksp;
 
-	if (tsk == current) {
-		asm volatile("mov %0, r8\n":"=r"(fp));
-		savesched = 1;
+	if (regs) {
+		sp = user_stack_pointer(regs);
+		pc = instruction_pointer(regs);
+	} else if (task == NULL || task == current) {
+		const register unsigned long current_sp __asm__ ("sp");
+		sp = current_sp;
+		pc = (unsigned long)walk_stackframe;
 	} else {
-		fp = (unsigned long *)thread_saved_fp(tsk);
-		savesched = 0;
+		/* task blocked in __switch_to */
+		sp = thread_saved_sp(task);
+		pc = thread_saved_lr(task);
 	}
 
-	addr = (unsigned long) fp & THREAD_MASK;
-	stack_start = (unsigned long *) addr;
-	stack_end = (unsigned long *) (addr + THREAD_SIZE);
-
-	while (fp > stack_start && fp < stack_end) {
-		unsigned long lpp, fpp;
+	if (unlikely(sp & 0x3))
+		return;
 
-		fpp = fp[0];
-		lpp = fp[1];
-		if (!__kernel_text_address(lpp))
+	ksp = (unsigned long *)sp;
+	while (!kstack_end(ksp)) {
+		if (__kernel_text_address(pc) && unlikely(fn(pc, arg)))
 			break;
-		else
-			lpp = ftrace_graph_ret_addr(tsk, &graph_idx, lpp, NULL);
-
-		if (savesched || !in_sched_functions(lpp)) {
-			if (skip) {
-				skip--;
-			} else {
-				trace->entries[trace->nr_entries++] = lpp;
-				if (trace->nr_entries >= trace->max_entries)
-					break;
-			}
-		}
-		fp = (unsigned long *)fpp;
+		pc = (*ksp++) - 0x4;
 	}
 }
+#endif /* CONFIG_FRAME_POINTER */
+
+static bool print_trace_address(unsigned long pc, void *arg)
+{
+	print_ip_sym(pc);
+	return false;
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp)
+{
+	pr_cont("Call Trace:\n");
+	walk_stackframe(task, NULL, print_trace_address, NULL);
+}
+
+static bool save_wchan(unsigned long pc, void *arg)
+{
+	if (!in_sched_functions(pc)) {
+		unsigned long *p = arg;
+		*p = pc;
+		return true;
+	}
+	return false;
+}
+
+unsigned long get_wchan(struct task_struct *task)
+{
+	unsigned long pc = 0;
+
+	if (likely(task && task != current && task->state != TASK_RUNNING))
+		walk_stackframe(task, NULL, save_wchan, &pc);
+	return pc;
+}
+
+#ifdef CONFIG_STACKTRACE
+static bool __save_trace(unsigned long pc, void *arg, bool nosched)
+{
+	struct stack_trace *trace = arg;
+
+	if (unlikely(nosched && in_sched_functions(pc)))
+		return false;
+	if (unlikely(trace->skip > 0)) {
+		trace->skip--;
+		return false;
+	}
+
+	trace->entries[trace->nr_entries++] = pc;
+	return (trace->nr_entries >= trace->max_entries);
+}
+
+static bool save_trace(unsigned long pc, void *arg)
+{
+	return __save_trace(pc, arg, false);
+}
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ */
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	walk_stackframe(tsk, NULL, save_trace, trace);
+}
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	save_stack_trace_tsk(NULL, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+#endif /* CONFIG_STACKTRACE */
diff --git a/arch/csky/lib/usercopy.c b/arch/csky/lib/usercopy.c
index 647a23986fb5..3c9bd645e643 100644
--- a/arch/csky/lib/usercopy.c
+++ b/arch/csky/lib/usercopy.c
@@ -7,10 +7,7 @@
 unsigned long raw_copy_from_user(void *to, const void *from,
 			unsigned long n)
 {
-	if (access_ok(from, n))
-		__copy_user_zeroing(to, from, n);
-	else
-		memset(to, 0, n);
+	___copy_from_user(to, from, n);
 	return n;
 }
 EXPORT_SYMBOL(raw_copy_from_user);
@@ -18,8 +15,7 @@ EXPORT_SYMBOL(raw_copy_from_user);
 unsigned long raw_copy_to_user(void *to, const void *from,
 			unsigned long n)
 {
-	if (access_ok(to, n))
-		__copy_user(to, from, n);
+	___copy_to_user(to, from, n);
 	return n;
 }
 EXPORT_SYMBOL(raw_copy_to_user);
diff --git a/arch/h8300/kernel/.gitignore b/arch/h8300/kernel/.gitignore
new file mode 100644
index 000000000000..bbb90f92d051
--- /dev/null
+++ b/arch/h8300/kernel/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+vmlinux.lds
diff --git a/arch/hexagon/include/asm/module.h b/arch/hexagon/include/asm/vermagic.h
index e8de4fe03543..0e8dedc8c486 100644
--- a/arch/hexagon/include/asm/module.h
+++ b/arch/hexagon/include/asm/vermagic.h
@@ -3,11 +3,11 @@
  * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
  */
 
-#ifndef _ASM_MODULE_H
-#define _ASM_MODULE_H
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
 
-#include <asm-generic/module.h>
+#include <linux/stringify.h>
 
 #define MODULE_ARCH_VERMAGIC __stringify(PROCESSOR_MODEL_NAME) " "
 
-#endif
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/ia64/include/asm/device.h b/arch/ia64/include/asm/device.h
index 410a769ece95..3eb397415381 100644
--- a/arch/ia64/include/asm/device.h
+++ b/arch/ia64/include/asm/device.h
@@ -6,7 +6,7 @@
 #define _ASM_IA64_DEVICE_H
 
 struct dev_archdata {
-#ifdef CONFIG_INTEL_IOMMU
+#ifdef CONFIG_IOMMU_API
 	void *iommu; /* hook for IOMMU specific extension */
 #endif
 };
diff --git a/arch/ia64/include/asm/module.h b/arch/ia64/include/asm/module.h
index f319144260ce..5a29652e6def 100644
--- a/arch/ia64/include/asm/module.h
+++ b/arch/ia64/include/asm/module.h
@@ -26,10 +26,6 @@ struct mod_arch_specific {
 	unsigned int next_got_entry;	/* index of next available got entry */
 };
 
-#define MODULE_PROC_FAMILY	"ia64"
-#define MODULE_ARCH_VERMAGIC	MODULE_PROC_FAMILY \
-	"gcc-" __stringify(__GNUC__) "." __stringify(__GNUC_MINOR__)
-
 #define ARCH_SHF_SMALL	SHF_IA_64_SHORT
 
 #endif /* _ASM_IA64_MODULE_H */
diff --git a/arch/ia64/include/asm/vermagic.h b/arch/ia64/include/asm/vermagic.h
new file mode 100644
index 000000000000..29c7424f4c25
--- /dev/null
+++ b/arch/ia64/include/asm/vermagic.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ */
+
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#include <linux/stringify.h>
+
+#define MODULE_ARCH_VERMAGIC	"ia64" \
+	"gcc-" __stringify(__GNUC__) "." __stringify(__GNUC_MINOR__)
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index f69f3fe0532e..a54eacbc61a9 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -57,12 +57,12 @@ unsigned long hcdp_phys = EFI_INVALID_TABLE_ADDR;
 unsigned long sal_systab_phys = EFI_INVALID_TABLE_ADDR;
 
 static const efi_config_table_type_t arch_tables[] __initconst = {
-	{ESI_TABLE_GUID, "ESI", &esi_phys},
-	{HCDP_TABLE_GUID, "HCDP", &hcdp_phys},
-	{MPS_TABLE_GUID, "MPS", &mps_phys},
-	{PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID, "PALO", &palo_phys},
-	{SAL_SYSTEM_TABLE_GUID, "SALsystab", &sal_systab_phys},
-	{NULL_GUID, NULL, 0},
+	{ESI_TABLE_GUID,				&esi_phys,		"ESI"		},
+	{HCDP_TABLE_GUID,				&hcdp_phys,		"HCDP"		},
+	{MPS_TABLE_GUID,				&mps_phys,		"MPS"		},
+	{PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID,	&palo_phys,		"PALO"		},
+	{SAL_SYSTEM_TABLE_GUID,				&sal_systab_phys,	"SALsystab"	},
+	{},
 };
 
 extern efi_status_t efi_call_phys (void *, ...);
diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index c32ab8041cf6..4eb911d64e8d 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -221,6 +221,7 @@ static void __init amiga_identify(void)
 	case AMI_1200:
 		AMIGAHW_SET(A1200_IDE);
 		AMIGAHW_SET(PCMCIA);
+		fallthrough;
 	case AMI_500:
 	case AMI_500PLUS:
 	case AMI_1000:
@@ -233,7 +234,7 @@ static void __init amiga_identify(void)
 	case AMI_3000T:
 		AMIGAHW_SET(AMBER_FF);
 		AMIGAHW_SET(MAGIC_REKICK);
-		/* fall through */
+		fallthrough;
 	case AMI_3000PLUS:
 		AMIGAHW_SET(A3000_SCSI);
 		AMIGAHW_SET(A3000_CLK);
@@ -242,7 +243,7 @@ static void __init amiga_identify(void)
 
 	case AMI_4000T:
 		AMIGAHW_SET(A4000_SCSI);
-		/* fall through */
+		fallthrough;
 	case AMI_4000:
 		AMIGAHW_SET(A4000_IDE);
 		AMIGAHW_SET(A3000_CLK);
@@ -628,7 +629,7 @@ struct savekmsg {
 	unsigned long magic2;		/* SAVEKMSG_MAGIC2 */
 	unsigned long magicptr;		/* address of magic1 */
 	unsigned long size;
-	char data[0];
+	char data[];
 };
 
 static struct savekmsg *savekmsg;
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 5b3a273ae3da..888b75e7fd79 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -100,7 +100,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -381,6 +380,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -452,6 +452,7 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_MSM6242=m
 CONFIG_RTC_DRV_RP5C01=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -472,6 +473,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -619,9 +621,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 0bf0907a7c80..45303846b659 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -96,7 +96,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -360,6 +359,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -408,6 +408,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -428,6 +429,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -575,9 +577,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 876e69292294..de824c1bc3d3 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -103,7 +103,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -376,6 +375,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -430,6 +430,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -450,6 +451,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -597,9 +599,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index aa59c242e715..071839ca6a59 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -93,7 +93,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -358,6 +357,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -401,6 +401,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -421,6 +422,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -568,9 +570,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 308cd93929a9..37ac7b019ec1 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -95,7 +95,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -359,6 +358,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -410,6 +410,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -430,6 +431,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -577,9 +579,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 0bc210ace870..608779866260 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -94,7 +94,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -375,6 +374,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -432,6 +432,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -452,6 +453,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -599,9 +601,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 3b3b832dee80..0abb53c38c20 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -114,7 +114,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -419,6 +418,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -518,6 +518,7 @@ CONFIG_RTC_DRV_MSM6242=m
 CONFIG_RTC_DRV_RP5C01=m
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -538,6 +539,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -685,9 +687,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index e3633c66926f..cb14c234d3ad 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -92,7 +92,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -357,6 +356,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -400,6 +400,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -420,6 +421,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -567,9 +569,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 88b3f7f9f146..e8a1920aded7 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -93,7 +93,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -358,6 +357,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -401,6 +401,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -421,6 +422,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -568,9 +570,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 3dd5b536921e..2cbf416fc725 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -94,7 +94,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -365,6 +364,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -419,6 +419,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -439,6 +440,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -586,9 +588,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 715e015ed270..fed3cc7abcc4 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -90,7 +90,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -355,6 +354,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -403,6 +403,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -423,6 +424,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -570,8 +572,10 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index f9ff129ac7c2..0954fde256e6 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -90,7 +90,6 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
-CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
 CONFIG_NFT_NUMGEN=m
@@ -355,6 +354,7 @@ CONFIG_IPVLAN=m
 CONFIG_IPVTAP=m
 CONFIG_VXLAN=m
 CONFIG_GENEVE=m
+CONFIG_BAREUDP=m
 CONFIG_GTP=m
 CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
@@ -402,6 +402,7 @@ CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
 CONFIG_EXT4_FS=y
@@ -422,6 +423,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_CHILDREN=y
 CONFIG_TMPFS=y
@@ -569,9 +571,11 @@ CONFIG_XZ_DEC_TEST=m
 CONFIG_STRING_SELFTEST=m
 # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_WW_MUTEX_SELFTEST=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_TEST_LIST_SORT=m
+CONFIG_TEST_MIN_HEAP=m
 CONFIG_TEST_SORT=m
 CONFIG_REED_SOLOMON_TEST=m
 CONFIG_ATOMIC64_SELFTEST=m
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index a0765aa60ea9..1bff55aa2d54 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 generated-y += syscall_table.h
 generic-y += extable.h
-generic-y += hardirq.h
 generic-y += kvm_para.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/m68k/include/asm/mac_via.h b/arch/m68k/include/asm/mac_via.h
index de1470c4d829..1149251ea58d 100644
--- a/arch/m68k/include/asm/mac_via.h
+++ b/arch/m68k/include/asm/mac_via.h
@@ -257,6 +257,7 @@ extern int rbv_present,via_alt_mapping;
 
 struct irq_desc;
 
+extern void via_l2_flush(int writeback);
 extern void via_register_interrupts(void);
 extern void via_irq_enable(int);
 extern void via_irq_disable(int);
diff --git a/arch/m68k/include/asm/uaccess_mm.h b/arch/m68k/include/asm/uaccess_mm.h
index 7e85de984df1..9ae9f8d05925 100644
--- a/arch/m68k/include/asm/uaccess_mm.h
+++ b/arch/m68k/include/asm/uaccess_mm.h
@@ -142,7 +142,7 @@ asm volatile ("\n"					\
 		__get_user_asm(__gu_err, x, ptr, u32, l, r, -EFAULT);	\
 		break;							\
 	case 8: {							\
-		const void *__gu_ptr = (ptr);				\
+		const void __user *__gu_ptr = (ptr);			\
 		union {							\
 			u64 l;						\
 			__typeof__(*(ptr)) t;				\
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 611f73bfc87c..d0126ab01360 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -59,7 +59,6 @@ extern void iop_preinit(void);
 extern void iop_init(void);
 extern void via_init(void);
 extern void via_init_clock(irq_handler_t func);
-extern void via_flush_cache(void);
 extern void oss_init(void);
 extern void psc_init(void);
 extern void baboon_init(void);
@@ -130,21 +129,6 @@ int __init mac_parse_bootinfo(const struct bi_record *record)
 	return unknown;
 }
 
-/*
- * Flip into 24bit mode for an instant - flushes the L2 cache card. We
- * have to disable interrupts for this. Our IRQ handlers will crap
- * themselves if they take an IRQ in 24bit mode!
- */
-
-static void mac_cache_card_flush(int writeback)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	via_flush_cache();
-	local_irq_restore(flags);
-}
-
 void __init config_mac(void)
 {
 	if (!MACH_IS_MAC)
@@ -175,9 +159,8 @@ void __init config_mac(void)
 	 * not.
 	 */
 
-	if (macintosh_config->ident == MAC_MODEL_IICI
-	    || macintosh_config->ident == MAC_MODEL_IIFX)
-		mach_l2_flush = mac_cache_card_flush;
+	if (macintosh_config->ident == MAC_MODEL_IICI)
+		mach_l2_flush = via_l2_flush;
 }
 
 
diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c
index 9bfa17015768..d3775afb0f07 100644
--- a/arch/m68k/mac/iop.c
+++ b/arch/m68k/mac/iop.c
@@ -299,7 +299,6 @@ void __init iop_init(void)
 
 /*
  * Register the interrupt handler for the IOPs.
- * TODO: might be wrong for non-OSS machines. Anyone?
  */
 
 void __init iop_register_interrupts(void)
@@ -566,36 +565,42 @@ irqreturn_t iop_ism_irq(int irq, void *dev_id)
 	uint iop_num = (uint) dev_id;
 	volatile struct mac_iop *iop = iop_base[iop_num];
 	int i,state;
+	u8 events = iop->status_ctrl & (IOP_INT0 | IOP_INT1);
 
 	iop_pr_debug("status %02X\n", iop->status_ctrl);
 
-	/* INT0 indicates a state change on an outgoing message channel */
-
-	if (iop->status_ctrl & IOP_INT0) {
-		iop->status_ctrl = IOP_INT0 | IOP_RUN | IOP_AUTOINC;
-		iop_pr_debug("new status %02X, send states", iop->status_ctrl);
-		for (i = 0 ; i < NUM_IOP_CHAN  ; i++) {
-			state = iop_readb(iop, IOP_ADDR_SEND_STATE + i);
-			iop_pr_cont(" %02X", state);
-			if (state == IOP_MSG_COMPLETE) {
-				iop_handle_send(iop_num, i);
+	do {
+		/* INT0 indicates state change on an outgoing message channel */
+		if (events & IOP_INT0) {
+			iop->status_ctrl = IOP_INT0 | IOP_RUN | IOP_AUTOINC;
+			iop_pr_debug("new status %02X, send states",
+				     iop->status_ctrl);
+			for (i = 0; i < NUM_IOP_CHAN; i++) {
+				state = iop_readb(iop, IOP_ADDR_SEND_STATE + i);
+				iop_pr_cont(" %02X", state);
+				if (state == IOP_MSG_COMPLETE)
+					iop_handle_send(iop_num, i);
 			}
+			iop_pr_cont("\n");
 		}
-		iop_pr_cont("\n");
-	}
 
-	if (iop->status_ctrl & IOP_INT1) {	/* INT1 for incoming msgs */
-		iop->status_ctrl = IOP_INT1 | IOP_RUN | IOP_AUTOINC;
-		iop_pr_debug("new status %02X, recv states", iop->status_ctrl);
-		for (i = 0 ; i < NUM_IOP_CHAN ; i++) {
-			state = iop_readb(iop, IOP_ADDR_RECV_STATE + i);
-			iop_pr_cont(" %02X", state);
-			if (state == IOP_MSG_NEW) {
-				iop_handle_recv(iop_num, i);
+		/* INT1 for incoming messages */
+		if (events & IOP_INT1) {
+			iop->status_ctrl = IOP_INT1 | IOP_RUN | IOP_AUTOINC;
+			iop_pr_debug("new status %02X, recv states",
+				     iop->status_ctrl);
+			for (i = 0; i < NUM_IOP_CHAN; i++) {
+				state = iop_readb(iop, IOP_ADDR_RECV_STATE + i);
+				iop_pr_cont(" %02X", state);
+				if (state == IOP_MSG_NEW)
+					iop_handle_recv(iop_num, i);
 			}
+			iop_pr_cont("\n");
 		}
-		iop_pr_cont("\n");
-	}
+
+		events = iop->status_ctrl & (IOP_INT0 | IOP_INT1);
+	} while (events);
+
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 3c2cfcb74982..1f0fad2a98a0 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -294,10 +294,14 @@ void via_debug_dump(void)
  * the system into 24-bit mode for an instant.
  */
 
-void via_flush_cache(void)
+void via_l2_flush(int writeback)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	via2[gBufB] &= ~VIA2B_vMode32;
 	via2[gBufB] |= VIA2B_vMode32;
+	local_irq_restore(flags);
 }
 
 /*
diff --git a/arch/m68k/tools/amiga/dmesg.c b/arch/m68k/tools/amiga/dmesg.c
index 7340f5b6cf6d..f8005a7efb0b 100644
--- a/arch/m68k/tools/amiga/dmesg.c
+++ b/arch/m68k/tools/amiga/dmesg.c
@@ -34,7 +34,7 @@ struct savekmsg {
     u_long magic2;	/* SAVEKMSG_MAGIC2 */
     u_long magicptr;	/* address of magic1 */
     u_long size;
-    char data[0];
+    char data[];
 };
 
 
diff --git a/arch/microblaze/kernel/microblaze_ksyms.c b/arch/microblaze/kernel/microblaze_ksyms.c
index 92e12c2c2ec1..51c43ee5e380 100644
--- a/arch/microblaze/kernel/microblaze_ksyms.c
+++ b/arch/microblaze/kernel/microblaze_ksyms.c
@@ -6,7 +6,6 @@
 
 #include <linux/export.h>
 #include <linux/string.h>
-#include <linux/cryptohash.h>
 #include <linux/delay.h>
 #include <linux/in6.h>
 #include <linux/syscalls.h>
diff --git a/arch/mips/cavium-octeon/crypto/octeon-md5.c b/arch/mips/cavium-octeon/crypto/octeon-md5.c
index d1ed066e1a17..8c8ea139653e 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-md5.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-md5.c
@@ -25,7 +25,6 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <asm/byteorder.h>
-#include <linux/cryptohash.h>
 #include <asm/octeon/octeon.h>
 #include <crypto/internal/hash.h>
 
diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h
index 9846047b3d3d..724a0882576b 100644
--- a/arch/mips/include/asm/module.h
+++ b/arch/mips/include/asm/module.h
@@ -83,65 +83,4 @@ search_module_dbetables(unsigned long addr)
 }
 #endif
 
-#ifdef CONFIG_CPU_BMIPS
-#define MODULE_PROC_FAMILY "BMIPS "
-#elif defined CONFIG_CPU_MIPS32_R1
-#define MODULE_PROC_FAMILY "MIPS32_R1 "
-#elif defined CONFIG_CPU_MIPS32_R2
-#define MODULE_PROC_FAMILY "MIPS32_R2 "
-#elif defined CONFIG_CPU_MIPS32_R6
-#define MODULE_PROC_FAMILY "MIPS32_R6 "
-#elif defined CONFIG_CPU_MIPS64_R1
-#define MODULE_PROC_FAMILY "MIPS64_R1 "
-#elif defined CONFIG_CPU_MIPS64_R2
-#define MODULE_PROC_FAMILY "MIPS64_R2 "
-#elif defined CONFIG_CPU_MIPS64_R6
-#define MODULE_PROC_FAMILY "MIPS64_R6 "
-#elif defined CONFIG_CPU_R3000
-#define MODULE_PROC_FAMILY "R3000 "
-#elif defined CONFIG_CPU_TX39XX
-#define MODULE_PROC_FAMILY "TX39XX "
-#elif defined CONFIG_CPU_VR41XX
-#define MODULE_PROC_FAMILY "VR41XX "
-#elif defined CONFIG_CPU_R4X00
-#define MODULE_PROC_FAMILY "R4X00 "
-#elif defined CONFIG_CPU_TX49XX
-#define MODULE_PROC_FAMILY "TX49XX "
-#elif defined CONFIG_CPU_R5000
-#define MODULE_PROC_FAMILY "R5000 "
-#elif defined CONFIG_CPU_R5500
-#define MODULE_PROC_FAMILY "R5500 "
-#elif defined CONFIG_CPU_NEVADA
-#define MODULE_PROC_FAMILY "NEVADA "
-#elif defined CONFIG_CPU_R10000
-#define MODULE_PROC_FAMILY "R10000 "
-#elif defined CONFIG_CPU_RM7000
-#define MODULE_PROC_FAMILY "RM7000 "
-#elif defined CONFIG_CPU_SB1
-#define MODULE_PROC_FAMILY "SB1 "
-#elif defined CONFIG_CPU_LOONGSON32
-#define MODULE_PROC_FAMILY "LOONGSON32 "
-#elif defined CONFIG_CPU_LOONGSON2EF
-#define MODULE_PROC_FAMILY "LOONGSON2EF "
-#elif defined CONFIG_CPU_LOONGSON64
-#define MODULE_PROC_FAMILY "LOONGSON64 "
-#elif defined CONFIG_CPU_CAVIUM_OCTEON
-#define MODULE_PROC_FAMILY "OCTEON "
-#elif defined CONFIG_CPU_XLR
-#define MODULE_PROC_FAMILY "XLR "
-#elif defined CONFIG_CPU_XLP
-#define MODULE_PROC_FAMILY "XLP "
-#else
-#error MODULE_PROC_FAMILY undefined for your processor configuration
-#endif
-
-#ifdef CONFIG_32BIT
-#define MODULE_KERNEL_TYPE "32BIT "
-#elif defined CONFIG_64BIT
-#define MODULE_KERNEL_TYPE "64BIT "
-#endif
-
-#define MODULE_ARCH_VERMAGIC \
-	MODULE_PROC_FAMILY MODULE_KERNEL_TYPE
-
 #endif /* _ASM_MODULE_H */
diff --git a/arch/mips/include/asm/vermagic.h b/arch/mips/include/asm/vermagic.h
new file mode 100644
index 000000000000..24dc3d35161c
--- /dev/null
+++ b/arch/mips/include/asm/vermagic.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#ifdef CONFIG_CPU_BMIPS
+#define MODULE_PROC_FAMILY "BMIPS "
+#elif defined CONFIG_CPU_MIPS32_R1
+#define MODULE_PROC_FAMILY "MIPS32_R1 "
+#elif defined CONFIG_CPU_MIPS32_R2
+#define MODULE_PROC_FAMILY "MIPS32_R2 "
+#elif defined CONFIG_CPU_MIPS32_R6
+#define MODULE_PROC_FAMILY "MIPS32_R6 "
+#elif defined CONFIG_CPU_MIPS64_R1
+#define MODULE_PROC_FAMILY "MIPS64_R1 "
+#elif defined CONFIG_CPU_MIPS64_R2
+#define MODULE_PROC_FAMILY "MIPS64_R2 "
+#elif defined CONFIG_CPU_MIPS64_R6
+#define MODULE_PROC_FAMILY "MIPS64_R6 "
+#elif defined CONFIG_CPU_R3000
+#define MODULE_PROC_FAMILY "R3000 "
+#elif defined CONFIG_CPU_TX39XX
+#define MODULE_PROC_FAMILY "TX39XX "
+#elif defined CONFIG_CPU_VR41XX
+#define MODULE_PROC_FAMILY "VR41XX "
+#elif defined CONFIG_CPU_R4X00
+#define MODULE_PROC_FAMILY "R4X00 "
+#elif defined CONFIG_CPU_TX49XX
+#define MODULE_PROC_FAMILY "TX49XX "
+#elif defined CONFIG_CPU_R5000
+#define MODULE_PROC_FAMILY "R5000 "
+#elif defined CONFIG_CPU_R5500
+#define MODULE_PROC_FAMILY "R5500 "
+#elif defined CONFIG_CPU_NEVADA
+#define MODULE_PROC_FAMILY "NEVADA "
+#elif defined CONFIG_CPU_R10000
+#define MODULE_PROC_FAMILY "R10000 "
+#elif defined CONFIG_CPU_RM7000
+#define MODULE_PROC_FAMILY "RM7000 "
+#elif defined CONFIG_CPU_SB1
+#define MODULE_PROC_FAMILY "SB1 "
+#elif defined CONFIG_CPU_LOONGSON32
+#define MODULE_PROC_FAMILY "LOONGSON32 "
+#elif defined CONFIG_CPU_LOONGSON2EF
+#define MODULE_PROC_FAMILY "LOONGSON2EF "
+#elif defined CONFIG_CPU_LOONGSON64
+#define MODULE_PROC_FAMILY "LOONGSON64 "
+#elif defined CONFIG_CPU_CAVIUM_OCTEON
+#define MODULE_PROC_FAMILY "OCTEON "
+#elif defined CONFIG_CPU_XLR
+#define MODULE_PROC_FAMILY "XLR "
+#elif defined CONFIG_CPU_XLP
+#define MODULE_PROC_FAMILY "XLP "
+#else
+#error MODULE_PROC_FAMILY undefined for your processor configuration
+#endif
+
+#ifdef CONFIG_32BIT
+#define MODULE_KERNEL_TYPE "32BIT "
+#elif defined CONFIG_64BIT
+#define MODULE_KERNEL_TYPE "64BIT "
+#endif
+
+#define MODULE_ARCH_VERMAGIC \
+	MODULE_PROC_FAMILY MODULE_KERNEL_TYPE
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/nds32/include/asm/module.h b/arch/nds32/include/asm/vermagic.h
index a3a08e993c65..f772e7ba33f1 100644
--- a/arch/nds32/include/asm/module.h
+++ b/arch/nds32/include/asm/vermagic.h
@@ -1,11 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2005-2017 Andes Technology Corporation
 
-#ifndef _ASM_NDS32_MODULE_H
-#define _ASM_NDS32_MODULE_H
-
-#include <asm-generic/module.h>
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
 
 #define MODULE_ARCH_VERMAGIC	"NDS32v3"
 
-#endif /* _ASM_NDS32_MODULE_H */
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c
index e1a8fee3ad49..d46b6709ec56 100644
--- a/arch/parisc/kernel/perf.c
+++ b/arch/parisc/kernel/perf.c
@@ -300,7 +300,7 @@ static ssize_t perf_write(struct file *file, const char __user *buf,
 	else
 		return -EFAULT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	if (count != sizeof(uint32_t))
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 5224fb38d766..01d7071b23f7 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -562,7 +562,7 @@ void __init mem_init(void)
 			> BITS_PER_LONG);
 
 	high_memory = __va((max_pfn << PAGE_SHIFT));
-	set_max_mapnr(page_to_pfn(virt_to_page(high_memory - 1)) + 1);
+	set_max_mapnr(max_low_pfn);
 	memblock_free_all();
 
 #ifdef CONFIG_PA11
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 924c541a9260..b29d7cb38368 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -126,11 +126,12 @@ config PPC
 	select ARCH_HAS_MMIOWB			if PPC64
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_DEVMAP		if PPC_BOOK3S_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
-	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !HIBERNATION)
+	select ARCH_HAS_STRICT_KERNEL_RWX	if (PPC32 && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
 	select ARCH_HAS_UACCESS_MCSAFE		if PPC64
diff --git a/arch/powerpc/crypto/md5-glue.c b/arch/powerpc/crypto/md5-glue.c
index 7d1bf2fcf668..c24f605033bd 100644
--- a/arch/powerpc/crypto/md5-glue.c
+++ b/arch/powerpc/crypto/md5-glue.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/md5.h>
 #include <asm/byteorder.h>
diff --git a/arch/powerpc/crypto/sha1-spe-glue.c b/arch/powerpc/crypto/sha1-spe-glue.c
index 6379990bd604..cb57be4ada61 100644
--- a/arch/powerpc/crypto/sha1-spe-glue.c
+++ b/arch/powerpc/crypto/sha1-spe-glue.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <asm/byteorder.h>
diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
index 7b43fc352089..b40dc50a6908 100644
--- a/arch/powerpc/crypto/sha1.c
+++ b/arch/powerpc/crypto/sha1.c
@@ -16,14 +16,13 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <asm/byteorder.h>
 
-extern void powerpc_sha_transform(u32 *state, const u8 *src, u32 *temp);
+void powerpc_sha_transform(u32 *state, const u8 *src);
 
-static int sha1_init(struct shash_desc *desc)
+static int powerpc_sha1_init(struct shash_desc *desc)
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
@@ -34,8 +33,8 @@ static int sha1_init(struct shash_desc *desc)
 	return 0;
 }
 
-static int sha1_update(struct shash_desc *desc, const u8 *data,
-			unsigned int len)
+static int powerpc_sha1_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len)
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 	unsigned int partial, done;
@@ -47,7 +46,6 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
 	src = data;
 
 	if ((partial + len) > 63) {
-		u32 temp[SHA_WORKSPACE_WORDS];
 
 		if (partial) {
 			done = -partial;
@@ -56,12 +54,11 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
 		}
 
 		do {
-			powerpc_sha_transform(sctx->state, src, temp);
+			powerpc_sha_transform(sctx->state, src);
 			done += 64;
 			src = data + done;
 		} while (done + 63 < len);
 
-		memzero_explicit(temp, sizeof(temp));
 		partial = 0;
 	}
 	memcpy(sctx->buffer + partial, src, len - done);
@@ -71,7 +68,7 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
 
 
 /* Add padding and return the message digest. */
-static int sha1_final(struct shash_desc *desc, u8 *out)
+static int powerpc_sha1_final(struct shash_desc *desc, u8 *out)
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 	__be32 *dst = (__be32 *)out;
@@ -84,10 +81,10 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
 	/* Pad out to 56 mod 64 */
 	index = sctx->count & 0x3f;
 	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
-	sha1_update(desc, padding, padlen);
+	powerpc_sha1_update(desc, padding, padlen);
 
 	/* Append length */
-	sha1_update(desc, (const u8 *)&bits, sizeof(bits));
+	powerpc_sha1_update(desc, (const u8 *)&bits, sizeof(bits));
 
 	/* Store state in digest */
 	for (i = 0; i < 5; i++)
@@ -99,7 +96,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
-static int sha1_export(struct shash_desc *desc, void *out)
+static int powerpc_sha1_export(struct shash_desc *desc, void *out)
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
@@ -107,7 +104,7 @@ static int sha1_export(struct shash_desc *desc, void *out)
 	return 0;
 }
 
-static int sha1_import(struct shash_desc *desc, const void *in)
+static int powerpc_sha1_import(struct shash_desc *desc, const void *in)
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
@@ -117,11 +114,11 @@ static int sha1_import(struct shash_desc *desc, const void *in)
 
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
-	.init		=	sha1_init,
-	.update		=	sha1_update,
-	.final		=	sha1_final,
-	.export		=	sha1_export,
-	.import		=	sha1_import,
+	.init		=	powerpc_sha1_init,
+	.update		=	powerpc_sha1_update,
+	.final		=	powerpc_sha1_final,
+	.export		=	powerpc_sha1_export,
+	.import		=	powerpc_sha1_import,
 	.descsize	=	sizeof(struct sha1_state),
 	.statesize	=	sizeof(struct sha1_state),
 	.base		=	{
diff --git a/arch/powerpc/crypto/sha256-spe-glue.c b/arch/powerpc/crypto/sha256-spe-glue.c
index 84939e563b81..ceb0b6c980b3 100644
--- a/arch/powerpc/crypto/sha256-spe-glue.c
+++ b/arch/powerpc/crypto/sha256-spe-glue.c
@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <asm/byteorder.h>
diff --git a/arch/powerpc/include/asm/book3s/32/hash.h b/arch/powerpc/include/asm/book3s/32/hash.h
index 34a7215ae81e..2a0a467d2985 100644
--- a/arch/powerpc/include/asm/book3s/32/hash.h
+++ b/arch/powerpc/include/asm/book3s/32/hash.h
@@ -17,9 +17,9 @@
  * updating the accessed and modified bits in the page table tree.
  */
 
-#define _PAGE_USER	0x001	/* usermode access allowed */
-#define _PAGE_RW	0x002	/* software: user write access allowed */
-#define _PAGE_PRESENT	0x004	/* software: pte contains a translation */
+#define _PAGE_PRESENT	0x001	/* software: pte contains a translation */
+#define _PAGE_HASHPTE	0x002	/* hash_page has made an HPTE for this pte */
+#define _PAGE_USER	0x004	/* usermode access allowed */
 #define _PAGE_GUARDED	0x008	/* G: prohibit speculative access */
 #define _PAGE_COHERENT	0x010	/* M: enforce memory coherence (SMP systems) */
 #define _PAGE_NO_CACHE	0x020	/* I: cache inhibit */
@@ -27,7 +27,7 @@
 #define _PAGE_DIRTY	0x080	/* C: page changed */
 #define _PAGE_ACCESSED	0x100	/* R: page referenced */
 #define _PAGE_EXEC	0x200	/* software: exec allowed */
-#define _PAGE_HASHPTE	0x400	/* hash_page has made an HPTE for this pte */
+#define _PAGE_RW	0x400	/* software: user write access allowed */
 #define _PAGE_SPECIAL	0x800	/* software: Special page */
 
 #ifdef CONFIG_PTE_64BIT
diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index 3c0ba22dc360..db0a1c281587 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -75,7 +75,7 @@
 
 .macro kuap_check	current, gpr
 #ifdef CONFIG_PPC_KUAP_DEBUG
-	lwz	\gpr2, KUAP(thread)
+	lwz	\gpr, KUAP(thread)
 999:	twnei	\gpr, 0
 	EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
 #endif
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index e0e71777961f..3a0db7b0b46e 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -250,9 +250,27 @@ static inline bool arch_irqs_disabled(void)
 	}								\
 } while(0)
 
+static inline bool __lazy_irq_pending(u8 irq_happened)
+{
+	return !!(irq_happened & ~PACA_IRQ_HARD_DIS);
+}
+
+/*
+ * Check if a lazy IRQ is pending. Should be called with IRQs hard disabled.
+ */
 static inline bool lazy_irq_pending(void)
 {
-	return !!(get_paca()->irq_happened & ~PACA_IRQ_HARD_DIS);
+	return __lazy_irq_pending(get_paca()->irq_happened);
+}
+
+/*
+ * Check if a lazy IRQ is pending, with no debugging checks.
+ * Should be called with IRQs hard disabled.
+ * For use in RI disabled code or other constrained situations.
+ */
+static inline bool lazy_irq_pending_nocheck(void)
+{
+	return __lazy_irq_pending(local_paca->irq_happened);
 }
 
 /*
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index 356658711a86..5398bfc465b4 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -3,28 +3,10 @@
 #define _ASM_POWERPC_MODULE_H
 #ifdef __KERNEL__
 
-/*
- */
-
 #include <linux/list.h>
 #include <asm/bug.h>
 #include <asm-generic/module.h>
 
-
-#ifdef CONFIG_MPROFILE_KERNEL
-#define MODULE_ARCH_VERMAGIC_FTRACE	"mprofile-kernel "
-#else
-#define MODULE_ARCH_VERMAGIC_FTRACE	""
-#endif
-
-#ifdef CONFIG_RELOCATABLE
-#define MODULE_ARCH_VERMAGIC_RELOCATABLE	"relocatable "
-#else
-#define MODULE_ARCH_VERMAGIC_RELOCATABLE	""
-#endif
-
-#define MODULE_ARCH_VERMAGIC MODULE_ARCH_VERMAGIC_FTRACE MODULE_ARCH_VERMAGIC_RELOCATABLE
-
 #ifndef __powerpc64__
 /*
  * Thanks to Paul M for explaining this.
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 2f500debae21..0969285996cb 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -166,13 +166,17 @@ do {								\
 ({								\
 	long __pu_err;						\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
+	__typeof__(*(ptr)) __pu_val = (x);			\
+	__typeof__(size) __pu_size = (size);			\
+								\
 	if (!is_kernel_addr((unsigned long)__pu_addr))		\
 		might_fault();					\
-	__chk_user_ptr(ptr);					\
+	__chk_user_ptr(__pu_addr);				\
 	if (do_allow)								\
-		__put_user_size((x), __pu_addr, (size), __pu_err);		\
+		__put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err);	\
 	else									\
-		__put_user_size_allowed((x), __pu_addr, (size), __pu_err);	\
+		__put_user_size_allowed(__pu_val, __pu_addr, __pu_size, __pu_err); \
+								\
 	__pu_err;						\
 })
 
@@ -180,9 +184,13 @@ do {								\
 ({									\
 	long __pu_err = -EFAULT;					\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);			\
+	__typeof__(*(ptr)) __pu_val = (x);				\
+	__typeof__(size) __pu_size = (size);				\
+									\
 	might_fault();							\
-	if (access_ok(__pu_addr, size))			\
-		__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	if (access_ok(__pu_addr, __pu_size))				\
+		__put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \
+									\
 	__pu_err;							\
 })
 
@@ -190,8 +198,12 @@ do {								\
 ({								\
 	long __pu_err;						\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
-	__chk_user_ptr(ptr);					\
-	__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	__typeof__(*(ptr)) __pu_val = (x);			\
+	__typeof__(size) __pu_size = (size);			\
+								\
+	__chk_user_ptr(__pu_addr);				\
+	__put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \
+								\
 	__pu_err;						\
 })
 
@@ -283,15 +295,18 @@ do {								\
 	long __gu_err;						\
 	__long_type(*(ptr)) __gu_val;				\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
-	__chk_user_ptr(ptr);					\
+	__typeof__(size) __gu_size = (size);			\
+								\
+	__chk_user_ptr(__gu_addr);				\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
 	barrier_nospec();					\
 	if (do_allow)								\
-		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);		\
+		__get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err);	\
 	else									\
-		__get_user_size_allowed(__gu_val, __gu_addr, (size), __gu_err);	\
+		__get_user_size_allowed(__gu_val, __gu_addr, __gu_size, __gu_err); \
 	(x) = (__typeof__(*(ptr)))__gu_val;			\
+								\
 	__gu_err;						\
 })
 
@@ -300,12 +315,15 @@ do {								\
 	long __gu_err = -EFAULT;					\
 	__long_type(*(ptr)) __gu_val = 0;				\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
+	__typeof__(size) __gu_size = (size);				\
+									\
 	might_fault();							\
-	if (access_ok(__gu_addr, (size))) {		\
+	if (access_ok(__gu_addr, __gu_size)) {				\
 		barrier_nospec();					\
-		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+		__get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \
 	}								\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;				\
+									\
 	__gu_err;							\
 })
 
@@ -314,10 +332,13 @@ do {								\
 	long __gu_err;						\
 	__long_type(*(ptr)) __gu_val;				\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
-	__chk_user_ptr(ptr);					\
+	__typeof__(size) __gu_size = (size);			\
+								\
+	__chk_user_ptr(__gu_addr);				\
 	barrier_nospec();					\
-	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	__get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+								\
 	__gu_err;						\
 })
 
diff --git a/arch/powerpc/include/asm/vermagic.h b/arch/powerpc/include/asm/vermagic.h
new file mode 100644
index 000000000000..b054a8576e5d
--- /dev/null
+++ b/arch/powerpc/include/asm/vermagic.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#ifdef CONFIG_MPROFILE_KERNEL
+#define MODULE_ARCH_VERMAGIC_FTRACE	"mprofile-kernel "
+#else
+#define MODULE_ARCH_VERMAGIC_FTRACE	""
+#endif
+
+#ifdef CONFIG_RELOCATABLE
+#define MODULE_ARCH_VERMAGIC_RELOCATABLE	"relocatable "
+#else
+#define MODULE_ARCH_VERMAGIC_RELOCATABLE	""
+#endif
+
+#define MODULE_ARCH_VERMAGIC \
+		MODULE_ARCH_VERMAGIC_FTRACE MODULE_ARCH_VERMAGIC_RELOCATABLE
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 1c4385852d3d..244542ae2a91 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -162,6 +162,9 @@ UBSAN_SANITIZE_kprobes.o := n
 GCOV_PROFILE_kprobes-ftrace.o := n
 KCOV_INSTRUMENT_kprobes-ftrace.o := n
 UBSAN_SANITIZE_kprobes-ftrace.o := n
+GCOV_PROFILE_syscall_64.o := n
+KCOV_INSTRUMENT_syscall_64.o := n
+UBSAN_SANITIZE_syscall_64.o := n
 UBSAN_SANITIZE_vdso.o := n
 
 # Necessary for booting with kcov enabled on book3e machines
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index a6371fb8f761..8420abd4ea1c 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -732,7 +732,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE)
 	stw	r10,_CCR(r1)
 	stw	r1,KSP(r3)	/* Set old stack pointer */
 
-	kuap_check r2, r4
+	kuap_check r2, r0
 #ifdef CONFIG_SMP
 	/* We need a sync somewhere here to make sure that if the
 	 * previous task gets rescheduled on another CPU, it sees all
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 9a1e5d636dea..b3c9f15089b6 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -472,15 +472,17 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 #ifdef CONFIG_PPC_BOOK3S
 	/*
 	 * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
-	 * touched, AMR not set, no exit work created, then this can be used.
+	 * touched, no exit work created, then this can be used.
 	 */
 	.balign IFETCH_ALIGN_BYTES
 	.globl fast_interrupt_return
 fast_interrupt_return:
 _ASM_NOKPROBE_SYMBOL(fast_interrupt_return)
+	kuap_check_amr r3, r4
 	ld	r4,_MSR(r1)
 	andi.	r0,r4,MSR_PR
 	bne	.Lfast_user_interrupt_return
+	kuap_restore_amr r3
 	andi.	r0,r4,MSR_RI
 	li	r3,0 /* 0 return value, no EMULATE_STACK_STORE */
 	bne+	.Lfast_kernel_interrupt_return
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 728ccb0f560c..ebeebab74b56 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -971,6 +971,7 @@ EXC_COMMON_BEGIN(system_reset_common)
 	ld	r10,SOFTE(r1)
 	stb	r10,PACAIRQSOFTMASK(r13)
 
+	kuap_restore_amr r10
 	EXCEPTION_RESTORE_REGS
 	RFI_TO_USER_OR_KERNEL
 
@@ -2410,6 +2411,7 @@ EXC_COMMON_BEGIN(facility_unavailable_common)
 	GEN_COMMON facility_unavailable
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	facility_unavailable_exception
+	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
 	b	interrupt_return
 
 	GEN_KVM facility_unavailable
@@ -2439,6 +2441,7 @@ EXC_COMMON_BEGIN(h_facility_unavailable_common)
 	GEN_COMMON h_facility_unavailable
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	facility_unavailable_exception
+	REST_NVGPRS(r1) /* XXX Shouldn't be necessary in practice */
 	b	interrupt_return
 
 	GEN_KVM h_facility_unavailable
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index daaa153950c2..97c887950c3c 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -348,7 +348,7 @@ BEGIN_MMU_FTR_SECTION
 	andis.	r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
 #endif
 	bne	handle_page_fault_tramp_2	/* if not, try to put a PTE */
-	rlwinm	r3, r5, 32 - 24, 30, 30		/* DSISR_STORE -> _PAGE_RW */
+	rlwinm	r3, r5, 32 - 15, 21, 21		/* DSISR_STORE -> _PAGE_RW */
 	bl	hash_page
 	b	handle_page_fault_tramp_1
 FTR_SECTION_ELSE
@@ -497,6 +497,7 @@ InstructionTLBMiss:
 	andc.	r1,r1,r0		/* check access & ~permission */
 	bne-	InstructionAddressInvalid /* return if access not permitted */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
+	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
 	ori	r1, r1, 0xe06		/* clear out reserved bits */
 	andc	r1, r0, r1		/* PP = user? 1 : 0 */
 BEGIN_FTR_SECTION
@@ -564,8 +565,9 @@ DataLoadTLBMiss:
 	 * we would need to update the pte atomically with lwarx/stwcx.
 	 */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwinm	r1,r0,0,30,30		/* _PAGE_RW -> PP msb */
-	rlwimi	r0,r0,1,30,30		/* _PAGE_USER -> PP msb */
+	rlwinm	r1,r0,32-9,30,30	/* _PAGE_RW -> PP msb */
+	rlwimi	r0,r0,32-1,30,30	/* _PAGE_USER -> PP msb */
+	rlwimi	r0,r0,32-1,31,31	/* _PAGE_USER -> PP lsb */
 	ori	r1,r1,0xe04		/* clear out reserved bits */
 	andc	r1,r0,r1		/* PP = user? rw? 1: 3: 0 */
 BEGIN_FTR_SECTION
@@ -643,6 +645,7 @@ DataStoreTLBMiss:
 	 * we would need to update the pte atomically with lwarx/stwcx.
 	 */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
+	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
 	li	r1,0xe06		/* clear out reserved bits & PP msb */
 	andc	r1,r0,r1		/* PP = user? 1: 0 */
 BEGIN_FTR_SECTION
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 9bb663977e84..2cec543c38f0 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -344,8 +344,9 @@ _ENTRY(saved_ksp_limit)
 /* 0x0C00 - System Call Exception */
 	START_EXCEPTION(0x0C00,	SystemCall)
 	SYSCALL_ENTRY	0xc00
+/*	Trap_0D is commented out to get more space for system call exception */
 
-	EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_STD)
+/*	EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_STD) */
 	EXCEPTION(0x0E00, Trap_0E, unknown_exception, EXC_XFER_STD)
 	EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_STD)
 
diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c
index e34116255ced..957abd592075 100644
--- a/arch/powerpc/kernel/ima_arch.c
+++ b/arch/powerpc/kernel/ima_arch.c
@@ -19,12 +19,12 @@ bool arch_ima_get_secureboot(void)
  * to be stored as an xattr or as an appended signature.
  *
  * To avoid duplicate signature verification as much as possible, the IMA
- * policy rule for module appraisal is added only if CONFIG_MODULE_SIG_FORCE
+ * policy rule for module appraisal is added only if CONFIG_MODULE_SIG
  * is not enabled.
  */
 static const char *const secure_rules[] = {
 	"appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
-#ifndef CONFIG_MODULE_SIG_FORCE
+#ifndef CONFIG_MODULE_SIG
 	"appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
 #endif
 	NULL
@@ -50,7 +50,7 @@ static const char *const secure_and_trusted_rules[] = {
 	"measure func=KEXEC_KERNEL_CHECK template=ima-modsig",
 	"measure func=MODULE_CHECK template=ima-modsig",
 	"appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
-#ifndef CONFIG_MODULE_SIG_FORCE
+#ifndef CONFIG_MODULE_SIG
 	"appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig",
 #endif
 	NULL
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index fb4f61096613..0cd1c88bfc8b 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -655,9 +655,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 	int rc = -1;
 
 	switch (reason) {
-	case KMSG_DUMP_RESTART:
-	case KMSG_DUMP_HALT:
-	case KMSG_DUMP_POWEROFF:
+	case KMSG_DUMP_SHUTDOWN:
 		/* These are almost always orderly shutdowns. */
 		return;
 	case KMSG_DUMP_OOPS:
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 438a9befce41..8105010b0e76 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -534,6 +534,8 @@ static bool __init parse_cache_info(struct device_node *np,
 	lsizep = of_get_property(np, propnames[3], NULL);
 	if (bsizep == NULL)
 		bsizep = lsizep;
+	if (lsizep == NULL)
+		lsizep = bsizep;
 	if (lsizep != NULL)
 		lsize = be32_to_cpu(*lsizep);
 	if (bsizep != NULL)
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index c74295a7765b..7b7c89cad901 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -35,6 +35,8 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	BUG_ON(!FULL_REGS(regs));
 	BUG_ON(regs->softe != IRQS_ENABLED);
 
+	kuap_check_amr();
+
 	account_cpu_user_entry();
 
 #ifdef CONFIG_PPC_SPLPAR
@@ -47,8 +49,6 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	}
 #endif
 
-	kuap_check_amr();
-
 	/*
 	 * This is not required for the syscall exit path, but makes the
 	 * stack frame look nicer. If this was initialised in the first stack
@@ -117,6 +117,8 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	unsigned long ti_flags;
 	unsigned long ret = 0;
 
+	kuap_check_amr();
+
 	regs->result = r3;
 
 	/* Check whether the syscall is issued inside a restartable sequence */
@@ -189,7 +191,7 @@ again:
 
 	/* This pattern matches prep_irq_for_idle */
 	__hard_EE_RI_disable();
-	if (unlikely(lazy_irq_pending())) {
+	if (unlikely(lazy_irq_pending_nocheck())) {
 		__hard_RI_enable();
 		trace_hardirqs_off();
 		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
@@ -204,8 +206,6 @@ again:
 	local_paca->tm_scratch = regs->msr;
 #endif
 
-	kuap_check_amr();
-
 	account_cpu_user_exit();
 
 	return ret;
@@ -228,6 +228,8 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 	BUG_ON(!FULL_REGS(regs));
 	BUG_ON(regs->softe != IRQS_ENABLED);
 
+	kuap_check_amr();
+
 	local_irq_save(flags);
 
 again:
@@ -264,7 +266,7 @@ again:
 
 	trace_hardirqs_on();
 	__hard_EE_RI_disable();
-	if (unlikely(lazy_irq_pending())) {
+	if (unlikely(lazy_irq_pending_nocheck())) {
 		__hard_RI_enable();
 		trace_hardirqs_off();
 		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
@@ -292,8 +294,6 @@ again:
 	local_paca->tm_scratch = regs->msr;
 #endif
 
-	kuap_check_amr();
-
 	account_cpu_user_exit();
 
 	return ret;
@@ -313,6 +313,8 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 	BUG_ON(regs->msr & MSR_PR);
 	BUG_ON(!FULL_REGS(regs));
 
+	kuap_check_amr();
+
 	if (unlikely(*ti_flagsp & _TIF_EMULATE_STACK_STORE)) {
 		clear_bits(_TIF_EMULATE_STACK_STORE, ti_flagsp);
 		ret = 1;
@@ -334,7 +336,7 @@ again:
 
 		trace_hardirqs_on();
 		__hard_EE_RI_disable();
-		if (unlikely(lazy_irq_pending())) {
+		if (unlikely(lazy_irq_pending_nocheck())) {
 			__hard_RI_enable();
 			irq_soft_mask_set(IRQS_ALL_DISABLED);
 			trace_hardirqs_off();
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 3fca22276bb1..b44dd75de517 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -441,15 +441,9 @@ nonrecoverable:
 void system_reset_exception(struct pt_regs *regs)
 {
 	unsigned long hsrr0, hsrr1;
-	bool nested = in_nmi();
 	bool saved_hsrrs = false;
 
-	/*
-	 * Avoid crashes in case of nested NMI exceptions. Recoverability
-	 * is determined by RI and in_nmi
-	 */
-	if (!nested)
-		nmi_enter();
+	nmi_enter();
 
 	/*
 	 * System reset can interrupt code where HSRRs are live and MSR[RI]=1.
@@ -521,8 +515,7 @@ out:
 		mtspr(SPRN_HSRR1, hsrr1);
 	}
 
-	if (!nested)
-		nmi_exit();
+	nmi_exit();
 
 	/* What should we do here? We could issue a shutdown or hard reset. */
 }
@@ -823,9 +816,8 @@ int machine_check_generic(struct pt_regs *regs)
 void machine_check_exception(struct pt_regs *regs)
 {
 	int recover = 0;
-	bool nested = in_nmi();
-	if (!nested)
-		nmi_enter();
+
+	nmi_enter();
 
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
@@ -851,8 +843,7 @@ void machine_check_exception(struct pt_regs *regs)
 	if (check_io_access(regs))
 		goto bail;
 
-	if (!nested)
-		nmi_exit();
+	nmi_exit();
 
 	die("Machine check", regs, SIGBUS);
 
@@ -863,8 +854,7 @@ void machine_check_exception(struct pt_regs *regs)
 	return;
 
 bail:
-	if (!nested)
-		nmi_exit();
+	nmi_exit();
 }
 
 void SMIException(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index a3951567118a..e7f8f9f1b3f4 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -218,11 +218,11 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
 	blr
 
 	/*
-	 * invalid clock
+	 * syscall fallback
 	 */
 99:
-	li	r3, EINVAL
-	crset	so
+	li	r0,__NR_clock_getres
+	sc
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_clock_getres)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 31a0f201fb6f..a1706b63b82d 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -90,6 +90,7 @@ SECTIONS
 #ifdef CONFIG_PPC64
 		*(.tramp.ftrace.text);
 #endif
+		NOINSTR_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT
 		LOCK_TEXT
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 6404df613ea3..2b35f9bcf892 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -604,18 +604,19 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 */
 	local_irq_disable();
 	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+	pte = __pte(0);
+	if (ptep)
+		pte = *ptep;
+	local_irq_enable();
 	/*
 	 * If the PTE disappeared temporarily due to a THP
 	 * collapse, just return and let the guest try again.
 	 */
-	if (!ptep) {
-		local_irq_enable();
+	if (!pte_present(pte)) {
 		if (page)
 			put_page(page);
 		return RESUME_GUEST;
 	}
-	pte = *ptep;
-	local_irq_enable();
 	hpa = pte_pfn(pte) << PAGE_SHIFT;
 	pte_size = PAGE_SIZE;
 	if (shift)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 9f050064d2a2..aa12cd4078b3 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -815,18 +815,19 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 	 */
 	local_irq_disable();
 	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+	pte = __pte(0);
+	if (ptep)
+		pte = *ptep;
+	local_irq_enable();
 	/*
 	 * If the PTE disappeared temporarily due to a THP
 	 * collapse, just return and let the guest try again.
 	 */
-	if (!ptep) {
-		local_irq_enable();
+	if (!pte_present(pte)) {
 		if (page)
 			put_page(page);
 		return RESUME_GUEST;
 	}
-	pte = *ptep;
-	local_irq_enable();
 
 	/* If we're logging dirty pages, always map single pages */
 	large_enable = !(memslot->flags & KVM_MEM_LOG_DIRTY_PAGES);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index e15166b0a16d..ad2f172c26a6 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -521,6 +521,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_IMMEDIATE_EXIT:
+	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
 		break;
 	case KVM_CAP_PPC_GUEST_DEBUG_SSTEP:
diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S
index 6d236080cb1a..877d880890fe 100644
--- a/arch/powerpc/mm/book3s32/hash_low.S
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -35,7 +35,7 @@ mmu_hash_lock:
 /*
  * Load a PTE into the hash table, if possible.
  * The address is in r4, and r3 contains an access flag:
- * _PAGE_RW (0x002) if a write.
+ * _PAGE_RW (0x400) if a write.
  * r9 contains the SRR1 value, from which we use the MSR_PR bit.
  * SPRG_THREAD contains the physical address of the current task's thread.
  *
@@ -69,7 +69,7 @@ _GLOBAL(hash_page)
 	blt+	112f			/* assume user more likely */
 	lis	r5, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
-	rlwimi	r3,r9,32-14,31,31	/* MSR_PR -> _PAGE_USER */
+	rlwimi	r3,r9,32-12,29,29	/* MSR_PR -> _PAGE_USER */
 112:
 #ifndef CONFIG_PTE_64BIT
 	rlwimi	r5,r4,12,20,29		/* insert top 10 bits of address */
@@ -94,7 +94,7 @@ _GLOBAL(hash_page)
 #else
 	rlwimi	r8,r4,23,20,28		/* compute pte address */
 #endif
-	rlwinm	r0,r3,6,24,24		/* _PAGE_RW access -> _PAGE_DIRTY */
+	rlwinm	r0,r3,32-3,24,24	/* _PAGE_RW access -> _PAGE_DIRTY */
 	ori	r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE
 
 	/*
@@ -310,9 +310,11 @@ Hash_msk = (((1 << Hash_bits) - 1) * 64)
 
 _GLOBAL(create_hpte)
 	/* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */
+	rlwinm	r8,r5,32-9,30,30	/* _PAGE_RW -> PP msb */
 	rlwinm	r0,r5,32-6,30,30	/* _PAGE_DIRTY -> PP msb */
-	and	r8,r5,r0		/* writable if _RW & _DIRTY */
-	rlwimi	r5,r5,1,30,30		/* _PAGE_USER -> PP msb */
+	and	r8,r8,r0		/* writable if _RW & _DIRTY */
+	rlwimi	r5,r5,32-1,30,30	/* _PAGE_USER -> PP msb */
+	rlwimi	r5,r5,32-2,31,31	/* _PAGE_USER -> PP lsb */
 	ori	r8,r8,0xe04		/* clear out reserved bits */
 	andc	r8,r5,r8		/* PP = user? (rw&dirty? 1: 3): 0 */
 BEGIN_FTR_SECTION
@@ -564,7 +566,7 @@ _GLOBAL(flush_hash_pages)
 33:	lwarx	r8,0,r5			/* fetch the pte flags word */
 	andi.	r0,r8,_PAGE_HASHPTE
 	beq	8f			/* done if HASHPTE is already clear */
-	rlwinm	r8,r8,0,~_PAGE_HASHPTE	/* clear HASHPTE bit */
+	rlwinm	r8,r8,0,31,29		/* clear HASHPTE bit */
 	stwcx.	r8,0,r5			/* update the pte */
 	bne-	33b
 
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index 3189308dece4..d83a12c5bc7f 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -185,6 +185,7 @@ void mmu_mark_initmem_nx(void)
 			mmu_mapin_ram_chunk(etext8, einittext8, PAGE_KERNEL);
 		}
 	}
+	_tlbil_all();
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
@@ -199,6 +200,8 @@ void mmu_mark_rodata_ro(void)
 				      ~(LARGE_PAGE_SIZE_8M - 1)));
 	mmu_patch_addis(&patch__dtlbmiss_romem_top, -__pa(_sinittext));
 
+	_tlbil_all();
+
 	/* Update page tables for PTDUMP and BDI */
 	mmu_mapin_ram_chunk(0, sinittext, __pgprot(0));
 	mmu_mapin_ram_chunk(0, etext, PAGE_KERNEL_ROX);
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index eb82dda884e5..0edcfd0b491d 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -976,7 +976,7 @@ static int thread_imc_event_init(struct perf_event *event)
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	/* Sampling not supported */
@@ -1412,7 +1412,7 @@ static int trace_imc_event_init(struct perf_event *event)
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	/* Return if this is a couting event */
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 0c3c1902135c..27a81c291be8 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -397,7 +397,7 @@ config PPC_KUAP
 
 config PPC_KUAP_DEBUG
 	bool "Extra debugging for Kernel Userspace Access Protection"
-	depends on PPC_KUAP && (PPC_RADIX_MMU || PPC_32)
+	depends on PPC_KUAP && (PPC_RADIX_MMU || PPC32)
 	help
 	  Add extra debugging for Kernel Userspace Access Protection (KUAP)
 	  If you're unsure, say N.
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index a197258595ef..a31e1a41913a 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -54,13 +54,13 @@ config RISCV
 	select GENERIC_ARCH_TOPOLOGY if SMP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MMIOWB
-	select ARCH_HAS_DEBUG_VIRTUAL
-	select HAVE_EBPF_JIT
+	select ARCH_HAS_DEBUG_VIRTUAL if MMU
+	select HAVE_EBPF_JIT if MMU
 	select EDAC_SUPPORT
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_STRICT_KERNEL_RWX
+	select ARCH_HAS_STRICT_KERNEL_RWX if MMU
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select SPARSEMEM_STATIC if 32BIT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
@@ -136,6 +136,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
 config SYS_SUPPORTS_HUGETLBFS
+	depends on MMU
 	def_bool y
 
 config STACKTRACE_SUPPORT
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index 216286db81c9..d646332e44f1 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -11,14 +11,15 @@ config SOC_SIFIVE
 	  This enables support for SiFive SoC platform hardware.
 
 config SOC_VIRT
-       bool "QEMU Virt Machine"
-       select POWER_RESET_SYSCON
-       select POWER_RESET_SYSCON_POWEROFF
-       select GOLDFISH
-       select RTC_DRV_GOLDFISH
-       select SIFIVE_PLIC
-       help
-         This enables support for QEMU Virt Machine.
+	bool "QEMU Virt Machine"
+	select POWER_RESET
+	select POWER_RESET_SYSCON
+	select POWER_RESET_SYSCON_POWEROFF
+	select GOLDFISH
+	select RTC_DRV_GOLDFISH if RTC_CLASS
+	select SIFIVE_PLIC
+	help
+	  This enables support for QEMU Virt Machine.
 
 config SOC_KENDRYTE
 	bool "Kendryte K210 SoC"
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 8e18d2c64399..cec462e198ce 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -51,13 +51,10 @@
 #define CAUSE_IRQ_FLAG		(_AC(1, UL) << (__riscv_xlen - 1))
 
 /* Interrupt causes (minus the high bit) */
-#define IRQ_U_SOFT		0
 #define IRQ_S_SOFT		1
 #define IRQ_M_SOFT		3
-#define IRQ_U_TIMER		4
 #define IRQ_S_TIMER		5
 #define IRQ_M_TIMER		7
-#define IRQ_U_EXT		8
 #define IRQ_S_EXT		9
 #define IRQ_M_EXT		11
 
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 1bb0cd04aec3..5ce50468aff1 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -8,6 +8,7 @@
 #ifndef _ASM_RISCV_HWCAP_H
 #define _ASM_RISCV_HWCAP_H
 
+#include <linux/bits.h>
 #include <uapi/asm/hwcap.h>
 
 #ifndef __ASSEMBLY__
@@ -22,6 +23,27 @@ enum {
 };
 
 extern unsigned long elf_hwcap;
+
+#define RISCV_ISA_EXT_a		('a' - 'a')
+#define RISCV_ISA_EXT_c		('c' - 'a')
+#define RISCV_ISA_EXT_d		('d' - 'a')
+#define RISCV_ISA_EXT_f		('f' - 'a')
+#define RISCV_ISA_EXT_h		('h' - 'a')
+#define RISCV_ISA_EXT_i		('i' - 'a')
+#define RISCV_ISA_EXT_m		('m' - 'a')
+#define RISCV_ISA_EXT_s		('s' - 'a')
+#define RISCV_ISA_EXT_u		('u' - 'a')
+
+#define RISCV_ISA_EXT_MAX	64
+
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
+
+#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext)
+
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
+#define riscv_isa_extension_available(isa_bitmap, ext)	\
+	__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
+
 #endif
 
 #endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h
index a2c809df2733..56053c9838b2 100644
--- a/arch/riscv/include/asm/mmio.h
+++ b/arch/riscv/include/asm/mmio.h
@@ -16,6 +16,8 @@
 
 #ifndef CONFIG_MMU
 #define pgprot_noncached(x)	(x)
+#define pgprot_writecombine(x)	(x)
+#define pgprot_device(x)	(x)
 #endif /* CONFIG_MMU */
 
 /* Generic IO read/write.  These perform native-endian accesses. */
diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h
index bb4091ff4a21..0b2333e71fdc 100644
--- a/arch/riscv/include/asm/mmiowb.h
+++ b/arch/riscv/include/asm/mmiowb.h
@@ -9,6 +9,7 @@
  */
 #define mmiowb()	__asm__ __volatile__ ("fence o,w" : : : "memory");
 
+#include <linux/smp.h>
 #include <asm-generic/mmiowb.h>
 
 #endif	/* _ASM_RISCV_MMIOWB_H */
diff --git a/arch/riscv/include/asm/module.h b/arch/riscv/include/asm/module.h
index 46202dad365d..76aa96a9fc08 100644
--- a/arch/riscv/include/asm/module.h
+++ b/arch/riscv/include/asm/module.h
@@ -6,8 +6,6 @@
 
 #include <asm-generic/module.h>
 
-#define MODULE_ARCH_VERMAGIC    "riscv"
-
 struct module;
 unsigned long module_emit_got_entry(struct module *mod, unsigned long val);
 unsigned long module_emit_plt_entry(struct module *mod, unsigned long val);
diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h
index 0234048b12bc..062efd3a1d5d 100644
--- a/arch/riscv/include/asm/perf_event.h
+++ b/arch/riscv/include/asm/perf_event.h
@@ -12,19 +12,14 @@
 #include <linux/ptrace.h>
 #include <linux/interrupt.h>
 
+#ifdef CONFIG_RISCV_BASE_PMU
 #define RISCV_BASE_COUNTERS	2
 
 /*
  * The RISCV_MAX_COUNTERS parameter should be specified.
  */
 
-#ifdef CONFIG_RISCV_BASE_PMU
 #define RISCV_MAX_COUNTERS	2
-#endif
-
-#ifndef RISCV_MAX_COUNTERS
-#error "Please provide a valid RISCV_MAX_COUNTERS for the PMU."
-#endif
 
 /*
  * These are the indexes of bits in counteren register *minus* 1,
@@ -82,6 +77,7 @@ struct riscv_pmu {
 	int		irq;
 };
 
+#endif
 #ifdef CONFIG_PERF_EVENTS
 #define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs
 #endif
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 9c188ad2e52d..35b60035b6b0 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -470,12 +470,15 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 
 #else /* CONFIG_MMU */
 
+#define PAGE_SHARED		__pgprot(0)
 #define PAGE_KERNEL		__pgprot(0)
 #define swapper_pg_dir		NULL
 #define VMALLOC_START		0
 
 #define TASK_SIZE 0xffffffffUL
 
+static inline void __kernel_map_pages(struct page *page, int numpages, int enable) {}
+
 #endif /* !CONFIG_MMU */
 
 #define kern_addr_valid(addr)   (1) /* FIXME */
diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h
index c38df4771c09..4c5bae7ca01c 100644
--- a/arch/riscv/include/asm/set_memory.h
+++ b/arch/riscv/include/asm/set_memory.h
@@ -22,14 +22,6 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; }
 static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
-#ifdef CONFIG_STRICT_KERNEL_RWX
-void set_kernel_text_ro(void);
-void set_kernel_text_rw(void);
-#else
-static inline void set_kernel_text_ro(void) { }
-static inline void set_kernel_text_rw(void) { }
-#endif
-
 int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);
 
diff --git a/arch/riscv/include/asm/vermagic.h b/arch/riscv/include/asm/vermagic.h
new file mode 100644
index 000000000000..7b9441a57466
--- /dev/null
+++ b/arch/riscv/include/asm/vermagic.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#define MODULE_ARCH_VERMAGIC    "riscv"
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 86c83081044f..d8bbd3207100 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -43,7 +43,7 @@ obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
 
-obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o
+obj-$(CONFIG_RISCV_BASE_PMU)	+= perf_event.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
 obj-$(CONFIG_HAVE_PERF_REGS)	+= perf_regs.o
 obj-$(CONFIG_RISCV_SBI)		+= sbi.o
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
index c4c33bf02369..0ec22354018c 100644
--- a/arch/riscv/kernel/cpu_ops.c
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -15,8 +15,8 @@
 
 const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
-void *__cpu_up_stack_pointer[NR_CPUS];
-void *__cpu_up_task_pointer[NR_CPUS];
+void *__cpu_up_stack_pointer[NR_CPUS] __section(.data);
+void *__cpu_up_task_pointer[NR_CPUS] __section(.data);
 
 extern const struct cpu_operations cpu_ops_sbi;
 extern const struct cpu_operations cpu_ops_spinwait;
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index a5ad00043104..ac202f44a670 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/bitmap.h>
 #include <linux/of.h>
 #include <asm/processor.h>
 #include <asm/hwcap.h>
@@ -13,15 +14,57 @@
 #include <asm/switch_to.h>
 
 unsigned long elf_hwcap __read_mostly;
+
+/* Host ISA bitmap */
+static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
+
 #ifdef CONFIG_FPU
 bool has_fpu __read_mostly;
 #endif
 
+/**
+ * riscv_isa_extension_base() - Get base extension word
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * Return: base extension word as unsigned long value
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap)
+{
+	if (!isa_bitmap)
+		return riscv_isa[0];
+	return isa_bitmap[0];
+}
+EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
+
+/**
+ * __riscv_isa_extension_available() - Check whether given extension
+ * is available or not
+ *
+ * @isa_bitmap: ISA bitmap to use
+ * @bit: bit position of the desired extension
+ * Return: true or false
+ *
+ * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
+ */
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
+{
+	const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa;
+
+	if (bit >= RISCV_ISA_EXT_MAX)
+		return false;
+
+	return test_bit(bit, bmap) ? true : false;
+}
+EXPORT_SYMBOL_GPL(__riscv_isa_extension_available);
+
 void riscv_fill_hwcap(void)
 {
 	struct device_node *node;
 	const char *isa;
-	size_t i;
+	char print_str[BITS_PER_LONG + 1];
+	size_t i, j, isa_len;
 	static unsigned long isa2hwcap[256] = {0};
 
 	isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I;
@@ -33,8 +76,11 @@ void riscv_fill_hwcap(void)
 
 	elf_hwcap = 0;
 
+	bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX);
+
 	for_each_of_cpu_node(node) {
 		unsigned long this_hwcap = 0;
+		unsigned long this_isa = 0;
 
 		if (riscv_of_processor_hartid(node) < 0)
 			continue;
@@ -44,8 +90,24 @@ void riscv_fill_hwcap(void)
 			continue;
 		}
 
-		for (i = 0; i < strlen(isa); ++i)
+		i = 0;
+		isa_len = strlen(isa);
+#if IS_ENABLED(CONFIG_32BIT)
+		if (!strncmp(isa, "rv32", 4))
+			i += 4;
+#elif IS_ENABLED(CONFIG_64BIT)
+		if (!strncmp(isa, "rv64", 4))
+			i += 4;
+#endif
+		for (; i < isa_len; ++i) {
 			this_hwcap |= isa2hwcap[(unsigned char)(isa[i])];
+			/*
+			 * TODO: X, Y and Z extension parsing for Host ISA
+			 * bitmap will be added in-future.
+			 */
+			if ('a' <= isa[i] && isa[i] < 'x')
+				this_isa |= (1UL << (isa[i] - 'a'));
+		}
 
 		/*
 		 * All "okay" hart should have same isa. Set HWCAP based on
@@ -56,6 +118,11 @@ void riscv_fill_hwcap(void)
 			elf_hwcap &= this_hwcap;
 		else
 			elf_hwcap = this_hwcap;
+
+		if (riscv_isa[0])
+			riscv_isa[0] &= this_isa;
+		else
+			riscv_isa[0] = this_isa;
 	}
 
 	/* We don't support systems with F but without D, so mask those out
@@ -65,7 +132,17 @@ void riscv_fill_hwcap(void)
 		elf_hwcap &= ~COMPAT_HWCAP_ISA_F;
 	}
 
-	pr_info("elf_hwcap is 0x%lx\n", elf_hwcap);
+	memset(print_str, 0, sizeof(print_str));
+	for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+		if (riscv_isa[0] & BIT_MASK(i))
+			print_str[j++] = (char)('a' + i);
+	pr_info("riscv: ISA extensions %s\n", print_str);
+
+	memset(print_str, 0, sizeof(print_str));
+	for (i = 0, j = 0; i < BITS_PER_LONG; i++)
+		if (elf_hwcap & BIT_MASK(i))
+			print_str[j++] = (char)('a' + i);
+	pr_info("riscv: ELF capabilities %s\n", print_str);
 
 #ifdef CONFIG_FPU
 	if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D))
diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c
index 91626d9ae5f2..c835f0362d94 100644
--- a/arch/riscv/kernel/perf_event.c
+++ b/arch/riscv/kernel/perf_event.c
@@ -147,7 +147,7 @@ static int riscv_map_hw_event(u64 config)
 	return riscv_pmu->hw_events[config];
 }
 
-int riscv_map_cache_decode(u64 config, unsigned int *type,
+static int riscv_map_cache_decode(u64 config, unsigned int *type,
 			   unsigned int *op, unsigned int *result)
 {
 	return -ENOENT;
@@ -342,7 +342,7 @@ static void riscv_pmu_del(struct perf_event *event, int flags)
 
 static DEFINE_MUTEX(pmc_reserve_mutex);
 
-irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
+static irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
 {
 	return IRQ_NONE;
 }
@@ -361,7 +361,7 @@ static int reserve_pmc_hardware(void)
 	return err;
 }
 
-void release_pmc_hardware(void)
+static void release_pmc_hardware(void)
 {
 	mutex_lock(&pmc_reserve_mutex);
 	if (riscv_pmu->irq >= 0)
@@ -464,7 +464,7 @@ static const struct of_device_id riscv_pmu_of_ids[] = {
 	{ /* sentinel value */ }
 };
 
-int __init init_hw_perf_events(void)
+static int __init init_hw_perf_events(void)
 {
 	struct device_node *node = of_find_node_by_type(NULL, "pmu");
 	const struct of_device_id *of_id;
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 610c11e91606..824d117cf202 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -22,7 +22,7 @@
 #include <asm/switch_to.h>
 #include <asm/thread_info.h>
 
-unsigned long gp_in_global __asm__("gp");
+register unsigned long gp_in_global __asm__("gp");
 
 extern asmlinkage void ret_from_fork(void);
 extern asmlinkage void ret_from_kernel_thread(void);
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index 7c24da59bccf..f383ef5672b2 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -102,7 +102,7 @@ void sbi_shutdown(void)
 {
 	sbi_ecall(SBI_EXT_0_1_SHUTDOWN, 0, 0, 0, 0, 0, 0, 0);
 }
-EXPORT_SYMBOL(sbi_set_timer);
+EXPORT_SYMBOL(sbi_shutdown);
 
 /**
  * sbi_clear_ipi() - Clear any pending IPIs for the calling hart.
@@ -113,7 +113,7 @@ void sbi_clear_ipi(void)
 {
 	sbi_ecall(SBI_EXT_0_1_CLEAR_IPI, 0, 0, 0, 0, 0, 0, 0);
 }
-EXPORT_SYMBOL(sbi_shutdown);
+EXPORT_SYMBOL(sbi_clear_ipi);
 
 /**
  * sbi_set_timer_v01() - Program the timer for next timer event.
@@ -167,6 +167,11 @@ static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
 
 	return result;
 }
+
+static void sbi_set_power_off(void)
+{
+	pm_power_off = sbi_shutdown;
+}
 #else
 static void __sbi_set_timer_v01(uint64_t stime_value)
 {
@@ -191,6 +196,8 @@ static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
 
 	return 0;
 }
+
+static void sbi_set_power_off(void) {}
 #endif /* CONFIG_RISCV_SBI_V01 */
 
 static void __sbi_set_timer_v02(uint64_t stime_value)
@@ -540,16 +547,12 @@ static inline long sbi_get_firmware_version(void)
 	return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION);
 }
 
-static void sbi_power_off(void)
-{
-	sbi_shutdown();
-}
 
 int __init sbi_init(void)
 {
 	int ret;
 
-	pm_power_off = sbi_power_off;
+	sbi_set_power_off();
 	ret = sbi_get_spec_version();
 	if (ret > 0)
 		sbi_spec_version = ret;
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index e0a6293093f1..a65a8fa0c22d 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -10,6 +10,7 @@
 
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
+#include <linux/module.h>
 #include <linux/profile.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
@@ -63,6 +64,7 @@ void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out)
 	for_each_cpu(cpu, in)
 		cpumask_set_cpu(cpuid_to_hartid_map(cpu), out);
 }
+EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask);
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 02087fe539c6..837b9b38f825 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -12,6 +12,8 @@
 #include <linux/stacktrace.h>
 #include <linux/ftrace.h>
 
+register unsigned long sp_in_global __asm__("sp");
+
 #ifdef CONFIG_FRAME_POINTER
 
 struct stackframe {
@@ -19,8 +21,6 @@ struct stackframe {
 	unsigned long ra;
 };
 
-register unsigned long sp_in_global __asm__("sp");
-
 void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 			     bool (*fn)(unsigned long, void *), void *arg)
 {
@@ -65,7 +65,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 
 #else /* !CONFIG_FRAME_POINTER */
 
-static void notrace walk_stackframe(struct task_struct *task,
+void notrace walk_stackframe(struct task_struct *task,
 	struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg)
 {
 	unsigned long sp, pc;
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 33b16f4212f7..4c8b2a4a6a70 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -12,7 +12,7 @@ vdso-syms += getcpu
 vdso-syms += flush_icache
 
 # Files to link into the vdso
-obj-vdso = $(patsubst %, %.o, $(vdso-syms))
+obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
 # Build rules
 targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o
@@ -33,15 +33,15 @@ $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE
 	$(call if_changed,vdsold)
 
 # We also create a special relocatable object that should mirror the symbol
-# table and layout of the linked DSO.  With ld -R we can then refer to
-# these symbols in the kernel code rather than hand-coded addresses.
+# table and layout of the linked DSO. With ld --just-symbols we can then
+# refer to these symbols in the kernel code rather than hand-coded addresses.
 
 SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
 	-Wl,--build-id -Wl,--hash-style=both
 $(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE
 	$(call if_changed,vdsold)
 
-LDFLAGS_vdso-syms.o := -r -R
+LDFLAGS_vdso-syms.o := -r --just-symbols
 $(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE
 	$(call if_changed,ld)
 
diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S
new file mode 100644
index 000000000000..2a956c942211
--- /dev/null
+++ b/arch/riscv/kernel/vdso/note.S
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/elfnote.h>
+#include <linux/version.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index b55be44ff9bd..736de6c8739f 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -47,7 +47,7 @@ static void setup_zero_page(void)
 	memset((void *)empty_zero_page, 0, PAGE_SIZE);
 }
 
-#ifdef CONFIG_DEBUG_VM
+#if defined(CONFIG_MMU) && defined(CONFIG_DEBUG_VM)
 static inline void print_mlk(char *name, unsigned long b, unsigned long t)
 {
 	pr_notice("%12s : 0x%08lx - 0x%08lx   (%4ld kB)\n", name, b, t,
@@ -150,7 +150,8 @@ void __init setup_bootmem(void)
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
 	set_max_mapnr(PFN_DOWN(mem_size));
-	max_low_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	max_low_pfn = max_pfn;
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();
@@ -501,22 +502,6 @@ static inline void setup_vm_final(void)
 #endif /* CONFIG_MMU */
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
-void set_kernel_text_rw(void)
-{
-	unsigned long text_start = (unsigned long)_text;
-	unsigned long text_end = (unsigned long)_etext;
-
-	set_memory_rw(text_start, (text_end - text_start) >> PAGE_SHIFT);
-}
-
-void set_kernel_text_ro(void)
-{
-	unsigned long text_start = (unsigned long)_text;
-	unsigned long text_end = (unsigned long)_etext;
-
-	set_memory_ro(text_start, (text_end - text_start) >> PAGE_SHIFT);
-}
-
 void mark_rodata_ro(void)
 {
 	unsigned long text_start = (unsigned long)_text;
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index cc1985d8750a..d208a9fd6c52 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -110,6 +110,16 @@ static bool is_32b_int(s64 val)
 	return -(1L << 31) <= val && val < (1L << 31);
 }
 
+static bool in_auipc_jalr_range(s64 val)
+{
+	/*
+	 * auipc+jalr can reach any signed PC-relative offset in the range
+	 * [-2^31 - 2^11, 2^31 - 2^11).
+	 */
+	return (-(1L << 31) - (1L << 11)) <= val &&
+		val < ((1L << 31) - (1L << 11));
+}
+
 static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx)
 {
 	/* Note that the immediate from the add is sign-extended,
@@ -380,20 +390,24 @@ static void emit_sext_32_rd(u8 *rd, struct rv_jit_context *ctx)
 	*rd = RV_REG_T2;
 }
 
-static void emit_jump_and_link(u8 rd, s64 rvoff, bool force_jalr,
-			       struct rv_jit_context *ctx)
+static int emit_jump_and_link(u8 rd, s64 rvoff, bool force_jalr,
+			      struct rv_jit_context *ctx)
 {
 	s64 upper, lower;
 
 	if (rvoff && is_21b_int(rvoff) && !force_jalr) {
 		emit(rv_jal(rd, rvoff >> 1), ctx);
-		return;
+		return 0;
+	} else if (in_auipc_jalr_range(rvoff)) {
+		upper = (rvoff + (1 << 11)) >> 12;
+		lower = rvoff & 0xfff;
+		emit(rv_auipc(RV_REG_T1, upper), ctx);
+		emit(rv_jalr(rd, RV_REG_T1, lower), ctx);
+		return 0;
 	}
 
-	upper = (rvoff + (1 << 11)) >> 12;
-	lower = rvoff & 0xfff;
-	emit(rv_auipc(RV_REG_T1, upper), ctx);
-	emit(rv_jalr(rd, RV_REG_T1, lower), ctx);
+	pr_err("bpf-jit: target offset 0x%llx is out of range\n", rvoff);
+	return -ERANGE;
 }
 
 static bool is_signed_bpf_cond(u8 cond)
@@ -407,18 +421,16 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx)
 	s64 off = 0;
 	u64 ip;
 	u8 rd;
+	int ret;
 
 	if (addr && ctx->insns) {
 		ip = (u64)(long)(ctx->insns + ctx->ninsns);
 		off = addr - ip;
-		if (!is_32b_int(off)) {
-			pr_err("bpf-jit: target call addr %pK is out of range\n",
-			       (void *)addr);
-			return -ERANGE;
-		}
 	}
 
-	emit_jump_and_link(RV_REG_RA, off, !fixed, ctx);
+	ret = emit_jump_and_link(RV_REG_RA, off, !fixed, ctx);
+	if (ret)
+		return ret;
 	rd = bpf_to_rv_reg(BPF_REG_0, ctx);
 	emit(rv_addi(rd, RV_REG_A0, 0), ctx);
 	return 0;
@@ -429,7 +441,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 {
 	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
 		    BPF_CLASS(insn->code) == BPF_JMP;
-	int s, e, rvoff, i = insn - ctx->prog->insnsi;
+	int s, e, rvoff, ret, i = insn - ctx->prog->insnsi;
 	struct bpf_prog_aux *aux = ctx->prog->aux;
 	u8 rd = -1, rs = -1, code = insn->code;
 	s16 off = insn->off;
@@ -699,7 +711,9 @@ out_be:
 	/* JUMP off */
 	case BPF_JMP | BPF_JA:
 		rvoff = rv_offset(i, off, ctx);
-		emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx);
+		ret = emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx);
+		if (ret)
+			return ret;
 		break;
 
 	/* IF (dst COND src) JUMP off */
@@ -801,7 +815,6 @@ out_be:
 	case BPF_JMP | BPF_CALL:
 	{
 		bool fixed;
-		int ret;
 		u64 addr;
 
 		mark_call(ctx);
@@ -826,7 +839,9 @@ out_be:
 			break;
 
 		rvoff = epilogue_offset(ctx);
-		emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx);
+		ret = emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx);
+		if (ret)
+			return ret;
 		break;
 
 	/* dst = imm64 */
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
index 8fde561f1d07..f887a479cdc7 100644
--- a/arch/s390/boot/uv.c
+++ b/arch/s390/boot/uv.c
@@ -7,9 +7,7 @@
 #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
 int __bootdata_preserved(prot_virt_guest);
 #endif
-#if IS_ENABLED(CONFIG_KVM)
 struct uv_info __bootdata_preserved(uv_info);
-#endif
 
 void uv_query_info(void)
 {
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index 7c15542d3685..698b1e6d3c14 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -27,7 +27,7 @@
 
 #include "sha.h"
 
-static int sha1_init(struct shash_desc *desc)
+static int s390_sha1_init(struct shash_desc *desc)
 {
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 
@@ -42,7 +42,7 @@ static int sha1_init(struct shash_desc *desc)
 	return 0;
 }
 
-static int sha1_export(struct shash_desc *desc, void *out)
+static int s390_sha1_export(struct shash_desc *desc, void *out)
 {
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 	struct sha1_state *octx = out;
@@ -53,7 +53,7 @@ static int sha1_export(struct shash_desc *desc, void *out)
 	return 0;
 }
 
-static int sha1_import(struct shash_desc *desc, const void *in)
+static int s390_sha1_import(struct shash_desc *desc, const void *in)
 {
 	struct s390_sha_ctx *sctx = shash_desc_ctx(desc);
 	const struct sha1_state *ictx = in;
@@ -67,11 +67,11 @@ static int sha1_import(struct shash_desc *desc, const void *in)
 
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
-	.init		=	sha1_init,
+	.init		=	s390_sha1_init,
 	.update		=	s390_sha_update,
 	.final		=	s390_sha_final,
-	.export		=	sha1_export,
-	.import		=	sha1_import,
+	.export		=	s390_sha1_export,
+	.import		=	s390_sha1_import,
 	.descsize	=	sizeof(struct s390_sha_ctx),
 	.statesize	=	sizeof(struct sha1_state),
 	.base		=	{
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index cd060b5dd8fd..e4dc64cc9c55 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -8,6 +8,10 @@
 #include <linux/slab.h>
 #include <asm/pci_insn.h>
 
+/* I/O size constraints */
+#define ZPCI_MAX_READ_SIZE	8
+#define ZPCI_MAX_WRITE_SIZE	128
+
 /* I/O Map */
 #define ZPCI_IOMAP_SHIFT		48
 #define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000UL
@@ -140,7 +144,8 @@ static inline int zpci_memcpy_fromio(void *dst,
 
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) src,
-					       (u64) dst, n, 8);
+					       (u64) dst, n,
+					       ZPCI_MAX_READ_SIZE);
 		rc = zpci_read_single(dst, src, size);
 		if (rc)
 			break;
@@ -161,7 +166,8 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst,
 
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) dst,
-					       (u64) src, n, 128);
+					       (u64) src, n,
+					       ZPCI_MAX_WRITE_SIZE);
 		if (size > 8) /* main path */
 			rc = zpci_write_block(dst, src, size);
 		else
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index 61f2b0412345..ccba63aaeb47 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -133,7 +133,7 @@ void diag_stat_inc(enum diag_stat_enum nr)
 }
 EXPORT_SYMBOL(diag_stat_inc);
 
-void diag_stat_inc_norecursion(enum diag_stat_enum nr)
+void notrace diag_stat_inc_norecursion(enum diag_stat_enum nr)
 {
 	this_cpu_inc(diag_stat.counter[nr]);
 	trace_s390_diagnose_norecursion(diag_map[nr].code);
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 8415ae7d2a23..f9e4baa64b67 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -151,7 +151,7 @@ static int kexec_file_add_initrd(struct kimage *image,
 		buf.mem += crashk_res.start;
 	buf.memsz = buf.bufsz;
 
-	data->parm->initrd_start = buf.mem;
+	data->parm->initrd_start = data->memsz;
 	data->parm->initrd_size = buf.memsz;
 	data->memsz += buf.memsz;
 
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
index d5035de9020e..b7182cec48dc 100644
--- a/arch/s390/kernel/machine_kexec_reloc.c
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -28,6 +28,7 @@ int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
 		break;
 	case R_390_64:		/* Direct 64 bit.  */
 	case R_390_GLOB_DAT:
+	case R_390_JMP_SLOT:
 		*(u64 *)loc = val;
 		break;
 	case R_390_PC16:	/* PC relative 16 bit.	*/
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 7eaabbab2213..10dbb12eb14d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -403,7 +403,7 @@ int smp_find_processor_id(u16 address)
 	return -1;
 }
 
-bool arch_vcpu_is_preempted(int cpu)
+bool notrace arch_vcpu_is_preempted(int cpu)
 {
 	if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu))
 		return false;
@@ -413,7 +413,7 @@ bool arch_vcpu_is_preempted(int cpu)
 }
 EXPORT_SYMBOL(arch_vcpu_is_preempted);
 
-void smp_yield_cpu(int cpu)
+void notrace smp_yield_cpu(int cpu)
 {
 	if (!MACHINE_HAS_DIAG9C)
 		return;
diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c
index 490b52e85014..11a669f3cc93 100644
--- a/arch/s390/kernel/trace.c
+++ b/arch/s390/kernel/trace.c
@@ -14,7 +14,7 @@ EXPORT_TRACEPOINT_SYMBOL(s390_diagnose);
 
 static DEFINE_PER_CPU(unsigned int, diagnose_trace_depth);
 
-void trace_s390_diagnose_norecursion(int diag_nr)
+void notrace trace_s390_diagnose_norecursion(int diag_nr)
 {
 	unsigned long flags;
 	unsigned int *depth;
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index c86d654351d1..4c0677fc8904 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -23,10 +23,11 @@
 int __bootdata_preserved(prot_virt_guest);
 #endif
 
+struct uv_info __bootdata_preserved(uv_info);
+
 #if IS_ENABLED(CONFIG_KVM)
 int prot_virt_host;
 EXPORT_SYMBOL(prot_virt_host);
-struct uv_info __bootdata_preserved(uv_info);
 EXPORT_SYMBOL(uv_info);
 
 static int __init prot_virt_setup(char *val)
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 8191106bf7b9..bfb481134994 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -393,7 +393,7 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
 	if (psw_mchk_disabled(vcpu))
 		active_mask &= ~IRQ_PEND_MCHK_MASK;
 	/* PV guest cpus can have a single interruption injected at a time. */
-	if (kvm_s390_pv_cpu_is_protected(vcpu) &&
+	if (kvm_s390_pv_cpu_get_handle(vcpu) &&
 	    vcpu->arch.sie_block->iictl != IICTL_CODE_NONE)
 		active_mask &= ~(IRQ_PEND_EXT_II_MASK |
 				 IRQ_PEND_IO_MASK |
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 19a81024fe16..d05bb040fd42 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -545,6 +545,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_AIS:
 	case KVM_CAP_S390_AIS_MIGRATION:
 	case KVM_CAP_S390_VCPU_RESETS:
+	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
 		break;
 	case KVM_CAP_S390_HPAGE_1M:
@@ -1939,6 +1940,9 @@ static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn)
 			start = slot + 1;
 	}
 
+	if (start >= slots->used_slots)
+		return slots->used_slots - 1;
+
 	if (gfn >= memslots[start].base_gfn &&
 	    gfn < memslots[start].base_gfn + memslots[start].npages) {
 		atomic_set(&slots->lru_slot, start);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 69a824f9ef0b..893893642415 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -626,10 +626,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu)
 	 * available for the guest are AQIC and TAPQ with the t bit set
 	 * since we do not set IC.3 (FIII) we currently will only intercept
 	 * the AQIC function code.
+	 * Note: running nested under z/VM can result in intercepts for other
+	 * function codes, e.g. PQAP(QCI). We do not support this and bail out.
 	 */
 	reg0 = vcpu->run->s.regs.gprs[0];
 	fc = (reg0 >> 24) & 0xff;
-	if (WARN_ON_ONCE(fc != 0x03))
+	if (fc != 0x03)
 		return -EOPNOTSUPP;
 
 	/* PQAP instruction is allowed for guest kernel only */
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index c4f8039a35e8..0267405ab7c6 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -64,10 +64,13 @@ mm_segment_t enable_sacf_uaccess(void)
 {
 	mm_segment_t old_fs;
 	unsigned long asce, cr;
+	unsigned long flags;
 
 	old_fs = current->thread.mm_segment;
 	if (old_fs & 1)
 		return old_fs;
+	/* protect against a concurrent page table upgrade */
+	local_irq_save(flags);
 	current->thread.mm_segment |= 1;
 	asce = S390_lowcore.kernel_asce;
 	if (likely(old_fs == USER_DS)) {
@@ -83,6 +86,7 @@ mm_segment_t enable_sacf_uaccess(void)
 		__ctl_load(asce, 7, 7);
 		set_cpu_flag(CIF_ASCE_SECONDARY);
 	}
+	local_irq_restore(flags);
 	return old_fs;
 }
 EXPORT_SYMBOL(enable_sacf_uaccess);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index f01daddcbc5e..4632d4e26b66 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -159,10 +159,13 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		rste &= ~_SEGMENT_ENTRY_NOEXEC;
 
 	/* Set correct table type for 2G hugepages */
-	if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
-		rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE;
-	else
+	if ((pte_val(*ptep) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) {
+		if (likely(pte_present(pte)))
+			rste |= _REGION3_ENTRY_LARGE;
+		rste |= _REGION_ENTRY_TYPE_R3;
+	} else if (likely(pte_present(pte)))
 		rste |= _SEGMENT_ENTRY_LARGE;
+
 	clear_huge_pte_skeys(mm, rste);
 	pte_val(*ptep) = rste;
 }
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 498c98a312f4..fff169d64711 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -70,8 +70,20 @@ static void __crst_table_upgrade(void *arg)
 {
 	struct mm_struct *mm = arg;
 
-	if (current->active_mm == mm)
-		set_user_asce(mm);
+	/* we must change all active ASCEs to avoid the creation of new TLBs */
+	if (current->active_mm == mm) {
+		S390_lowcore.user_asce = mm->context.asce;
+		if (current->thread.mm_segment == USER_DS) {
+			__ctl_load(S390_lowcore.user_asce, 1, 1);
+			/* Mark user-ASCE present in CR1 */
+			clear_cpu_flag(CIF_ASCE_PRIMARY);
+		}
+		if (current->thread.mm_segment == USER_DS_SACF) {
+			__ctl_load(S390_lowcore.user_asce, 7, 7);
+			/* enable_sacf_uaccess does all or nothing */
+			WARN_ON(!test_cpu_flag(CIF_ASCE_SECONDARY));
+		}
+	}
 	__tlb_flush_local();
 }
 
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index fbe97ab2e228..743f257cf2cb 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -115,7 +115,6 @@ static struct irq_chip zpci_irq_chip = {
 	.name = "PCI-MSI",
 	.irq_unmask = pci_msi_unmask_irq,
 	.irq_mask = pci_msi_mask_irq,
-	.irq_set_affinity = zpci_set_irq_affinity,
 };
 
 static void zpci_handle_cpu_local_irq(bool rescan)
@@ -276,7 +275,9 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 		rc = -EIO;
 		if (hwirq - bit >= msi_vecs)
 			break;
-		irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE, msi->affinity);
+		irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE,
+				(irq_delivery == DIRECTED) ?
+				msi->affinity : NULL);
 		if (irq < 0)
 			return -ENOMEM;
 		rc = irq_set_msi_desc(irq, msi);
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 7d42a8794f10..020a2c514d96 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -11,6 +11,113 @@
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/pci.h>
+#include <asm/pci_io.h>
+#include <asm/pci_debug.h>
+
+static inline void zpci_err_mmio(u8 cc, u8 status, u64 offset)
+{
+	struct {
+		u64 offset;
+		u8 cc;
+		u8 status;
+	} data = {offset, cc, status};
+
+	zpci_err_hex(&data, sizeof(data));
+}
+
+static inline int __pcistb_mio_inuser(
+		void __iomem *ioaddr, const void __user *src,
+		u64 len, u8 *status)
+{
+	int cc = -ENXIO;
+
+	asm volatile (
+		"       sacf 256\n"
+		"0:     .insn   rsy,0xeb00000000d4,%[len],%[ioaddr],%[src]\n"
+		"1:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"2:     sacf 768\n"
+		EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+		: [cc] "+d" (cc), [len] "+d" (len)
+		: [ioaddr] "a" (ioaddr), [src] "Q" (*((u8 __force *)src))
+		: "cc", "memory");
+	*status = len >> 24 & 0xff;
+	return cc;
+}
+
+static inline int __pcistg_mio_inuser(
+		void __iomem *ioaddr, const void __user *src,
+		u64 ulen, u8 *status)
+{
+	register u64 addr asm("2") = (u64 __force) ioaddr;
+	register u64 len asm("3") = ulen;
+	int cc = -ENXIO;
+	u64 val = 0;
+	u64 cnt = ulen;
+	u8 tmp;
+
+	/*
+	 * copy 0 < @len <= 8 bytes from @src into the right most bytes of
+	 * a register, then store it to PCI at @ioaddr while in secondary
+	 * address space. pcistg then uses the user mappings.
+	 */
+	asm volatile (
+		"       sacf    256\n"
+		"0:     llgc    %[tmp],0(%[src])\n"
+		"       sllg    %[val],%[val],8\n"
+		"       aghi    %[src],1\n"
+		"       ogr     %[val],%[tmp]\n"
+		"       brctg   %[cnt],0b\n"
+		"1:     .insn   rre,0xb9d40000,%[val],%[ioaddr]\n"
+		"2:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"3:     sacf    768\n"
+		EX_TABLE(0b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
+		:
+		[src] "+a" (src), [cnt] "+d" (cnt),
+		[val] "+d" (val), [tmp] "=d" (tmp),
+		[len] "+d" (len), [cc] "+d" (cc),
+		[ioaddr] "+a" (addr)
+		:: "cc", "memory");
+	*status = len >> 24 & 0xff;
+
+	/* did we read everything from user memory? */
+	if (!cc && cnt != 0)
+		cc = -EFAULT;
+
+	return cc;
+}
+
+static inline int __memcpy_toio_inuser(void __iomem *dst,
+				   const void __user *src, size_t n)
+{
+	int size, rc = 0;
+	u8 status = 0;
+	mm_segment_t old_fs;
+
+	if (!src)
+		return -EINVAL;
+
+	old_fs = enable_sacf_uaccess();
+	while (n > 0) {
+		size = zpci_get_max_write_size((u64 __force) dst,
+					       (u64 __force) src, n,
+					       ZPCI_MAX_WRITE_SIZE);
+		if (size > 8) /* main path */
+			rc = __pcistb_mio_inuser(dst, src, size, &status);
+		else
+			rc = __pcistg_mio_inuser(dst, src, size, &status);
+		if (rc)
+			break;
+		src += size;
+		dst += size;
+		n -= size;
+	}
+	disable_sacf_uaccess(old_fs);
+	if (rc)
+		zpci_err_mmio(rc, status, (__force u64) dst);
+	return rc;
+}
 
 static long get_pfn(unsigned long user_addr, unsigned long access,
 		    unsigned long *pfn)
@@ -46,6 +153,20 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 
 	if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
 		return -EINVAL;
+
+	/*
+	 * Only support read access to MIO capable devices on a MIO enabled
+	 * system. Otherwise we would have to check for every address if it is
+	 * a special ZPCI_ADDR and we would have to do a get_pfn() which we
+	 * don't need for MIO capable devices.
+	 */
+	if (static_branch_likely(&have_mio)) {
+		ret = __memcpy_toio_inuser((void  __iomem *) mmio_addr,
+					user_buffer,
+					length);
+		return ret;
+	}
+
 	if (length > 64) {
 		buf = kmalloc(length, GFP_KERNEL);
 		if (!buf)
@@ -56,7 +177,8 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 	ret = get_pfn(mmio_addr, VM_WRITE, &pfn);
 	if (ret)
 		goto out;
-	io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK));
+	io_addr = (void __iomem *)((pfn << PAGE_SHIFT) |
+			(mmio_addr & ~PAGE_MASK));
 
 	ret = -EFAULT;
 	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE)
@@ -72,6 +194,78 @@ out:
 	return ret;
 }
 
+static inline int __pcilg_mio_inuser(
+		void __user *dst, const void __iomem *ioaddr,
+		u64 ulen, u8 *status)
+{
+	register u64 addr asm("2") = (u64 __force) ioaddr;
+	register u64 len asm("3") = ulen;
+	u64 cnt = ulen;
+	int shift = ulen * 8;
+	int cc = -ENXIO;
+	u64 val, tmp;
+
+	/*
+	 * read 0 < @len <= 8 bytes from the PCI memory mapped at @ioaddr (in
+	 * user space) into a register using pcilg then store these bytes at
+	 * user address @dst
+	 */
+	asm volatile (
+		"       sacf    256\n"
+		"0:     .insn   rre,0xb9d60000,%[val],%[ioaddr]\n"
+		"1:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"       ltr     %[cc],%[cc]\n"
+		"       jne     4f\n"
+		"2:     ahi     %[shift],-8\n"
+		"       srlg    %[tmp],%[val],0(%[shift])\n"
+		"3:     stc     %[tmp],0(%[dst])\n"
+		"       aghi    %[dst],1\n"
+		"       brctg   %[cnt],2b\n"
+		"4:     sacf    768\n"
+		EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b)
+		:
+		[cc] "+d" (cc), [val] "=d" (val), [len] "+d" (len),
+		[dst] "+a" (dst), [cnt] "+d" (cnt), [tmp] "=d" (tmp),
+		[shift] "+d" (shift)
+		:
+		[ioaddr] "a" (addr)
+		: "cc", "memory");
+
+	/* did we write everything to the user space buffer? */
+	if (!cc && cnt != 0)
+		cc = -EFAULT;
+
+	*status = len >> 24 & 0xff;
+	return cc;
+}
+
+static inline int __memcpy_fromio_inuser(void __user *dst,
+				     const void __iomem *src,
+				     unsigned long n)
+{
+	int size, rc = 0;
+	u8 status;
+	mm_segment_t old_fs;
+
+	old_fs = enable_sacf_uaccess();
+	while (n > 0) {
+		size = zpci_get_max_write_size((u64 __force) src,
+					       (u64 __force) dst, n,
+					       ZPCI_MAX_READ_SIZE);
+		rc = __pcilg_mio_inuser(dst, src, size, &status);
+		if (rc)
+			break;
+		src += size;
+		dst += size;
+		n -= size;
+	}
+	disable_sacf_uaccess(old_fs);
+	if (rc)
+		zpci_err_mmio(rc, status, (__force u64) dst);
+	return rc;
+}
+
 SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 		void __user *, user_buffer, size_t, length)
 {
@@ -86,12 +280,27 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 
 	if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length)
 		return -EINVAL;
+
+	/*
+	 * Only support write access to MIO capable devices on a MIO enabled
+	 * system. Otherwise we would have to check for every address if it is
+	 * a special ZPCI_ADDR and we would have to do a get_pfn() which we
+	 * don't need for MIO capable devices.
+	 */
+	if (static_branch_likely(&have_mio)) {
+		ret = __memcpy_fromio_inuser(
+				user_buffer, (const void __iomem *)mmio_addr,
+				length);
+		return ret;
+	}
+
 	if (length > 64) {
 		buf = kmalloc(length, GFP_KERNEL);
 		if (!buf)
 			return -ENOMEM;
-	} else
+	} else {
 		buf = local_buf;
+	}
 
 	ret = get_pfn(mmio_addr, VM_READ, &pfn);
 	if (ret)
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index b4f0e37b83eb..97656d20b9ea 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -71,7 +71,6 @@ config SUPERH32
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_ARCH_KGDB
diff --git a/arch/sh/include/asm/module.h b/arch/sh/include/asm/module.h
index 9f38fb35fe96..337663a028db 100644
--- a/arch/sh/include/asm/module.h
+++ b/arch/sh/include/asm/module.h
@@ -11,32 +11,4 @@ struct mod_arch_specific {
 };
 #endif
 
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-# ifdef CONFIG_CPU_SH2
-#  define MODULE_PROC_FAMILY "SH2LE "
-# elif defined  CONFIG_CPU_SH3
-#  define MODULE_PROC_FAMILY "SH3LE "
-# elif defined  CONFIG_CPU_SH4
-#  define MODULE_PROC_FAMILY "SH4LE "
-# elif defined  CONFIG_CPU_SH5
-#  define MODULE_PROC_FAMILY "SH5LE "
-# else
-#  error unknown processor family
-# endif
-#else
-# ifdef CONFIG_CPU_SH2
-#  define MODULE_PROC_FAMILY "SH2BE "
-# elif defined  CONFIG_CPU_SH3
-#  define MODULE_PROC_FAMILY "SH3BE "
-# elif defined  CONFIG_CPU_SH4
-#  define MODULE_PROC_FAMILY "SH4BE "
-# elif defined  CONFIG_CPU_SH5
-#  define MODULE_PROC_FAMILY "SH5BE "
-# else
-#  error unknown processor family
-# endif
-#endif
-
-#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
-
 #endif /* _ASM_SH_MODULE_H */
diff --git a/arch/sh/include/asm/vermagic.h b/arch/sh/include/asm/vermagic.h
new file mode 100644
index 000000000000..13d8eaa9188e
--- /dev/null
+++ b/arch/sh/include/asm/vermagic.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# ifdef CONFIG_CPU_SH2
+#  define MODULE_PROC_FAMILY "SH2LE "
+# elif defined  CONFIG_CPU_SH3
+#  define MODULE_PROC_FAMILY "SH3LE "
+# elif defined  CONFIG_CPU_SH4
+#  define MODULE_PROC_FAMILY "SH4LE "
+# elif defined  CONFIG_CPU_SH5
+#  define MODULE_PROC_FAMILY "SH5LE "
+# else
+#  error unknown processor family
+# endif
+#else
+# ifdef CONFIG_CPU_SH2
+#  define MODULE_PROC_FAMILY "SH2BE "
+# elif defined  CONFIG_CPU_SH3
+#  define MODULE_PROC_FAMILY "SH3BE "
+# elif defined  CONFIG_CPU_SH4
+#  define MODULE_PROC_FAMILY "SH4BE "
+# elif defined  CONFIG_CPU_SH5
+#  define MODULE_PROC_FAMILY "SH5BE "
+# else
+#  error unknown processor family
+# endif
+#endif
+
+#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/sh/include/uapi/asm/sockios.h b/arch/sh/include/uapi/asm/sockios.h
index 3da561453260..ef01ced9e169 100644
--- a/arch/sh/include/uapi/asm/sockios.h
+++ b/arch/sh/include/uapi/asm/sockios.h
@@ -2,6 +2,8 @@
 #ifndef __ASM_SH_SOCKIOS_H
 #define __ASM_SH_SOCKIOS_H
 
+#include <linux/time_types.h>
+
 /* Socket-level I/O control calls. */
 #define FIOGETOWN	_IOR('f', 123, int)
 #define FIOSETOWN 	_IOW('f', 124, int)
diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index 63cf17bc760d..2130381c9d57 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -170,11 +170,21 @@ BUILD_TRAP_HANDLER(bug)
 	force_sig(SIGTRAP);
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void arch_ftrace_nmi_enter(void);
+extern void arch_ftrace_nmi_exit(void);
+#else
+static inline void arch_ftrace_nmi_enter(void) { }
+static inline void arch_ftrace_nmi_exit(void) { }
+#endif
+
 BUILD_TRAP_HANDLER(nmi)
 {
 	unsigned int cpu = smp_processor_id();
 	TRAP_HANDLER_DECL;
 
+	arch_ftrace_nmi_enter();
+
 	nmi_enter();
 	nmi_count(cpu)++;
 
@@ -190,4 +200,6 @@ BUILD_TRAP_HANDLER(nmi)
 	}
 
 	nmi_exit();
+
+	arch_ftrace_nmi_exit();
 }
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index b9de2d4fa57e..8d2a68aea1fc 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -412,7 +412,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot)
+	if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot))
 		return -EINVAL;
 
 	/* We only have ZONE_NORMAL, so this is easy.. */
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index 14f6c15be6ae..111283fe837e 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -18,7 +18,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/md5.h>
 
diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c
index 7c1666304441..dc017782be52 100644
--- a/arch/sparc/crypto/sha1_glue.c
+++ b/arch/sparc/crypto/sha1_glue.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
index f403ce9ba6e4..286bc8ecf15b 100644
--- a/arch/sparc/crypto/sha256_glue.c
+++ b/arch/sparc/crypto/sha256_glue.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 
diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c
index a3b532e43c07..3b2ca732ff7a 100644
--- a/arch/sparc/crypto/sha512_glue.c
+++ b/arch/sparc/crypto/sha512_glue.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index b7c94de70cca..a8c2f2615fc6 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -331,9 +331,9 @@ static void __init srmmu_nocache_init(void)
 
 	while (vaddr < srmmu_nocache_end) {
 		pgd = pgd_offset_k(vaddr);
-		p4d = p4d_offset(__nocache_fix(pgd), vaddr);
-		pud = pud_offset(__nocache_fix(p4d), vaddr);
-		pmd = pmd_offset(__nocache_fix(pgd), vaddr);
+		p4d = p4d_offset(pgd, vaddr);
+		pud = pud_offset(p4d, vaddr);
+		pmd = pmd_offset(__nocache_fix(pud), vaddr);
 		pte = pte_offset_kernel(__nocache_fix(pmd), vaddr);
 
 		pteval = ((paddr >> 4) | SRMMU_ET_PTE | SRMMU_PRIV);
diff --git a/arch/um/Makefile b/arch/um/Makefile
index d2daa206872d..275f5ffdf6f0 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -140,6 +140,7 @@ export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE)
 # When cleaning we don't include .config, so we don't include
 # TT or skas makefiles and don't clean skas_ptregs.h.
 CLEAN_FILES += linux x.i gmon.out
+MRPROPER_DIRS += arch/$(SUBARCH)/include/generated
 
 archclean:
 	@find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \
diff --git a/arch/um/drivers/vector_user.h b/arch/um/drivers/vector_user.h
index 91f35b266aba..d29d5fdd98fa 100644
--- a/arch/um/drivers/vector_user.h
+++ b/arch/um/drivers/vector_user.h
@@ -17,7 +17,7 @@
 #define TRANS_TAP_LEN strlen(TRANS_TAP)
 
 #define TRANS_GRE "gre"
-#define TRANS_GRE_LEN strlen(TRANS_RAW)
+#define TRANS_GRE_LEN strlen(TRANS_GRE)
 
 #define TRANS_L2TPV3 "l2tpv3"
 #define TRANS_L2TPV3_LEN strlen(TRANS_L2TPV3)
diff --git a/arch/um/include/asm/xor.h b/arch/um/include/asm/xor.h
index 7a3208c47cfc..36b33d62a35d 100644
--- a/arch/um/include/asm/xor.h
+++ b/arch/um/include/asm/xor.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <asm-generic/xor.h>
-#include <shared/timer-internal.h>
+#include <linux/time-internal.h>
 
 /* pick an arbitrary one - measuring isn't possible with inf-cpu */
 #define XOR_SELECT_TEMPLATE(x)	\
diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c
index 0a12d5a09217..3d91f89fd852 100644
--- a/arch/um/kernel/skas/syscall.c
+++ b/arch/um/kernel/skas/syscall.c
@@ -11,6 +11,7 @@
 #include <sysdep/ptrace_user.h>
 #include <sysdep/syscalls.h>
 #include <linux/time-internal.h>
+#include <asm/unistd.h>
 
 void handle_syscall(struct uml_pt_regs *r)
 {
diff --git a/arch/unicore32/kernel/ksyms.c b/arch/unicore32/kernel/ksyms.c
index f4b84872d640..731445008932 100644
--- a/arch/unicore32/kernel/ksyms.c
+++ b/arch/unicore32/kernel/ksyms.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/string.h>
-#include <linux/cryptohash.h>
 #include <linux/delay.h>
 #include <linux/in6.h>
 #include <linux/syscalls.h>
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d6104ea8af0..6e23037f3b51 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -68,6 +68,7 @@ config X86
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
@@ -91,6 +92,7 @@ config X86
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_USE_SYM_ANNOTATIONS
 	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	select ARCH_WANT_DEFAULT_BPF_JIT	if X86_64
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
@@ -149,7 +151,7 @@ config X86
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
-	select HAVE_ARCH_USERFAULTFD_WP		if USERFAULTFD
+	select HAVE_ARCH_USERFAULTFD_WP         if X86_64 && USERFAULTFD
 	select HAVE_ARCH_VMAP_STACK		if X86_64
 	select HAVE_ARCH_WITHIN_STACK_FRAMES
 	select HAVE_ASM_MODVERSIONS
@@ -1610,19 +1612,10 @@ config NODES_SHIFT
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accommodate various tables.
 
-config ARCH_HAVE_MEMORY_PRESENT
-	def_bool y
-	depends on X86_32 && DISCONTIGMEM
-
 config ARCH_FLATMEM_ENABLE
 	def_bool y
 	depends on X86_32 && !NUMA
 
-config ARCH_DISCONTIGMEM_ENABLE
-	def_bool n
-	depends on NUMA && X86_32
-	depends on BROKEN
-
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	depends on X86_64 || NUMA || X86_32 || X86_32_NON_STANDARD
@@ -1887,10 +1880,10 @@ config X86_UMIP
 	  results are dummy.
 
 config X86_INTEL_MEMORY_PROTECTION_KEYS
-	prompt "Intel Memory Protection Keys"
+	prompt "Memory Protection Keys"
 	def_bool y
 	# Note: only available in 64-bit mode
-	depends on CPU_SUP_INTEL && X86_64
+	depends on X86_64 && (CPU_SUP_INTEL || CPU_SUP_AMD)
 	select ARCH_USES_HIGH_VMA_FLAGS
 	select ARCH_HAS_PKEYS
 	---help---
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 2e74690b028a..f909d3ce36e6 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -99,15 +99,6 @@ config DEBUG_WX
 
 	  If in doubt, say "Y".
 
-config DOUBLEFAULT
-	default y
-	bool "Enable doublefault exception handler" if EXPERT && X86_32
-	---help---
-	  This option allows trapping of rare doublefault exceptions that
-	  would otherwise cause a system to silently reboot. Disabling this
-	  option saves about 4k and might cause you much additional grey
-	  hair.
-
 config DEBUG_TLBFLUSH
 	bool "Set upper limit of TLB entries to flush one-by-one"
 	depends on DEBUG_KERNEL
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index b65ec63c7db7..00e378de8bc0 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -246,7 +246,7 @@ drivers-$(CONFIG_FB) += arch/x86/video/
 
 boot := arch/x86/boot
 
-BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage
+BOOT_TARGETS = bzdisk fdimage fdimage144 fdimage288 isoimage
 
 PHONY += bzImage $(BOOT_TARGETS)
 
@@ -267,8 +267,8 @@ endif
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
-PHONY += install
-install:
+PHONY += install bzlilo
+install bzlilo:
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
 PHONY += vdso_install
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index e17be90ab312..4c5355684321 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -57,11 +57,10 @@ $(obj)/cpu.o: $(obj)/cpustr.h
 
 quiet_cmd_cpustr = CPUSTR  $@
       cmd_cpustr = $(obj)/mkcpustr > $@
-targets += cpustr.h
 $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
 	$(call if_changed,cpustr)
 endif
-clean-files += cpustr.h
+targets += cpustr.h
 
 # ---------------------------------------------------------------------------
 
@@ -129,6 +128,8 @@ quiet_cmd_genimage = GENIMAGE $3
 cmd_genimage = sh $(srctree)/$(src)/genimage.sh $2 $3 $(obj)/bzImage \
 			$(obj)/mtools.conf '$(image_cmdline)' $(FDINITRD)
 
+PHONY += bzdisk fdimage fdimage144 fdimage288 isoimage bzlilo install
+
 # This requires write access to /dev/fd0
 bzdisk: $(obj)/bzImage $(obj)/mtools.conf
 	$(call cmd,genimage,bzdisk,/dev/fd0)
@@ -146,7 +147,7 @@ isoimage: $(obj)/bzImage
 	$(call cmd,genimage,isoimage,$(obj)/image.iso)
 	@$(kecho) 'Kernel: $(obj)/image.iso is ready'
 
-bzlilo: $(obj)/bzImage
+bzlilo:
 	if [ -f $(INSTALL_PATH)/vmlinuz ]; then mv $(INSTALL_PATH)/vmlinuz $(INSTALL_PATH)/vmlinuz.old; fi
 	if [ -f $(INSTALL_PATH)/System.map ]; then mv $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi
 	cat $(obj)/bzImage > $(INSTALL_PATH)/vmlinuz
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index ef2ad7253cd5..8bcbcee54aa1 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -280,9 +280,9 @@ acpi_physical_address get_rsdp_addr(void)
  */
 #define MAX_ADDR_LEN 19
 
-static acpi_physical_address get_cmdline_acpi_rsdp(void)
+static unsigned long get_cmdline_acpi_rsdp(void)
 {
-	acpi_physical_address addr = 0;
+	unsigned long addr = 0;
 
 #ifdef CONFIG_KEXEC
 	char val[MAX_ADDR_LEN] = { };
@@ -292,7 +292,7 @@ static acpi_physical_address get_cmdline_acpi_rsdp(void)
 	if (ret < 0)
 		return 0;
 
-	if (kstrtoull(val, 16, &addr))
+	if (boot_kstrtoul(val, 16, &addr))
 		return 0;
 #endif
 	return addr;
@@ -314,7 +314,6 @@ static unsigned long get_acpi_srat_table(void)
 	 * different ideas about whether to trust a command-line parameter.
 	 */
 	rsdp = (struct acpi_table_rsdp *)get_cmdline_acpi_rsdp();
-
 	if (!rsdp)
 		rsdp = (struct acpi_table_rsdp *)(long)
 			boot_params->acpi_rsdp_addr;
diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S
index 2b2049259619..c4bb0f9363f5 100644
--- a/arch/x86/boot/compressed/efi_thunk_64.S
+++ b/arch/x86/boot/compressed/efi_thunk_64.S
@@ -28,8 +28,6 @@ SYM_FUNC_START(__efi64_thunk)
 	push	%rbx
 
 	leaq	1f(%rip), %rbp
-	leaq	efi_gdt64(%rip), %rbx
-	movl	%ebx, 2(%rbx)		/* Fixup the gdt base address */
 
 	movl	%ds, %eax
 	push	%rax
@@ -48,7 +46,8 @@ SYM_FUNC_START(__efi64_thunk)
 	movl	%r8d, 0xc(%rsp)
 	movl	%r9d, 0x10(%rsp)
 
-	sgdt	0x14(%rsp)
+	leaq	0x14(%rsp), %rbx
+	sgdt	(%rbx)
 
 	/*
 	 * Switch to gdt with 32-bit segments. This is the firmware GDT
@@ -68,8 +67,7 @@ SYM_FUNC_START(__efi64_thunk)
 	pushq	%rax
 	lretq
 
-1:	lgdt	0x14(%rsp)
-	addq	$32, %rsp
+1:	addq	$32, %rsp
 	movq	%rdi, %rax
 
 	pop	%rbx
@@ -175,14 +173,3 @@ SYM_DATA_END(efi32_boot_cs)
 SYM_DATA_START(efi32_boot_ds)
 	.word	0
 SYM_DATA_END(efi32_boot_ds)
-
-SYM_DATA_START(efi_gdt64)
-	.word	efi_gdt64_end - efi_gdt64
-	.long	0			/* Filled out by user */
-	.word	0
-	.quad	0x0000000000000000	/* NULL descriptor */
-	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
-	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
-	.quad	0x0080890000000000	/* TS descriptor */
-	.quad   0x0000000000000000	/* TS continued */
-SYM_DATA_END_LABEL(efi_gdt64, SYM_L_LOCAL, efi_gdt64_end)
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index ab3307036ba4..03557f2174bf 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -49,16 +49,17 @@
  * Position Independent Executable (PIE) so that linker won't optimize
  * R_386_GOT32X relocation to its fixed symbol address.  Older
  * linkers generate R_386_32 relocations against locally defined symbols,
- * _bss, _ebss, _got and _egot, in PIE.  It isn't wrong, just less
+ * _bss, _ebss, _got, _egot and _end, in PIE.  It isn't wrong, just less
  * optimal than R_386_RELATIVE.  But the x86 kernel fails to properly handle
  * R_386_32 relocations when relocating the kernel.  To generate
- * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as
+ * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as
  * hidden:
  */
 	.hidden _bss
 	.hidden _ebss
 	.hidden _got
 	.hidden _egot
+	.hidden _end
 
 	__HEAD
 SYM_FUNC_START(startup_32)
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 4f7e6b84be07..e821a7d7d5c4 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -42,6 +42,7 @@
 	.hidden _ebss
 	.hidden _got
 	.hidden _egot
+	.hidden _end
 
 	__HEAD
 	.code32
@@ -393,6 +394,14 @@ SYM_CODE_START(startup_64)
 	addq	%rax, 2(%rax)
 	lgdt	(%rax)
 
+	/* Reload CS so IRET returns to a CS actually in the GDT */
+	pushq	$__KERNEL_CS
+	leaq	.Lon_kernel_cs(%rip), %rax
+	pushq	%rax
+	lretq
+
+.Lon_kernel_cs:
+
 	/*
 	 * paging_prepare() sets up the trampoline and checks if we need to
 	 * enable 5-level paging.
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 508cfa6828c5..8f1025d1f681 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -52,6 +52,7 @@ SECTIONS
 		_data = . ;
 		*(.data)
 		*(.data.*)
+		*(.bss.efistub)
 		_edata = . ;
 	}
 	. = ALIGN(L1_CACHE_BYTES);
@@ -73,4 +74,6 @@ SECTIONS
 #endif
 	. = ALIGN(PAGE_SIZE);	/* keep ZO size page aligned */
 	_end = .;
+
+	DISCARDS
 }
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 8272a4492844..8a3fff9128bb 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -117,7 +117,6 @@ static unsigned int simple_guess_base(const char *cp)
  * @endp: A pointer to the end of the parsed string will be placed here
  * @base: The number base to use
  */
-
 unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base)
 {
 	unsigned long long result = 0;
@@ -335,3 +334,45 @@ int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
 		s++;
 	return _kstrtoull(s, base, res);
 }
+
+static int _kstrtoul(const char *s, unsigned int base, unsigned long *res)
+{
+	unsigned long long tmp;
+	int rv;
+
+	rv = kstrtoull(s, base, &tmp);
+	if (rv < 0)
+		return rv;
+	if (tmp != (unsigned long)tmp)
+		return -ERANGE;
+	*res = tmp;
+	return 0;
+}
+
+/**
+ * kstrtoul - convert a string to an unsigned long
+ * @s: The start of the string. The string must be null-terminated, and may also
+ *  include a single newline before its terminating null. The first character
+ *  may also be a plus sign, but not a minus sign.
+ * @base: The number base to use. The maximum supported base is 16. If base is
+ *  given as 0, then the base of the string is automatically detected with the
+ *  conventional semantics - If it begins with 0x the number will be parsed as a
+ *  hexadecimal (case insensitive), if it otherwise begins with 0, it will be
+ *  parsed as an octal number. Otherwise it will be parsed as a decimal.
+ * @res: Where to write the result of the conversion on success.
+ *
+ * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
+ * Used as a replacement for the simple_strtoull.
+ */
+int boot_kstrtoul(const char *s, unsigned int base, unsigned long *res)
+{
+	/*
+	 * We want to shortcut function call, but
+	 * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0.
+	 */
+	if (sizeof(unsigned long) == sizeof(unsigned long long) &&
+	    __alignof__(unsigned long) == __alignof__(unsigned long long))
+		return kstrtoull(s, base, (unsigned long long *)res);
+	else
+		return _kstrtoul(s, base, res);
+}
diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h
index 38d8f2f5e47e..995f7b7ad512 100644
--- a/arch/x86/boot/string.h
+++ b/arch/x86/boot/string.h
@@ -30,4 +30,5 @@ extern unsigned long long simple_strtoull(const char *cp, char **endp,
 					  unsigned int base);
 
 int kstrtoull(const char *s, unsigned int base, unsigned long long *res);
+int boot_kstrtoul(const char *s, unsigned int base, unsigned long *res);
 #endif /* BOOT_STRING_H */
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 8f8c8e386cea..c8b8c1a8d1fc 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -59,14 +59,14 @@ u8 buf[SETUP_SECT_MAX*512];
 #define PECOFF_COMPAT_RESERVE 0x0
 #endif
 
-unsigned long efi32_stub_entry;
-unsigned long efi64_stub_entry;
-unsigned long efi_pe_entry;
-unsigned long efi32_pe_entry;
-unsigned long kernel_info;
-unsigned long startup_64;
-unsigned long _ehead;
-unsigned long _end;
+static unsigned long efi32_stub_entry;
+static unsigned long efi64_stub_entry;
+static unsigned long efi_pe_entry;
+static unsigned long efi32_pe_entry;
+static unsigned long kernel_info;
+static unsigned long startup_64;
+static unsigned long _ehead;
+static unsigned long _end;
 
 /*----------------------------------------------------------------------*/
 
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index cad6e1bfa7d5..54e7d15dbd0d 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -2758,7 +2758,7 @@ SYM_FUNC_START(aesni_xts_crypt8)
 	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
-	CALL_NOSPEC %r11
+	CALL_NOSPEC r11
 
 	movdqu 0x00(OUTP), INC
 	pxor INC, STATE1
@@ -2803,7 +2803,7 @@ SYM_FUNC_START(aesni_xts_crypt8)
 	_aesni_gf128mul_x_ble()
 	movups IV, (IVP)
 
-	CALL_NOSPEC %r11
+	CALL_NOSPEC r11
 
 	movdqu 0x40(OUTP), INC
 	pxor INC, STATE1
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
index 06ef2d4a4701..6737bcea1fa1 100644
--- a/arch/x86/crypto/blake2s-glue.c
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -32,16 +32,16 @@ void blake2s_compress_arch(struct blake2s_state *state,
 			   const u32 inc)
 {
 	/* SIMD disables preemption, so relax after processing each page. */
-	BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8);
+	BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8);
 
 	if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) {
 		blake2s_compress_generic(state, block, nblocks, inc);
 		return;
 	}
 
-	for (;;) {
+	do {
 		const size_t blocks = min_t(size_t, nblocks,
-					    PAGE_SIZE / BLAKE2S_BLOCK_SIZE);
+					    SZ_4K / BLAKE2S_BLOCK_SIZE);
 
 		kernel_fpu_begin();
 		if (IS_ENABLED(CONFIG_AS_AVX512) &&
@@ -52,10 +52,8 @@ void blake2s_compress_arch(struct blake2s_state *state,
 		kernel_fpu_end();
 
 		nblocks -= blocks;
-		if (!nblocks)
-			break;
 		block += blocks * BLAKE2S_BLOCK_SIZE;
-	}
+	} while (nblocks);
 }
 EXPORT_SYMBOL(blake2s_compress_arch);
 
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index d01ddd73de65..ecc0a9a905c4 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -1228,7 +1228,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way)
 	vpxor 14 * 16(%rax), %xmm15, %xmm14;
 	vpxor 15 * 16(%rax), %xmm15, %xmm15;
 
-	CALL_NOSPEC %r9;
+	CALL_NOSPEC r9;
 
 	addq $(16 * 16), %rsp;
 
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index 563ef6e83cdd..0907243c501c 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -1339,7 +1339,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way)
 	vpxor 14 * 32(%rax), %ymm15, %ymm14;
 	vpxor 15 * 32(%rax), %ymm15, %ymm15;
 
-	CALL_NOSPEC %r9;
+	CALL_NOSPEC r9;
 
 	addq $(16 * 32), %rsp;
 
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index b412c21ee06e..22250091cdbe 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -153,9 +153,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
 	    bytes <= CHACHA_BLOCK_SIZE)
 		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
 
-	kernel_fpu_begin();
-	chacha_dosimd(state, dst, src, bytes, nrounds);
-	kernel_fpu_end();
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		kernel_fpu_begin();
+		chacha_dosimd(state, dst, src, todo, nrounds);
+		kernel_fpu_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
 }
 EXPORT_SYMBOL(chacha_crypt_arch);
 
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 0e6690e3618c..8501ec4532f4 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -75,7 +75,7 @@
 
 .text
 SYM_FUNC_START(crc_pcl)
-#define    bufp		%rdi
+#define    bufp		rdi
 #define    bufp_dw	%edi
 #define    bufp_w	%di
 #define    bufp_b	%dil
@@ -105,9 +105,9 @@ SYM_FUNC_START(crc_pcl)
 	## 1) ALIGN:
 	################################################################
 
-	mov     bufp, bufptmp		# rdi = *buf
-	neg     bufp
-	and     $7, bufp		# calculate the unalignment amount of
+	mov     %bufp, bufptmp		# rdi = *buf
+	neg     %bufp
+	and     $7, %bufp		# calculate the unalignment amount of
 					# the address
 	je      proc_block		# Skip if aligned
 
@@ -123,13 +123,13 @@ SYM_FUNC_START(crc_pcl)
 do_align:
 	#### Calculate CRC of unaligned bytes of the buffer (if any)
 	movq    (bufptmp), tmp		# load a quadward from the buffer
-	add     bufp, bufptmp		# align buffer pointer for quadword
+	add     %bufp, bufptmp		# align buffer pointer for quadword
 					# processing
-	sub     bufp, len		# update buffer length
+	sub     %bufp, len		# update buffer length
 align_loop:
 	crc32b  %bl, crc_init_dw 	# compute crc32 of 1-byte
 	shr     $8, tmp			# get next byte
-	dec     bufp
+	dec     %bufp
 	jne     align_loop
 
 proc_block:
@@ -169,10 +169,10 @@ continue_block:
 	xor     crc2, crc2
 
 	## branch into array
-	lea	jump_table(%rip), bufp
-	movzxw  (bufp, %rax, 2), len
-	lea	crc_array(%rip), bufp
-	lea     (bufp, len, 1), bufp
+	lea	jump_table(%rip), %bufp
+	movzxw  (%bufp, %rax, 2), len
+	lea	crc_array(%rip), %bufp
+	lea     (%bufp, len, 1), %bufp
 	JMP_NOSPEC bufp
 
 	################################################################
@@ -218,9 +218,9 @@ LABEL crc_ %i
 	## 4) Combine three results:
 	################################################################
 
-	lea	(K_table-8)(%rip), bufp		# first entry is for idx 1
+	lea	(K_table-8)(%rip), %bufp		# first entry is for idx 1
 	shlq    $3, %rax			# rax *= 8
-	pmovzxdq (bufp,%rax), %xmm0		# 2 consts: K1:K2
+	pmovzxdq (%bufp,%rax), %xmm0		# 2 consts: K1:K2
 	leal	(%eax,%eax,2), %eax		# rax *= 3 (total *24)
 	subq    %rax, tmp			# tmp -= rax*24
 
diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
index f7567cbd35b6..80fcb85736e1 100644
--- a/arch/x86/crypto/nhpoly1305-avx2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -29,7 +29,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc,
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
-		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_fpu_begin();
 		crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2);
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
index a661ede3b5cf..cc6b7c1a2705 100644
--- a/arch/x86/crypto/nhpoly1305-sse2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -29,7 +29,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc,
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
-		unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE);
+		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_fpu_begin();
 		crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2);
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 6dfec19f7d57..dfe921efa9b2 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -91,8 +91,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len,
 	struct poly1305_arch_internal *state = ctx;
 
 	/* SIMD disables preemption, so relax after processing each page. */
-	BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE ||
-		     PAGE_SIZE % POLY1305_BLOCK_SIZE);
+	BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE ||
+		     SZ_4K % POLY1305_BLOCK_SIZE);
 
 	if (!static_branch_likely(&poly1305_use_avx) ||
 	    (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) ||
@@ -102,8 +102,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len,
 		return;
 	}
 
-	for (;;) {
-		const size_t bytes = min_t(size_t, len, PAGE_SIZE);
+	do {
+		const size_t bytes = min_t(size_t, len, SZ_4K);
 
 		kernel_fpu_begin();
 		if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512))
@@ -113,11 +113,10 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len,
 		else
 			poly1305_blocks_avx(ctx, inp, bytes, padbit);
 		kernel_fpu_end();
+
 		len -= bytes;
-		if (!len)
-			break;
 		inp += bytes;
-	}
+	} while (len);
 }
 
 static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE],
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index a801ffc10cbb..18200135603f 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -21,7 +21,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 6394b5fe8db6..dd06249229e1 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -34,7 +34,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 82cc1b3ced1d..b0b05c93409e 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -32,7 +32,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 0789e13ece90..1c7f13bb6728 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with
 #define SIZEOF_PTREGS	21*8
 
 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
-	/*
-	 * Push registers and sanitize registers of values that a
-	 * speculation attack might otherwise want to exploit. The
-	 * lower registers are likely clobbered well before they
-	 * could be put to use in a speculative execution gadget.
-	 * Interleave XOR with PUSH for better uop scheduling:
-	 */
 	.if \save_ret
 	pushq	%rsi		/* pt_regs->si */
 	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
@@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with
 	pushq   %rsi		/* pt_regs->si */
 	.endif
 	pushq	\rdx		/* pt_regs->dx */
-	xorl	%edx, %edx	/* nospec   dx */
 	pushq   %rcx		/* pt_regs->cx */
-	xorl	%ecx, %ecx	/* nospec   cx */
 	pushq   \rax		/* pt_regs->ax */
 	pushq   %r8		/* pt_regs->r8 */
-	xorl	%r8d, %r8d	/* nospec   r8 */
 	pushq   %r9		/* pt_regs->r9 */
-	xorl	%r9d, %r9d	/* nospec   r9 */
 	pushq   %r10		/* pt_regs->r10 */
-	xorl	%r10d, %r10d	/* nospec   r10 */
 	pushq   %r11		/* pt_regs->r11 */
-	xorl	%r11d, %r11d	/* nospec   r11*/
 	pushq	%rbx		/* pt_regs->rbx */
-	xorl    %ebx, %ebx	/* nospec   rbx*/
 	pushq	%rbp		/* pt_regs->rbp */
-	xorl    %ebp, %ebp	/* nospec   rbp*/
 	pushq	%r12		/* pt_regs->r12 */
-	xorl	%r12d, %r12d	/* nospec   r12*/
 	pushq	%r13		/* pt_regs->r13 */
-	xorl	%r13d, %r13d	/* nospec   r13*/
 	pushq	%r14		/* pt_regs->r14 */
-	xorl	%r14d, %r14d	/* nospec   r14*/
 	pushq	%r15		/* pt_regs->r15 */
-	xorl	%r15d, %r15d	/* nospec   r15*/
 	UNWIND_HINT_REGS
+
 	.if \save_ret
 	pushq	%rsi		/* return address on top of stack */
 	.endif
+
+	/*
+	 * Sanitize registers of values that a speculation attack might
+	 * otherwise want to exploit. The lower registers are likely clobbered
+	 * well before they could be put to use in a speculative execution
+	 * gadget.
+	 */
+	xorl	%edx,  %edx	/* nospec dx  */
+	xorl	%ecx,  %ecx	/* nospec cx  */
+	xorl	%r8d,  %r8d	/* nospec r8  */
+	xorl	%r9d,  %r9d	/* nospec r9  */
+	xorl	%r10d, %r10d	/* nospec r10 */
+	xorl	%r11d, %r11d	/* nospec r11 */
+	xorl	%ebx,  %ebx	/* nospec rbx */
+	xorl	%ebp,  %ebp	/* nospec rbp */
+	xorl	%r12d, %r12d	/* nospec r12 */
+	xorl	%r13d, %r13d	/* nospec r13 */
+	xorl	%r14d, %r14d	/* nospec r14 */
+	xorl	%r15d, %r15d	/* nospec r15 */
+
 .endm
 
 .macro POP_REGS pop_rdi=1 skip_r11rcx=0
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index b67bae7091d7..ac232f456396 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -816,7 +816,7 @@ SYM_CODE_START(ret_from_fork)
 
 	/* kernel thread */
 1:	movl	%edi, %eax
-	CALL_NOSPEC %ebx
+	CALL_NOSPEC ebx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()
@@ -1501,7 +1501,7 @@ SYM_CODE_START_LOCAL_NOALIGN(common_exception_read_cr2)
 
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
-	CALL_NOSPEC %edi
+	CALL_NOSPEC edi
 	jmp	ret_from_exception
 SYM_CODE_END(common_exception_read_cr2)
 
@@ -1522,7 +1522,7 @@ SYM_CODE_START_LOCAL_NOALIGN(common_exception)
 
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
-	CALL_NOSPEC %edi
+	CALL_NOSPEC edi
 	jmp	ret_from_exception
 SYM_CODE_END(common_exception)
 
@@ -1536,7 +1536,6 @@ SYM_CODE_START(debug)
 	jmp	common_exception
 SYM_CODE_END(debug)
 
-#ifdef CONFIG_DOUBLEFAULT
 SYM_CODE_START(double_fault)
 1:
 	/*
@@ -1576,7 +1575,6 @@ SYM_CODE_START(double_fault)
 	hlt
 	jmp 1b
 SYM_CODE_END(double_fault)
-#endif
 
 /*
  * NMI is doubly nasty.  It can happen on the first instruction of
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 0e9504fabe52..64fe3d82157e 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -249,7 +249,6 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 */
 syscall_return_via_sysret:
 	/* rcx and r11 are already restored (see code above) */
-	UNWIND_HINT_EMPTY
 	POP_REGS pop_rdi=0 skip_r11rcx=1
 
 	/*
@@ -258,6 +257,7 @@ syscall_return_via_sysret:
 	 */
 	movq	%rsp, %rdi
 	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+	UNWIND_HINT_EMPTY
 
 	pushq	RSP-RDI(%rdi)	/* RSP */
 	pushq	(%rdi)		/* RDI */
@@ -279,8 +279,7 @@ SYM_CODE_END(entry_SYSCALL_64)
  * %rdi: prev task
  * %rsi: next task
  */
-SYM_CODE_START(__switch_to_asm)
-	UNWIND_HINT_FUNC
+SYM_FUNC_START(__switch_to_asm)
 	/*
 	 * Save callee-saved registers
 	 * This must match the order in inactive_task_frame
@@ -321,7 +320,7 @@ SYM_CODE_START(__switch_to_asm)
 	popq	%rbp
 
 	jmp	__switch_to
-SYM_CODE_END(__switch_to_asm)
+SYM_FUNC_END(__switch_to_asm)
 
 /*
  * A newly forked process directly context switches into this address.
@@ -349,7 +348,7 @@ SYM_CODE_START(ret_from_fork)
 	/* kernel thread */
 	UNWIND_HINT_EMPTY
 	movq	%r12, %rdi
-	CALL_NOSPEC %rbx
+	CALL_NOSPEC rbx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()
@@ -512,7 +511,7 @@ SYM_CODE_END(spurious_entries_start)
  * +----------------------------------------------------+
  */
 SYM_CODE_START(interrupt_entry)
-	UNWIND_HINT_FUNC
+	UNWIND_HINT_IRET_REGS offset=16
 	ASM_CLAC
 	cld
 
@@ -544,9 +543,9 @@ SYM_CODE_START(interrupt_entry)
 	pushq	5*8(%rdi)		/* regs->eflags */
 	pushq	4*8(%rdi)		/* regs->cs */
 	pushq	3*8(%rdi)		/* regs->ip */
+	UNWIND_HINT_IRET_REGS
 	pushq	2*8(%rdi)		/* regs->orig_ax */
 	pushq	8(%rdi)			/* return address */
-	UNWIND_HINT_FUNC
 
 	movq	(%rdi), %rdi
 	jmp	2f
@@ -637,6 +636,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	 */
 	movq	%rsp, %rdi
 	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+	UNWIND_HINT_EMPTY
 
 	/* Copy the IRET frame to the trampoline stack. */
 	pushq	6*8(%rdi)	/* SS */
@@ -1739,7 +1739,7 @@ SYM_CODE_START(rewind_stack_do_exit)
 
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
 	leaq	-PTREGS_SIZE(%rax), %rsp
-	UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE
+	UNWIND_HINT_REGS
 
 	call	do_exit
 SYM_CODE_END(rewind_stack_do_exit)
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 433a1259f61d..54e03ab26ff3 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -24,6 +24,8 @@ VDSO32-$(CONFIG_IA32_EMULATION)	:= y
 
 # files to link into the vdso
 vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
+vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
+vobjs32-y += vdso32/vclock_gettime.o
 
 # files to link into kernel
 obj-y				+= vma.o
@@ -37,10 +39,12 @@ vdso_img-$(VDSO32-y)		+= 32
 obj-$(VDSO32-y)			+= vdso32-setup.o
 
 vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F)
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
 targets += vdso.lds $(vobjs-y)
+targets += vdso32/vdso32.lds $(vobjs32-y)
 
 # Build the vDSO image C files and link them in.
 vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
@@ -130,10 +134,6 @@ $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
 CPPFLAGS_vdso32/vdso32.lds = $(CPPFLAGS_vdso.lds)
 VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
 
-targets += vdso32/vdso32.lds
-targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
-targets += vdso32/vclock_gettime.o
-
 KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) -DBUILD_VDSO
 $(obj)/vdso32.so.dbg: KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
 $(obj)/vdso32.so.dbg: asflags-$(CONFIG_X86_64) += -m32
@@ -158,12 +158,7 @@ endif
 
 $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
 
-$(obj)/vdso32.so.dbg: FORCE \
-		      $(obj)/vdso32/vdso32.lds \
-		      $(obj)/vdso32/vclock_gettime.o \
-		      $(obj)/vdso32/note.o \
-		      $(obj)/vdso32/system_call.o \
-		      $(obj)/vdso32/sigreturn.o
+$(obj)/vdso32.so.dbg: $(obj)/vdso32/vdso32.lds $(vobjs32) FORCE
 	$(call if_changed,vdso_and_check)
 
 #
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 3842873b3ae3..7380908045c7 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -187,7 +187,7 @@ static void map_input(const char *name, void **addr, size_t *len, int prot)
 
 	int fd = open(name, O_RDONLY);
 	if (fd == -1)
-		err(1, "%s", name);
+		err(1, "open(%s)", name);
 
 	tmp_len = lseek(fd, 0, SEEK_END);
 	if (tmp_len == (off_t)-1)
@@ -240,7 +240,7 @@ int main(int argc, char **argv)
 	outfilename = argv[3];
 	outfile = fopen(outfilename, "w");
 	if (!outfile)
-		err(1, "%s", argv[2]);
+		err(1, "fopen(%s)", outfilename);
 
 	go(raw_addr, raw_len, stripped_addr, stripped_len, outfile, name);
 
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index a20b134de2a8..6f46e11ce539 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -13,8 +13,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	unsigned long load_size = -1;  /* Work around bogus warning */
 	unsigned long mapping_size;
 	ELF(Ehdr) *hdr = (ELF(Ehdr) *)raw_addr;
-	int i;
-	unsigned long j;
+	unsigned long i, syms_nr;
 	ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr,
 		*alt_sec = NULL;
 	ELF(Dyn) *dyn = 0, *dyn_end = 0;
@@ -86,11 +85,10 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	strtab_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
 		GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link);
 
+	syms_nr = GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize);
 	/* Walk the symbol table */
-	for (i = 0;
-	     i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize);
-	     i++) {
-		int k;
+	for (i = 0; i < syms_nr; i++) {
+		unsigned int k;
 		ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
 			GET_LE(&symtab_hdr->sh_entsize) * i;
 		const char *sym_name = raw_addr +
@@ -150,11 +148,11 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	fprintf(outfile,
 		"static unsigned char raw_data[%lu] __ro_after_init __aligned(PAGE_SIZE) = {",
 		mapping_size);
-	for (j = 0; j < stripped_len; j++) {
-		if (j % 10 == 0)
+	for (i = 0; i < stripped_len; i++) {
+		if (i % 10 == 0)
 			fprintf(outfile, "\n\t");
 		fprintf(outfile, "0x%02X, ",
-			(int)((unsigned char *)stripped_addr)[j]);
+			(int)((unsigned char *)stripped_addr)[i]);
 	}
 	fprintf(outfile, "\n};\n\n");
 
diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig
index 9a7a1446cb3a..4a809c6cbd2f 100644
--- a/arch/x86/events/Kconfig
+++ b/arch/x86/events/Kconfig
@@ -10,11 +10,11 @@ config PERF_EVENTS_INTEL_UNCORE
 	available on NehalemEX and more modern processors.
 
 config PERF_EVENTS_INTEL_RAPL
-	tristate "Intel rapl performance events"
-	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+	tristate "Intel/AMD rapl performance events"
+	depends on PERF_EVENTS && (CPU_SUP_INTEL || CPU_SUP_AMD) && PCI
 	default y
 	---help---
-	Include support for Intel rapl performance events for power
+	Include support for Intel and AMD rapl performance events for power
 	monitoring on modern processors.
 
 config PERF_EVENTS_INTEL_CSTATE
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 9e07f554333f..12c42eba77ec 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,5 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y					+= core.o probe.o
+obj-$(PERF_EVENTS_INTEL_RAPL)		+= rapl.o
 obj-y					+= amd/
 obj-$(CONFIG_X86_LOCAL_APIC)            += msr.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/
+obj-$(CONFIG_CPU_SUP_CENTAUR)		+= zhaoxin/
+obj-$(CONFIG_CPU_SUP_ZHAOXIN)		+= zhaoxin/
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index a619763e96e1..9e63ee50b19a 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1839,6 +1839,10 @@ static int __init init_hw_perf_events(void)
 		err = amd_pmu_init();
 		x86_pmu.name = "HYGON";
 		break;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		err = zhaoxin_pmu_init();
+		break;
 	default:
 		err = -ENOTSUPP;
 	}
diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile
index 3468b0c1dc7c..e67a5886336c 100644
--- a/arch/x86/events/intel/Makefile
+++ b/arch/x86/events/intel/Makefile
@@ -2,8 +2,6 @@
 obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl-perf.o
-intel-rapl-perf-objs			:= rapl.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
 intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 6a3b599ee0fe..731dd8d0dbb1 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -58,7 +58,7 @@ struct bts_buffer {
 	local_t		head;
 	unsigned long	end;
 	void		**data_pages;
-	struct bts_phys	buf[0];
+	struct bts_phys	buf[];
 };
 
 static struct pmu bts_pmu;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 332954cccece..ca35c8b5ee10 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1892,8 +1892,8 @@ static __initconst const u64 tnt_hw_cache_extra_regs
 
 static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
-	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0),
-	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1),
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x800ff0ffffff9fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xff0ffffff9fffull, RSP_1),
 	EVENT_EXTRA_END
 };
 
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index e4aa20c0426f..442e1ed4acd4 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -643,6 +643,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&glm_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	&glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	&glm_cstates),
 
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_cstates),
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 1db7a51d9792..e94af4a54d0d 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -226,8 +226,6 @@ static int __init pt_pmu_hw_init(void)
 			pt_pmu.vmx = true;
 	}
 
-	attrs = NULL;
-
 	for (i = 0; i < PT_CPUID_LEAVES; i++) {
 		cpuid_count(20, i,
 			    &pt_pmu.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM],
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 0da4a4605536..b469ddd45515 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -130,7 +130,7 @@ struct intel_uncore_box {
 	struct list_head list;
 	struct list_head active_list;
 	void __iomem *io_addr;
-	struct intel_uncore_extra_reg shared_regs[0];
+	struct intel_uncore_extra_reg shared_regs[];
 };
 
 /* CFL uncore 8th cbox MSRs */
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index f1cd1ca1a77b..e17a3d8a47ed 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -618,6 +618,7 @@ struct x86_pmu {
 
 	/* PMI handler bits */
 	unsigned int	late_ack		:1,
+			enabled_ack		:1,
 			counter_freezing	:1;
 	/*
 	 * sysfs attrs
@@ -1133,3 +1134,12 @@ static inline int is_ht_workaround_enabled(void)
 	return 0;
 }
 #endif /* CONFIG_CPU_SUP_INTEL */
+
+#if ((defined CONFIG_CPU_SUP_CENTAUR) || (defined CONFIG_CPU_SUP_ZHAOXIN))
+int zhaoxin_pmu_init(void);
+#else
+static inline int zhaoxin_pmu_init(void)
+{
+	return 0;
+}
+#endif /*CONFIG_CPU_SUP_CENTAUR or CONFIG_CPU_SUP_ZHAOXIN*/
diff --git a/arch/x86/events/probe.c b/arch/x86/events/probe.c
index c2ede2f3b277..136a1e847254 100644
--- a/arch/x86/events/probe.c
+++ b/arch/x86/events/probe.c
@@ -10,6 +10,11 @@ not_visible(struct kobject *kobj, struct attribute *attr, int i)
 	return 0;
 }
 
+/*
+ * Accepts msr[] array with non populated entries as long as either
+ * msr[i].msr is 0 or msr[i].grp is NULL. Note that the default sysfs
+ * visibility is visible when group->is_visible callback is set.
+ */
 unsigned long
 perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
 {
@@ -24,8 +29,16 @@ perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
 		if (!msr[bit].no_check) {
 			struct attribute_group *grp = msr[bit].grp;
 
+			/* skip entry with no group */
+			if (!grp)
+				continue;
+
 			grp->is_visible = not_visible;
 
+			/* skip unpopulated entry */
+			if (!msr[bit].msr)
+				continue;
+
 			if (msr[bit].test && !msr[bit].test(bit, data))
 				continue;
 			/* Virt sucks; you cannot tell if a R/O MSR is present :/ */
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/rapl.c
index a5dbd25852cb..0f2bf59f4354 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -1,11 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Support Intel RAPL energy consumption counters
+ * Support Intel/AMD RAPL energy consumption counters
  * Copyright (C) 2013 Google, Inc., Stephane Eranian
  *
  * Intel RAPL interface is specified in the IA-32 Manual Vol3b
  * section 14.7.1 (September 2013)
  *
+ * AMD RAPL interface for Fam17h is described in the public PPR:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=206537
+ *
  * RAPL provides more controls than just reporting energy consumption
  * however here we only expose the 3 energy consumption free running
  * counters (pp0, pkg, dram).
@@ -58,8 +61,8 @@
 #include <linux/nospec.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
-#include "../perf_event.h"
-#include "../probe.h"
+#include "perf_event.h"
+#include "probe.h"
 
 MODULE_LICENSE("GPL");
 
@@ -128,7 +131,9 @@ struct rapl_pmus {
 };
 
 struct rapl_model {
+	struct perf_msr *rapl_msrs;
 	unsigned long	events;
+	unsigned int	msr_power_unit;
 	bool		apply_quirk;
 };
 
@@ -138,7 +143,7 @@ static struct rapl_pmus *rapl_pmus;
 static cpumask_t rapl_cpu_mask;
 static unsigned int rapl_cntr_mask;
 static u64 rapl_timer_ms;
-static struct perf_msr rapl_msrs[];
+static struct perf_msr *rapl_msrs;
 
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
@@ -455,9 +460,16 @@ static struct attribute *rapl_events_cores[] = {
 	NULL,
 };
 
+static umode_t
+rapl_not_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return 0;
+}
+
 static struct attribute_group rapl_events_cores_group = {
 	.name  = "events",
 	.attrs = rapl_events_cores,
+	.is_visible = rapl_not_visible,
 };
 
 static struct attribute *rapl_events_pkg[] = {
@@ -470,6 +482,7 @@ static struct attribute *rapl_events_pkg[] = {
 static struct attribute_group rapl_events_pkg_group = {
 	.name  = "events",
 	.attrs = rapl_events_pkg,
+	.is_visible = rapl_not_visible,
 };
 
 static struct attribute *rapl_events_ram[] = {
@@ -482,6 +495,7 @@ static struct attribute *rapl_events_ram[] = {
 static struct attribute_group rapl_events_ram_group = {
 	.name  = "events",
 	.attrs = rapl_events_ram,
+	.is_visible = rapl_not_visible,
 };
 
 static struct attribute *rapl_events_gpu[] = {
@@ -494,6 +508,7 @@ static struct attribute *rapl_events_gpu[] = {
 static struct attribute_group rapl_events_gpu_group = {
 	.name  = "events",
 	.attrs = rapl_events_gpu,
+	.is_visible = rapl_not_visible,
 };
 
 static struct attribute *rapl_events_psys[] = {
@@ -506,6 +521,7 @@ static struct attribute *rapl_events_psys[] = {
 static struct attribute_group rapl_events_psys_group = {
 	.name  = "events",
 	.attrs = rapl_events_psys,
+	.is_visible = rapl_not_visible,
 };
 
 static bool test_msr(int idx, void *data)
@@ -513,7 +529,7 @@ static bool test_msr(int idx, void *data)
 	return test_bit(idx, (unsigned long *) data);
 }
 
-static struct perf_msr rapl_msrs[] = {
+static struct perf_msr intel_rapl_msrs[] = {
 	[PERF_RAPL_PP0]  = { MSR_PP0_ENERGY_STATUS,      &rapl_events_cores_group, test_msr },
 	[PERF_RAPL_PKG]  = { MSR_PKG_ENERGY_STATUS,      &rapl_events_pkg_group,   test_msr },
 	[PERF_RAPL_RAM]  = { MSR_DRAM_ENERGY_STATUS,     &rapl_events_ram_group,   test_msr },
@@ -521,6 +537,16 @@ static struct perf_msr rapl_msrs[] = {
 	[PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group,  test_msr },
 };
 
+/*
+ * Force to PERF_RAPL_MAX size due to:
+ * - perf_msr_probe(PERF_RAPL_MAX)
+ * - want to use same event codes across both architectures
+ */
+static struct perf_msr amd_rapl_msrs[PERF_RAPL_MAX] = {
+	[PERF_RAPL_PKG]  = { MSR_AMD_PKG_ENERGY_STATUS,  &rapl_events_pkg_group,   test_msr },
+};
+
+
 static int rapl_cpu_offline(unsigned int cpu)
 {
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
@@ -575,13 +601,13 @@ static int rapl_cpu_online(unsigned int cpu)
 	return 0;
 }
 
-static int rapl_check_hw_unit(bool apply_quirk)
+static int rapl_check_hw_unit(struct rapl_model *rm)
 {
 	u64 msr_rapl_power_unit_bits;
 	int i;
 
 	/* protect rdmsrl() to handle virtualization */
-	if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+	if (rdmsrl_safe(rm->msr_power_unit, &msr_rapl_power_unit_bits))
 		return -1;
 	for (i = 0; i < NR_RAPL_DOMAINS; i++)
 		rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
@@ -592,7 +618,7 @@ static int rapl_check_hw_unit(bool apply_quirk)
 	 * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2
 	 * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
 	 */
-	if (apply_quirk)
+	if (rm->apply_quirk)
 		rapl_hw_unit[PERF_RAPL_RAM] = 16;
 
 	/*
@@ -673,6 +699,8 @@ static struct rapl_model model_snb = {
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_PP1),
 	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_snbep = {
@@ -680,6 +708,8 @@ static struct rapl_model model_snbep = {
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_hsw = {
@@ -688,6 +718,8 @@ static struct rapl_model model_hsw = {
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1),
 	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_hsx = {
@@ -695,12 +727,16 @@ static struct rapl_model model_hsx = {
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.apply_quirk	= true,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_knl = {
 	.events		= BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.apply_quirk	= true,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_skl = {
@@ -710,6 +746,15 @@ static struct rapl_model model_skl = {
 			  BIT(PERF_RAPL_PP1) |
 			  BIT(PERF_RAPL_PSYS),
 	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
+};
+
+static struct rapl_model model_amd_fam17h = {
+	.events		= BIT(PERF_RAPL_PKG),
+	.apply_quirk	= false,
+	.msr_power_unit = MSR_AMD_RAPL_POWER_UNIT,
+	.rapl_msrs      = amd_rapl_msrs,
 };
 
 static const struct x86_cpu_id rapl_model_match[] __initconst = {
@@ -738,8 +783,11 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&model_hsw),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&model_hsx),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
+	X86_MATCH_VENDOR_FAM(AMD, 0x17, &model_amd_fam17h),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
@@ -755,10 +803,13 @@ static int __init rapl_pmu_init(void)
 		return -ENODEV;
 
 	rm = (struct rapl_model *) id->driver_data;
+
+	rapl_msrs = rm->rapl_msrs;
+
 	rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
 					false, (void *) &rm->events);
 
-	ret = rapl_check_hw_unit(rm->apply_quirk);
+	ret = rapl_check_hw_unit(rm);
 	if (ret)
 		return ret;
 
diff --git a/arch/x86/events/zhaoxin/Makefile b/arch/x86/events/zhaoxin/Makefile
new file mode 100644
index 000000000000..642c1174d662
--- /dev/null
+++ b/arch/x86/events/zhaoxin/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y	+= core.o
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
new file mode 100644
index 000000000000..898fa1ae9ceb
--- /dev/null
+++ b/arch/x86/events/zhaoxin/core.c
@@ -0,0 +1,613 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Zhoaxin PMU; like Intel Architectural PerfMon-v2
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/nmi.h>
+
+#include <asm/cpufeature.h>
+#include <asm/hardirq.h>
+#include <asm/apic.h>
+
+#include "../perf_event.h"
+
+/*
+ * Zhaoxin PerfMon, used on zxc and later.
+ */
+static u64 zx_pmon_event_map[PERF_COUNT_HW_MAX] __read_mostly = {
+
+	[PERF_COUNT_HW_CPU_CYCLES]        = 0x0082,
+	[PERF_COUNT_HW_INSTRUCTIONS]      = 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]  = 0x0515,
+	[PERF_COUNT_HW_CACHE_MISSES]      = 0x051a,
+	[PERF_COUNT_HW_BUS_CYCLES]        = 0x0083,
+};
+
+static struct event_constraint zxc_event_constraints[] __read_mostly = {
+
+	FIXED_EVENT_CONSTRAINT(0x0082, 1), /* unhalted core clock cycles */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint zxd_event_constraints[] __read_mostly = {
+
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* retired instructions */
+	FIXED_EVENT_CONSTRAINT(0x0082, 1), /* unhalted core clock cycles */
+	FIXED_EVENT_CONSTRAINT(0x0083, 2), /* unhalted bus clock cycles */
+	EVENT_CONSTRAINT_END
+};
+
+static __initconst const u64 zxd_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0042,
+		[C(RESULT_MISS)] = 0x0538,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0043,
+		[C(RESULT_MISS)] = 0x0562,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0300,
+		[C(RESULT_MISS)] = 0x0301,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x030a,
+		[C(RESULT_MISS)] = 0x030b,
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0042,
+		[C(RESULT_MISS)] = 0x052c,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0043,
+		[C(RESULT_MISS)] = 0x0530,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x0564,
+		[C(RESULT_MISS)] = 0x0565,
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x00c0,
+		[C(RESULT_MISS)] = 0x0534,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(BPU)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0700,
+		[C(RESULT_MISS)] = 0x0709,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+};
+
+static __initconst const u64 zxe_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0568,
+		[C(RESULT_MISS)] = 0x054b,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0669,
+		[C(RESULT_MISS)] = 0x0562,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0300,
+		[C(RESULT_MISS)] = 0x0301,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x030a,
+		[C(RESULT_MISS)] = 0x030b,
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0,
+		[C(RESULT_MISS)] = 0x0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0,
+		[C(RESULT_MISS)] = 0x0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x0,
+		[C(RESULT_MISS)] = 0x0,
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0568,
+		[C(RESULT_MISS)] = 0x052c,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0669,
+		[C(RESULT_MISS)] = 0x0530,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x0564,
+		[C(RESULT_MISS)] = 0x0565,
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x00c0,
+		[C(RESULT_MISS)] = 0x0534,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(BPU)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0028,
+		[C(RESULT_MISS)] = 0x0029,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+};
+
+static void zhaoxin_pmu_disable_all(void)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+}
+
+static void zhaoxin_pmu_enable_all(int added)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+}
+
+static inline u64 zhaoxin_pmu_get_status(void)
+{
+	u64 status;
+
+	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+
+	return status;
+}
+
+static inline void zhaoxin_pmu_ack_status(u64 ack)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+}
+
+static inline void zxc_pmu_ack_status(u64 ack)
+{
+	/*
+	 * ZXC needs global control enabled in order to clear status bits.
+	 */
+	zhaoxin_pmu_enable_all(0);
+	zhaoxin_pmu_ack_status(ack);
+	zhaoxin_pmu_disable_all();
+}
+
+static void zhaoxin_pmu_disable_fixed(struct hw_perf_event *hwc)
+{
+	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
+	u64 ctrl_val, mask;
+
+	mask = 0xfULL << (idx * 4);
+
+	rdmsrl(hwc->config_base, ctrl_val);
+	ctrl_val &= ~mask;
+	wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static void zhaoxin_pmu_disable_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+		zhaoxin_pmu_disable_fixed(hwc);
+		return;
+	}
+
+	x86_pmu_disable_event(event);
+}
+
+static void zhaoxin_pmu_enable_fixed(struct hw_perf_event *hwc)
+{
+	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
+	u64 ctrl_val, bits, mask;
+
+	/*
+	 * Enable IRQ generation (0x8),
+	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
+	 * if requested:
+	 */
+	bits = 0x8ULL;
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
+		bits |= 0x2;
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+		bits |= 0x1;
+
+	bits <<= (idx * 4);
+	mask = 0xfULL << (idx * 4);
+
+	rdmsrl(hwc->config_base, ctrl_val);
+	ctrl_val &= ~mask;
+	ctrl_val |= bits;
+	wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static void zhaoxin_pmu_enable_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+		zhaoxin_pmu_enable_fixed(hwc);
+		return;
+	}
+
+	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+}
+
+/*
+ * This handler is triggered by the local APIC, so the APIC IRQ handling
+ * rules apply:
+ */
+static int zhaoxin_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	int handled = 0;
+	u64 status;
+	int bit;
+
+	cpuc = this_cpu_ptr(&cpu_hw_events);
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	zhaoxin_pmu_disable_all();
+	status = zhaoxin_pmu_get_status();
+	if (!status)
+		goto done;
+
+again:
+	if (x86_pmu.enabled_ack)
+		zxc_pmu_ack_status(status);
+	else
+		zhaoxin_pmu_ack_status(status);
+
+	inc_irq_stat(apic_perf_irqs);
+
+	/*
+	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
+	 * and clear the bit.
+	 */
+	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+		if (!status)
+			goto done;
+	}
+
+	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
+		struct perf_event *event = cpuc->events[bit];
+
+		handled++;
+
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+
+		x86_perf_event_update(event);
+		perf_sample_data_init(&data, 0, event->hw.last_period);
+
+		if (!x86_perf_event_set_period(event))
+			continue;
+
+		if (perf_event_overflow(event, &data, regs))
+			x86_pmu_stop(event, 0);
+	}
+
+	/*
+	 * Repeat if there is more work to be done:
+	 */
+	status = zhaoxin_pmu_get_status();
+	if (status)
+		goto again;
+
+done:
+	zhaoxin_pmu_enable_all(0);
+	return handled;
+}
+
+static u64 zhaoxin_pmu_event_map(int hw_event)
+{
+	return zx_pmon_event_map[hw_event];
+}
+
+static struct event_constraint *
+zhaoxin_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	if (x86_pmu.event_constraints) {
+		for_each_event_constraint(c, x86_pmu.event_constraints) {
+			if ((event->hw.config & c->cmask) == c->code)
+				return c;
+		}
+	}
+
+	return &unconstrained;
+}
+
+PMU_FORMAT_ATTR(event,	"config:0-7");
+PMU_FORMAT_ATTR(umask,	"config:8-15");
+PMU_FORMAT_ATTR(edge,	"config:18");
+PMU_FORMAT_ATTR(inv,	"config:23");
+PMU_FORMAT_ATTR(cmask,	"config:24-31");
+
+static struct attribute *zx_arch_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
+static ssize_t zhaoxin_event_sysfs_show(char *page, u64 config)
+{
+	u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT);
+
+	return x86_event_sysfs_show(page, config, event);
+}
+
+static const struct x86_pmu zhaoxin_pmu __initconst = {
+	.name			= "zhaoxin",
+	.handle_irq		= zhaoxin_pmu_handle_irq,
+	.disable_all		= zhaoxin_pmu_disable_all,
+	.enable_all		= zhaoxin_pmu_enable_all,
+	.enable			= zhaoxin_pmu_enable_event,
+	.disable		= zhaoxin_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= zhaoxin_pmu_event_map,
+	.max_events		= ARRAY_SIZE(zx_pmon_event_map),
+	.apic			= 1,
+	/*
+	 * For zxd/zxe, read/write operation for PMCx MSR is 48 bits.
+	 */
+	.max_period		= (1ULL << 47) - 1,
+	.get_event_constraints	= zhaoxin_get_event_constraints,
+
+	.format_attrs		= zx_arch_formats_attr,
+	.events_sysfs_show	= zhaoxin_event_sysfs_show,
+};
+
+static const struct { int id; char *name; } zx_arch_events_map[] __initconst = {
+	{ PERF_COUNT_HW_CPU_CYCLES, "cpu cycles" },
+	{ PERF_COUNT_HW_INSTRUCTIONS, "instructions" },
+	{ PERF_COUNT_HW_BUS_CYCLES, "bus cycles" },
+	{ PERF_COUNT_HW_CACHE_REFERENCES, "cache references" },
+	{ PERF_COUNT_HW_CACHE_MISSES, "cache misses" },
+	{ PERF_COUNT_HW_BRANCH_INSTRUCTIONS, "branch instructions" },
+	{ PERF_COUNT_HW_BRANCH_MISSES, "branch misses" },
+};
+
+static __init void zhaoxin_arch_events_quirk(void)
+{
+	int bit;
+
+	/* disable event that reported as not presend by cpuid */
+	for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(zx_arch_events_map)) {
+		zx_pmon_event_map[zx_arch_events_map[bit].id] = 0;
+		pr_warn("CPUID marked event: \'%s\' unavailable\n",
+			zx_arch_events_map[bit].name);
+	}
+}
+
+__init int zhaoxin_pmu_init(void)
+{
+	union cpuid10_edx edx;
+	union cpuid10_eax eax;
+	union cpuid10_ebx ebx;
+	struct event_constraint *c;
+	unsigned int unused;
+	int version;
+
+	pr_info("Welcome to zhaoxin pmu!\n");
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * hw_event or not.
+	 */
+	cpuid(10, &eax.full, &ebx.full, &unused, &edx.full);
+
+	if (eax.split.mask_length < ARCH_PERFMON_EVENTS_COUNT - 1)
+		return -ENODEV;
+
+	version = eax.split.version_id;
+	if (version != 2)
+		return -ENODEV;
+
+	x86_pmu = zhaoxin_pmu;
+	pr_info("Version check pass!\n");
+
+	x86_pmu.version			= version;
+	x86_pmu.num_counters		= eax.split.num_counters;
+	x86_pmu.cntval_bits		= eax.split.bit_width;
+	x86_pmu.cntval_mask		= (1ULL << eax.split.bit_width) - 1;
+	x86_pmu.events_maskl		= ebx.full;
+	x86_pmu.events_mask_len		= eax.split.mask_length;
+
+	x86_pmu.num_counters_fixed = edx.split.num_counters_fixed;
+	x86_add_quirk(zhaoxin_arch_events_quirk);
+
+	switch (boot_cpu_data.x86) {
+	case 0x06:
+		if (boot_cpu_data.x86_model == 0x0f || boot_cpu_data.x86_model == 0x19) {
+
+			x86_pmu.max_period = x86_pmu.cntval_mask >> 1;
+
+			/* Clearing status works only if the global control is enable on zxc. */
+			x86_pmu.enabled_ack = 1;
+
+			x86_pmu.event_constraints = zxc_event_constraints;
+			zx_pmon_event_map[PERF_COUNT_HW_INSTRUCTIONS] = 0;
+			zx_pmon_event_map[PERF_COUNT_HW_CACHE_REFERENCES] = 0;
+			zx_pmon_event_map[PERF_COUNT_HW_CACHE_MISSES] = 0;
+			zx_pmon_event_map[PERF_COUNT_HW_BUS_CYCLES] = 0;
+
+			pr_cont("ZXC events, ");
+			break;
+		}
+		return -ENODEV;
+
+	case 0x07:
+		zx_pmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event = 0x01, .umask = 0x01, .inv = 0x01, .cmask = 0x01);
+
+		zx_pmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event = 0x0f, .umask = 0x04, .inv = 0, .cmask = 0);
+
+		switch (boot_cpu_data.x86_model) {
+		case 0x1b:
+			memcpy(hw_cache_event_ids, zxd_hw_cache_event_ids,
+			       sizeof(hw_cache_event_ids));
+
+			x86_pmu.event_constraints = zxd_event_constraints;
+
+			zx_pmon_event_map[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x0700;
+			zx_pmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x0709;
+
+			pr_cont("ZXD events, ");
+			break;
+		case 0x3b:
+			memcpy(hw_cache_event_ids, zxe_hw_cache_event_ids,
+			       sizeof(hw_cache_event_ids));
+
+			x86_pmu.event_constraints = zxd_event_constraints;
+
+			zx_pmon_event_map[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x0028;
+			zx_pmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x0029;
+
+			pr_cont("ZXE events, ");
+			break;
+		default:
+			return -ENODEV;
+		}
+		break;
+
+	default:
+		return -ENODEV;
+	}
+
+	x86_pmu.intel_ctrl = (1 << (x86_pmu.num_counters)) - 1;
+	x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+
+	if (x86_pmu.event_constraints) {
+		for_each_event_constraint(c, x86_pmu.event_constraints) {
+			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+			c->weight += x86_pmu.num_counters;
+		}
+	}
+
+	return 0;
+}
+
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index b0da5320bcff..acf76b466db6 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 #include <linux/hyperv.h>
 #include <linux/slab.h>
+#include <linux/kernel.h>
 #include <linux/cpuhotplug.h>
 #include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
@@ -72,7 +73,8 @@ static int hv_cpu_init(unsigned int cpu)
 	struct page *pg;
 
 	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
-	pg = alloc_page(GFP_KERNEL);
+	/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
+	pg = alloc_page(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL);
 	if (unlikely(!pg))
 		return -ENOMEM;
 	*input_arg = page_address(pg);
@@ -224,10 +226,18 @@ static int hv_cpu_die(unsigned int cpu)
 
 	rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
 	if (re_ctrl.target_vp == hv_vp_index[cpu]) {
-		/* Reassign to some other online CPU */
+		/*
+		 * Reassign reenlightenment notifications to some other online
+		 * CPU or just disable the feature if there are no online CPUs
+		 * left (happens on hibernation).
+		 */
 		new_cpu = cpumask_any_but(cpu_online_mask, cpu);
 
-		re_ctrl.target_vp = hv_vp_index[new_cpu];
+		if (new_cpu < nr_cpu_ids)
+			re_ctrl.target_vp = hv_vp_index[new_cpu];
+		else
+			re_ctrl.enabled = 0;
+
 		wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
 	}
 
@@ -253,6 +263,7 @@ static int __init hv_pci_init(void)
 static int hv_suspend(void)
 {
 	union hv_x64_msr_hypercall_contents hypercall_msr;
+	int ret;
 
 	/*
 	 * Reset the hypercall page as it is going to be invalidated
@@ -269,12 +280,17 @@ static int hv_suspend(void)
 	hypercall_msr.enable = 0;
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
-	return 0;
+	ret = hv_cpu_die(0);
+	return ret;
 }
 
 static void hv_resume(void)
 {
 	union hv_x64_msr_hypercall_contents hypercall_msr;
+	int ret;
+
+	ret = hv_cpu_init(0);
+	WARN_ON(ret);
 
 	/* Re-enable the hypercall page */
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
@@ -285,8 +301,16 @@ static void hv_resume(void)
 
 	hv_hypercall_pg = hv_hypercall_pg_saved;
 	hv_hypercall_pg_saved = NULL;
+
+	/*
+	 * Reenlightenment notifications are disabled by hv_cpu_die(0),
+	 * reenable them here if hv_reenlightenment_cb was previously set.
+	 */
+	if (hv_reenlightenment_cb)
+		set_hv_tscchange_cb(hv_reenlightenment_cb);
 }
 
+/* Note: when the ops are called, only CPU0 is online and IRQs are disabled. */
 static struct syscore_ops hv_syscore_ops = {
 	.suspend	= hv_suspend,
 	.resume		= hv_resume,
@@ -419,11 +443,14 @@ void hyperv_cleanup(void)
 }
 EXPORT_SYMBOL_GPL(hyperv_cleanup);
 
-void hyperv_report_panic(struct pt_regs *regs, long err)
+void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
 {
 	static bool panic_reported;
 	u64 guest_id;
 
+	if (in_die && !panic_on_oops)
+		return;
+
 	/*
 	 * We prefer to report panic on 'die' chain as we have proper
 	 * registers to report, but if we miss it (e.g. on BUG()) we need
diff --git a/arch/x86/ia32/audit.c b/arch/x86/ia32/audit.c
index 3d21eab7aaed..6efe6cb3768a 100644
--- a/arch/x86/ia32/audit.c
+++ b/arch/x86/ia32/audit.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <asm/unistd_32.h>
+#include <asm/audit.h>
 
 unsigned ia32_dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
diff --git a/arch/x86/include/asm/GEN-for-each-reg.h b/arch/x86/include/asm/GEN-for-each-reg.h
new file mode 100644
index 000000000000..1b07fb102c4e
--- /dev/null
+++ b/arch/x86/include/asm/GEN-for-each-reg.h
@@ -0,0 +1,25 @@
+#ifdef CONFIG_64BIT
+GEN(rax)
+GEN(rbx)
+GEN(rcx)
+GEN(rdx)
+GEN(rsi)
+GEN(rdi)
+GEN(rbp)
+GEN(r8)
+GEN(r9)
+GEN(r10)
+GEN(r11)
+GEN(r12)
+GEN(r13)
+GEN(r14)
+GEN(r15)
+#else
+GEN(eax)
+GEN(ebx)
+GEN(ecx)
+GEN(edx)
+GEN(esi)
+GEN(edi)
+GEN(ebp)
+#endif
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index 99bb207fc04c..87ce8e963215 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -25,11 +25,7 @@
 #define APBT_MIN_FREQ          1000000
 #define APBT_MMAP_SIZE         1024
 
-#define APBT_DEV_USED  1
-
 extern void apbt_time_init(void);
-extern unsigned long apbt_quick_calibrate(void);
-extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
 extern void apbt_setup_secondary_clock(void);
 
 extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
@@ -38,7 +34,6 @@ extern int sfi_mtimer_num;
 
 #else /* CONFIG_APB_TIMER */
 
-static inline unsigned long apbt_quick_calibrate(void) {return 0; }
 static inline void apbt_time_init(void) { }
 
 #endif
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 7a4bb1bd4bdb..ebc248e49549 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -15,16 +15,6 @@
 
 #define RDRAND_RETRY_LOOPS	10
 
-#define RDRAND_INT	".byte 0x0f,0xc7,0xf0"
-#define RDSEED_INT	".byte 0x0f,0xc7,0xf8"
-#ifdef CONFIG_X86_64
-# define RDRAND_LONG	".byte 0x48,0x0f,0xc7,0xf0"
-# define RDSEED_LONG	".byte 0x48,0x0f,0xc7,0xf8"
-#else
-# define RDRAND_LONG	RDRAND_INT
-# define RDSEED_LONG	RDSEED_INT
-#endif
-
 /* Unconditional execution of RDRAND and RDSEED */
 
 static inline bool __must_check rdrand_long(unsigned long *v)
@@ -32,9 +22,9 @@ static inline bool __must_check rdrand_long(unsigned long *v)
 	bool ok;
 	unsigned int retry = RDRAND_RETRY_LOOPS;
 	do {
-		asm volatile(RDRAND_LONG
+		asm volatile("rdrand %[out]"
 			     CC_SET(c)
-			     : CC_OUT(c) (ok), "=a" (*v));
+			     : CC_OUT(c) (ok), [out] "=r" (*v));
 		if (ok)
 			return true;
 	} while (--retry);
@@ -46,9 +36,9 @@ static inline bool __must_check rdrand_int(unsigned int *v)
 	bool ok;
 	unsigned int retry = RDRAND_RETRY_LOOPS;
 	do {
-		asm volatile(RDRAND_INT
+		asm volatile("rdrand %[out]"
 			     CC_SET(c)
-			     : CC_OUT(c) (ok), "=a" (*v));
+			     : CC_OUT(c) (ok), [out] "=r" (*v));
 		if (ok)
 			return true;
 	} while (--retry);
@@ -58,18 +48,18 @@ static inline bool __must_check rdrand_int(unsigned int *v)
 static inline bool __must_check rdseed_long(unsigned long *v)
 {
 	bool ok;
-	asm volatile(RDSEED_LONG
+	asm volatile("rdseed %[out]"
 		     CC_SET(c)
-		     : CC_OUT(c) (ok), "=a" (*v));
+		     : CC_OUT(c) (ok), [out] "=r" (*v));
 	return ok;
 }
 
 static inline bool __must_check rdseed_int(unsigned int *v)
 {
 	bool ok;
-	asm volatile(RDSEED_INT
+	asm volatile("rdseed %[out]"
 		     CC_SET(c)
-		     : CC_OUT(c) (ok), "=a" (*v));
+		     : CC_OUT(c) (ok), [out] "=r" (*v));
 	return ok;
 }
 
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index ce92c4acc913..9bf2620ce817 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -17,24 +17,19 @@ extern void cmpxchg8b_emu(void);
 #endif
 
 #ifdef CONFIG_RETPOLINE
-#ifdef CONFIG_X86_32
-#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void);
-#else
-#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void);
-INDIRECT_THUNK(8)
-INDIRECT_THUNK(9)
-INDIRECT_THUNK(10)
-INDIRECT_THUNK(11)
-INDIRECT_THUNK(12)
-INDIRECT_THUNK(13)
-INDIRECT_THUNK(14)
-INDIRECT_THUNK(15)
-#endif
-INDIRECT_THUNK(ax)
-INDIRECT_THUNK(bx)
-INDIRECT_THUNK(cx)
-INDIRECT_THUNK(dx)
-INDIRECT_THUNK(si)
-INDIRECT_THUNK(di)
-INDIRECT_THUNK(bp)
+
+#define DECL_INDIRECT_THUNK(reg) \
+	extern asmlinkage void __x86_indirect_thunk_ ## reg (void);
+
+#define DECL_RETPOLINE(reg) \
+	extern asmlinkage void __x86_retpoline_ ## reg (void);
+
+#undef GEN
+#define GEN(reg) DECL_INDIRECT_THUNK(reg)
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) DECL_RETPOLINE(reg)
+#include <asm/GEN-for-each-reg.h>
+
 #endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/audit.h b/arch/x86/include/asm/audit.h
new file mode 100644
index 000000000000..36aec57ea7a3
--- /dev/null
+++ b/arch/x86/include/asm/audit.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_AUDIT_H
+#define _ASM_X86_AUDIT_H
+
+int ia32_classify_syscall(unsigned int syscall);
+
+#endif /* _ASM_X86_AUDIT_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 53f246e9df5a..0367efdc5b7a 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -52,9 +52,9 @@ static __always_inline void
 arch_set_bit(long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
-		asm volatile(LOCK_PREFIX "orb %1,%0"
+		asm volatile(LOCK_PREFIX "orb %b1,%0"
 			: CONST_MASK_ADDR(nr, addr)
-			: "iq" (CONST_MASK(nr) & 0xff)
+			: "iq" (CONST_MASK(nr))
 			: "memory");
 	} else {
 		asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
@@ -72,9 +72,9 @@ static __always_inline void
 arch_clear_bit(long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
-		asm volatile(LOCK_PREFIX "andb %1,%0"
+		asm volatile(LOCK_PREFIX "andb %b1,%0"
 			: CONST_MASK_ADDR(nr, addr)
-			: "iq" (CONST_MASK(nr) ^ 0xff));
+			: "iq" (~CONST_MASK(nr)));
 	} else {
 		asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
 			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
@@ -123,9 +123,9 @@ static __always_inline void
 arch_change_bit(long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
-		asm volatile(LOCK_PREFIX "xorb %1,%0"
+		asm volatile(LOCK_PREFIX "xorb %b1,%0"
 			: CONST_MASK_ADDR(nr, addr)
-			: "iq" ((u8)CONST_MASK(nr)));
+			: "iq" (CONST_MASK(nr)));
 	} else {
 		asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
 			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index cf3d621c6892..eb8fcede9e3b 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -20,12 +20,14 @@
 #define X86_CENTAUR_FAM6_C7_D		0xd
 #define X86_CENTAUR_FAM6_NANO		0xf
 
+#define X86_STEPPINGS(mins, maxs)    GENMASK(maxs, mins)
 /**
- * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Base macro for CPU matching
+ * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
  * @_vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
  *		The name is expanded to X86_VENDOR_@_vendor
  * @_family:	The family number or X86_FAMILY_ANY
  * @_model:	The model number, model constant or X86_MODEL_ANY
+ * @_steppings:	Bitmask for steppings, stepping constant or X86_STEPPING_ANY
  * @_feature:	A X86_FEATURE bit or X86_FEATURE_ANY
  * @_data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
@@ -37,16 +39,35 @@
  * into another macro at the usage site for good reasons, then please
  * start this local macro with X86_MATCH to allow easy grepping.
  */
-#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(_vendor, _family, _model,	\
-					   _feature, _data) {		\
+#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
+						    _steppings, _feature, _data) { \
 	.vendor		= X86_VENDOR_##_vendor,				\
 	.family		= _family,					\
 	.model		= _model,					\
+	.steppings	= _steppings,					\
 	.feature	= _feature,					\
 	.driver_data	= (unsigned long) _data				\
 }
 
 /**
+ * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Macro for CPU matching
+ * @_vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ *		The name is expanded to X86_VENDOR_@_vendor
+ * @_family:	The family number or X86_FAMILY_ANY
+ * @_model:	The model number, model constant or X86_MODEL_ANY
+ * @_feature:	A X86_FEATURE bit or X86_FEATURE_ANY
+ * @_data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * The steppings arguments of X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE() is
+ * set to wildcards.
+ */
+#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model, feature, data) \
+	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(vendor, family, model, \
+						X86_STEPPING_ANY, feature, data)
+
+/**
  * X86_MATCH_VENDOR_FAM_FEATURE - Macro for matching vendor, family and CPU feature
  * @vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
  *		The name is expanded to X86_VENDOR_@vendor
@@ -139,6 +160,10 @@
 #define X86_MATCH_INTEL_FAM6_MODEL(model, data)				\
 	X86_MATCH_VENDOR_FAM_MODEL(INTEL, 6, INTEL_FAM6_##model, data)
 
+#define X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(model, steppings, data)	\
+	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
+						     steppings, X86_FEATURE_ANY, data)
+
 /*
  * Match specific microcode revisions.
  *
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 7e31f7f1bb06..49bd6cf3eec9 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -3,7 +3,7 @@
 #define _ASM_X86_DEVICE_H
 
 struct dev_archdata {
-#if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU)
+#ifdef CONFIG_IOMMU_API
 	void *iommu; /* hook for IOMMU specific extension */
 #endif
 };
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 00f7cf45e699..8e95aa4b0d17 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -74,7 +74,7 @@
 #define MAX_DMA_PFN   ((16UL * 1024 * 1024) >> PAGE_SHIFT)
 
 /* 4GB broken PCI/AGP hardware bus master zone */
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
+#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT))
 
 #ifdef CONFIG_X86_32
 /* The maximum address that we can perform a DMA transfer to on this platform */
diff --git a/arch/x86/include/asm/doublefault.h b/arch/x86/include/asm/doublefault.h
index af9a14ac8962..54a6e4a2e132 100644
--- a/arch/x86/include/asm/doublefault.h
+++ b/arch/x86/include/asm/doublefault.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_DOUBLEFAULT_H
 #define _ASM_X86_DOUBLEFAULT_H
 
-#if defined(CONFIG_X86_32) && defined(CONFIG_DOUBLEFAULT)
+#ifdef CONFIG_X86_32
 extern void doublefault_init_cpu_tss(void);
 #else
 static inline void doublefault_init_cpu_tss(void)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index cdcf48d52a12..89dcc7aa7e2c 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -9,6 +9,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/mmu_context.h>
 #include <linux/build_bug.h>
+#include <linux/kernel.h>
 
 extern unsigned long efi_fw_vendor, efi_config_table;
 
@@ -178,8 +179,10 @@ extern void efi_free_boot_services(void);
 extern pgd_t * __init efi_uv1_memmap_phys_prolog(void);
 extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd);
 
+/* kexec external ABI */
 struct efi_setup_data {
 	u64 fw_vendor;
+	u64 __unused;
 	u64 tables;
 	u64 smbios;
 	u64 reserved[8];
@@ -223,14 +226,21 @@ efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size,
 
 /* arch specific definitions used by the stub code */
 
-__attribute_const__ bool efi_is_64bit(void);
+#ifdef CONFIG_EFI_MIXED
+
+#define ARCH_HAS_EFISTUB_WRAPPERS
+
+static inline bool efi_is_64bit(void)
+{
+	extern const bool efi_is64;
+
+	return efi_is64;
+}
 
 static inline bool efi_is_native(void)
 {
 	if (!IS_ENABLED(CONFIG_X86_64))
 		return true;
-	if (!IS_ENABLED(CONFIG_EFI_MIXED))
-		return true;
 	return efi_is_64bit();
 }
 
@@ -284,6 +294,15 @@ static inline u32 efi64_convert_status(efi_status_t status)
 #define __efi64_argmap_allocate_pool(type, size, buffer)		\
 	((type), (size), efi64_zero_upper(buffer))
 
+#define __efi64_argmap_create_event(type, tpl, f, c, event)		\
+	((type), (tpl), (f), (c), efi64_zero_upper(event))
+
+#define __efi64_argmap_set_timer(event, type, time)			\
+	((event), (type), lower_32_bits(time), upper_32_bits(time))
+
+#define __efi64_argmap_wait_for_event(num, event, index)		\
+	((num), (event), efi64_zero_upper(index))
+
 #define __efi64_argmap_handle_protocol(handle, protocol, interface)	\
 	((handle), (protocol), efi64_zero_upper(interface))
 
@@ -305,6 +324,10 @@ static inline u32 efi64_convert_status(efi_status_t status)
 #define __efi64_argmap_load_file(protocol, path, policy, bufsize, buf)	\
 	((protocol), (path), (policy), efi64_zero_upper(bufsize), (buf))
 
+/* Graphics Output Protocol */
+#define __efi64_argmap_query_mode(gop, mode, size, info)		\
+	((gop), (mode), efi64_zero_upper(size), efi64_zero_upper(info))
+
 /*
  * The macros below handle the plumbing for the argument mapping. To add a
  * mapping for a specific EFI method, simply define a macro
@@ -333,15 +356,26 @@ static inline u32 efi64_convert_status(efi_status_t status)
 
 #define efi_bs_call(func, ...)						\
 	(efi_is_native()						\
-		? efi_system_table()->boottime->func(__VA_ARGS__)	\
-		: __efi64_thunk_map(efi_table_attr(efi_system_table(),	\
-				boottime), func, __VA_ARGS__))
+		? efi_system_table->boottime->func(__VA_ARGS__)		\
+		: __efi64_thunk_map(efi_table_attr(efi_system_table,	\
+						   boottime),		\
+				    func, __VA_ARGS__))
 
 #define efi_rt_call(func, ...)						\
 	(efi_is_native()						\
-		? efi_system_table()->runtime->func(__VA_ARGS__)	\
-		: __efi64_thunk_map(efi_table_attr(efi_system_table(),	\
-				runtime), func, __VA_ARGS__))
+		? efi_system_table->runtime->func(__VA_ARGS__)		\
+		: __efi64_thunk_map(efi_table_attr(efi_system_table,	\
+						   runtime),		\
+				    func, __VA_ARGS__))
+
+#else /* CONFIG_EFI_MIXED */
+
+static inline bool efi_is_64bit(void)
+{
+	return IS_ENABLED(CONFIG_X86_64);
+}
+
+#endif /* CONFIG_EFI_MIXED */
 
 extern bool efi_reboot_required(void);
 extern bool efi_is_table_address(unsigned long phys_addr);
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 44c48e34d799..42159f45bf9c 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -31,7 +31,8 @@ extern void fpu__save(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
 extern void fpu__drop(struct fpu *fpu);
 extern int  fpu__copy(struct task_struct *dst, struct task_struct *src);
-extern void fpu__clear(struct fpu *fpu);
+extern void fpu__clear_user_states(struct fpu *fpu);
+extern void fpu__clear_all(struct fpu *fpu);
 extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
 extern int  dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
 
@@ -92,7 +93,7 @@ static inline void fpstate_init_xstate(struct xregs_state *xsave)
 	 * XRSTORS requires these bits set in xcomp_bv, or it will
 	 * trigger #GP:
 	 */
-	xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask;
+	xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all;
 }
 
 static inline void fpstate_init_fxstate(struct fxregs_state *fx)
@@ -399,7 +400,10 @@ static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask)
 	u32 hmask = mask >> 32;
 	int err;
 
-	XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+	if (static_cpu_has(X86_FEATURE_XSAVES))
+		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+	else
+		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
 
 	return err;
 }
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index c6136d79f8c0..422d8369012a 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -21,19 +21,29 @@
 #define XSAVE_YMM_SIZE	    256
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
-/* Supervisor features */
-#define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
-
-/* All currently supported features */
-#define XCNTXT_MASK		(XFEATURE_MASK_FP | \
-				 XFEATURE_MASK_SSE | \
-				 XFEATURE_MASK_YMM | \
-				 XFEATURE_MASK_OPMASK | \
-				 XFEATURE_MASK_ZMM_Hi256 | \
-				 XFEATURE_MASK_Hi16_ZMM	 | \
-				 XFEATURE_MASK_PKRU | \
-				 XFEATURE_MASK_BNDREGS | \
-				 XFEATURE_MASK_BNDCSR)
+/* All currently supported user features */
+#define XFEATURE_MASK_USER_SUPPORTED (XFEATURE_MASK_FP | \
+				      XFEATURE_MASK_SSE | \
+				      XFEATURE_MASK_YMM | \
+				      XFEATURE_MASK_OPMASK | \
+				      XFEATURE_MASK_ZMM_Hi256 | \
+				      XFEATURE_MASK_Hi16_ZMM	 | \
+				      XFEATURE_MASK_PKRU | \
+				      XFEATURE_MASK_BNDREGS | \
+				      XFEATURE_MASK_BNDCSR)
+
+/* All currently supported supervisor features */
+#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (0)
+
+/*
+ * Unsupported supervisor features. When a supervisor feature in this mask is
+ * supported in the future, move it to the supported supervisor feature mask.
+ */
+#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT)
+
+/* All supervisor states including supported and unsupported states. */
+#define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \
+				      XFEATURE_MASK_SUPERVISOR_UNSUPPORTED)
 
 #ifdef CONFIG_X86_64
 #define REX_PREFIX	"0x48, "
@@ -41,7 +51,18 @@
 #define REX_PREFIX
 #endif
 
-extern u64 xfeatures_mask;
+extern u64 xfeatures_mask_all;
+
+static inline u64 xfeatures_mask_supervisor(void)
+{
+	return xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
+}
+
+static inline u64 xfeatures_mask_user(void)
+{
+	return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED;
+}
+
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
 extern void __init update_regset_xstate_info(unsigned int size,
@@ -54,8 +75,9 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
 int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
 int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
+void copy_supervisor_to_kernel(struct xregs_state *xsave);
 
 /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
-extern int validate_xstate_header(const struct xstate_header *hdr);
+int validate_user_xstate_header(const struct xstate_header *hdr);
 
 #endif
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 85be2f506272..84b9449be080 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -56,16 +56,23 @@ struct dyn_arch_ftrace {
 
 #ifndef __ASSEMBLY__
 
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+extern void set_ftrace_ops_ro(void);
+#else
+static inline void set_ftrace_ops_ro(void) { }
+#endif
+
 #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
 static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
 {
 	/*
 	 * Compare the symbol name with the system call name. Skip the
-	 * "__x64_sys", "__ia32_sys" or simple "sys" prefix.
+	 * "__x64_sys", "__ia32_sys", "__do_sys" or simple "sys" prefix.
 	 */
 	return !strcmp(sym + 3, name + 3) ||
 		(!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) ||
-		(!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3));
+		(!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)) ||
+		(!strncmp(sym, "__do_sys", 8) && !strcmp(sym + 8, name + 3));
 }
 
 #ifndef COMPILE_OFFSETS
diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h
index 989cfa86de85..734482afbf81 100644
--- a/arch/x86/include/asm/invpcid.h
+++ b/arch/x86/include/asm/invpcid.h
@@ -12,12 +12,9 @@ static inline void __invpcid(unsigned long pcid, unsigned long addr,
 	 * stale TLB entries and, especially if we're flushing global
 	 * mappings, we don't want the compiler to reorder any subsequent
 	 * memory accesses before the TLB flush.
-	 *
-	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
-	 * invpcid (%rcx), %rax in long mode.
 	 */
-	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
-		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+	asm volatile("invpcid %[desc], %[type]"
+		     :: [desc] "m" (desc), [type] "r" (type) : "memory");
 }
 
 #define INVPCID_TYPE_INDIV_ADDR		0
diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h
index 07344d82e88e..ac1a99ffbd8d 100644
--- a/arch/x86/include/asm/io_bitmap.h
+++ b/arch/x86/include/asm/io_bitmap.h
@@ -17,7 +17,7 @@ struct task_struct;
 
 #ifdef CONFIG_X86_IOPL_IOPERM
 void io_bitmap_share(struct task_struct *tsk);
-void io_bitmap_exit(void);
+void io_bitmap_exit(struct task_struct *tsk);
 
 void native_tss_update_io_bitmap(void);
 
@@ -29,7 +29,7 @@ void native_tss_update_io_bitmap(void);
 
 #else
 static inline void io_bitmap_share(struct task_struct *tsk) { }
-static inline void io_bitmap_exit(void) { }
+static inline void io_bitmap_exit(struct task_struct *tsk) { }
 static inline void tss_update_io_bitmap(void) { }
 #endif
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 42a2d0d3984a..0a6b35353fc7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -578,6 +578,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr4;
 	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
+	u32 host_pkru;
 	u32 pkru;
 	u32 hflags;
 	u64 efer;
@@ -1093,8 +1094,6 @@ struct kvm_x86_ops {
 	void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
-	u64 (*get_dr6)(struct kvm_vcpu *vcpu);
-	void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
 	void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
@@ -1449,6 +1448,7 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu);
 
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
+void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload);
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
@@ -1663,8 +1663,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
 {
 	/* We can only post Fixed and LowPrio IRQs */
-	return (irq->delivery_mode == dest_Fixed ||
-		irq->delivery_mode == dest_LowestPrio);
+	return (irq->delivery_mode == APIC_DM_FIXED ||
+		irq->delivery_mode == APIC_DM_LOWEST);
 }
 
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 6685e1218959..7063b5a43220 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -41,7 +41,7 @@ struct microcode_amd {
 	unsigned int			mpb[0];
 };
 
-#define PATCH_MAX_SIZE PAGE_SIZE
+#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
 
 #ifdef CONFIG_MICROCODE_AMD
 extern void __init load_ucode_amd_bsp(unsigned int family);
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 73d8dd14dda2..2d4515e8b7df 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -14,43 +14,4 @@ extern struct pglist_data *node_data[];
 #define NODE_DATA(nid)	(node_data[nid])
 #endif /* CONFIG_NUMA */
 
-#ifdef CONFIG_DISCONTIGMEM
-
-/*
- * generic node memory support, the following assumptions apply:
- *
- * 1) memory comes in 64Mb contiguous chunks which are either present or not
- * 2) we will not have more than 64Gb in total
- *
- * for now assume that 64Gb is max amount of RAM for whole system
- *    64Gb / 4096bytes/page = 16777216 pages
- */
-#define MAX_NR_PAGES 16777216
-#define MAX_SECTIONS 1024
-#define PAGES_PER_SECTION (MAX_NR_PAGES/MAX_SECTIONS)
-
-extern s8 physnode_map[];
-
-static inline int pfn_to_nid(unsigned long pfn)
-{
-#ifdef CONFIG_NUMA
-	return((int) physnode_map[(pfn) / PAGES_PER_SECTION]);
-#else
-	return 0;
-#endif
-}
-
-static inline int pfn_valid(int pfn)
-{
-	int nid = pfn_to_nid(pfn);
-
-	if (nid >= 0)
-		return (pfn < node_end_pfn(nid));
-	return 0;
-}
-
-#define early_pfn_valid(pfn)	pfn_valid((pfn))
-
-#endif /* CONFIG_DISCONTIGMEM */
-
 #endif /* _ASM_X86_MMZONE_32_H */
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index c215d2762488..e988bac0a4a1 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -13,64 +13,4 @@ struct mod_arch_specific {
 #endif
 };
 
-#ifdef CONFIG_X86_64
-/* X86_64 does not define MODULE_PROC_FAMILY */
-#elif defined CONFIG_M486SX
-#define MODULE_PROC_FAMILY "486SX "
-#elif defined CONFIG_M486
-#define MODULE_PROC_FAMILY "486 "
-#elif defined CONFIG_M586
-#define MODULE_PROC_FAMILY "586 "
-#elif defined CONFIG_M586TSC
-#define MODULE_PROC_FAMILY "586TSC "
-#elif defined CONFIG_M586MMX
-#define MODULE_PROC_FAMILY "586MMX "
-#elif defined CONFIG_MCORE2
-#define MODULE_PROC_FAMILY "CORE2 "
-#elif defined CONFIG_MATOM
-#define MODULE_PROC_FAMILY "ATOM "
-#elif defined CONFIG_M686
-#define MODULE_PROC_FAMILY "686 "
-#elif defined CONFIG_MPENTIUMII
-#define MODULE_PROC_FAMILY "PENTIUMII "
-#elif defined CONFIG_MPENTIUMIII
-#define MODULE_PROC_FAMILY "PENTIUMIII "
-#elif defined CONFIG_MPENTIUMM
-#define MODULE_PROC_FAMILY "PENTIUMM "
-#elif defined CONFIG_MPENTIUM4
-#define MODULE_PROC_FAMILY "PENTIUM4 "
-#elif defined CONFIG_MK6
-#define MODULE_PROC_FAMILY "K6 "
-#elif defined CONFIG_MK7
-#define MODULE_PROC_FAMILY "K7 "
-#elif defined CONFIG_MK8
-#define MODULE_PROC_FAMILY "K8 "
-#elif defined CONFIG_MELAN
-#define MODULE_PROC_FAMILY "ELAN "
-#elif defined CONFIG_MCRUSOE
-#define MODULE_PROC_FAMILY "CRUSOE "
-#elif defined CONFIG_MEFFICEON
-#define MODULE_PROC_FAMILY "EFFICEON "
-#elif defined CONFIG_MWINCHIPC6
-#define MODULE_PROC_FAMILY "WINCHIPC6 "
-#elif defined CONFIG_MWINCHIP3D
-#define MODULE_PROC_FAMILY "WINCHIP3D "
-#elif defined CONFIG_MCYRIXIII
-#define MODULE_PROC_FAMILY "CYRIXIII "
-#elif defined CONFIG_MVIAC3_2
-#define MODULE_PROC_FAMILY "VIAC3-2 "
-#elif defined CONFIG_MVIAC7
-#define MODULE_PROC_FAMILY "VIAC7 "
-#elif defined CONFIG_MGEODEGX1
-#define MODULE_PROC_FAMILY "GEODEGX1 "
-#elif defined CONFIG_MGEODE_LX
-#define MODULE_PROC_FAMILY "GEODE "
-#else
-#error unknown processor family
-#endif
-
-#ifdef CONFIG_X86_32
-# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
-#endif
-
 #endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 1c42ecbe75cb..d30805ed323e 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -35,6 +35,8 @@ typedef int (*hyperv_fill_flush_list_func)(
 	rdmsrl(HV_X64_MSR_SINT0 + int_num, val)
 #define hv_set_synint_state(int_num, val) \
 	wrmsrl(HV_X64_MSR_SINT0 + int_num, val)
+#define hv_recommend_using_aeoi() \
+	(!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED))
 
 #define hv_get_crash_ctl(val) \
 	rdmsrl(HV_X64_MSR_CRASH_CTL, val)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 12c9684d59ba..ef452b817f44 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -301,6 +301,9 @@
 #define MSR_PP1_ENERGY_STATUS		0x00000641
 #define MSR_PP1_POLICY			0x00000642
 
+#define MSR_AMD_PKG_ENERGY_STATUS	0xc001029b
+#define MSR_AMD_RAPL_POWER_UNIT		0xc0010299
+
 /* Config TDP MSRs */
 #define MSR_CONFIG_TDP_NOMINAL		0x00000648
 #define MSR_CONFIG_TDP_LEVEL_1		0x00000649
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 07e95dcb40ad..d52d1aacdd97 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -4,20 +4,13 @@
 #define _ASM_X86_NOSPEC_BRANCH_H_
 
 #include <linux/static_key.h>
+#include <linux/frame.h>
 
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
-
-/*
- * This should be used immediately before a retpoline alternative. It tells
- * objtool where the retpolines are so that it can make sense of the control
- * flow by just reading the original instruction(s) and ignoring the
- * alternatives.
- */
-#define ANNOTATE_NOSPEC_ALTERNATIVE \
-	ANNOTATE_IGNORE_ALTERNATIVE
+#include <asm/unwind_hints.h>
 
 /*
  * Fill the CPU return stack buffer.
@@ -46,21 +39,25 @@
 #define __FILL_RETURN_BUFFER(reg, nr, sp)	\
 	mov	$(nr/2), reg;			\
 771:						\
+	ANNOTATE_INTRA_FUNCTION_CALL;		\
 	call	772f;				\
 773:	/* speculation trap */			\
+	UNWIND_HINT_EMPTY;			\
 	pause;					\
 	lfence;					\
 	jmp	773b;				\
 772:						\
+	ANNOTATE_INTRA_FUNCTION_CALL;		\
 	call	774f;				\
 775:	/* speculation trap */			\
+	UNWIND_HINT_EMPTY;			\
 	pause;					\
 	lfence;					\
 	jmp	775b;				\
 774:						\
+	add	$(BITS_PER_LONG/8) * 2, sp;	\
 	dec	reg;				\
-	jnz	771b;				\
-	add	$(BITS_PER_LONG/8) * nr, sp;
+	jnz	771b;
 
 #ifdef __ASSEMBLY__
 
@@ -77,57 +74,27 @@
 .endm
 
 /*
- * These are the bare retpoline primitives for indirect jmp and call.
- * Do not use these directly; they only exist to make the ALTERNATIVE
- * invocation below less ugly.
- */
-.macro RETPOLINE_JMP reg:req
-	call	.Ldo_rop_\@
-.Lspec_trap_\@:
-	pause
-	lfence
-	jmp	.Lspec_trap_\@
-.Ldo_rop_\@:
-	mov	\reg, (%_ASM_SP)
-	ret
-.endm
-
-/*
- * This is a wrapper around RETPOLINE_JMP so the called function in reg
- * returns to the instruction after the macro.
- */
-.macro RETPOLINE_CALL reg:req
-	jmp	.Ldo_call_\@
-.Ldo_retpoline_jmp_\@:
-	RETPOLINE_JMP \reg
-.Ldo_call_\@:
-	call	.Ldo_retpoline_jmp_\@
-.endm
-
-/*
  * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
  * indirect jmp/call which may be susceptible to the Spectre variant 2
  * attack.
  */
 .macro JMP_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
-	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg),	\
-		__stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE,	\
-		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
+		      __stringify(jmp __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
 #else
-	jmp	*\reg
+	jmp	*%\reg
 #endif
 .endm
 
 .macro CALL_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
-	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg),	\
-		__stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
-		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \
+		      __stringify(call __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_AMD
 #else
-	call	*\reg
+	call	*%\reg
 #endif
 .endm
 
@@ -137,10 +104,8 @@
   */
 .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
 #ifdef CONFIG_RETPOLINE
-	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE "jmp .Lskip_rsb_\@",				\
-		__stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP))	\
-		\ftr
+	ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
+	__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
 .Lskip_rsb_\@:
 #endif
 .endm
@@ -161,16 +126,16 @@
  * which is ensured when CONFIG_RETPOLINE is defined.
  */
 # define CALL_NOSPEC						\
-	ANNOTATE_NOSPEC_ALTERNATIVE				\
 	ALTERNATIVE_2(						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
+	"call __x86_retpoline_%V[thunk_target]\n",		\
 	X86_FEATURE_RETPOLINE,					\
 	"lfence;\n"						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
 	X86_FEATURE_RETPOLINE_AMD)
+
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 
 #else /* CONFIG_X86_32 */
@@ -180,7 +145,6 @@
  * here, anyway.
  */
 # define CALL_NOSPEC						\
-	ANNOTATE_NOSPEC_ALTERNATIVE				\
 	ALTERNATIVE_2(						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
@@ -237,27 +201,6 @@ enum ssb_mitigation {
 extern char __indirect_thunk_start[];
 extern char __indirect_thunk_end[];
 
-/*
- * On VMEXIT we must ensure that no RSB predictions learned in the guest
- * can be followed in the host, by overwriting the RSB completely. Both
- * retpoline and IBRS mitigations for Spectre v2 need this; only on future
- * CPUs with IBRS_ALL *might* it be avoided.
- */
-static inline void vmexit_fill_RSB(void)
-{
-#ifdef CONFIG_RETPOLINE
-	unsigned long loops;
-
-	asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
-		      ALTERNATIVE("jmp 910f",
-				  __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
-				  X86_FEATURE_RETPOLINE)
-		      "910:"
-		      : "=r" (loops), ASM_CALL_CONSTRAINT
-		      : : "memory" );
-#endif
-}
-
 static __always_inline
 void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
 {
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 6e060907c163..d25534940bde 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -58,8 +58,7 @@
 #define ORC_TYPE_CALL			0
 #define ORC_TYPE_REGS			1
 #define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_SAVE		3
-#define UNWIND_HINT_TYPE_RESTORE	4
+#define UNWIND_HINT_TYPE_RET_OFFSET	3
 
 #ifndef __ASSEMBLY__
 /*
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 0dca7f7aeff2..be7b19646897 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -66,8 +66,7 @@ do {						\
 #endif /* !__ASSEMBLY__ */
 
 /*
- * kern_addr_valid() is (1) for FLATMEM and (0) for
- * SPARSEMEM and DISCONTIGMEM
+ * kern_addr_valid() is (1) for FLATMEM and (0) for SPARSEMEM
  */
 #ifdef CONFIG_FLATMEM
 #define kern_addr_valid(addr)	(1)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3bcf27caf6c9..29ee0c088009 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -113,9 +113,10 @@ struct cpuinfo_x86 {
 	/* in KB - valid for CPUS which support this call: */
 	unsigned int		x86_cache_size;
 	int			x86_cache_alignment;	/* In bytes */
-	/* Cache QoS architectural values: */
+	/* Cache QoS architectural values, valid only on the BSP: */
 	int			x86_cache_max_rmid;	/* max index */
 	int			x86_cache_occ_scale;	/* scale to bytes */
+	int			x86_cache_mbm_width_offset;
 	int			x86_power;
 	unsigned long		loops_per_jiffy;
 	/* cpuid returned max cores value: */
@@ -727,7 +728,6 @@ static inline void sync_core(void)
 	unsigned int tmp;
 
 	asm volatile (
-		UNWIND_HINT_SAVE
 		"mov %%ss, %0\n\t"
 		"pushq %q0\n\t"
 		"pushq %%rsp\n\t"
@@ -737,7 +737,6 @@ static inline void sync_core(void)
 		"pushq %q0\n\t"
 		"pushq $1f\n\t"
 		"iretq\n\t"
-		UNWIND_HINT_RESTORE
 		"1:"
 		: "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
 #endif
diff --git a/arch/x86/include/asm/resctrl_sched.h b/arch/x86/include/asm/resctrl.h
index f6b7fe2833cc..07603064df8f 100644
--- a/arch/x86/include/asm/resctrl_sched.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_RESCTRL_SCHED_H
-#define _ASM_X86_RESCTRL_SCHED_H
+#ifndef _ASM_X86_RESCTRL_H
+#define _ASM_X86_RESCTRL_H
 
 #ifdef CONFIG_X86_CPU_RESCTRL
 
@@ -84,10 +84,13 @@ static inline void resctrl_sched_in(void)
 		__resctrl_sched_in();
 }
 
+void resctrl_cpu_detect(struct cpuinfo_x86 *c);
+
 #else
 
 static inline void resctrl_sched_in(void) {}
+static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {}
 
 #endif /* CONFIG_X86_CPU_RESCTRL */
 
-#endif /* _ASM_X86_RESCTRL_SCHED_H */
+#endif /* _ASM_X86_RESCTRL_H */
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 27c47d183f4b..8b58d6975d5d 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -57,8 +57,10 @@ static __always_inline unsigned long smap_save(void)
 {
 	unsigned long flags;
 
-	asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC,
-				  X86_FEATURE_SMAP)
+	asm volatile ("# smap_save\n\t"
+		      ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+		      "pushf; pop %0; " __ASM_CLAC "\n\t"
+		      "1:"
 		      : "=rm" (flags) : : "memory", "cc");
 
 	return flags;
@@ -66,7 +68,10 @@ static __always_inline unsigned long smap_save(void)
 
 static __always_inline void smap_restore(unsigned long flags)
 {
-	asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP)
+	asm volatile ("# smap_restore\n\t"
+		      ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+		      "push %0; popf\n\t"
+		      "1:"
 		      : : "g" (flags) : "memory", "cc");
 }
 
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index bf3e34b25afc..323db6c5852a 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -3,29 +3,7 @@
 #define _ASM_X86_SPINLOCK_TYPES_H
 
 #include <linux/types.h>
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-#define __TICKET_LOCK_INC	2
-#define TICKET_SLOWPATH_FLAG	((__ticket_t)1)
-#else
-#define __TICKET_LOCK_INC	1
-#define TICKET_SLOWPATH_FLAG	((__ticket_t)0)
-#endif
-
-#if (CONFIG_NR_CPUS < (256 / __TICKET_LOCK_INC))
-typedef u8  __ticket_t;
-typedef u16 __ticketpair_t;
-#else
-typedef u16 __ticket_t;
-typedef u32 __ticketpair_t;
-#endif
-
-#define TICKET_LOCK_INC	((__ticket_t)__TICKET_LOCK_INC)
-
-#define TICKET_SHIFT	(sizeof(__ticket_t) * 8)
-
 #include <asm-generic/qspinlock_types.h>
-
 #include <asm-generic/qrwlock_types.h>
 
 #endif /* _ASM_X86_SPINLOCK_TYPES_H */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 91e29b6a86a5..9804a7957f4e 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -55,8 +55,13 @@
 /*
  * Initialize the stackprotector canary value.
  *
- * NOTE: this must only be called from functions that never return,
+ * NOTE: this must only be called from functions that never return
  * and it must always be inlined.
+ *
+ * In addition, it should be called from a compilation unit for which
+ * stack protector is disabled. Alternatively, the caller should not end
+ * with a function call which gets tail-call optimized as that would
+ * lead to checking a modified canary value.
  */
 static __always_inline void boot_init_stack_canary(void)
 {
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index c26a7e1d8a2c..2ae904bf25e4 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -69,9 +69,7 @@ dotraplinkage void do_overflow(struct pt_regs *regs, long error_code);
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code);
 dotraplinkage void do_invalid_op(struct pt_regs *regs, long error_code);
 dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code);
-#if defined(CONFIG_X86_64) || defined(CONFIG_DOUBLEFAULT)
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long cr2);
-#endif
 dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *regs, long error_code);
 dotraplinkage void do_invalid_TSS(struct pt_regs *regs, long error_code);
 dotraplinkage void do_segment_not_present(struct pt_regs *regs, long error_code);
@@ -118,11 +116,6 @@ void smp_spurious_interrupt(struct pt_regs *regs);
 void smp_error_interrupt(struct pt_regs *regs);
 asmlinkage void smp_irq_move_cleanup_interrupt(void);
 
-extern void ist_enter(struct pt_regs *regs);
-extern void ist_exit(struct pt_regs *regs);
-extern void ist_begin_non_atomic(struct pt_regs *regs);
-extern void ist_end_non_atomic(void);
-
 #ifdef CONFIG_VMAP_STACK
 void __noreturn handle_stack_overflow(const char *message,
 				      struct pt_regs *regs,
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 499578f7e6d7..70fc159ebe69 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -19,7 +19,7 @@ struct unwind_state {
 #if defined(CONFIG_UNWINDER_ORC)
 	bool signal, full_regs;
 	unsigned long sp, bp, ip;
-	struct pt_regs *regs;
+	struct pt_regs *regs, *prev_regs;
 #elif defined(CONFIG_UNWINDER_FRAME_POINTER)
 	bool got_irq;
 	unsigned long *bp, *orig_sp, ip;
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index f5e2eb12cb71..7d903fdb3f43 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -86,32 +86,15 @@
 	UNWIND_HINT sp_offset=\sp_offset
 .endm
 
-.macro UNWIND_HINT_SAVE
-	UNWIND_HINT type=UNWIND_HINT_TYPE_SAVE
-.endm
-
-.macro UNWIND_HINT_RESTORE
-	UNWIND_HINT type=UNWIND_HINT_TYPE_RESTORE
+/*
+ * RET_OFFSET: Used on instructions that terminate a function; mostly RETURN
+ * and sibling calls. On these, sp_offset denotes the expected offset from
+ * initial_func_cfi.
+ */
+.macro UNWIND_HINT_RET_OFFSET sp_offset=8
+	UNWIND_HINT type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
 .endm
 
-#else /* !__ASSEMBLY__ */
-
-#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
-	"987: \n\t"						\
-	".pushsection .discard.unwind_hints\n\t"		\
-	/* struct unwind_hint */				\
-	".long 987b - .\n\t"					\
-	".short " __stringify(sp_offset) "\n\t"			\
-	".byte " __stringify(sp_reg) "\n\t"			\
-	".byte " __stringify(type) "\n\t"			\
-	".byte " __stringify(end) "\n\t"			\
-	".balign 4 \n\t"					\
-	".popsection\n\t"
-
-#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0)
-
-#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0)
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_UNWIND_HINTS_H */
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index 389174eaec79..2fcc3ac12e76 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -123,12 +123,6 @@ enum uv_memprotect {
 	UV_MEMPROT_ALLOW_RW
 };
 
-/*
- * bios calls have 6 parameters
- */
-extern s64 uv_bios_call(enum uv_bios_cmd, u64, u64, u64, u64, u64);
-extern s64 uv_bios_call_irqsave(enum uv_bios_cmd, u64, u64, u64, u64, u64);
-
 extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *, long *);
 extern s64 uv_bios_freq_base(u64, u64 *);
 extern int uv_bios_mq_watchlist_alloc(unsigned long, unsigned int,
@@ -146,7 +140,6 @@ extern long sn_partition_id;
 extern long sn_coherency_id;
 extern long sn_region_size;
 extern long system_serial_number;
-#define uv_partition_coherence_id()	(sn_coherency_id)
 
 extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
 
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 45ea95ce79b4..ae587ce544f4 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -31,7 +31,6 @@ static inline bool is_early_uv_system(void)
 }
 extern int is_uv_system(void);
 extern int is_uv_hubbed(int uvtype);
-extern int is_uv_hubless(int uvtype);
 extern void uv_cpu_init(void);
 extern void uv_nmi_init(void);
 extern void uv_system_init(void);
@@ -44,7 +43,6 @@ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
 static inline bool is_early_uv_system(void)	{ return 0; }
 static inline int is_uv_system(void)	{ return 0; }
 static inline int is_uv_hubbed(int uv)	{ return 0; }
-static inline int is_uv_hubless(int uv) { return 0; }
 static inline void uv_cpu_init(void)	{ }
 static inline void uv_system_init(void)	{ }
 static inline const struct cpumask *
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 950cd1395d5d..60ca0afdeaf9 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -219,20 +219,6 @@ static inline struct uv_hub_info_s *uv_cpu_hub_info(int cpu)
 	return (struct uv_hub_info_s *)uv_cpu_info_per(cpu)->p_uv_hub_info;
 }
 
-#define	UV_HUB_INFO_VERSION	0x7150
-extern int uv_hub_info_version(void);
-static inline int uv_hub_info_check(int version)
-{
-	if (uv_hub_info_version() == version)
-		return 0;
-
-	pr_crit("UV: uv_hub_info version(%x) mismatch, expecting(%x)\n",
-		uv_hub_info_version(), version);
-
-	BUG();	/* Catastrophic - cannot continue on unknown UV system */
-}
-#define	_uv_hub_info_check()	uv_hub_info_check(UV_HUB_INFO_VERSION)
-
 /*
  * HUB revision ranges for each UV HUB architecture.
  * This is a software convention - NOT the hardware revision numbers in
@@ -244,51 +230,32 @@ static inline int uv_hub_info_check(int version)
 #define UV4_HUB_REVISION_BASE		7
 #define UV4A_HUB_REVISION_BASE		8	/* UV4 (fixed) rev 2 */
 
-/* WARNING: UVx_HUB_IS_SUPPORTED defines are deprecated and will be removed */
 static inline int is_uv1_hub(void)
 {
-#ifdef	UV1_HUB_IS_SUPPORTED
 	return is_uv_hubbed(uv(1));
-#else
-	return 0;
-#endif
 }
 
 static inline int is_uv2_hub(void)
 {
-#ifdef	UV2_HUB_IS_SUPPORTED
 	return is_uv_hubbed(uv(2));
-#else
-	return 0;
-#endif
 }
 
 static inline int is_uv3_hub(void)
 {
-#ifdef	UV3_HUB_IS_SUPPORTED
 	return is_uv_hubbed(uv(3));
-#else
-	return 0;
-#endif
 }
 
 /* First test "is UV4A", then "is UV4" */
 static inline int is_uv4a_hub(void)
 {
-#ifdef	UV4A_HUB_IS_SUPPORTED
 	if (is_uv_hubbed(uv(4)))
 		return (uv_hub_info->hub_revision == UV4A_HUB_REVISION_BASE);
-#endif
 	return 0;
 }
 
 static inline int is_uv4_hub(void)
 {
-#ifdef	UV4_HUB_IS_SUPPORTED
 	return is_uv_hubbed(uv(4));
-#else
-	return 0;
-#endif
 }
 
 static inline int is_uvx_hub(void)
@@ -692,7 +659,6 @@ static inline int uv_cpu_blade_processor_id(int cpu)
 {
 	return uv_cpu_info_per(cpu)->blade_cpu_id;
 }
-#define _uv_cpu_blade_processor_id 1	/* indicate function available */
 
 /* Blade number to Node number (UV1..UV4 is 1:1) */
 static inline int uv_blade_to_node(int blade)
@@ -856,26 +822,6 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 }
 
 extern unsigned int uv_apicid_hibits;
-static unsigned long uv_hub_ipi_value(int apicid, int vector, int mode)
-{
-	apicid |= uv_apicid_hibits;
-	return (1UL << UVH_IPI_INT_SEND_SHFT) |
-			((apicid) << UVH_IPI_INT_APIC_ID_SHFT) |
-			(mode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
-			(vector << UVH_IPI_INT_VECTOR_SHFT);
-}
-
-static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
-{
-	unsigned long val;
-	unsigned long dmode = dest_Fixed;
-
-	if (vector == NMI_VECTOR)
-		dmode = dest_NMI;
-
-	val = uv_hub_ipi_value(apicid, vector, dmode);
-	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
-}
 
 /*
  * Get the minimum revision number of the hub chips within the partition.
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 62c79e26a59a..9ee5ed6e8b34 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -99,13 +99,6 @@
 #define UV3_HUB_PART_NUMBER_X	0x4321
 #define UV4_HUB_PART_NUMBER	0x99a1
 
-/* Compat: Indicate which UV Hubs are supported. */
-#define UV1_HUB_IS_SUPPORTED	1
-#define UV2_HUB_IS_SUPPORTED	1
-#define UV3_HUB_IS_SUPPORTED	1
-#define UV4_HUB_IS_SUPPORTED	1
-#define UV4A_HUB_IS_SUPPORTED	1
-
 /* Error function to catch undefined references */
 extern unsigned long uv_undefined(char *str);
 
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
new file mode 100644
index 000000000000..75884d2cdec3
--- /dev/null
+++ b/arch/x86/include/asm/vermagic.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#ifdef CONFIG_X86_64
+/* X86_64 does not define MODULE_PROC_FAMILY */
+#elif defined CONFIG_M486SX
+#define MODULE_PROC_FAMILY "486SX "
+#elif defined CONFIG_M486
+#define MODULE_PROC_FAMILY "486 "
+#elif defined CONFIG_M586
+#define MODULE_PROC_FAMILY "586 "
+#elif defined CONFIG_M586TSC
+#define MODULE_PROC_FAMILY "586TSC "
+#elif defined CONFIG_M586MMX
+#define MODULE_PROC_FAMILY "586MMX "
+#elif defined CONFIG_MCORE2
+#define MODULE_PROC_FAMILY "CORE2 "
+#elif defined CONFIG_MATOM
+#define MODULE_PROC_FAMILY "ATOM "
+#elif defined CONFIG_M686
+#define MODULE_PROC_FAMILY "686 "
+#elif defined CONFIG_MPENTIUMII
+#define MODULE_PROC_FAMILY "PENTIUMII "
+#elif defined CONFIG_MPENTIUMIII
+#define MODULE_PROC_FAMILY "PENTIUMIII "
+#elif defined CONFIG_MPENTIUMM
+#define MODULE_PROC_FAMILY "PENTIUMM "
+#elif defined CONFIG_MPENTIUM4
+#define MODULE_PROC_FAMILY "PENTIUM4 "
+#elif defined CONFIG_MK6
+#define MODULE_PROC_FAMILY "K6 "
+#elif defined CONFIG_MK7
+#define MODULE_PROC_FAMILY "K7 "
+#elif defined CONFIG_MK8
+#define MODULE_PROC_FAMILY "K8 "
+#elif defined CONFIG_MELAN
+#define MODULE_PROC_FAMILY "ELAN "
+#elif defined CONFIG_MCRUSOE
+#define MODULE_PROC_FAMILY "CRUSOE "
+#elif defined CONFIG_MEFFICEON
+#define MODULE_PROC_FAMILY "EFFICEON "
+#elif defined CONFIG_MWINCHIPC6
+#define MODULE_PROC_FAMILY "WINCHIPC6 "
+#elif defined CONFIG_MWINCHIP3D
+#define MODULE_PROC_FAMILY "WINCHIP3D "
+#elif defined CONFIG_MCYRIXIII
+#define MODULE_PROC_FAMILY "CYRIXIII "
+#elif defined CONFIG_MVIAC3_2
+#define MODULE_PROC_FAMILY "VIAC3-2 "
+#elif defined CONFIG_MVIAC7
+#define MODULE_PROC_FAMILY "VIAC7 "
+#elif defined CONFIG_MGEODEGX1
+#define MODULE_PROC_FAMILY "GEODEGX1 "
+#elif defined CONFIG_MGEODE_LX
+#define MODULE_PROC_FAMILY "GEODE "
+#else
+#error unknown processor family
+#endif
+
+#ifdef CONFIG_X86_32
+# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
+#else
+# define MODULE_ARCH_VERMAGIC ""
+#endif
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h
index 196fdd02b8b1..be5e2e747f50 100644
--- a/arch/x86/include/uapi/asm/unistd.h
+++ b/arch/x86/include/uapi/asm/unistd.h
@@ -2,8 +2,15 @@
 #ifndef _UAPI_ASM_X86_UNISTD_H
 #define _UAPI_ASM_X86_UNISTD_H
 
-/* x32 syscall flag bit */
-#define __X32_SYSCALL_BIT	0x40000000UL
+/*
+ * x32 syscall flag bit.  Some user programs expect syscall NR macros
+ * and __X32_SYSCALL_BIT to have type int, even though syscall numbers
+ * are, for practical purposes, unsigned long.
+ *
+ * Fortunately, expressions like (nr & ~__X32_SYSCALL_BIT) do the right
+ * thing regardless.
+ */
+#define __X32_SYSCALL_BIT	0x40000000
 
 #ifndef __KERNEL__
 # ifdef __i386__
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index ba89cabe5fcf..2a7c3afa62e2 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -102,9 +102,7 @@ obj-$(CONFIG_KEXEC_FILE)	+= kexec-bzimage64.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
 obj-y				+= kprobes/
 obj-$(CONFIG_MODULES)		+= module.o
-ifeq ($(CONFIG_X86_32),y)
-obj-$(CONFIG_DOUBLEFAULT)	+= doublefault_32.o
-endif
+obj-$(CONFIG_X86_32)		+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_VM86)		+= vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index fe698f96617c..263eeaddb0aa 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -345,56 +345,3 @@ out_noapbt:
 	apb_timer_block_enabled = 0;
 	panic("failed to enable APB timer\n");
 }
-
-/* called before apb_timer_enable, use early map */
-unsigned long apbt_quick_calibrate(void)
-{
-	int i, scale;
-	u64 old, new;
-	u64 t1, t2;
-	unsigned long khz = 0;
-	u32 loop, shift;
-
-	apbt_set_mapping();
-	dw_apb_clocksource_start(clocksource_apbt);
-
-	/* check if the timer can count down, otherwise return */
-	old = dw_apb_clocksource_read(clocksource_apbt);
-	i = 10000;
-	while (--i) {
-		if (old != dw_apb_clocksource_read(clocksource_apbt))
-			break;
-	}
-	if (!i)
-		goto failed;
-
-	/* count 16 ms */
-	loop = (apbt_freq / 1000) << 4;
-
-	/* restart the timer to ensure it won't get to 0 in the calibration */
-	dw_apb_clocksource_start(clocksource_apbt);
-
-	old = dw_apb_clocksource_read(clocksource_apbt);
-	old += loop;
-
-	t1 = rdtsc();
-
-	do {
-		new = dw_apb_clocksource_read(clocksource_apbt);
-	} while (new < old);
-
-	t2 = rdtsc();
-
-	shift = 5;
-	if (unlikely(loop >> shift == 0)) {
-		printk(KERN_INFO
-		       "APBT TSC calibration failed, not enough resolution\n");
-		return 0;
-	}
-	scale = (int)div_u64((t2 - t1), loop >> shift);
-	khz = (scale * (apbt_freq / 1000)) >> shift;
-	printk(KERN_INFO "TSC freq calculated by APB timer is %lu khz\n", khz);
-	return khz;
-failed:
-	return 0;
-}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 81b9c63dae1b..4b1d31be50b4 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 		 * According to Intel, MFENCE can do the serialization here.
 		 */
 		asm volatile("mfence" : : : "memory");
-
-		printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
 		return;
 	}
 
@@ -546,46 +544,20 @@ static struct clock_event_device lapic_clockevent = {
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
-static u32 hsx_deadline_rev(void)
-{
-	switch (boot_cpu_data.x86_stepping) {
-	case 0x02: return 0x3a; /* EP */
-	case 0x04: return 0x0f; /* EX */
-	}
-
-	return ~0U;
-}
-
-static u32 bdx_deadline_rev(void)
-{
-	switch (boot_cpu_data.x86_stepping) {
-	case 0x02: return 0x00000011;
-	case 0x03: return 0x0700000e;
-	case 0x04: return 0x0f00000c;
-	case 0x05: return 0x0e000003;
-	}
-
-	return ~0U;
-}
+static const struct x86_cpu_id deadline_match[] __initconst = {
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x2, 0x2), 0x3a), /* EP */
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x4, 0x4), 0x0f), /* EX */
 
-static u32 skx_deadline_rev(void)
-{
-	switch (boot_cpu_data.x86_stepping) {
-	case 0x03: return 0x01000136;
-	case 0x04: return 0x02000014;
-	}
-
-	if (boot_cpu_data.x86_stepping > 4)
-		return 0;
+	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X,	0x0b000020),
 
-	return ~0U;
-}
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x2, 0x2), 0x00000011),
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x3, 0x3), 0x0700000e),
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x4, 0x4), 0x0f00000c),
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x5, 0x5), 0x0e000003),
 
-static const struct x86_cpu_id deadline_match[] = {
-	X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X,		&hsx_deadline_rev),
-	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X,	0x0b000020),
-	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D,	&bdx_deadline_rev),
-	X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_X,		&skx_deadline_rev),
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x3, 0x3), 0x01000136),
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x4, 0x4), 0x02000014),
+	X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x5, 0xf), 0),
 
 	X86_MATCH_INTEL_FAM6_MODEL( HASWELL,		0x22),
 	X86_MATCH_INTEL_FAM6_MODEL( HASWELL_L,		0x20),
@@ -603,34 +575,29 @@ static const struct x86_cpu_id deadline_match[] = {
 	{},
 };
 
-static void apic_check_deadline_errata(void)
+static __init bool apic_validate_deadline_timer(void)
 {
 	const struct x86_cpu_id *m;
 	u32 rev;
 
-	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) ||
-	    boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		return;
+	if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+		return false;
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return true;
 
 	m = x86_match_cpu(deadline_match);
 	if (!m)
-		return;
+		return true;
 
-	/*
-	 * Function pointers will have the MSB set due to address layout,
-	 * immediate revisions will not.
-	 */
-	if ((long)m->driver_data < 0)
-		rev = ((u32 (*)(void))(m->driver_data))();
-	else
-		rev = (u32)m->driver_data;
+	rev = (u32)m->driver_data;
 
 	if (boot_cpu_data.microcode >= rev)
-		return;
+		return true;
 
 	setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 	pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; "
 	       "please update microcode to version: 0x%x (or later)\n", rev);
+	return false;
 }
 
 /*
@@ -2092,7 +2059,8 @@ void __init init_apic_mappings(void)
 {
 	unsigned int new_apicid;
 
-	apic_check_deadline_errata();
+	if (apic_validate_deadline_timer())
+		pr_debug("TSC deadline timer available\n");
 
 	if (x2apic_mode) {
 		boot_cpu_physical_apicid = read_apic_id();
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 913c88617848..ce61e3e7d399 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -154,19 +154,6 @@ static inline bool mp_is_legacy_irq(int irq)
 	return irq >= 0 && irq < nr_legacy_irqs();
 }
 
-/*
- * Initialize all legacy IRQs and all pins on the first IOAPIC
- * if we have legacy interrupt controller. Kernel boot option "pirq="
- * may rely on non-legacy pins on the first IOAPIC.
- */
-static inline int mp_init_irq_at_boot(int ioapic, int irq)
-{
-	if (!nr_legacy_irqs())
-		return 0;
-
-	return ioapic == 0 || mp_is_legacy_irq(irq);
-}
-
 static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic)
 {
 	return ioapics[ioapic].irqdomain;
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index ad53b2abc859..69e70ed0f5e6 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -30,8 +30,6 @@ static enum uv_system_type	uv_system_type;
 static int			uv_hubbed_system;
 static int			uv_hubless_system;
 static u64			gru_start_paddr, gru_end_paddr;
-static u64			gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr;
-static u64			gru_dist_lmask, gru_dist_umask;
 static union uvh_apicid		uvh_apicid;
 
 /* Unpack OEM/TABLE ID's to be NULL terminated strings */
@@ -48,11 +46,9 @@ static struct {
 	unsigned int gnode_shift;
 } uv_cpuid;
 
-int uv_min_hub_revision_id;
-EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
+static int uv_min_hub_revision_id;
 
 unsigned int uv_apicid_hibits;
-EXPORT_SYMBOL_GPL(uv_apicid_hibits);
 
 static struct apic apic_x2apic_uv_x;
 static struct uv_hub_info_s uv_hub_info_node0;
@@ -85,20 +81,7 @@ static unsigned long __init uv_early_read_mmr(unsigned long addr)
 
 static inline bool is_GRU_range(u64 start, u64 end)
 {
-	if (gru_dist_base) {
-		u64 su = start & gru_dist_umask; /* Upper (incl pnode) bits */
-		u64 sl = start & gru_dist_lmask; /* Base offset bits */
-		u64 eu = end & gru_dist_umask;
-		u64 el = end & gru_dist_lmask;
-
-		/* Must reside completely within a single GRU range: */
-		return (sl == gru_dist_base && el == gru_dist_base &&
-			su >= gru_first_node_paddr &&
-			su <= gru_last_node_paddr &&
-			eu == su);
-	} else {
-		return start >= gru_start_paddr && end <= gru_end_paddr;
-	}
+	return start >= gru_start_paddr && end <= gru_end_paddr;
 }
 
 static bool uv_is_untracked_pat_range(u64 start, u64 end)
@@ -385,11 +368,10 @@ int is_uv_hubbed(int uvtype)
 }
 EXPORT_SYMBOL_GPL(is_uv_hubbed);
 
-int is_uv_hubless(int uvtype)
+static int is_uv_hubless(int uvtype)
 {
 	return (uv_hubless_system & uvtype);
 }
-EXPORT_SYMBOL_GPL(is_uv_hubless);
 
 void **__uv_hub_info_list;
 EXPORT_SYMBOL_GPL(__uv_hub_info_list);
@@ -417,12 +399,6 @@ static __initdata struct uv_gam_range_s		*_gr_table;
 
 #define	SOCK_EMPTY	((unsigned short)~0)
 
-extern int uv_hub_info_version(void)
-{
-	return UV_HUB_INFO_VERSION;
-}
-EXPORT_SYMBOL(uv_hub_info_version);
-
 /* Default UV memory block size is 2GB */
 static unsigned long mem_block_size __initdata = (2UL << 30);
 
@@ -590,12 +566,21 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 
 static void uv_send_IPI_one(int cpu, int vector)
 {
-	unsigned long apicid;
-	int pnode;
+	unsigned long apicid = per_cpu(x86_cpu_to_apicid, cpu);
+	int pnode = uv_apicid_to_pnode(apicid);
+	unsigned long dmode, val;
+
+	if (vector == NMI_VECTOR)
+		dmode = dest_NMI;
+	else
+		dmode = dest_Fixed;
+
+	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
+		((apicid | uv_apicid_hibits) << UVH_IPI_INT_APIC_ID_SHFT) |
+		(dmode << UVH_IPI_INT_DELIVERY_MODE_SHFT) |
+		(vector << UVH_IPI_INT_VECTOR_SHFT);
 
-	apicid = per_cpu(x86_cpu_to_apicid, cpu);
-	pnode = uv_apicid_to_pnode(apicid);
-	uv_hub_send_ipi(pnode, apicid, vector);
+	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 }
 
 static void uv_send_IPI_mask(const struct cpumask *mask, int vector)
@@ -797,42 +782,6 @@ static __init void map_high(char *id, unsigned long base, int pshift, int bshift
 		init_extra_mapping_wb(paddr, bytes);
 }
 
-static __init void map_gru_distributed(unsigned long c)
-{
-	union uvh_rh_gam_gru_overlay_config_mmr_u gru;
-	u64 paddr;
-	unsigned long bytes;
-	int nid;
-
-	gru.v = c;
-
-	/* Only base bits 42:28 relevant in dist mode */
-	gru_dist_base = gru.v & 0x000007fff0000000UL;
-	if (!gru_dist_base) {
-		pr_info("UV: Map GRU_DIST base address NULL\n");
-		return;
-	}
-
-	bytes = 1UL << UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
-	gru_dist_lmask = ((1UL << uv_hub_info->m_val) - 1) & ~(bytes - 1);
-	gru_dist_umask = ~((1UL << uv_hub_info->m_val) - 1);
-	gru_dist_base &= gru_dist_lmask; /* Clear bits above M */
-
-	for_each_online_node(nid) {
-		paddr = ((u64)uv_node_to_pnode(nid) << uv_hub_info->m_val) |
-				gru_dist_base;
-		init_extra_mapping_wb(paddr, bytes);
-		gru_first_node_paddr = min(paddr, gru_first_node_paddr);
-		gru_last_node_paddr = max(paddr, gru_last_node_paddr);
-	}
-
-	/* Save upper (63:M) bits of address only for is_GRU_range */
-	gru_first_node_paddr &= gru_dist_umask;
-	gru_last_node_paddr &= gru_dist_umask;
-
-	pr_debug("UV: Map GRU_DIST base 0x%016llx  0x%016llx - 0x%016llx\n", gru_dist_base, gru_first_node_paddr, gru_last_node_paddr);
-}
-
 static __init void map_gru_high(int max_pnode)
 {
 	union uvh_rh_gam_gru_overlay_config_mmr_u gru;
@@ -846,12 +795,6 @@ static __init void map_gru_high(int max_pnode)
 		return;
 	}
 
-	/* Only UV3 has distributed GRU mode */
-	if (is_uv3_hub() && gru.s3.mode) {
-		map_gru_distributed(gru.v);
-		return;
-	}
-
 	base = (gru.v & mask) >> shift;
 	map_high("GRU", base, shift, shift, max_pnode, map_wb);
 	gru_start_paddr = ((u64)base << shift);
diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c
index e1efe44ebefc..83d9cad4e68b 100644
--- a/arch/x86/kernel/audit_64.c
+++ b/arch/x86/kernel/audit_64.c
@@ -3,6 +3,7 @@
 #include <linux/types.h>
 #include <linux/audit.h>
 #include <asm/unistd.h>
+#include <asm/audit.h>
 
 static unsigned dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
@@ -41,7 +42,6 @@ int audit_classify_arch(int arch)
 int audit_classify_syscall(int abi, unsigned syscall)
 {
 #ifdef CONFIG_IA32_EMULATION
-	extern int ia32_classify_syscall(unsigned);
 	if (abi == AUDIT_ARCH_I386)
 		return ia32_classify_syscall(syscall);
 #endif
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 547ad7bbf0e0..d4806eac9325 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -18,6 +18,7 @@
 #include <asm/pci-direct.h>
 #include <asm/delay.h>
 #include <asm/debugreg.h>
+#include <asm/resctrl.h>
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
@@ -597,6 +598,8 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 			x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
 		}
 	}
+
+	resctrl_cpu_detect(c);
 }
 
 static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
@@ -1142,8 +1145,7 @@ static const int amd_erratum_383[] =
 
 /* #1054: Instructions Retired Performance Counter May Be Inaccurate */
 static const int amd_erratum_1054[] =
-	AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
-
+	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
 
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index bed0cb83fe24..d07809286b95 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -854,30 +854,6 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	}
 }
 
-static void init_cqm(struct cpuinfo_x86 *c)
-{
-	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
-		c->x86_cache_max_rmid  = -1;
-		c->x86_cache_occ_scale = -1;
-		return;
-	}
-
-	/* will be overridden if occupancy monitoring exists */
-	c->x86_cache_max_rmid = cpuid_ebx(0xf);
-
-	if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
-	    cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
-	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
-		u32 eax, ebx, ecx, edx;
-
-		/* QoS sub-leaf, EAX=0Fh, ECX=1 */
-		cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
-
-		c->x86_cache_max_rmid  = ecx;
-		c->x86_cache_occ_scale = ebx;
-	}
-}
-
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
@@ -945,7 +921,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
-	init_cqm(c);
 
 	/*
 	 * Clear/Set all flags overridden by options, after probe.
@@ -1377,20 +1352,6 @@ static void generic_identify(struct cpuinfo_x86 *c)
 #endif
 }
 
-static void x86_init_cache_qos(struct cpuinfo_x86 *c)
-{
-	/*
-	 * The heavy lifting of max_rmid and cache_occ_scale are handled
-	 * in get_cpu_cap().  Here we just set the max_rmid for the boot_cpu
-	 * in case CQM bits really aren't there in this CPU.
-	 */
-	if (c != &boot_cpu_data) {
-		boot_cpu_data.x86_cache_max_rmid =
-			min(boot_cpu_data.x86_cache_max_rmid,
-			    c->x86_cache_max_rmid);
-	}
-}
-
 /*
  * Validate that ACPI/mptables have the same information about the
  * effective APIC id and update the package map.
@@ -1503,7 +1464,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 #endif
 
 	x86_init_rdrand(c);
-	x86_init_cache_qos(c);
 	setup_pku(c);
 
 	/*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index bf08d4508ecb..166d7c355896 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -22,6 +22,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cmdline.h>
 #include <asm/traps.h>
+#include <asm/resctrl.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -322,6 +323,11 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		detect_ht_early(c);
 }
 
+static void bsp_init_intel(struct cpuinfo_x86 *c)
+{
+	resctrl_cpu_detect(c);
+}
+
 #ifdef CONFIG_X86_32
 /*
  *	Early probe support logic for ppro memory erratum #50
@@ -961,6 +967,7 @@ static const struct cpu_dev intel_cpu_dev = {
 #endif
 	.c_detect_tlb	= intel_detect_tlb,
 	.c_early_init   = early_init_intel,
+	.c_bsp_init	= bsp_init_intel,
 	.c_init		= init_intel,
 	.c_x86_vendor	= X86_VENDOR_INTEL,
 };
@@ -1119,35 +1126,53 @@ void switch_to_sld(unsigned long tifn)
 	sld_update_msr(!(tifn & _TIF_SLD));
 }
 
-#define SPLIT_LOCK_CPU(model) {X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY}
-
 /*
- * The following processors have the split lock detection feature. But
- * since they don't have the IA32_CORE_CAPABILITIES MSR, the feature cannot
- * be enumerated. Enable it by family and model matching on these
- * processors.
+ * Bits in the IA32_CORE_CAPABILITIES are not architectural, so they should
+ * only be trusted if it is confirmed that a CPU model implements a
+ * specific feature at a particular bit position.
+ *
+ * The possible driver data field values:
+ *
+ * - 0: CPU models that are known to have the per-core split-lock detection
+ *	feature even though they do not enumerate IA32_CORE_CAPABILITIES.
+ *
+ * - 1: CPU models which may enumerate IA32_CORE_CAPABILITIES and if so use
+ *      bit 5 to enumerate the per-core split-lock detection feature.
  */
 static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
-	SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_X),
-	SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_L),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		0),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		0),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	1),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	1),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	1),
 	{}
 };
 
 void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
 {
-	u64 ia32_core_caps = 0;
+	const struct x86_cpu_id *m;
+	u64 ia32_core_caps;
 
-	if (c->x86_vendor != X86_VENDOR_INTEL)
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return;
-	if (cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) {
-		/* Enumerate features reported in IA32_CORE_CAPABILITIES MSR. */
+
+	m = x86_match_cpu(split_lock_cpu_ids);
+	if (!m)
+		return;
+
+	switch (m->driver_data) {
+	case 0:
+		break;
+	case 1:
+		if (!cpu_has(c, X86_FEATURE_CORE_CAPABILITIES))
+			return;
 		rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps);
-	} else if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
-		/* Enumerate split lock detection by family and model. */
-		if (x86_match_cpu(split_lock_cpu_ids))
-			ia32_core_caps |= MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT;
+		if (!(ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT))
+			return;
+		break;
+	default:
+		return;
 	}
 
-	if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)
-		split_lock_setup();
+	split_lock_setup();
 }
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index d3482eb43ff3..ad6776081e60 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -39,13 +39,18 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 	const struct x86_cpu_id *m;
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	for (m = match; m->vendor | m->family | m->model | m->feature; m++) {
+	for (m = match;
+	     m->vendor | m->family | m->model | m->steppings | m->feature;
+	     m++) {
 		if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor)
 			continue;
 		if (m->family != X86_FAMILY_ANY && c->x86 != m->family)
 			continue;
 		if (m->model != X86_MODEL_ANY && c->x86_model != m->model)
 			continue;
+		if (m->steppings != X86_STEPPING_ANY &&
+		    !(BIT(c->x86_stepping) & m->steppings))
+			continue;
 		if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature))
 			continue;
 		return m;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 54165f3569e8..e9265e2f28c9 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -42,6 +42,8 @@
 #include <linux/export.h>
 #include <linux/jump_label.h>
 #include <linux/set_memory.h>
+#include <linux/task_work.h>
+#include <linux/hardirq.h>
 
 #include <asm/intel-family.h>
 #include <asm/processor.h>
@@ -1086,23 +1088,6 @@ static void mce_clear_state(unsigned long *toclear)
 	}
 }
 
-static int do_memory_failure(struct mce *m)
-{
-	int flags = MF_ACTION_REQUIRED;
-	int ret;
-
-	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
-	if (!(m->mcgstatus & MCG_STATUS_RIPV))
-		flags |= MF_MUST_KILL;
-	ret = memory_failure(m->addr >> PAGE_SHIFT, flags);
-	if (ret)
-		pr_err("Memory error not recovered");
-	else
-		set_mce_nospec(m->addr >> PAGE_SHIFT);
-	return ret;
-}
-
-
 /*
  * Cases where we avoid rendezvous handler timeout:
  * 1) If this CPU is offline.
@@ -1204,6 +1189,29 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 	*m = *final;
 }
 
+static void kill_me_now(struct callback_head *ch)
+{
+	force_sig(SIGBUS);
+}
+
+static void kill_me_maybe(struct callback_head *cb)
+{
+	struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me);
+	int flags = MF_ACTION_REQUIRED;
+
+	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
+	if (!(p->mce_status & MCG_STATUS_RIPV))
+		flags |= MF_MUST_KILL;
+
+	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) {
+		set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
+		return;
+	}
+
+	pr_err("Memory error not recovered");
+	kill_me_now(cb);
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1222,7 +1230,7 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
  * backing the user stack, tracing that reads the user stack will cause
  * potentially infinite recursion.
  */
-void notrace do_machine_check(struct pt_regs *regs, long error_code)
+void noinstr do_machine_check(struct pt_regs *regs, long error_code)
 {
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
@@ -1259,7 +1267,7 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code)
 	if (__mc_check_crashing_cpu(cpu))
 		return;
 
-	ist_enter(regs);
+	nmi_enter();
 
 	this_cpu_inc(mce_exception_count);
 
@@ -1352,23 +1360,24 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code)
 
 	/* Fault was in user mode and we need to take some action */
 	if ((m.cs & 3) == 3) {
-		ist_begin_non_atomic(regs);
-		local_irq_enable();
-
-		if (kill_it || do_memory_failure(&m))
-			force_sig(SIGBUS);
-		local_irq_disable();
-		ist_end_non_atomic();
+		/* If this triggers there is no way to recover. Die hard. */
+		BUG_ON(!on_thread_stack() || !user_mode(regs));
+
+		current->mce_addr = m.addr;
+		current->mce_status = m.mcgstatus;
+		current->mce_kill_me.func = kill_me_maybe;
+		if (kill_it)
+			current->mce_kill_me.func = kill_me_now;
+		task_work_add(current, &current->mce_kill_me, true);
 	} else {
 		if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0))
 			mce_panic("Failed kernel mode recovery", &m, msg);
 	}
 
 out_ist:
-	ist_exit(regs);
+	nmi_exit();
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
-NOKPROBE_SYMBOL(do_machine_check);
 
 #ifndef CONFIG_MEMORY_FAILURE
 int memory_failure(unsigned long pfn, int flags)
diff --git a/arch/x86/kernel/cpu/mce/p5.c b/arch/x86/kernel/cpu/mce/p5.c
index 4ae6df556526..5ee94aa1b766 100644
--- a/arch/x86/kernel/cpu/mce/p5.c
+++ b/arch/x86/kernel/cpu/mce/p5.c
@@ -7,6 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/smp.h>
+#include <linux/hardirq.h>
 
 #include <asm/processor.h>
 #include <asm/traps.h>
@@ -24,7 +25,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 {
 	u32 loaddr, hi, lotype;
 
-	ist_enter(regs);
+	nmi_enter();
 
 	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
 	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
@@ -39,7 +40,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs);
+	nmi_exit();
 }
 
 /* Set up machine check reporting for processors with Intel style MCE: */
diff --git a/arch/x86/kernel/cpu/mce/winchip.c b/arch/x86/kernel/cpu/mce/winchip.c
index a30ea13cccc2..b3938c195365 100644
--- a/arch/x86/kernel/cpu/mce/winchip.c
+++ b/arch/x86/kernel/cpu/mce/winchip.c
@@ -6,6 +6,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/hardirq.h>
 
 #include <asm/processor.h>
 #include <asm/traps.h>
@@ -18,12 +19,12 @@
 /* Machine check handler for WinChip C6: */
 static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
-	ist_enter(regs);
+	nmi_enter();
 
 	pr_emerg("CPU0: Machine Check Exception.\n");
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
-	ist_exit(regs);
+	nmi_exit();
 }
 
 /* Set up machine check reporting on the Winchip C6 series */
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 7019d4b2df0c..baec68b7e010 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -545,8 +545,7 @@ static int __wait_for_cpus(atomic_t *t, long long timeout)
 /*
  * Returns:
  * < 0 - on error
- *   0 - no update done
- *   1 - microcode was updated
+ *   0 - success (no update done or microcode was updated)
  */
 static int __reload_late(void *info)
 {
@@ -573,11 +572,11 @@ static int __reload_late(void *info)
 	else
 		goto wait_for_siblings;
 
-	if (err > UCODE_NFOUND) {
-		pr_warn("Error reloading microcode on CPU %d\n", cpu);
+	if (err >= UCODE_NFOUND) {
+		if (err == UCODE_ERROR)
+			pr_warn("Error reloading microcode on CPU %d\n", cpu);
+
 		ret = -1;
-	} else if (err == UCODE_UPDATED || err == UCODE_OK) {
-		ret = 1;
 	}
 
 wait_for_siblings:
@@ -608,7 +607,7 @@ static int microcode_reload_late(void)
 	atomic_set(&late_cpus_out, 0);
 
 	ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
-	if (ret > 0)
+	if (ret == 0)
 		microcode_check();
 
 	pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode);
@@ -649,7 +648,7 @@ static ssize_t reload_store(struct device *dev,
 put:
 	put_online_cpus();
 
-	if (ret >= 0)
+	if (ret == 0)
 		ret = size;
 
 	return ret;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index caa032ce3fe3..ebf34c7bc8bc 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -227,8 +227,8 @@ static void __init ms_hyperv_init_platform(void)
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
-	pr_info("Hyper-V: features 0x%x, hints 0x%x\n",
-		ms_hyperv.features, ms_hyperv.hints);
+	pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n",
+		ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features);
 
 	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
 	ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -263,6 +263,16 @@ static void __init ms_hyperv_init_platform(void)
 			cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
 	}
 
+	/*
+	 * Hyper-V expects to get crash register data or kmsg when
+	 * crash enlightment is available and system crashes. Set
+	 * crash_kexec_post_notifiers to be true to make sure that
+	 * calling crash enlightment interface before running kdump
+	 * kernel.
+	 */
+	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
+		crash_kexec_post_notifiers = true;
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 9556930cd8c1..a5ee607a3b89 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -63,6 +63,10 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BPU_PERFCTR0;
 		}
+		fallthrough;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		return msr - MSR_ARCH_PERFMON_PERFCTR0;
 	}
 	return 0;
 }
@@ -92,6 +96,10 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BSU_ESCR0;
 		}
+		fallthrough;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		return msr - MSR_ARCH_PERFMON_EVENTSEL0;
 	}
 	return 0;
 
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 89049b343c7a..12f967c6b603 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,7 +22,7 @@
 #include <linux/cpuhotplug.h>
 
 #include <asm/intel-family.h>
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include "internal.h"
 
 /* Mutex to protect rdtgroup access. */
@@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	d->id = id;
 	cpumask_set_cpu(cpu, &d->cpu_mask);
 
+	rdt_domain_reconfigure_cdp(r);
+
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
 		kfree(d);
 		return;
@@ -956,6 +958,36 @@ static __init void rdt_init_res_defs(void)
 
 static enum cpuhp_state rdt_online;
 
+/* Runs once on the BSP during boot. */
+void resctrl_cpu_detect(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+		c->x86_cache_max_rmid  = -1;
+		c->x86_cache_occ_scale = -1;
+		c->x86_cache_mbm_width_offset = -1;
+		return;
+	}
+
+	/* will be overridden if occupancy monitoring exists */
+	c->x86_cache_max_rmid = cpuid_ebx(0xf);
+
+	if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+		u32 eax, ebx, ecx, edx;
+
+		/* QoS sub-leaf, EAX=0Fh, ECX=1 */
+		cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+
+		c->x86_cache_max_rmid  = ecx;
+		c->x86_cache_occ_scale = ebx;
+		if (c->x86_vendor == X86_VENDOR_INTEL)
+			c->x86_cache_mbm_width_offset = eax & 0xff;
+		else
+			c->x86_cache_mbm_width_offset = -1;
+	}
+}
+
 static int __init resctrl_late_init(void)
 {
 	struct rdt_resource *r;
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 055c8613b531..934c8fb8a64a 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -495,14 +495,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 	return ret;
 }
 
-void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
-		    struct rdtgroup *rdtgrp, int evtid, int first)
+void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
+		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    int evtid, int first)
 {
 	/*
 	 * setup the parameters to send to the IPI to read the data.
 	 */
 	rr->rgrp = rdtgrp;
 	rr->evtid = evtid;
+	rr->r = r;
 	rr->d = d;
 	rr->val = 0;
 	rr->first = first;
@@ -539,7 +541,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		goto out;
 	}
 
-	mon_event_read(&rr, d, rdtgrp, evtid, false);
+	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
 	if (rr.val & RMID_VAL_ERROR)
 		seq_puts(m, "Error\n");
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 181c992f448c..f20a47d120b1 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -31,7 +31,7 @@
 
 #define CQM_LIMBOCHECK_INTERVAL	1000
 
-#define MBM_CNTR_WIDTH			24
+#define MBM_CNTR_WIDTH_BASE		24
 #define MBM_OVERFLOW_INTERVAL		1000
 #define MAX_MBA_BW			100u
 #define MBA_IS_LINEAR			0x4
@@ -40,6 +40,12 @@
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
+/*
+ * With the above fields in use 62 bits remain in MSR_IA32_QM_CTR for
+ * data to be returned. The counter width is discovered from the hardware
+ * as an offset from MBM_CNTR_WIDTH_BASE.
+ */
+#define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE)
 
 
 struct rdt_fs_context {
@@ -87,6 +93,7 @@ union mon_data_bits {
 
 struct rmid_read {
 	struct rdtgroup		*rgrp;
+	struct rdt_resource	*r;
 	struct rdt_domain	*d;
 	int			evtid;
 	bool			first;
@@ -460,6 +467,7 @@ struct rdt_resource {
 	struct list_head	evt_list;
 	int			num_rmid;
 	unsigned int		mon_scale;
+	unsigned int		mbm_width;
 	unsigned long		fflags;
 };
 
@@ -587,8 +595,9 @@ void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 				    unsigned int dom_id);
 void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 				    struct rdt_domain *d);
-void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
-		    struct rdtgroup *rdtgrp, int evtid, int first);
+void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
+		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
+		    int evtid, int first);
 void mbm_setup_overflow_handler(struct rdt_domain *dom,
 				unsigned long delay_ms);
 void mbm_handle_overflow(struct work_struct *work);
@@ -601,5 +610,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
 bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 773124b0e18a..837d7d012b7b 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -214,9 +214,9 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr)
+static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 {
-	u64 shift = 64 - MBM_CNTR_WIDTH, chunks;
+	u64 shift = 64 - width, chunks;
 
 	chunks = (cur_msr << shift) - (prev_msr << shift);
 	return chunks >>= shift;
@@ -256,7 +256,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 		return 0;
 	}
 
-	chunks = mbm_overflow_count(m->prev_msr, tval);
+	chunks = mbm_overflow_count(m->prev_msr, tval, rr->r->mbm_width);
 	m->chunks += chunks;
 	m->prev_msr = tval;
 
@@ -278,7 +278,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
 		return;
 
-	chunks = mbm_overflow_count(m->prev_bw_msr, tval);
+	chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
 	m->chunks_bw += chunks;
 	m->chunks = m->chunks_bw;
 	cur_bw = (chunks * r->mon_scale) >> 20;
@@ -433,11 +433,12 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
 	}
 }
 
-static void mbm_update(struct rdt_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 {
 	struct rmid_read rr;
 
 	rr.first = false;
+	rr.r = r;
 	rr.d = d;
 
 	/*
@@ -510,6 +511,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	struct rdtgroup *prgrp, *crgrp;
 	int cpu = smp_processor_id();
 	struct list_head *head;
+	struct rdt_resource *r;
 	struct rdt_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
@@ -517,16 +519,18 @@ void mbm_handle_overflow(struct work_struct *work)
 	if (!static_branch_likely(&rdt_mon_enable_key))
 		goto out_unlock;
 
-	d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]);
+	r = &rdt_resources_all[RDT_RESOURCE_L3];
+
+	d = get_domain_from_cpu(cpu, r);
 	if (!d)
 		goto out_unlock;
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mbm_update(d, prgrp->mon.rmid);
+		mbm_update(r, d, prgrp->mon.rmid);
 
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
-			mbm_update(d, crgrp->mon.rmid);
+			mbm_update(r, d, crgrp->mon.rmid);
 
 		if (is_mba_sc(NULL))
 			update_mba_bw(prgrp, d);
@@ -614,11 +618,18 @@ static void l3_mon_evt_init(struct rdt_resource *r)
 
 int rdt_get_mon_l3_config(struct rdt_resource *r)
 {
+	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	unsigned int cl_size = boot_cpu_data.x86_cache_size;
 	int ret;
 
 	r->mon_scale = boot_cpu_data.x86_cache_occ_scale;
 	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+	r->mbm_width = MBM_CNTR_WIDTH_BASE;
+
+	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
+		r->mbm_width += mbm_offset;
+	else if (mbm_offset > MBM_CNTR_WIDTH_OFFSET_MAX)
+		pr_warn("Ignoring impossible MBM counter offset\n");
 
 	/*
 	 * A reasonable upper limit on the max threshold is the number
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index d7623e1b927d..4bd28b388a1a 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -24,7 +24,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/intel-family.h>
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include <asm/perf_event.h>
 
 #include "../../events/perf_event.h" /* For X86_CONFIG() */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 064e9ef44cd6..d7cb5ab0d1f0 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -29,7 +29,7 @@
 
 #include <uapi/linux/magic.h>
 
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include "internal.h"
 
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
@@ -1859,6 +1859,19 @@ static int set_cache_qos_cfg(int level, bool enable)
 	return 0;
 }
 
+/* Restore the qos cfg state when a domain comes online */
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
+{
+	if (!r->alloc_capable)
+		return;
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA])
+		l2_qos_cfg_update(&r->alloc_enabled);
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA])
+		l3_qos_cfg_update(&r->alloc_enabled);
+}
+
 /*
  * Enable or disable the MBA software controller
  * which helps user specify bandwidth in MBps.
@@ -2459,7 +2472,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 			goto out_destroy;
 
 		if (is_mbm_event(mevt->evtid))
-			mon_event_read(&rr, d, prgrp, mevt->evtid, true);
+			mon_event_read(&rr, r, d, prgrp, mevt->evtid, true);
 	}
 	kernfs_activate(kn);
 	return 0;
@@ -3072,7 +3085,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	 * If the rdtgroup is a mon group and parent directory
 	 * is a valid "mon_groups" directory, remove the mon group.
 	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
+	    rdtgrp != &rdtgroup_default) {
 		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
 			ret = rdtgroup_ctrl_remove(kn, rdtgrp);
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 8e3a8fedfa4d..722fd712e1cf 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -87,7 +87,6 @@ static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 
 static bool in_doublefault_stack(unsigned long *stack, struct stack_info *info)
 {
-#ifdef CONFIG_DOUBLEFAULT
 	struct cpu_entry_area *cea = get_cpu_entry_area(raw_smp_processor_id());
 	struct doublefault_stack *ss = &cea->doublefault_stack;
 
@@ -103,9 +102,6 @@ static bool in_doublefault_stack(unsigned long *stack, struct stack_info *info)
 	info->next_sp	= (unsigned long *)this_cpu_read(cpu_tss_rw.x86_tss.sp);
 
 	return true;
-#else
-	return false;
-#endif
 }
 
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 87b97897a881..460ae7f66818 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -183,7 +183,8 @@ recursion_check:
 	 */
 	if (visit_mask) {
 		if (*visit_mask & (1UL << info->type)) {
-			printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type);
+			if (task == current)
+				printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type);
 			goto unknown;
 		}
 		*visit_mask |= 1UL << info->type;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index c5399e80c59c..4d13c57f370a 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -910,14 +910,6 @@ static int __init parse_memmap_one(char *p)
 		return -EINVAL;
 
 	if (!strncmp(p, "exactmap", 8)) {
-#ifdef CONFIG_CRASH_DUMP
-		/*
-		 * If we are doing a crash dump, we still need to know
-		 * the real memory size before the original memory map is
-		 * reset.
-		 */
-		saved_max_pfn = e820__end_of_ram_pfn();
-#endif
 		e820_table->nr_entries = 0;
 		userdef = 1;
 		return 0;
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 9b33904251a9..93fbdff2974f 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -15,12 +15,9 @@
 #include <xen/hvc-console.h>
 #include <asm/pci-direct.h>
 #include <asm/fixmap.h>
-#include <asm/intel-mid.h>
 #include <asm/pgtable.h>
 #include <linux/usb/ehci_def.h>
 #include <linux/usb/xhci-dbgp.h>
-#include <linux/efi.h>
-#include <asm/efi.h>
 #include <asm/pci_x86.h>
 
 /* Simple VGA output */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 12c70840980e..06c818967bb6 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -291,15 +291,13 @@ void fpu__drop(struct fpu *fpu)
 }
 
 /*
- * Clear FPU registers by setting them up from
- * the init fpstate:
+ * Clear FPU registers by setting them up from the init fpstate.
+ * Caller must do fpregs_[un]lock() around it.
  */
-static inline void copy_init_fpstate_to_fpregs(void)
+static inline void copy_init_fpstate_to_fpregs(u64 features_mask)
 {
-	fpregs_lock();
-
 	if (use_xsave())
-		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+		copy_kernel_to_xregs(&init_fpstate.xsave, features_mask);
 	else if (static_cpu_has(X86_FEATURE_FXSR))
 		copy_kernel_to_fxregs(&init_fpstate.fxsave);
 	else
@@ -307,9 +305,6 @@ static inline void copy_init_fpstate_to_fpregs(void)
 
 	if (boot_cpu_has(X86_FEATURE_OSPKE))
 		copy_init_pkru_to_fpregs();
-
-	fpregs_mark_activate();
-	fpregs_unlock();
 }
 
 /*
@@ -318,18 +313,40 @@ static inline void copy_init_fpstate_to_fpregs(void)
  * Called by sys_execve(), by the signal handler code and by various
  * error paths.
  */
-void fpu__clear(struct fpu *fpu)
+static void fpu__clear(struct fpu *fpu, bool user_only)
 {
-	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
+	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	fpu__drop(fpu);
+	if (!static_cpu_has(X86_FEATURE_FPU)) {
+		fpu__drop(fpu);
+		fpu__initialize(fpu);
+		return;
+	}
 
-	/*
-	 * Make sure fpstate is cleared and initialized.
-	 */
-	fpu__initialize(fpu);
-	if (static_cpu_has(X86_FEATURE_FPU))
-		copy_init_fpstate_to_fpregs();
+	fpregs_lock();
+
+	if (user_only) {
+		if (!fpregs_state_valid(fpu, smp_processor_id()) &&
+		    xfeatures_mask_supervisor())
+			copy_kernel_to_xregs(&fpu->state.xsave,
+					     xfeatures_mask_supervisor());
+		copy_init_fpstate_to_fpregs(xfeatures_mask_user());
+	} else {
+		copy_init_fpstate_to_fpregs(xfeatures_mask_all);
+	}
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+}
+
+void fpu__clear_user_states(struct fpu *fpu)
+{
+	fpu__clear(fpu, true);
+}
+
+void fpu__clear_all(struct fpu *fpu)
+{
+	fpu__clear(fpu, false);
 }
 
 /*
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 6ce7e0a23268..61ddc3a5e5c2 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -224,7 +224,8 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  */
 u64 __init fpu__get_supported_xfeatures_mask(void)
 {
-	return XCNTXT_MASK;
+	return XFEATURE_MASK_USER_SUPPORTED |
+	       XFEATURE_MASK_SUPERVISOR_SUPPORTED;
 }
 
 /* Legacy code to initialize eager fpu mode. */
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index d652b939ccfb..bd1d0649f8ce 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -139,7 +139,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 	} else {
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
 		if (!ret)
-			ret = validate_xstate_header(&xsave->header);
+			ret = validate_user_xstate_header(&xsave->header);
 	}
 
 	/*
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 400a05e1c1c5..9393a445d73c 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -211,9 +211,9 @@ retry:
 }
 
 static inline void
-sanitize_restored_xstate(union fpregs_state *state,
-			 struct user_i387_ia32_struct *ia32_env,
-			 u64 xfeatures, int fx_only)
+sanitize_restored_user_xstate(union fpregs_state *state,
+			      struct user_i387_ia32_struct *ia32_env,
+			      u64 user_xfeatures, int fx_only)
 {
 	struct xregs_state *xsave = &state->xsave;
 	struct xstate_header *header = &xsave->header;
@@ -226,13 +226,22 @@ sanitize_restored_xstate(union fpregs_state *state,
 		 */
 
 		/*
-		 * Init the state that is not present in the memory
-		 * layout and not enabled by the OS.
+		 * 'user_xfeatures' might have bits clear which are
+		 * set in header->xfeatures. This represents features that
+		 * were in init state prior to a signal delivery, and need
+		 * to be reset back to the init state.  Clear any user
+		 * feature bits which are set in the kernel buffer to get
+		 * them back to the init state.
+		 *
+		 * Supervisor state is unchanged by input from userspace.
+		 * Ensure supervisor state bits stay set and supervisor
+		 * state is not modified.
 		 */
 		if (fx_only)
 			header->xfeatures = XFEATURE_MASK_FPSSE;
 		else
-			header->xfeatures &= xfeatures;
+			header->xfeatures &= user_xfeatures |
+					     xfeatures_mask_supervisor();
 	}
 
 	if (use_fxsr()) {
@@ -252,16 +261,24 @@ sanitize_restored_xstate(union fpregs_state *state,
  */
 static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
 {
+	u64 init_bv;
+	int r;
+
 	if (use_xsave()) {
 		if (fx_only) {
-			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
-			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
-			return copy_user_to_fxregs(buf);
+			init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE;
+
+			r = copy_user_to_fxregs(buf);
+			if (!r)
+				copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+			return r;
 		} else {
-			u64 init_bv = xfeatures_mask & ~xbv;
-			if (unlikely(init_bv))
+			init_bv = xfeatures_mask_user() & ~xbv;
+
+			r = copy_user_to_xregs(buf, xbv);
+			if (!r && unlikely(init_bv))
 				copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
-			return copy_user_to_xregs(buf, xbv);
+			return r;
 		}
 	} else if (use_fxsr()) {
 		return copy_user_to_fxregs(buf);
@@ -277,7 +294,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 	struct task_struct *tsk = current;
 	struct fpu *fpu = &tsk->thread.fpu;
 	struct user_i387_ia32_struct env;
-	u64 xfeatures = 0;
+	u64 user_xfeatures = 0;
 	int fx_only = 0;
 	int ret = 0;
 
@@ -285,7 +302,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
 
 	if (!buf) {
-		fpu__clear(fpu);
+		fpu__clear_user_states(fpu);
 		return 0;
 	}
 
@@ -310,32 +327,14 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 			trace_x86_fpu_xstate_check_failed(fpu);
 		} else {
 			state_size = fx_sw_user.xstate_size;
-			xfeatures = fx_sw_user.xfeatures;
+			user_xfeatures = fx_sw_user.xfeatures;
 		}
 	}
 
-	/*
-	 * The current state of the FPU registers does not matter. By setting
-	 * TIF_NEED_FPU_LOAD unconditionally it is ensured that the our xstate
-	 * is not modified on context switch and that the xstate is considered
-	 * to be loaded again on return to userland (overriding last_cpu avoids
-	 * the optimisation).
-	 */
-	set_thread_flag(TIF_NEED_FPU_LOAD);
-	__fpu_invalidate_fpregs_state(fpu);
-
 	if ((unsigned long)buf_fx % 64)
 		fx_only = 1;
-	/*
-	 * For 32-bit frames with fxstate, copy the fxstate so it can be
-	 * reconstructed later.
-	 */
-	if (ia32_fxstate) {
-		ret = __copy_from_user(&env, buf, sizeof(env));
-		if (ret)
-			goto err_out;
-		envp = &env;
-	} else {
+
+	if (!ia32_fxstate) {
 		/*
 		 * Attempt to restore the FPU registers directly from user
 		 * memory. For that to succeed, the user access cannot cause
@@ -345,20 +344,65 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 		 */
 		fpregs_lock();
 		pagefault_disable();
-		ret = copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only);
+		ret = copy_user_to_fpregs_zeroing(buf_fx, user_xfeatures, fx_only);
 		pagefault_enable();
 		if (!ret) {
+
+			/*
+			 * Restore supervisor states: previous context switch
+			 * etc has done XSAVES and saved the supervisor states
+			 * in the kernel buffer from which they can be restored
+			 * now.
+			 *
+			 * We cannot do a single XRSTORS here - which would
+			 * be nice - because the rest of the FPU registers are
+			 * being restored from a user buffer directly. The
+			 * single XRSTORS happens below, when the user buffer
+			 * has been copied to the kernel one.
+			 */
+			if (test_thread_flag(TIF_NEED_FPU_LOAD) &&
+			    xfeatures_mask_supervisor())
+				copy_kernel_to_xregs(&fpu->state.xsave,
+						     xfeatures_mask_supervisor());
 			fpregs_mark_activate();
 			fpregs_unlock();
 			return 0;
 		}
-		fpregs_deactivate(fpu);
 		fpregs_unlock();
+	} else {
+		/*
+		 * For 32-bit frames with fxstate, copy the fxstate so it can
+		 * be reconstructed later.
+		 */
+		ret = __copy_from_user(&env, buf, sizeof(env));
+		if (ret)
+			goto err_out;
+		envp = &env;
 	}
 
+	/*
+	 * By setting TIF_NEED_FPU_LOAD it is ensured that our xstate is
+	 * not modified on context switch and that the xstate is considered
+	 * to be loaded again on return to userland (overriding last_cpu avoids
+	 * the optimisation).
+	 */
+	fpregs_lock();
+
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
+
+		/*
+		 * Supervisor states are not modified by user space input.  Save
+		 * current supervisor states first and invalidate the FPU regs.
+		 */
+		if (xfeatures_mask_supervisor())
+			copy_supervisor_to_kernel(&fpu->state.xsave);
+		set_thread_flag(TIF_NEED_FPU_LOAD);
+	}
+	__fpu_invalidate_fpregs_state(fpu);
+	fpregs_unlock();
 
 	if (use_xsave() && !fx_only) {
-		u64 init_bv = xfeatures_mask & ~xfeatures;
+		u64 init_bv = xfeatures_mask_user() & ~user_xfeatures;
 
 		if (using_compacted_format()) {
 			ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
@@ -366,17 +410,24 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 			ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
 
 			if (!ret && state_size > offsetof(struct xregs_state, header))
-				ret = validate_xstate_header(&fpu->state.xsave.header);
+				ret = validate_user_xstate_header(&fpu->state.xsave.header);
 		}
 		if (ret)
 			goto err_out;
 
-		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
+		sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures,
+					      fx_only);
 
 		fpregs_lock();
 		if (unlikely(init_bv))
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
-		ret = copy_kernel_to_xregs_err(&fpu->state.xsave, xfeatures);
+
+		/*
+		 * Restore previously saved supervisor xstates along with
+		 * copied-in user xstates.
+		 */
+		ret = copy_kernel_to_xregs_err(&fpu->state.xsave,
+					       user_xfeatures | xfeatures_mask_supervisor());
 
 	} else if (use_fxsr()) {
 		ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size);
@@ -385,11 +436,14 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 			goto err_out;
 		}
 
-		sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only);
+		sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures,
+					      fx_only);
 
 		fpregs_lock();
 		if (use_xsave()) {
-			u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
+			u64 init_bv;
+
+			init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE;
 			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
 		}
 
@@ -410,7 +464,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 
 err_out:
 	if (ret)
-		fpu__clear(fpu);
+		fpu__clear_user_states(fpu);
 	return ret;
 }
 
@@ -465,7 +519,7 @@ void fpu__init_prepare_fx_sw_frame(void)
 
 	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
 	fx_sw_reserved.extended_size = size;
-	fx_sw_reserved.xfeatures = xfeatures_mask;
+	fx_sw_reserved.xfeatures = xfeatures_mask_user();
 	fx_sw_reserved.xstate_size = fpu_user_xstate_size;
 
 	if (IS_ENABLED(CONFIG_IA32_EMULATION) ||
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 32b153d38748..bda2e5eaca0e 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -54,13 +54,15 @@ static short xsave_cpuid_features[] __initdata = {
 };
 
 /*
- * Mask of xstate features supported by the CPU and the kernel:
+ * This represents the full set of bits that should ever be set in a kernel
+ * XSAVE buffer, both supervisor and user xstates.
  */
-u64 xfeatures_mask __read_mostly;
+u64 xfeatures_mask_all __read_mostly;
 
 static unsigned int xstate_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
 static unsigned int xstate_sizes[XFEATURE_MAX]   = { [ 0 ... XFEATURE_MAX - 1] = -1};
 static unsigned int xstate_comp_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
+static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1};
 
 /*
  * The XSAVE area of kernel can be in standard or compacted format;
@@ -76,7 +78,7 @@ unsigned int fpu_user_xstate_size;
  */
 int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
 {
-	u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+	u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_all;
 
 	if (unlikely(feature_name)) {
 		long xfeature_idx, max_idx;
@@ -150,7 +152,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
 	 * None of the feature bits are in init state. So nothing else
 	 * to do for us, as the memory layout is up to date.
 	 */
-	if ((xfeatures & xfeatures_mask) == xfeatures_mask)
+	if ((xfeatures & xfeatures_mask_all) == xfeatures_mask_all)
 		return;
 
 	/*
@@ -177,7 +179,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
 	 * in a special way already:
 	 */
 	feature_bit = 0x2;
-	xfeatures = (xfeatures_mask & ~xfeatures) >> 2;
+	xfeatures = (xfeatures_mask_user() & ~xfeatures) >> 2;
 
 	/*
 	 * Update all the remaining memory layouts according to their
@@ -205,30 +207,39 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
  */
 void fpu__init_cpu_xstate(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask)
+	u64 unsup_bits;
+
+	if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_all)
 		return;
 	/*
-	 * Make it clear that XSAVES supervisor states are not yet
-	 * implemented should anyone expect it to work by changing
-	 * bits in XFEATURE_MASK_* macros and XCR0.
+	 * Unsupported supervisor xstates should not be found in
+	 * the xfeatures mask.
 	 */
-	WARN_ONCE((xfeatures_mask & XFEATURE_MASK_SUPERVISOR),
-		"x86/fpu: XSAVES supervisor states are not yet implemented.\n");
+	unsup_bits = xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_UNSUPPORTED;
+	WARN_ONCE(unsup_bits, "x86/fpu: Found unsupported supervisor xstates: 0x%llx\n",
+		  unsup_bits);
 
-	xfeatures_mask &= ~XFEATURE_MASK_SUPERVISOR;
+	xfeatures_mask_all &= ~XFEATURE_MASK_SUPERVISOR_UNSUPPORTED;
 
 	cr4_set_bits(X86_CR4_OSXSAVE);
-	xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+
+	/*
+	 * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features
+	 * managed by XSAVE{C, OPT, S} and XRSTOR{S}.  Only XSAVE user
+	 * states can be set here.
+	 */
+	xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user());
+
+	/*
+	 * MSR_IA32_XSS sets supervisor states managed by XSAVES.
+	 */
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
 }
 
-/*
- * Note that in the future we will likely need a pair of
- * functions here: one for user xstates and the other for
- * system xstates.  For now, they are the same.
- */
-static int xfeature_enabled(enum xfeature xfeature)
+static bool xfeature_enabled(enum xfeature xfeature)
 {
-	return !!(xfeatures_mask & (1UL << xfeature));
+	return xfeatures_mask_all & BIT_ULL(xfeature);
 }
 
 /*
@@ -383,6 +394,33 @@ static void __init setup_xstate_comp_offsets(void)
 }
 
 /*
+ * Setup offsets of a supervisor-state-only XSAVES buffer:
+ *
+ * The offsets stored in xstate_comp_offsets[] only work for one specific
+ * value of the Requested Feature BitMap (RFBM).  In cases where a different
+ * RFBM value is used, a different set of offsets is required.  This set of
+ * offsets is for when RFBM=xfeatures_mask_supervisor().
+ */
+static void __init setup_supervisor_only_offsets(void)
+{
+	unsigned int next_offset;
+	int i;
+
+	next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+
+	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
+		if (!xfeature_enabled(i) || !xfeature_is_supervisor(i))
+			continue;
+
+		if (xfeature_is_aligned(i))
+			next_offset = ALIGN(next_offset, 64);
+
+		xstate_supervisor_only_offsets[i] = next_offset;
+		next_offset += xstate_sizes[i];
+	}
+}
+
+/*
  * Print out xstate component offsets and sizes
  */
 static void __init print_xstate_offset_size(void)
@@ -415,7 +453,7 @@ static void __init setup_init_fpu_buf(void)
 
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		init_fpstate.xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT |
-						     xfeatures_mask;
+						     xfeatures_mask_all;
 
 	/*
 	 * Init all the features state with header.xfeatures being 0x0
@@ -438,7 +476,7 @@ static int xfeature_uncompacted_offset(int xfeature_nr)
 	 * format. Checking a supervisor state's uncompacted offset is
 	 * an error.
 	 */
-	if (XFEATURE_MASK_SUPERVISOR & BIT_ULL(xfeature_nr)) {
+	if (XFEATURE_MASK_SUPERVISOR_ALL & BIT_ULL(xfeature_nr)) {
 		WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr);
 		return -1;
 	}
@@ -472,10 +510,10 @@ int using_compacted_format(void)
 }
 
 /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
-int validate_xstate_header(const struct xstate_header *hdr)
+int validate_user_xstate_header(const struct xstate_header *hdr)
 {
 	/* No unknown or supervisor features may be set */
-	if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR))
+	if (hdr->xfeatures & ~xfeatures_mask_user())
 		return -EINVAL;
 
 	/* Userspace must use the uncompacted format */
@@ -610,15 +648,12 @@ static void do_extra_xstate_size_checks(void)
 
 
 /*
- * Get total size of enabled xstates in XCR0/xfeatures_mask.
+ * Get total size of enabled xstates in XCR0 | IA32_XSS.
  *
  * Note the SDM's wording here.  "sub-function 0" only enumerates
  * the size of the *user* states.  If we use it to size a buffer
  * that we use 'XSAVES' on, we could potentially overflow the
  * buffer because 'XSAVES' saves system states too.
- *
- * Note that we do not currently set any bits on IA32_XSS so
- * 'XCR0 | IA32_XSS == XCR0' for now.
  */
 static unsigned int __init get_xsaves_size(void)
 {
@@ -700,7 +735,7 @@ static int __init init_xstate_size(void)
  */
 static void fpu__init_disable_system_xstate(void)
 {
-	xfeatures_mask = 0;
+	xfeatures_mask_all = 0;
 	cr4_clear_bits(X86_CR4_OSXSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 }
@@ -735,16 +770,26 @@ void __init fpu__init_system_xstate(void)
 		return;
 	}
 
+	/*
+	 * Find user xstates supported by the processor.
+	 */
 	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-	xfeatures_mask = eax + ((u64)edx << 32);
+	xfeatures_mask_all = eax + ((u64)edx << 32);
 
-	if ((xfeatures_mask & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
+	/*
+	 * Find supervisor xstates supported by the processor.
+	 */
+	cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
+	xfeatures_mask_all |= ecx + ((u64)edx << 32);
+
+	if ((xfeatures_mask_user() & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
 		/*
 		 * This indicates that something really unexpected happened
 		 * with the enumeration.  Disable XSAVE and try to continue
 		 * booting without it.  This is too early to BUG().
 		 */
-		pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask);
+		pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n",
+		       xfeatures_mask_all);
 		goto out_disable;
 	}
 
@@ -753,10 +798,10 @@ void __init fpu__init_system_xstate(void)
 	 */
 	for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
 		if (!boot_cpu_has(xsave_cpuid_features[i]))
-			xfeatures_mask &= ~BIT(i);
+			xfeatures_mask_all &= ~BIT_ULL(i);
 	}
 
-	xfeatures_mask &= fpu__get_supported_xfeatures_mask();
+	xfeatures_mask_all &= fpu__get_supported_xfeatures_mask();
 
 	/* Enable xstate instructions to be able to continue with initialization: */
 	fpu__init_cpu_xstate();
@@ -768,15 +813,16 @@ void __init fpu__init_system_xstate(void)
 	 * Update info used for ptrace frames; use standard-format size and no
 	 * supervisor xstates:
 	 */
-	update_regset_xstate_info(fpu_user_xstate_size,	xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR);
+	update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user());
 
 	fpu__init_prepare_fx_sw_frame();
 	setup_init_fpu_buf();
 	setup_xstate_comp_offsets();
+	setup_supervisor_only_offsets();
 	print_xstate_offset_size();
 
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
-		xfeatures_mask,
+		xfeatures_mask_all,
 		fpu_kernel_xstate_size,
 		boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
 	return;
@@ -795,7 +841,14 @@ void fpu__resume_cpu(void)
 	 * Restore XCR0 on xsave capable CPUs:
 	 */
 	if (boot_cpu_has(X86_FEATURE_XSAVE))
-		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user());
+
+	/*
+	 * Restore IA32_XSS. The same CPUID bit enumerates support
+	 * of XSAVES and MSR_IA32_XSS.
+	 */
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
 }
 
 /*
@@ -840,10 +893,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 
 	/*
 	 * We should not ever be requesting features that we
-	 * have not enabled.  Remember that xfeatures_mask is
-	 * what we write to the XCR0 register.
+	 * have not enabled.
 	 */
-	WARN_ONCE(!(xfeatures_mask & BIT_ULL(xfeature_nr)),
+	WARN_ONCE(!(xfeatures_mask_all & BIT_ULL(xfeature_nr)),
 		  "get of unsupported state");
 	/*
 	 * This assumes the last 'xsave*' instruction to
@@ -957,18 +1009,31 @@ static inline bool xfeatures_mxcsr_quirk(u64 xfeatures)
 	return true;
 }
 
-/*
- * This is similar to user_regset_copyout(), but will not add offset to
- * the source data pointer or increment pos, count, kbuf, and ubuf.
- */
-static inline void
-__copy_xstate_to_kernel(void *kbuf, const void *data,
-			unsigned int offset, unsigned int size, unsigned int size_total)
+static void fill_gap(unsigned to, void **kbuf, unsigned *pos, unsigned *count)
 {
-	if (offset < size_total) {
-		unsigned int copy = min(size, size_total - offset);
+	if (*pos < to) {
+		unsigned size = to - *pos;
+
+		if (size > *count)
+			size = *count;
+		memcpy(*kbuf, (void *)&init_fpstate.xsave + *pos, size);
+		*kbuf += size;
+		*pos += size;
+		*count -= size;
+	}
+}
 
-		memcpy(kbuf + offset, data, copy);
+static void copy_part(unsigned offset, unsigned size, void *from,
+			void **kbuf, unsigned *pos, unsigned *count)
+{
+	fill_gap(offset, kbuf, pos, count);
+	if (size > *count)
+		size = *count;
+	if (size) {
+		memcpy(*kbuf, from, size);
+		*kbuf += size;
+		*pos += size;
+		*count -= size;
 	}
 }
 
@@ -981,8 +1046,9 @@ __copy_xstate_to_kernel(void *kbuf, const void *data,
  */
 int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
 {
-	unsigned int offset, size;
 	struct xstate_header header;
+	const unsigned off_mxcsr = offsetof(struct fxregs_state, mxcsr);
+	unsigned count = size_total;
 	int i;
 
 	/*
@@ -996,48 +1062,44 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 	 */
 	memset(&header, 0, sizeof(header));
 	header.xfeatures = xsave->header.xfeatures;
-	header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
-
+	header.xfeatures &= xfeatures_mask_user();
+
+	if (header.xfeatures & XFEATURE_MASK_FP)
+		copy_part(0, off_mxcsr,
+			  &xsave->i387, &kbuf, &offset_start, &count);
+	if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM))
+		copy_part(off_mxcsr, MXCSR_AND_FLAGS_SIZE,
+			  &xsave->i387.mxcsr, &kbuf, &offset_start, &count);
+	if (header.xfeatures & XFEATURE_MASK_FP)
+		copy_part(offsetof(struct fxregs_state, st_space), 128,
+			  &xsave->i387.st_space, &kbuf, &offset_start, &count);
+	if (header.xfeatures & XFEATURE_MASK_SSE)
+		copy_part(xstate_offsets[XFEATURE_MASK_SSE], 256,
+			  &xsave->i387.xmm_space, &kbuf, &offset_start, &count);
+	/*
+	 * Fill xsave->i387.sw_reserved value for ptrace frame:
+	 */
+	copy_part(offsetof(struct fxregs_state, sw_reserved), 48,
+		  xstate_fx_sw_bytes, &kbuf, &offset_start, &count);
 	/*
 	 * Copy xregs_state->header:
 	 */
-	offset = offsetof(struct xregs_state, header);
-	size = sizeof(header);
+	copy_part(offsetof(struct xregs_state, header), sizeof(header),
+		  &header, &kbuf, &offset_start, &count);
 
-	__copy_xstate_to_kernel(kbuf, &header, offset, size, size_total);
-
-	for (i = 0; i < XFEATURE_MAX; i++) {
+	for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
 		/*
 		 * Copy only in-use xstates:
 		 */
 		if ((header.xfeatures >> i) & 1) {
 			void *src = __raw_xsave_addr(xsave, i);
 
-			offset = xstate_offsets[i];
-			size = xstate_sizes[i];
-
-			/* The next component has to fit fully into the output buffer: */
-			if (offset + size > size_total)
-				break;
-
-			__copy_xstate_to_kernel(kbuf, src, offset, size, size_total);
+			copy_part(xstate_offsets[i], xstate_sizes[i],
+				  src, &kbuf, &offset_start, &count);
 		}
 
 	}
-
-	if (xfeatures_mxcsr_quirk(header.xfeatures)) {
-		offset = offsetof(struct fxregs_state, mxcsr);
-		size = MXCSR_AND_FLAGS_SIZE;
-		__copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total);
-	}
-
-	/*
-	 * Fill xsave->i387.sw_reserved value for ptrace frame:
-	 */
-	offset = offsetof(struct fxregs_state, sw_reserved);
-	size = sizeof(xstate_fx_sw_bytes);
-
-	__copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total);
+	fill_gap(size_total, &kbuf, &offset_start, &count);
 
 	return 0;
 }
@@ -1080,7 +1142,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i
 	 */
 	memset(&header, 0, sizeof(header));
 	header.xfeatures = xsave->header.xfeatures;
-	header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+	header.xfeatures &= xfeatures_mask_user();
 
 	/*
 	 * Copy xregs_state->header:
@@ -1147,7 +1209,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
 
 	memcpy(&hdr, kbuf + offset, size);
 
-	if (validate_xstate_header(&hdr))
+	if (validate_user_xstate_header(&hdr))
 		return -EINVAL;
 
 	for (i = 0; i < XFEATURE_MAX; i++) {
@@ -1173,7 +1235,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
 	 * The state that came in from userspace was user-state only.
 	 * Mask all the user states out of 'xfeatures':
 	 */
-	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL;
 
 	/*
 	 * Add back in the features that came in from userspace:
@@ -1201,7 +1263,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
 	if (__copy_from_user(&hdr, ubuf + offset, size))
 		return -EFAULT;
 
-	if (validate_xstate_header(&hdr))
+	if (validate_user_xstate_header(&hdr))
 		return -EINVAL;
 
 	for (i = 0; i < XFEATURE_MAX; i++) {
@@ -1229,7 +1291,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
 	 * The state that came in from userspace was user-state only.
 	 * Mask all the user states out of 'xfeatures':
 	 */
-	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+	xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL;
 
 	/*
 	 * Add back in the features that came in from userspace:
@@ -1239,6 +1301,61 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
 	return 0;
 }
 
+/*
+ * Save only supervisor states to the kernel buffer.  This blows away all
+ * old states, and is intended to be used only in __fpu__restore_sig(), where
+ * user states are restored from the user buffer.
+ */
+void copy_supervisor_to_kernel(struct xregs_state *xstate)
+{
+	struct xstate_header *header;
+	u64 max_bit, min_bit;
+	u32 lmask, hmask;
+	int err, i;
+
+	if (WARN_ON(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (!xfeatures_mask_supervisor())
+		return;
+
+	max_bit = __fls(xfeatures_mask_supervisor());
+	min_bit = __ffs(xfeatures_mask_supervisor());
+
+	lmask = xfeatures_mask_supervisor();
+	hmask = xfeatures_mask_supervisor() >> 32;
+	XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
+
+	/* We should never fault when copying to a kernel buffer: */
+	if (WARN_ON_FPU(err))
+		return;
+
+	/*
+	 * At this point, the buffer has only supervisor states and must be
+	 * converted back to normal kernel format.
+	 */
+	header = &xstate->header;
+	header->xcomp_bv |= xfeatures_mask_all;
+
+	/*
+	 * This only moves states up in the buffer.  Start with
+	 * the last state and move backwards so that states are
+	 * not overwritten until after they are moved.  Note:
+	 * memmove() allows overlapping src/dst buffers.
+	 */
+	for (i = max_bit; i >= min_bit; i--) {
+		u8 *xbuf = (u8 *)xstate;
+
+		if (!((header->xfeatures >> i) & 1))
+			continue;
+
+		/* Move xfeature 'i' into its normal location */
+		memmove(xbuf + xstate_comp_offsets[i],
+			xbuf + xstate_supervisor_only_offsets[i],
+			xstate_sizes[i]);
+	}
+}
+
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 /*
  * Report the amount of time elapsed in millisecond since last AVX512
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 37a0aeaf89e7..c84d28e90a58 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -282,7 +282,8 @@ static inline void tramp_free(void *tramp) { }
 
 /* Defined as markers to the end of the ftrace default trampolines */
 extern void ftrace_regs_caller_end(void);
-extern void ftrace_epilogue(void);
+extern void ftrace_regs_caller_ret(void);
+extern void ftrace_caller_end(void);
 extern void ftrace_caller_op_ptr(void);
 extern void ftrace_regs_caller_op_ptr(void);
 
@@ -334,7 +335,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		call_offset = (unsigned long)ftrace_regs_call;
 	} else {
 		start_offset = (unsigned long)ftrace_caller;
-		end_offset = (unsigned long)ftrace_epilogue;
+		end_offset = (unsigned long)ftrace_caller_end;
 		op_offset = (unsigned long)ftrace_caller_op_ptr;
 		call_offset = (unsigned long)ftrace_call;
 	}
@@ -366,6 +367,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	if (WARN_ON(ret < 0))
 		goto fail;
 
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+		ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller);
+		ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+		if (WARN_ON(ret < 0))
+			goto fail;
+	}
+
 	/*
 	 * The address of the ftrace_ops that is used for this trampoline
 	 * is stored at the end of the trampoline. This will be used to
@@ -407,7 +415,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	set_vm_flush_reset_perms(trampoline);
 
-	set_memory_ro((unsigned long)trampoline, npages);
+	if (likely(system_state != SYSTEM_BOOTING))
+		set_memory_ro((unsigned long)trampoline, npages);
 	set_memory_x((unsigned long)trampoline, npages);
 	return (unsigned long)trampoline;
 fail:
@@ -415,6 +424,32 @@ fail:
 	return 0;
 }
 
+void set_ftrace_ops_ro(void)
+{
+	struct ftrace_ops *ops;
+	unsigned long start_offset;
+	unsigned long end_offset;
+	unsigned long npages;
+	unsigned long size;
+
+	do_for_each_ftrace_op(ops, ftrace_ops_list) {
+		if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+			continue;
+
+		if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+			start_offset = (unsigned long)ftrace_regs_caller;
+			end_offset = (unsigned long)ftrace_regs_caller_end;
+		} else {
+			start_offset = (unsigned long)ftrace_caller;
+			end_offset = (unsigned long)ftrace_caller_end;
+		}
+		size = end_offset - start_offset;
+		size = size + RET_SIZE + sizeof(void *);
+		npages = DIV_ROUND_UP(size, PAGE_SIZE);
+		set_memory_ro((unsigned long)ops->trampoline, npages);
+	} while_for_each_ftrace_op(ops);
+}
+
 static unsigned long calc_trampoline_call_offset(bool save_regs)
 {
 	unsigned long start_offset;
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index e8a9f8370112..e405fe1a8bf4 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -189,5 +189,5 @@ return_to_handler:
 	movl	%eax, %ecx
 	popl	%edx
 	popl	%eax
-	JMP_NOSPEC %ecx
+	JMP_NOSPEC ecx
 #endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 369e61faacfe..aa5d28aeb31e 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -23,7 +23,7 @@
 #endif /* CONFIG_FRAME_POINTER */
 
 /* Size of stack used to save mcount regs in save_mcount_regs */
-#define MCOUNT_REG_SIZE		(SS+8 + MCOUNT_FRAME_SIZE)
+#define MCOUNT_REG_SIZE		(FRAME_SIZE + MCOUNT_FRAME_SIZE)
 
 /*
  * gcc -pg option adds a call to 'mcount' in most functions.
@@ -77,7 +77,7 @@
 	/*
 	 * We add enough stack to save all regs.
 	 */
-	subq $(MCOUNT_REG_SIZE - MCOUNT_FRAME_SIZE), %rsp
+	subq $(FRAME_SIZE), %rsp
 	movq %rax, RAX(%rsp)
 	movq %rcx, RCX(%rsp)
 	movq %rdx, RDX(%rsp)
@@ -157,8 +157,12 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	 * think twice before adding any new code or changing the
 	 * layout here.
 	 */
-SYM_INNER_LABEL(ftrace_epilogue, SYM_L_GLOBAL)
+SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL)
 
+	jmp ftrace_epilogue
+SYM_FUNC_END(ftrace_caller);
+
+SYM_FUNC_START(ftrace_epilogue)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	jmp ftrace_stub
@@ -170,14 +174,12 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
  */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
 	retq
-SYM_FUNC_END(ftrace_caller)
+SYM_FUNC_END(ftrace_epilogue)
 
 SYM_FUNC_START(ftrace_regs_caller)
 	/* Save the current flags before any operations that can change them */
 	pushfq
 
-	UNWIND_HINT_SAVE
-
 	/* added 8 bytes to save flags */
 	save_mcount_regs 8
 	/* save_mcount_regs fills in first two parameters */
@@ -233,10 +235,13 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	movq ORIG_RAX(%rsp), %rax
 	movq %rax, MCOUNT_REG_SIZE-8(%rsp)
 
-	/* If ORIG_RAX is anything but zero, make this a call to that */
+	/*
+	 * If ORIG_RAX is anything but zero, make this a call to that.
+	 * See arch_ftrace_set_direct_caller().
+	 */
 	movq ORIG_RAX(%rsp), %rax
-	cmpq	$0, %rax
-	je	1f
+	testq	%rax, %rax
+	jz	1f
 
 	/* Swap the flags with orig_rax */
 	movq MCOUNT_REG_SIZE(%rsp), %rdi
@@ -244,20 +249,14 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	movq %rax, MCOUNT_REG_SIZE(%rsp)
 
 	restore_mcount_regs 8
+	/* Restore flags */
+	popfq
 
-	jmp	2f
+SYM_INNER_LABEL(ftrace_regs_caller_ret, SYM_L_GLOBAL);
+	UNWIND_HINT_RET_OFFSET
+	jmp	ftrace_epilogue
 
 1:	restore_mcount_regs
-
-
-2:
-	/*
-	 * The stack layout is nondetermistic here, depending on which path was
-	 * taken.  This confuses objtool and ORC, rightfully so.  For now,
-	 * pretend the stack always looks like the non-direct case.
-	 */
-	UNWIND_HINT_RESTORE
-
 	/* Restore flags */
 	popfq
 
@@ -268,7 +267,6 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	 * to the return.
 	 */
 SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
-
 	jmp ftrace_epilogue
 
 SYM_FUNC_END(ftrace_regs_caller)
@@ -303,7 +301,7 @@ trace:
 	 * function tracing is enabled.
 	 */
 	movq ftrace_trace_function, %r8
-	CALL_NOSPEC %r8
+	CALL_NOSPEC r8
 	restore_mcount_regs
 
 	jmp fgraph_trace
@@ -340,6 +338,6 @@ SYM_CODE_START(return_to_handler)
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
 	addq $24, %rsp
-	JMP_NOSPEC %rdi
+	JMP_NOSPEC rdi
 SYM_CODE_END(return_to_handler)
 #endif
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index a53e7b4a7419..e2fab3ceb09f 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -33,15 +33,15 @@ void io_bitmap_share(struct task_struct *tsk)
 	set_tsk_thread_flag(tsk, TIF_IO_BITMAP);
 }
 
-static void task_update_io_bitmap(void)
+static void task_update_io_bitmap(struct task_struct *tsk)
 {
-	struct thread_struct *t = &current->thread;
+	struct thread_struct *t = &tsk->thread;
 
 	if (t->iopl_emul == 3 || t->io_bitmap) {
 		/* TSS update is handled on exit to user space */
-		set_thread_flag(TIF_IO_BITMAP);
+		set_tsk_thread_flag(tsk, TIF_IO_BITMAP);
 	} else {
-		clear_thread_flag(TIF_IO_BITMAP);
+		clear_tsk_thread_flag(tsk, TIF_IO_BITMAP);
 		/* Invalidate TSS */
 		preempt_disable();
 		tss_update_io_bitmap();
@@ -49,12 +49,12 @@ static void task_update_io_bitmap(void)
 	}
 }
 
-void io_bitmap_exit(void)
+void io_bitmap_exit(struct task_struct *tsk)
 {
-	struct io_bitmap *iobm = current->thread.io_bitmap;
+	struct io_bitmap *iobm = tsk->thread.io_bitmap;
 
-	current->thread.io_bitmap = NULL;
-	task_update_io_bitmap();
+	tsk->thread.io_bitmap = NULL;
+	task_update_io_bitmap(tsk);
 	if (iobm && refcount_dec_and_test(&iobm->refcnt))
 		kfree(iobm);
 }
@@ -102,7 +102,7 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
 		if (!iobm)
 			return -ENOMEM;
 		refcount_set(&iobm->refcnt, 1);
-		io_bitmap_exit();
+		io_bitmap_exit(current);
 	}
 
 	/*
@@ -134,7 +134,7 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	}
 	/* All permissions dropped? */
 	if (max_long == UINT_MAX) {
-		io_bitmap_exit();
+		io_bitmap_exit(current);
 		return 0;
 	}
 
@@ -192,7 +192,7 @@ SYSCALL_DEFINE1(iopl, unsigned int, level)
 	}
 
 	t->iopl_emul = level;
-	task_update_io_bitmap();
+	task_update_io_bitmap(current);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 6407ea21fa1b..bdcc5146de96 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -25,10 +25,6 @@
 #include <linux/atomic.h>
 #include <linux/sched/clock.h>
 
-#if defined(CONFIG_EDAC)
-#include <linux/edac.h>
-#endif
-
 #include <asm/cpu_entry_area.h>
 #include <asm/traps.h>
 #include <asm/mach_traps.h>
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9da70b279dad..ce6cd220f722 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -96,7 +96,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 }
 
 /*
- * Free current thread data structures etc..
+ * Free thread data structures etc..
  */
 void exit_thread(struct task_struct *tsk)
 {
@@ -104,7 +104,7 @@ void exit_thread(struct task_struct *tsk)
 	struct fpu *fpu = &t->fpu;
 
 	if (test_thread_flag(TIF_IO_BITMAP))
-		io_bitmap_exit();
+		io_bitmap_exit(tsk);
 
 	free_vm86(t);
 
@@ -191,7 +191,7 @@ void flush_thread(void)
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 
-	fpu__clear(&tsk->thread.fpu);
+	fpu__clear_all(&tsk->thread.fpu);
 }
 
 void disable_TSC(void)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 954b013cc585..538d4e8d6589 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -52,7 +52,7 @@
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>
 #include <asm/vm86.h>
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include <asm/proto.h>
 
 #include "process.h"
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 5ef9d8f25b0e..0c169a5687e1 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -52,7 +52,7 @@
 #include <asm/switch_to.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/vdso.h>
-#include <asm/resctrl_sched.h>
+#include <asm/resctrl.h>
 #include <asm/unistd.h>
 #include <asm/fsgsbase.h>
 #ifdef CONFIG_IA32_EMULATION
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4b3fa6cd3106..a3767e74c758 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -237,6 +237,9 @@ static u64 __init get_ramdisk_image(void)
 
 	ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32;
 
+	if (ramdisk_image == 0)
+		ramdisk_image = phys_initrd_start;
+
 	return ramdisk_image;
 }
 static u64 __init get_ramdisk_size(void)
@@ -245,6 +248,9 @@ static u64 __init get_ramdisk_size(void)
 
 	ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32;
 
+	if (ramdisk_size == 0)
+		ramdisk_size = phys_initrd_size;
+
 	return ramdisk_size;
 }
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 83b74fb38c8f..0052bbe5dfd4 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -732,7 +732,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		/*
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
-		fpu__clear(fpu);
+		fpu__clear_user_states(fpu);
 	}
 	signal_setup_done(failed, ksig, stepping);
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fe3ab9632f3b..2467f3dd35d3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -147,7 +147,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
 }
 
-static void init_freq_invariance(void);
+static void init_freq_invariance(bool secondary);
 
 /*
  * Report back to the Boot Processor during boot time or to the caller processor
@@ -185,7 +185,7 @@ static void smp_callin(void)
 	 */
 	set_cpu_sibling_map(raw_smp_processor_id());
 
-	init_freq_invariance();
+	init_freq_invariance(true);
 
 	/*
 	 * Get our bogomips.
@@ -266,6 +266,14 @@ static void notrace start_secondary(void *unused)
 
 	wmb();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+
+	/*
+	 * Prevent tail call to cpu_startup_entry() because the stack protector
+	 * guard has been changed a couple of function calls up, in
+	 * boot_init_stack_canary() and must not be checked before tail calling
+	 * another function.
+	 */
+	prevent_tail_call_optimization();
 }
 
 /**
@@ -1341,7 +1349,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	set_sched_topology(x86_topology);
 
 	set_cpu_sibling_map(0);
-	init_freq_invariance();
+	init_freq_invariance(false);
 	smp_sanity_check();
 
 	switch (apic_intr_mode) {
@@ -1376,12 +1384,12 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	speculative_store_bypass_ht_init();
 }
 
-void arch_enable_nonboot_cpus_begin(void)
+void arch_thaw_secondary_cpus_begin(void)
 {
 	set_mtrr_aps_delayed_init();
 }
 
-void arch_enable_nonboot_cpus_end(void)
+void arch_thaw_secondary_cpus_end(void)
 {
 	mtrr_aps_init();
 }
@@ -1849,24 +1857,25 @@ static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 
-#define ICPU(model) \
-	{X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF, 0}
+#define X86_MATCH(model)					\
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6,		\
+		INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)
 
 static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = {
-	ICPU(INTEL_FAM6_XEON_PHI_KNL),
-	ICPU(INTEL_FAM6_XEON_PHI_KNM),
+	X86_MATCH(XEON_PHI_KNL),
+	X86_MATCH(XEON_PHI_KNM),
 	{}
 };
 
 static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = {
-	ICPU(INTEL_FAM6_SKYLAKE_X),
+	X86_MATCH(SKYLAKE_X),
 	{}
 };
 
 static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
-	ICPU(INTEL_FAM6_ATOM_GOLDMONT),
-	ICPU(INTEL_FAM6_ATOM_GOLDMONT_D),
-	ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS),
+	X86_MATCH(ATOM_GOLDMONT),
+	X86_MATCH(ATOM_GOLDMONT_D),
+	X86_MATCH(ATOM_GOLDMONT_PLUS),
 	{}
 };
 
@@ -1877,9 +1886,6 @@ static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
 	int err, i;
 	u64 msr;
 
-	if (!x86_match_cpu(has_knl_turbo_ratio_limits))
-		return false;
-
 	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
 	if (err)
 		return false;
@@ -1945,18 +1951,23 @@ static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
 
 static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
 {
+	u64 msr;
 	int err;
 
 	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
 	if (err)
 		return false;
 
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, turbo_freq);
+	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
 	if (err)
 		return false;
 
-	*base_freq = (*base_freq >> 8) & 0xFF;      /* max P state */
-	*turbo_freq = (*turbo_freq >> 24) & 0xFF;   /* 4C turbo    */
+	*base_freq = (*base_freq >> 8) & 0xFF;    /* max P state */
+	*turbo_freq = (msr >> 24) & 0xFF;         /* 4C turbo    */
+
+	/* The CPU may have less than 4 cores */
+	if (!*turbo_freq)
+		*turbo_freq = msr & 0xFF;         /* 1C turbo    */
 
 	return true;
 }
@@ -1972,7 +1983,8 @@ static bool intel_set_max_freq_ratio(void)
 	    skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
 		goto out;
 
-	if (knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
+	if (x86_match_cpu(has_knl_turbo_ratio_limits) &&
+	    knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
 		goto out;
 
 	if (x86_match_cpu(has_skx_turbo_ratio_limits) &&
@@ -1985,13 +1997,22 @@ static bool intel_set_max_freq_ratio(void)
 	return false;
 
 out:
+	/*
+	 * Some hypervisors advertise X86_FEATURE_APERFMPERF
+	 * but then fill all MSR's with zeroes.
+	 */
+	if (!base_freq) {
+		pr_debug("Couldn't determine cpu base frequency, necessary for scale-invariant accounting.\n");
+		return false;
+	}
+
 	arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE,
 					base_freq);
 	arch_set_max_freq_ratio(turbo_disabled());
 	return true;
 }
 
-static void init_counter_refs(void *arg)
+static void init_counter_refs(void)
 {
 	u64 aperf, mperf;
 
@@ -2002,18 +2023,25 @@ static void init_counter_refs(void *arg)
 	this_cpu_write(arch_prev_mperf, mperf);
 }
 
-static void init_freq_invariance(void)
+static void init_freq_invariance(bool secondary)
 {
 	bool ret = false;
 
-	if (smp_processor_id() != 0 || !boot_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return;
 
+	if (secondary) {
+		if (static_branch_likely(&arch_scale_freq_key)) {
+			init_counter_refs();
+		}
+		return;
+	}
+
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
 		ret = intel_set_max_freq_ratio();
 
 	if (ret) {
-		on_each_cpu(init_counter_refs, NULL, 1);
+		init_counter_refs();
 		static_branch_enable(&arch_scale_freq_key);
 	} else {
 		pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index b89f6ac6a0c0..b2942b2dbfcf 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -35,8 +35,7 @@
 #include "../realmode/rm/wakeup.h"
 
 /* Global pointer to shared data; NULL means no measured launch. */
-struct tboot *tboot __read_mostly;
-EXPORT_SYMBOL(tboot);
+static struct tboot *tboot __read_mostly;
 
 /* timeout for APs (in secs) to enter wait-for-SIPI state during shutdown */
 #define AP_WAIT_TIMEOUT		1
@@ -46,6 +45,11 @@ EXPORT_SYMBOL(tboot);
 
 static u8 tboot_uuid[16] __initdata = TBOOT_UUID;
 
+bool tboot_enabled(void)
+{
+	return tboot != NULL;
+}
+
 void __init tboot_probe(void)
 {
 	/* Look for valid page-aligned address for shared page. */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d54cffdc7cac..428186d9de46 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -37,10 +37,12 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/io.h>
+#include <linux/hardirq.h>
+#include <linux/atomic.h>
+
 #include <asm/stacktrace.h>
 #include <asm/processor.h>
 #include <asm/debugreg.h>
-#include <linux/atomic.h>
 #include <asm/text-patching.h>
 #include <asm/ftrace.h>
 #include <asm/traps.h>
@@ -82,78 +84,6 @@ static inline void cond_local_irq_disable(struct pt_regs *regs)
 		local_irq_disable();
 }
 
-/*
- * In IST context, we explicitly disable preemption.  This serves two
- * purposes: it makes it much less likely that we would accidentally
- * schedule in IST context and it will force a warning if we somehow
- * manage to schedule by accident.
- */
-void ist_enter(struct pt_regs *regs)
-{
-	if (user_mode(regs)) {
-		RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
-	} else {
-		/*
-		 * We might have interrupted pretty much anything.  In
-		 * fact, if we're a machine check, we can even interrupt
-		 * NMI processing.  We don't want in_nmi() to return true,
-		 * but we need to notify RCU.
-		 */
-		rcu_nmi_enter();
-	}
-
-	preempt_disable();
-
-	/* This code is a bit fragile.  Test it. */
-	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
-}
-NOKPROBE_SYMBOL(ist_enter);
-
-void ist_exit(struct pt_regs *regs)
-{
-	preempt_enable_no_resched();
-
-	if (!user_mode(regs))
-		rcu_nmi_exit();
-}
-
-/**
- * ist_begin_non_atomic() - begin a non-atomic section in an IST exception
- * @regs:	regs passed to the IST exception handler
- *
- * IST exception handlers normally cannot schedule.  As a special
- * exception, if the exception interrupted userspace code (i.e.
- * user_mode(regs) would return true) and the exception was not
- * a double fault, it can be safe to schedule.  ist_begin_non_atomic()
- * begins a non-atomic section within an ist_enter()/ist_exit() region.
- * Callers are responsible for enabling interrupts themselves inside
- * the non-atomic section, and callers must call ist_end_non_atomic()
- * before ist_exit().
- */
-void ist_begin_non_atomic(struct pt_regs *regs)
-{
-	BUG_ON(!user_mode(regs));
-
-	/*
-	 * Sanity check: we need to be on the normal thread stack.  This
-	 * will catch asm bugs and any attempt to use ist_preempt_enable
-	 * from double_fault.
-	 */
-	BUG_ON(!on_thread_stack());
-
-	preempt_enable_no_resched();
-}
-
-/**
- * ist_end_non_atomic() - begin a non-atomic section in an IST exception
- *
- * Ends a non-atomic section started with ist_begin_non_atomic().
- */
-void ist_end_non_atomic(void)
-{
-	preempt_disable();
-}
-
 int is_valid_bugaddr(unsigned long addr)
 {
 	unsigned short ud;
@@ -326,7 +256,6 @@ __visible void __noreturn handle_stack_overflow(const char *message,
 }
 #endif
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_DOUBLEFAULT)
 /*
  * Runs on an IST stack for x86_64 and on a special task stack for x86_32.
  *
@@ -363,7 +292,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
 	 * The net result is that our #GP handler will think that we
 	 * entered from usermode with the bad user context.
 	 *
-	 * No need for ist_enter here because we don't use RCU.
+	 * No need for nmi_enter() here because we don't use RCU.
 	 */
 	if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY &&
 		regs->cs == __KERNEL_CS &&
@@ -398,7 +327,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
 	}
 #endif
 
-	ist_enter(regs);
+	nmi_enter();
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
 	tsk->thread.error_code = error_code;
@@ -450,7 +379,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
 	die("double fault", regs, error_code);
 	panic("Machine halted.");
 }
-#endif
 
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 {
@@ -592,19 +520,13 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 		return;
 
 	/*
-	 * Unlike any other non-IST entry, we can be called from a kprobe in
-	 * non-CONTEXT_KERNEL kernel mode or even during context tracking
-	 * state changes.  Make sure that we wake up RCU even if we're coming
-	 * from kernel code.
-	 *
-	 * This means that we can't schedule even if we came from a
-	 * preemptible kernel context.  That's okay.
+	 * Unlike any other non-IST entry, we can be called from pretty much
+	 * any location in the kernel through kprobes -- text_poke() will most
+	 * likely be handled by poke_int3_handler() above. This means this
+	 * handler is effectively NMI-like.
 	 */
-	if (!user_mode(regs)) {
-		rcu_nmi_enter();
-		preempt_disable();
-	}
-	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
+	if (!user_mode(regs))
+		nmi_enter();
 
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
@@ -626,10 +548,8 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	cond_local_irq_disable(regs);
 
 exit:
-	if (!user_mode(regs)) {
-		preempt_enable_no_resched();
-		rcu_nmi_exit();
-	}
+	if (!user_mode(regs))
+		nmi_exit();
 }
 NOKPROBE_SYMBOL(do_int3);
 
@@ -733,7 +653,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	unsigned long dr6;
 	int si_code;
 
-	ist_enter(regs);
+	nmi_enter();
 
 	get_debugreg(dr6, 6);
 	/*
@@ -826,7 +746,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_dec();
 
 exit:
-	ist_exit(regs);
+	nmi_exit();
 }
 NOKPROBE_SYMBOL(do_debug);
 
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 4d732a444711..8d5cbe1bbb3b 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -81,7 +81,7 @@
 #define	UMIP_INST_SLDT  3       /* 0F 00 /0 */
 #define	UMIP_INST_STR   4       /* 0F 00 /1 */
 
-const char * const umip_insns[5] = {
+static const char * const umip_insns[5] = {
 	[UMIP_INST_SGDT] = "SGDT",
 	[UMIP_INST_SIDT] = "SIDT",
 	[UMIP_INST_SMSW] = "SMSW",
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index a224b5ab103f..54226110bc7f 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -344,6 +344,9 @@ bad_address:
 	if (IS_ENABLED(CONFIG_X86_32))
 		goto the_end;
 
+	if (state->task != current)
+		goto the_end;
+
 	if (state->regs) {
 		printk_deferred_once(KERN_WARNING
 			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index e9cc182aa97e..7f969b2d240f 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -8,19 +8,21 @@
 #include <asm/orc_lookup.h>
 
 #define orc_warn(fmt, ...) \
-	printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)
+	printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__)
+
+#define orc_warn_current(args...)					\
+({									\
+	if (state->task == current)					\
+		orc_warn(args);						\
+})
 
 extern int __start_orc_unwind_ip[];
 extern int __stop_orc_unwind_ip[];
 extern struct orc_entry __start_orc_unwind[];
 extern struct orc_entry __stop_orc_unwind[];
 
-static DEFINE_MUTEX(sort_mutex);
-int *cur_orc_ip_table = __start_orc_unwind_ip;
-struct orc_entry *cur_orc_table = __start_orc_unwind;
-
-unsigned int lookup_num_blocks;
-bool orc_init;
+static bool orc_init __ro_after_init;
+static unsigned int lookup_num_blocks __ro_after_init;
 
 static inline unsigned long orc_ip(const int *ip)
 {
@@ -142,9 +144,6 @@ static struct orc_entry *orc_find(unsigned long ip)
 {
 	static struct orc_entry *orc;
 
-	if (!orc_init)
-		return NULL;
-
 	if (ip == 0)
 		return &null_orc_entry;
 
@@ -189,6 +188,10 @@ static struct orc_entry *orc_find(unsigned long ip)
 
 #ifdef CONFIG_MODULES
 
+static DEFINE_MUTEX(sort_mutex);
+static int *cur_orc_ip_table = __start_orc_unwind_ip;
+static struct orc_entry *cur_orc_table = __start_orc_unwind;
+
 static void orc_sort_swap(void *_a, void *_b, int size)
 {
 	struct orc_entry *orc_a, *orc_b;
@@ -317,12 +320,19 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
 unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 {
+	struct task_struct *task = state->task;
+
 	if (unwind_done(state))
 		return NULL;
 
 	if (state->regs)
 		return &state->regs->ip;
 
+	if (task != current && state->sp == task->thread.sp) {
+		struct inactive_task_frame *frame = (void *)task->thread.sp;
+		return &frame->ret_addr;
+	}
+
 	if (state->sp)
 		return (unsigned long *)state->sp - 1;
 
@@ -381,9 +391,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 	return true;
 }
 
+/*
+ * If state->regs is non-NULL, and points to a full pt_regs, just get the reg
+ * value from state->regs.
+ *
+ * Otherwise, if state->regs just points to IRET regs, and the previous frame
+ * had full regs, it's safe to get the value from the previous regs.  This can
+ * happen when early/late IRQ entry code gets interrupted by an NMI.
+ */
+static bool get_reg(struct unwind_state *state, unsigned int reg_off,
+		    unsigned long *val)
+{
+	unsigned int reg = reg_off/8;
+
+	if (!state->regs)
+		return false;
+
+	if (state->full_regs) {
+		*val = ((unsigned long *)state->regs)[reg];
+		return true;
+	}
+
+	if (state->prev_regs) {
+		*val = ((unsigned long *)state->prev_regs)[reg];
+		return true;
+	}
+
+	return false;
+}
+
 bool unwind_next_frame(struct unwind_state *state)
 {
-	unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp;
+	unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
 	bool indirect = false;
@@ -445,43 +484,39 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_REG_R10:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R10 at ip %pB\n",
-				 (void *)state->ip);
+		if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) {
+			orc_warn_current("missing R10 value at %pB\n",
+					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->r10;
 		break;
 
 	case ORC_REG_R13:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg R13 at ip %pB\n",
-				 (void *)state->ip);
+		if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) {
+			orc_warn_current("missing R13 value at %pB\n",
+					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->r13;
 		break;
 
 	case ORC_REG_DI:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DI at ip %pB\n",
-				 (void *)state->ip);
+		if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) {
+			orc_warn_current("missing RDI value at %pB\n",
+					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->di;
 		break;
 
 	case ORC_REG_DX:
-		if (!state->regs || !state->full_regs) {
-			orc_warn("missing regs for base reg DX at ip %pB\n",
-				 (void *)state->ip);
+		if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) {
+			orc_warn_current("missing DX value at %pB\n",
+					 (void *)state->ip);
 			goto err;
 		}
-		sp = state->regs->dx;
 		break;
 
 	default:
-		orc_warn("unknown SP base reg %d for ip %pB\n",
+		orc_warn("unknown SP base reg %d at %pB\n",
 			 orc->sp_reg, (void *)state->ip);
 		goto err;
 	}
@@ -504,44 +539,48 @@ bool unwind_next_frame(struct unwind_state *state)
 
 		state->sp = sp;
 		state->regs = NULL;
+		state->prev_regs = NULL;
 		state->signal = false;
 		break;
 
 	case ORC_TYPE_REGS:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
-			orc_warn("can't dereference registers at %p for ip %pB\n",
-				 (void *)sp, (void *)orig_ip);
+			orc_warn_current("can't access registers at %pB\n",
+					 (void *)orig_ip);
 			goto err;
 		}
 
 		state->regs = (struct pt_regs *)sp;
+		state->prev_regs = NULL;
 		state->full_regs = true;
 		state->signal = true;
 		break;
 
 	case ORC_TYPE_REGS_IRET:
 		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
-			orc_warn("can't dereference iret registers at %p for ip %pB\n",
-				 (void *)sp, (void *)orig_ip);
+			orc_warn_current("can't access iret registers at %pB\n",
+					 (void *)orig_ip);
 			goto err;
 		}
 
+		if (state->full_regs)
+			state->prev_regs = state->regs;
 		state->regs = (void *)sp - IRET_FRAME_OFFSET;
 		state->full_regs = false;
 		state->signal = true;
 		break;
 
 	default:
-		orc_warn("unknown .orc_unwind entry type %d for ip %pB\n",
+		orc_warn("unknown .orc_unwind entry type %d at %pB\n",
 			 orc->type, (void *)orig_ip);
-		break;
+		goto err;
 	}
 
 	/* Find BP: */
 	switch (orc->bp_reg) {
 	case ORC_REG_UNDEFINED:
-		if (state->regs && state->full_regs)
-			state->bp = state->regs->bp;
+		if (get_reg(state, offsetof(struct pt_regs, bp), &tmp))
+			state->bp = tmp;
 		break;
 
 	case ORC_REG_PREV_SP:
@@ -564,8 +603,8 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (state->stack_info.type == prev_type &&
 	    on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) &&
 	    state->sp <= prev_sp) {
-		orc_warn("stack going in the wrong direction? ip=%pB\n",
-			 (void *)orig_ip);
+		orc_warn_current("stack going in the wrong direction? at %pB\n",
+				 (void *)orig_ip);
 		goto err;
 	}
 
@@ -588,17 +627,20 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	memset(state, 0, sizeof(*state));
 	state->task = task;
 
+	if (!orc_init)
+		goto err;
+
 	/*
 	 * Refuse to unwind the stack of a task while it's executing on another
 	 * CPU.  This check is racy, but that's ok: the unwinder has other
 	 * checks to prevent it from going off the rails.
 	 */
 	if (task_on_another_cpu(task))
-		goto done;
+		goto err;
 
 	if (regs) {
 		if (user_mode(regs))
-			goto done;
+			goto the_end;
 
 		state->ip = regs->ip;
 		state->sp = regs->sp;
@@ -631,6 +673,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		 * generate some kind of backtrace if this happens.
 		 */
 		void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp);
+		state->error = true;
 		if (get_stack_info(next_page, state->task, &state->stack_info,
 				   &state->stack_mask))
 			return;
@@ -651,13 +694,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	/* Otherwise, skip ahead to the user-specified starting frame: */
 	while (!unwind_done(state) &&
 	       (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
-			state->sp <= (unsigned long)first_frame))
+			state->sp < (unsigned long)first_frame))
 		unwind_next_frame(state);
 
 	return;
 
-done:
+err:
+	state->error = true;
+the_end:
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
-	return;
 }
 EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index a789759b7261..4a3081e9f4b5 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -3,6 +3,10 @@
 ccflags-y += -Iarch/x86/kvm
 ccflags-$(CONFIG_KVM_WERROR) += -Werror
 
+ifeq ($(CONFIG_FRAME_POINTER),y)
+OBJECT_FILES_NON_STANDARD_vmenter.o := y
+endif
+
 KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index bcefa9d4e57e..54d4b98b49e1 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1427,7 +1427,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
 	 */
 	kvm_make_vcpus_request_mask(kvm,
 				    KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP,
-				    vcpu_mask, &hv_vcpu->tlb_flush);
+				    NULL, vcpu_mask, &hv_vcpu->tlb_flush);
 
 ret_success:
 	/* We always do full TLB flush, set rep_done = rep_cnt. */
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 750ff0b29404..d057376bd3d3 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -225,12 +225,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
 	}
 
 	/*
-	 * AMD SVM AVIC accelerate EOI write and do not trap,
-	 * in-kernel IOAPIC will not be able to receive the EOI.
-	 * In this case, we do lazy update of the pending EOI when
-	 * trying to set IOAPIC irq.
+	 * AMD SVM AVIC accelerate EOI write iff the interrupt is edge
+	 * triggered, in which case the in-kernel IOAPIC will not be able
+	 * to receive the EOI.  In this case, we do a lazy update of the
+	 * pending EOI when trying to set IOAPIC irq.
 	 */
-	if (kvm_apicv_activated(ioapic->kvm))
+	if (edge && kvm_apicv_activated(ioapic->kvm))
 		ioapic_lazy_update_eoi(ioapic, irq);
 
 	/*
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 90a1ca939627..9a2a62e5afeb 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 
 #include <asm/msr-index.h>
+#include <asm/debugreg.h>
 
 #include "kvm_emulate.h"
 #include "trace.h"
@@ -267,7 +268,7 @@ void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	svm->vmcb->save.rsp = nested_vmcb->save.rsp;
 	svm->vmcb->save.rip = nested_vmcb->save.rip;
 	svm->vmcb->save.dr7 = nested_vmcb->save.dr7;
-	svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
+	svm->vcpu.arch.dr6  = nested_vmcb->save.dr6;
 	svm->vmcb->save.cpl = nested_vmcb->save.cpl;
 
 	svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL;
@@ -482,7 +483,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	nested_vmcb->save.rsp    = vmcb->save.rsp;
 	nested_vmcb->save.rax    = vmcb->save.rax;
 	nested_vmcb->save.dr7    = vmcb->save.dr7;
-	nested_vmcb->save.dr6    = vmcb->save.dr6;
+	nested_vmcb->save.dr6    = svm->vcpu.arch.dr6;
 	nested_vmcb->save.cpl    = vmcb->save.cpl;
 
 	nested_vmcb->control.int_ctl           = vmcb->control.int_ctl;
@@ -606,26 +607,45 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 /* DB exceptions for our internal use must not cause vmexit */
 static int nested_svm_intercept_db(struct vcpu_svm *svm)
 {
-	unsigned long dr6;
+	unsigned long dr6 = svm->vmcb->save.dr6;
+
+	/* Always catch it and pass it to userspace if debugging.  */
+	if (svm->vcpu.guest_debug &
+	    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+		return NESTED_EXIT_HOST;
 
 	/* if we're not singlestepping, it's not ours */
 	if (!svm->nmi_singlestep)
-		return NESTED_EXIT_DONE;
+		goto reflected_db;
 
 	/* if it's not a singlestep exception, it's not ours */
-	if (kvm_get_dr(&svm->vcpu, 6, &dr6))
-		return NESTED_EXIT_DONE;
 	if (!(dr6 & DR6_BS))
-		return NESTED_EXIT_DONE;
+		goto reflected_db;
 
 	/* if the guest is singlestepping, it should get the vmexit */
 	if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) {
 		disable_nmi_singlestep(svm);
-		return NESTED_EXIT_DONE;
+		goto reflected_db;
 	}
 
 	/* it's ours, the nested hypervisor must not see this one */
 	return NESTED_EXIT_HOST;
+
+reflected_db:
+	/*
+	 * Synchronize guest DR6 here just like in kvm_deliver_exception_payload;
+	 * it will be moved into the nested VMCB by nested_svm_vmexit.  Once
+	 * exceptions will be moved to svm_check_nested_events, all this stuff
+	 * will just go away and we could just return NESTED_EXIT_HOST
+	 * unconditionally.  db_interception will queue the exception, which
+	 * will be processed by svm_check_nested_events if a nested vmexit is
+	 * required, and we will just use kvm_deliver_exception_payload to copy
+	 * the payload to DR6 before vmexit.
+	 */
+	WARN_ON(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT);
+	svm->vcpu.arch.dr6 &= ~(DR_TRAP_BITS | DR6_RTM);
+	svm->vcpu.arch.dr6 |= dr6 & ~DR6_FIXED_1;
+	return NESTED_EXIT_DONE;
 }
 
 static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
@@ -682,6 +702,9 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 		if (svm->nested.intercept_exceptions & excp_bits) {
 			if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR)
 				vmexit = nested_svm_intercept_db(svm);
+			else if (exit_code == SVM_EXIT_EXCP_BASE + BP_VECTOR &&
+				 svm->vcpu.guest_debug & KVM_GUESTDBG_USE_SW_BP)
+				vmexit = NESTED_EXIT_HOST;
 			else
 				vmexit = NESTED_EXIT_DONE;
 		}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0e3fc311d7da..89f7f3aebd31 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/highmem.h>
 #include <linux/psp-sev.h>
+#include <linux/pagemap.h>
 #include <linux/swap.h>
 
 #include "x86.h"
@@ -344,7 +345,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
 		return NULL;
 
 	/* Pin the user virtual address. */
-	npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
+	npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
 	if (npinned != npages) {
 		pr_err("SEV: Failure locking %lu pages.\n", npages);
 		goto err;
@@ -1117,7 +1118,7 @@ int __init sev_hardware_setup(void)
 	/* Maximum number of encrypted guests supported simultaneously */
 	max_sev_asid = cpuid_ecx(0x8000001F);
 
-	if (!max_sev_asid)
+	if (!svm_sev_enabled())
 		return 1;
 
 	/* Minimum ASID value that should be used for SEV guest */
@@ -1156,6 +1157,9 @@ err:
 
 void sev_hardware_teardown(void)
 {
+	if (!svm_sev_enabled())
+		return;
+
 	bitmap_free(sev_asid_bitmap);
 	bitmap_free(sev_reclaim_asid_bitmap);
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2be5bbae3a40..a862c768fd54 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1672,17 +1672,14 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 	mark_dirty(svm->vmcb, VMCB_ASID);
 }
 
-static u64 svm_get_dr6(struct kvm_vcpu *vcpu)
+static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value)
 {
-	return to_svm(vcpu)->vmcb->save.dr6;
-}
-
-static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb *vmcb = svm->vmcb;
 
-	svm->vmcb->save.dr6 = value;
-	mark_dirty(svm->vmcb, VMCB_DR);
+	if (unlikely(value != vmcb->save.dr6)) {
+		vmcb->save.dr6 = value;
+		mark_dirty(vmcb, VMCB_DR);
+	}
 }
 
 static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
@@ -1693,9 +1690,12 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 	get_debugreg(vcpu->arch.db[1], 1);
 	get_debugreg(vcpu->arch.db[2], 2);
 	get_debugreg(vcpu->arch.db[3], 3);
-	vcpu->arch.dr6 = svm_get_dr6(vcpu);
+	/*
+	 * We cannot reset svm->vmcb->save.dr6 to DR6_FIXED_1|DR6_RTM here,
+	 * because db_interception might need it.  We can do it before vmentry.
+	 */
+	vcpu->arch.dr6 = svm->vmcb->save.dr6;
 	vcpu->arch.dr7 = svm->vmcb->save.dr7;
-
 	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
 	set_dr_intercepts(svm);
 }
@@ -1739,7 +1739,8 @@ static int db_interception(struct vcpu_svm *svm)
 	if (!(svm->vcpu.guest_debug &
 	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
 		!svm->nmi_singlestep) {
-		kvm_queue_exception(&svm->vcpu, DB_VECTOR);
+		u32 payload = (svm->vmcb->save.dr6 ^ DR6_RTM) & ~DR6_FIXED_1;
+		kvm_queue_exception_p(&svm->vcpu, DB_VECTOR, payload);
 		return 1;
 	}
 
@@ -1752,6 +1753,8 @@ static int db_interception(struct vcpu_svm *svm)
 	if (svm->vcpu.guest_debug &
 	    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) {
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
+		kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6;
+		kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7;
 		kvm_run->debug.arch.pc =
 			svm->vmcb->save.cs.base + svm->vmcb->save.rip;
 		kvm_run->debug.arch.exception = DB_VECTOR;
@@ -3276,7 +3279,7 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)
 	svm_complete_interrupts(svm);
 }
 
-bool __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
+void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
 
 static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
@@ -3315,6 +3318,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 
+	/*
+	 * Run with all-zero DR6 unless needed, so that we can get the exact cause
+	 * of a #DB.
+	 */
+	if (unlikely(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
+		svm_set_dr6(svm, vcpu->arch.dr6);
+	else
+		svm_set_dr6(svm, DR6_FIXED_1 | DR6_RTM);
+
 	clgi();
 	kvm_load_guest_xsave_state(vcpu);
 
@@ -3330,13 +3342,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
 
-	local_irq_enable();
-
 	__svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs);
 
-	/* Eliminate branch target predictions from guest mode */
-	vmexit_fill_RSB();
-
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_GS_BASE, svm->host.gs_base);
 #else
@@ -3366,8 +3373,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	reload_tss(vcpu);
 
-	local_irq_disable();
-
 	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
 
 	vcpu->arch.cr2 = svm->vmcb->save.cr2;
@@ -3411,7 +3416,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	mark_all_clean(svm->vmcb);
 }
-STACK_FRAME_NON_STANDARD(svm_vcpu_run);
 
 static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root)
 {
@@ -3937,8 +3941,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.set_idt = svm_set_idt,
 	.get_gdt = svm_get_gdt,
 	.set_gdt = svm_set_gdt,
-	.get_dr6 = svm_get_dr6,
-	.set_dr6 = svm_set_dr6,
 	.set_dr7 = svm_set_dr7,
 	.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
 	.cache_reg = svm_cache_reg,
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index fa1af90067e9..bf944334003a 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -3,6 +3,7 @@
 #include <asm/asm.h>
 #include <asm/bitsperlong.h>
 #include <asm/kvm_vcpu_regs.h>
+#include <asm/nospec-branch.h>
 
 #define WORD_SIZE (BITS_PER_LONG / 8)
 
@@ -35,7 +36,6 @@
  */
 SYM_FUNC_START(__svm_vcpu_run)
 	push %_ASM_BP
-	mov  %_ASM_SP, %_ASM_BP
 #ifdef CONFIG_X86_64
 	push %r15
 	push %r14
@@ -78,6 +78,7 @@ SYM_FUNC_START(__svm_vcpu_run)
 	pop %_ASM_AX
 
 	/* Enter guest mode */
+	sti
 1:	vmload %_ASM_AX
 	jmp 3f
 2:	cmpb $0, kvm_rebooting
@@ -99,6 +100,13 @@ SYM_FUNC_START(__svm_vcpu_run)
 	ud2
 	_ASM_EXTABLE(5b, 6b)
 7:
+	cli
+
+#ifdef CONFIG_RETPOLINE
+	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+#endif
+
 	/* "POP" @regs to RAX. */
 	pop %_ASM_AX
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index cbc9ea2de28f..e44f33c82332 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5165,7 +5165,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	 */
 		break;
 	default:
-		BUG_ON(1);
+		BUG();
 		break;
 	}
 
@@ -5533,8 +5533,25 @@ static bool nested_vmx_exit_handled_vmcs_access(struct kvm_vcpu *vcpu,
 	return 1 & (b >> (field & 7));
 }
 
+static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12)
+{
+	u32 entry_intr_info = vmcs12->vm_entry_intr_info_field;
+
+	if (nested_cpu_has_mtf(vmcs12))
+		return true;
+
+	/*
+	 * An MTF VM-exit may be injected into the guest by setting the
+	 * interruption-type to 7 (other event) and the vector field to 0. Such
+	 * is the case regardless of the 'monitor trap flag' VM-execution
+	 * control.
+	 */
+	return entry_intr_info == (INTR_INFO_VALID_MASK
+				   | INTR_TYPE_OTHER_EVENT);
+}
+
 /*
- * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we
+ * Return true if we should exit from L2 to L1 to handle an exit, or false if we
  * should handle it ourselves in L0 (and then continue L2). Only call this
  * when in is_guest_mode (L2).
  */
@@ -5633,7 +5650,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 	case EXIT_REASON_MWAIT_INSTRUCTION:
 		return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
 	case EXIT_REASON_MONITOR_TRAP_FLAG:
-		return nested_cpu_has_mtf(vmcs12);
+		return nested_vmx_exit_handled_mtf(vmcs12);
 	case EXIT_REASON_MONITOR_INSTRUCTION:
 		return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
 	case EXIT_REASON_PAUSE_INSTRUCTION:
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 87f3f24fef37..51d1a82742fd 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -82,6 +82,9 @@ SYM_FUNC_START(vmx_vmexit)
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
 
+	/* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */
+	or $1, %_ASM_AX
+
 	pop %_ASM_AX
 .Lvmexit_skip_rsb:
 #endif
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 83050977490c..89c766fad889 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1372,7 +1372,6 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	vmx_vcpu_pi_load(vcpu, cpu);
 
-	vmx->host_pkru = read_pkru();
 	vmx->host_debugctlmsr = get_debugctlmsr();
 }
 
@@ -4572,7 +4571,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
  */
 static void kvm_machine_check(void)
 {
-#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
+#if defined(CONFIG_X86_MCE)
 	struct pt_regs regs = {
 		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
 		.flags = X86_EFLAGS_IF,
@@ -4677,15 +4676,13 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 		dr6 = vmcs_readl(EXIT_QUALIFICATION);
 		if (!(vcpu->guest_debug &
 		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
-			vcpu->arch.dr6 &= ~DR_TRAP_BITS;
-			vcpu->arch.dr6 |= dr6 | DR6_RTM;
 			if (is_icebp(intr_info))
 				WARN_ON(!skip_emulated_instruction(vcpu));
 
-			kvm_queue_exception(vcpu, DB_VECTOR);
+			kvm_queue_exception_p(vcpu, DB_VECTOR, dr6);
 			return 1;
 		}
-		kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
+		kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM;
 		kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
 		/* fall through */
 	case BP_VECTOR:
@@ -4929,16 +4926,14 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 		 * guest debugging itself.
 		 */
 		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
-			vcpu->run->debug.arch.dr6 = vcpu->arch.dr6;
+			vcpu->run->debug.arch.dr6 = DR6_BD | DR6_RTM | DR6_FIXED_1;
 			vcpu->run->debug.arch.dr7 = dr7;
 			vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu);
 			vcpu->run->debug.arch.exception = DB_VECTOR;
 			vcpu->run->exit_reason = KVM_EXIT_DEBUG;
 			return 0;
 		} else {
-			vcpu->arch.dr6 &= ~DR_TRAP_BITS;
-			vcpu->arch.dr6 |= DR6_BD | DR6_RTM;
-			kvm_queue_exception(vcpu, DB_VECTOR);
+			kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BD);
 			return 1;
 		}
 	}
@@ -4969,15 +4964,6 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 	return kvm_skip_emulated_instruction(vcpu);
 }
 
-static u64 vmx_get_dr6(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.dr6;
-}
-
-static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
-{
-}
-
 static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 {
 	get_debugreg(vcpu->arch.db[0], 0);
@@ -6577,11 +6563,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	kvm_load_guest_xsave_state(vcpu);
 
-	if (static_cpu_has(X86_FEATURE_PKU) &&
-	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
-	    vcpu->arch.pkru != vmx->host_pkru)
-		__write_pkru(vcpu->arch.pkru);
-
 	pt_guest_enter(vmx);
 
 	if (vcpu_to_pmu(vcpu)->version)
@@ -6671,18 +6652,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	pt_guest_exit(vmx);
 
-	/*
-	 * eager fpu is enabled if PKEY is supported and CR4 is switched
-	 * back on host, so it is safe to read guest PKRU from current
-	 * XSAVE.
-	 */
-	if (static_cpu_has(X86_FEATURE_PKU) &&
-	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
-		vcpu->arch.pkru = rdpkru();
-		if (vcpu->arch.pkru != vmx->host_pkru)
-			__write_pkru(vmx->host_pkru);
-	}
-
 	kvm_load_host_xsave_state(vcpu);
 
 	vmx->nested.nested_run_pending = 0;
@@ -7740,8 +7709,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.set_idt = vmx_set_idt,
 	.get_gdt = vmx_get_gdt,
 	.set_gdt = vmx_set_gdt,
-	.get_dr6 = vmx_get_dr6,
-	.set_dr6 = vmx_set_dr6,
 	.set_dr7 = vmx_set_dr7,
 	.sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
 	.cache_reg = vmx_cache_reg,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3bf2ecafd027..c17e6eb9ad43 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -572,11 +572,12 @@ void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 }
 EXPORT_SYMBOL_GPL(kvm_requeue_exception);
 
-static void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
-				  unsigned long payload)
+void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
+			   unsigned long payload)
 {
 	kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false);
 }
+EXPORT_SYMBOL_GPL(kvm_queue_exception_p);
 
 static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
 				    u32 error_code, unsigned long payload)
@@ -836,11 +837,25 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 		    vcpu->arch.ia32_xss != host_xss)
 			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
+
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) &&
+	    vcpu->arch.pkru != vcpu->arch.host_pkru)
+		__write_pkru(vcpu->arch.pkru);
 }
 EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
 
 void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 {
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
+		vcpu->arch.pkru = rdpkru();
+		if (vcpu->arch.pkru != vcpu->arch.host_pkru)
+			__write_pkru(vcpu->arch.host_pkru);
+	}
+
 	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
 
 		if (vcpu->arch.xcr0 != host_xcr0)
@@ -926,19 +941,6 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr);
 	__reserved_bits;				\
 })
 
-static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c)
-{
-	u64 reserved_bits = __cr4_reserved_bits(cpu_has, c);
-
-	if (kvm_cpu_cap_has(X86_FEATURE_LA57))
-		reserved_bits &= ~X86_CR4_LA57;
-
-	if (kvm_cpu_cap_has(X86_FEATURE_UMIP))
-		reserved_bits &= ~X86_CR4_UMIP;
-
-	return reserved_bits;
-}
-
 static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	if (cr4 & cr4_reserved_bits)
@@ -1058,12 +1060,6 @@ static void kvm_update_dr0123(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void kvm_update_dr6(struct kvm_vcpu *vcpu)
-{
-	if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
-		kvm_x86_ops.set_dr6(vcpu, vcpu->arch.dr6);
-}
-
 static void kvm_update_dr7(struct kvm_vcpu *vcpu)
 {
 	unsigned long dr7;
@@ -1103,7 +1099,6 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 		if (val & 0xffffffff00000000ULL)
 			return -1; /* #GP */
 		vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu);
-		kvm_update_dr6(vcpu);
 		break;
 	case 5:
 		/* fall through */
@@ -1139,10 +1134,7 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
 	case 4:
 		/* fall through */
 	case 6:
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
-			*val = vcpu->arch.dr6;
-		else
-			*val = kvm_x86_ops.get_dr6(vcpu);
+		*val = vcpu->arch.dr6;
 		break;
 	case 5:
 		/* fall through */
@@ -3060,6 +3052,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_PERF_CTL:
 	case MSR_AMD64_DC_CFG:
 	case MSR_F15H_EX_CFG:
+	/*
+	 * Intel Sandy Bridge CPUs must support the RAPL (running average power
+	 * limit) MSRs. Just return 0, as we do not want to expose the host
+	 * data here. Do not conditionalize this on CPUID, as KVM does not do
+	 * so for existing CPU-specific MSRs.
+	 */
+	case MSR_RAPL_POWER_UNIT:
+	case MSR_PP0_ENERGY_STATUS:	/* Power plane 0 (core) */
+	case MSR_PP1_ENERGY_STATUS:	/* Power plane 1 (graphics uncore) */
+	case MSR_PKG_ENERGY_STATUS:	/* Total package */
+	case MSR_DRAM_ENERGY_STATUS:	/* DRAM controller */
 		msr_info->data = 0;
 		break;
 	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
@@ -3374,6 +3377,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_GET_MSR_FEATURES:
 	case KVM_CAP_MSR_PLATFORM_INFO:
 	case KVM_CAP_EXCEPTION_PAYLOAD:
+	case KVM_CAP_SET_GUEST_DEBUG:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -3559,6 +3563,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_x86_ops.vcpu_load(vcpu, cpu);
 
+	/* Save host pkru register if supported */
+	vcpu->arch.host_pkru = read_pkru();
+
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
@@ -3752,7 +3759,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
 	unsigned bank_num = mcg_cap & 0xff, bank;
 
 	r = -EINVAL;
-	if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
+	if (!bank_num || bank_num > KVM_MAX_MCE_BANKS)
 		goto out;
 	if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000))
 		goto out;
@@ -4010,7 +4017,6 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
 	vcpu->arch.dr6 = dbgregs->dr6;
-	kvm_update_dr6(vcpu);
 	vcpu->arch.dr7 = dbgregs->dr7;
 	kvm_update_dr7(vcpu);
 
@@ -5049,10 +5055,13 @@ set_identity_unlock:
 		r = -EFAULT;
 		if (copy_from_user(&u.ps, argp, sizeof(u.ps)))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit_out;
 		r = kvm_vm_ioctl_set_pit(kvm, &u.ps);
+set_pit_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_GET_PIT2: {
@@ -5072,10 +5081,13 @@ set_identity_unlock:
 		r = -EFAULT;
 		if (copy_from_user(&u.ps2, argp, sizeof(u.ps2)))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit2_out;
 		r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2);
+set_pit2_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_REINJECT_CONTROL: {
@@ -6654,7 +6666,7 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu)
 
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
 		kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM;
-		kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
+		kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu);
 		kvm_run->debug.arch.exception = DB_VECTOR;
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
 		return 0;
@@ -6714,9 +6726,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
 					   vcpu->arch.db);
 
 		if (dr6 != 0) {
-			vcpu->arch.dr6 &= ~DR_TRAP_BITS;
-			vcpu->arch.dr6 |= dr6 | DR6_RTM;
-			kvm_queue_exception(vcpu, DB_VECTOR);
+			kvm_queue_exception_p(vcpu, DB_VECTOR, dr6);
 			*r = 1;
 			return true;
 		}
@@ -8037,7 +8047,7 @@ void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
 	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
 
 	kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC,
-				    vcpu_bitmap, cpus);
+				    NULL, vcpu_bitmap, cpus);
 
 	free_cpumask_var(cpus);
 }
@@ -8067,6 +8077,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv);
  */
 void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit)
 {
+	struct kvm_vcpu *except;
 	unsigned long old, new, expected;
 
 	if (!kvm_x86_ops.check_apicv_inhibit_reasons ||
@@ -8091,7 +8102,17 @@ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit)
 	trace_kvm_apicv_update_request(activate, bit);
 	if (kvm_x86_ops.pre_update_apicv_exec_ctrl)
 		kvm_x86_ops.pre_update_apicv_exec_ctrl(kvm, activate);
-	kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE);
+
+	/*
+	 * Sending request to update APICV for all other vcpus,
+	 * while update the calling vcpu immediately instead of
+	 * waiting for another #VMEXIT to handle the request.
+	 */
+	except = kvm_get_running_vcpu();
+	kvm_make_all_cpus_request_except(kvm, KVM_REQ_APICV_UPDATE,
+					 except);
+	if (except)
+		kvm_vcpu_update_apicv(except);
 }
 EXPORT_SYMBOL_GPL(kvm_request_apicv_update);
 
@@ -8415,7 +8436,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
 		kvm_x86_ops.sync_dirty_debug_regs(vcpu);
 		kvm_update_dr0123(vcpu);
-		kvm_update_dr6(vcpu);
 		kvm_update_dr7(vcpu);
 		vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
 	}
@@ -9476,7 +9496,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
 	vcpu->arch.dr6 = DR6_INIT;
-	kvm_update_dr6(vcpu);
 	vcpu->arch.dr7 = DR7_FIXED_1;
 	kvm_update_dr7(vcpu);
 
@@ -9658,7 +9677,9 @@ int kvm_arch_hardware_setup(void *opaque)
 	if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
 		supported_xss = 0;
 
-	cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data);
+#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f)
+	cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_);
+#undef __kvm_cpu_cap_has
 
 	if (kvm_has_tsc_control) {
 		/*
@@ -9690,7 +9711,8 @@ int kvm_arch_check_processor_compat(void *opaque)
 
 	WARN_ON(!irqs_disabled());
 
-	if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits)
+	if (__cr4_reserved_bits(cpu_has, c) !=
+	    __cr4_reserved_bits(cpu_has, &boot_cpu_data))
 		return -EIO;
 
 	return ops->check_processor_compatibility();
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 4742e8fa7ee7..d1d768912368 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -153,7 +153,7 @@ SYM_FUNC_START(csum_partial)
 	negl %ebx
 	lea 45f(%ebx,%ebx,2), %ebx
 	testl %esi, %esi
-	JMP_NOSPEC %ebx
+	JMP_NOSPEC ebx
 
 	# Handle 2-byte-aligned regions
 20:	addw (%esi), %ax
@@ -436,7 +436,7 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	andl $-32,%edx
 	lea 3f(%ebx,%ebx), %ebx
 	testl %esi, %esi 
-	JMP_NOSPEC %ebx
+	JMP_NOSPEC ebx
 1:	addl $64,%esi
 	addl $64,%edi 
 	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 363ec132df7e..b4c43a9b1483 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -7,15 +7,31 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
+#include <asm/unwind_hints.h>
+#include <asm/frame.h>
 
 .macro THUNK reg
 	.section .text.__x86.indirect_thunk
 
+	.align 32
 SYM_FUNC_START(__x86_indirect_thunk_\reg)
-	CFI_STARTPROC
-	JMP_NOSPEC %\reg
-	CFI_ENDPROC
+	JMP_NOSPEC \reg
 SYM_FUNC_END(__x86_indirect_thunk_\reg)
+
+SYM_FUNC_START_NOALIGN(__x86_retpoline_\reg)
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call	.Ldo_rop_\@
+.Lspec_trap_\@:
+	UNWIND_HINT_EMPTY
+	pause
+	lfence
+	jmp	.Lspec_trap_\@
+.Ldo_rop_\@:
+	mov	%\reg, (%_ASM_SP)
+	UNWIND_HINT_RET_OFFSET
+	ret
+SYM_FUNC_END(__x86_retpoline_\reg)
+
 .endm
 
 /*
@@ -24,25 +40,24 @@ SYM_FUNC_END(__x86_indirect_thunk_\reg)
  * only see one instance of "__x86_indirect_thunk_\reg" rather
  * than one per register with the correct names. So we do it
  * the simple and nasty way...
+ *
+ * Worse, you can only have a single EXPORT_SYMBOL per line,
+ * and CPP can't insert newlines, so we have to repeat everything
+ * at least twice.
  */
-#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
-#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
-#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
-
-GENERATE_THUNK(_ASM_AX)
-GENERATE_THUNK(_ASM_BX)
-GENERATE_THUNK(_ASM_CX)
-GENERATE_THUNK(_ASM_DX)
-GENERATE_THUNK(_ASM_SI)
-GENERATE_THUNK(_ASM_DI)
-GENERATE_THUNK(_ASM_BP)
-#ifdef CONFIG_64BIT
-GENERATE_THUNK(r8)
-GENERATE_THUNK(r9)
-GENERATE_THUNK(r10)
-GENERATE_THUNK(r11)
-GENERATE_THUNK(r12)
-GENERATE_THUNK(r13)
-GENERATE_THUNK(r14)
-GENERATE_THUNK(r15)
-#endif
+
+#define __EXPORT_THUNK(sym)	_ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
+#define EXPORT_THUNK(reg)	__EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
+#define EXPORT_RETPOLINE(reg)  __EXPORT_THUNK(__x86_retpoline_ ## reg)
+
+#undef GEN
+#define GEN(reg) THUNK reg
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) EXPORT_THUNK(reg)
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) EXPORT_RETPOLINE(reg)
+#include <asm/GEN-for-each-reg.h>
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index 56f9189bbadb..5199d8a1daf1 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -17,7 +17,7 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
 DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
 #endif
 
-#if defined(CONFIG_X86_32) && defined(CONFIG_DOUBLEFAULT)
+#ifdef CONFIG_X86_32
 DECLARE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack);
 #endif
 
@@ -114,12 +114,10 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu)
 #else
 static inline void percpu_setup_exception_stacks(unsigned int cpu)
 {
-#ifdef CONFIG_DOUBLEFAULT
 	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
 
 	cea_map_percpu_pages(&cea->doublefault_stack,
 			     &per_cpu(doublefault_stack, cpu), 1, PAGE_KERNEL);
-#endif
 }
 #endif
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 1bba16c5742b..a573a3e63f02 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -121,8 +121,6 @@ __ref void *alloc_low_pages(unsigned int num)
 	} else {
 		pfn = pgt_buf_end;
 		pgt_buf_end += num;
-		printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n",
-			pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1);
 	}
 
 	for (i = 0; i < num; i++) {
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3b289c2f75cd..8b5f73f5e207 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -54,6 +54,7 @@
 #include <asm/init.h>
 #include <asm/uv/uv.h>
 #include <asm/setup.h>
+#include <asm/ftrace.h>
 
 #include "mm_internal.h"
 
@@ -1291,6 +1292,8 @@ void mark_rodata_ro(void)
 	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
 	set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT);
 
+	set_ftrace_ops_ro();
+
 #ifdef CONFIG_CPA_DEBUG
 	printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end);
 	set_memory_rw(start, (end-start) >> PAGE_SHIFT);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index cb91eccc4960..c90c20904a60 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -18,7 +18,9 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/compat.h>
+#include <linux/elf-randomize.h>
 #include <asm/elf.h>
+#include <asm/io.h>
 
 #include "physaddr.h"
 
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 109325d77b3e..43fd19b3f118 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -372,7 +372,7 @@ static void enter_uniprocessor(void)
 	int cpu;
 	int err;
 
-	if (downed_cpus == NULL &&
+	if (!cpumask_available(downed_cpus) &&
 	    !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) {
 		pr_notice("Failed to allocate mask\n");
 		goto out;
@@ -402,7 +402,7 @@ static void leave_uniprocessor(void)
 	int cpu;
 	int err;
 
-	if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0)
+	if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0)
 		return;
 	pr_notice("Re-enabling CPUs...\n");
 	for_each_cpu(cpu, downed_cpus) {
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index f2bd3d61e16b..104544359d69 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -27,40 +27,6 @@
 
 #include "numa_internal.h"
 
-#ifdef CONFIG_DISCONTIGMEM
-/*
- * 4) physnode_map     - the mapping between a pfn and owning node
- * physnode_map keeps track of the physical memory layout of a generic
- * numa node on a 64Mb break (each element of the array will
- * represent 64Mb of memory and will be marked by the node id.  so,
- * if the first gig is on node 0, and the second gig is on node 1
- * physnode_map will contain:
- *
- *     physnode_map[0-15] = 0;
- *     physnode_map[16-31] = 1;
- *     physnode_map[32- ] = -1;
- */
-s8 physnode_map[MAX_SECTIONS] __read_mostly = { [0 ... (MAX_SECTIONS - 1)] = -1};
-EXPORT_SYMBOL(physnode_map);
-
-void memory_present(int nid, unsigned long start, unsigned long end)
-{
-	unsigned long pfn;
-
-	printk(KERN_INFO "Node: %d, start_pfn: %lx, end_pfn: %lx\n",
-			nid, start, end);
-	printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
-	printk(KERN_DEBUG "  ");
-	start = round_down(start, PAGES_PER_SECTION);
-	end = round_up(end, PAGES_PER_SECTION);
-	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
-		physnode_map[pfn / PAGES_PER_SECTION] = nid;
-		printk(KERN_CONT "%lx ", pfn);
-	}
-	printk(KERN_CONT "\n");
-}
-#endif
-
 extern unsigned long highend_pfn, highstart_pfn;
 
 void __init initmem_init(void)
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 59eca6a94ce7..b8c55a2e402d 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -43,7 +43,8 @@ struct cpa_data {
 	unsigned long	pfn;
 	unsigned int	flags;
 	unsigned int	force_split		: 1,
-			force_static_prot	: 1;
+			force_static_prot	: 1,
+			force_flush_all		: 1;
 	struct page	**pages;
 };
 
@@ -355,10 +356,10 @@ static void cpa_flush(struct cpa_data *data, int cache)
 		return;
 	}
 
-	if (cpa->numpages <= tlb_single_page_flush_ceiling)
-		on_each_cpu(__cpa_flush_tlb, cpa, 1);
-	else
+	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
 		flush_tlb_all();
+	else
+		on_each_cpu(__cpa_flush_tlb, cpa, 1);
 
 	if (!cache)
 		return;
@@ -1598,6 +1599,8 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 		alias_cpa.curpage = 0;
 
+		cpa->force_flush_all = 1;
+
 		ret = __change_page_attr_set_clr(&alias_cpa, 0);
 		if (ret)
 			return ret;
@@ -1618,6 +1621,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 		alias_cpa.curpage = 0;
 
+		cpa->force_flush_all = 1;
 		/*
 		 * The high mapping range is imprecise, so ignore the
 		 * return value.
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5ea7c2cf7ab4..42b6709e6dc7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -158,6 +158,19 @@ static bool is_ereg(u32 reg)
 			     BIT(BPF_REG_AX));
 }
 
+/*
+ * is_ereg_8l() == true if BPF register 'reg' is mapped to access x86-64
+ * lower 8-bit registers dil,sil,bpl,spl,r8b..r15b, which need extra byte
+ * of encoding. al,cl,dl,bl have simpler encoding.
+ */
+static bool is_ereg_8l(u32 reg)
+{
+	return is_ereg(reg) ||
+	    (1 << reg) & (BIT(BPF_REG_1) |
+			  BIT(BPF_REG_2) |
+			  BIT(BPF_REG_FP));
+}
+
 static bool is_axreg(u32 reg)
 {
 	return reg == BPF_REG_0;
@@ -598,9 +611,8 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 	switch (size) {
 	case BPF_B:
 		/* Emit 'mov byte ptr [rax + off], al' */
-		if (is_ereg(dst_reg) || is_ereg(src_reg) ||
-		    /* We have to add extra byte for x86 SIL, DIL regs */
-		    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
+		if (is_ereg(dst_reg) || is_ereg_8l(src_reg))
+			/* Add extra byte for eregs or SIL,DIL,BPL in src_reg */
 			EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
 		else
 			EMIT1(0x88);
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 4d2a7a764602..66cd150b7e54 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -1847,14 +1847,16 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			case BPF_B:
 			case BPF_H:
 			case BPF_W:
-				if (!bpf_prog->aux->verifier_zext)
+				if (bpf_prog->aux->verifier_zext)
 					break;
 				if (dstk) {
 					EMIT3(0xC7, add_1reg(0x40, IA32_EBP),
 					      STACK_VAR(dst_hi));
 					EMIT(0x0, 4);
 				} else {
-					EMIT3(0xC7, add_1reg(0xC0, dst_hi), 0);
+					/* xor dst_hi,dst_hi */
+					EMIT2(0x33,
+					      add_2reg(0xC0, dst_hi, dst_hi));
 				}
 				break;
 			case BPF_DW:
@@ -2013,8 +2015,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_JMP | BPF_JSET | BPF_X:
 		case BPF_JMP32 | BPF_JSET | BPF_X: {
 			bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP;
-			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
-			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 dreg_lo = IA32_EAX;
+			u8 dreg_hi = IA32_EDX;
 			u8 sreg_lo = sstk ? IA32_ECX : src_lo;
 			u8 sreg_hi = sstk ? IA32_EBX : src_hi;
 
@@ -2026,6 +2028,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 					      add_2reg(0x40, IA32_EBP,
 						       IA32_EDX),
 					      STACK_VAR(dst_hi));
+			} else {
+				/* mov dreg_lo,dst_lo */
+				EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo));
+				if (is_jmp64)
+					/* mov dreg_hi,dst_hi */
+					EMIT2(0x89,
+					      add_2reg(0xC0, dreg_hi, dst_hi));
 			}
 
 			if (sstk) {
@@ -2050,8 +2059,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_JMP | BPF_JSET | BPF_K:
 		case BPF_JMP32 | BPF_JSET | BPF_K: {
 			bool is_jmp64 = BPF_CLASS(insn->code) == BPF_JMP;
-			u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
-			u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
+			u8 dreg_lo = IA32_EAX;
+			u8 dreg_hi = IA32_EDX;
 			u8 sreg_lo = IA32_ECX;
 			u8 sreg_hi = IA32_EBX;
 			u32 hi;
@@ -2064,6 +2073,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 					      add_2reg(0x40, IA32_EBP,
 						       IA32_EDX),
 					      STACK_VAR(dst_hi));
+			} else {
+				/* mov dreg_lo,dst_lo */
+				EMIT2(0x89, add_2reg(0xC0, dreg_lo, dst_lo));
+				if (is_jmp64)
+					/* mov dreg_hi,dst_hi */
+					EMIT2(0x89,
+					      add_2reg(0xC0, dreg_hi, dst_hi));
 			}
 
 			/* mov ecx,imm32 */
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1aae5302501d..e966115d105c 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -62,12 +62,12 @@ static unsigned long efi_runtime, efi_nr_tables;
 unsigned long efi_fw_vendor, efi_config_table;
 
 static const efi_config_table_type_t arch_tables[] __initconst = {
-	{EFI_PROPERTIES_TABLE_GUID, "PROP", &prop_phys},
-	{UGA_IO_PROTOCOL_GUID, "UGA", &uga_phys},
+	{EFI_PROPERTIES_TABLE_GUID,	&prop_phys,		"PROP"		},
+	{UGA_IO_PROTOCOL_GUID,		&uga_phys,		"UGA"		},
 #ifdef CONFIG_X86_UV
-	{UV_SYSTEM_TABLE_GUID, "UVsystab", &uv_systab_phys},
+	{UV_SYSTEM_TABLE_GUID,		&uv_systab_phys,	"UVsystab"	},
 #endif
-	{NULL_GUID, NULL, NULL},
+	{},
 };
 
 static const unsigned long * const efi_tables[] = {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 211bb9358b73..c5e393f8bb3f 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -202,7 +202,7 @@ virt_to_phys_or_null_size(void *va, unsigned long size)
 
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
-	unsigned long pfn, text, pf;
+	unsigned long pfn, text, pf, rodata;
 	struct page *page;
 	unsigned npages;
 	pgd_t *pgd = efi_mm.pgd;
@@ -256,7 +256,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 
 	efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */
 
-	npages = (__end_rodata_aligned - _text) >> PAGE_SHIFT;
+	npages = (_etext - _text) >> PAGE_SHIFT;
 	text = __pa(_text);
 	pfn = text >> PAGE_SHIFT;
 
@@ -266,6 +266,14 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 		return 1;
 	}
 
+	npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT;
+	rodata = __pa(__start_rodata);
+	pfn = rodata >> PAGE_SHIFT;
+	if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) {
+		pr_err("Failed to map kernel rodata 1:1\n");
+		return 1;
+	}
+
 	return 0;
 }
 
@@ -638,7 +646,7 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	phys_vendor = virt_to_phys_or_null(vnd);
 	phys_data = virt_to_phys_or_null_size(data, data_size);
 
-	if (!phys_name || !phys_data)
+	if (!phys_name || (data && !phys_data))
 		status = EFI_INVALID_PARAMETER;
 	else
 		status = efi_thunk(set_variable, phys_name, phys_vendor,
@@ -669,7 +677,7 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
 	phys_vendor = virt_to_phys_or_null(vnd);
 	phys_data = virt_to_phys_or_null_size(data, data_size);
 
-	if (!phys_name || !phys_data)
+	if (!phys_name || (data && !phys_data))
 		status = EFI_INVALID_PARAMETER;
 	else
 		status = efi_thunk(set_variable, phys_name, phys_vendor,
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 15da118f04f0..90380a17ab23 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -21,7 +21,7 @@ SYM_FUNC_START(__efi_call)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
-	CALL_NOSPEC %rdi
+	CALL_NOSPEC rdi
 	leave
 	ret
 SYM_FUNC_END(__efi_call)
diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index c60255da5a6c..4494589a288a 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -45,7 +45,8 @@ static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 	return ret;
 }
 
-s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
+static s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4,
+		u64 a5)
 {
 	s64 ret;
 
@@ -57,10 +58,9 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(uv_bios_call);
 
-s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
-					u64 a4, u64 a5)
+static s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
+		u64 a4, u64 a5)
 {
 	unsigned long bios_flags;
 	s64 ret;
@@ -77,18 +77,13 @@ s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 	return ret;
 }
 
-
 long sn_partition_id;
 EXPORT_SYMBOL_GPL(sn_partition_id);
 long sn_coherency_id;
-EXPORT_SYMBOL_GPL(sn_coherency_id);
 long sn_region_size;
 EXPORT_SYMBOL_GPL(sn_region_size);
 long system_serial_number;
-EXPORT_SYMBOL_GPL(system_serial_number);
 int uv_type;
-EXPORT_SYMBOL_GPL(uv_type);
-
 
 s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher,
 		long *region, long *ssn)
@@ -115,7 +110,6 @@ s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher,
 		*ssn = v1;
 	return ret;
 }
-EXPORT_SYMBOL_GPL(uv_bios_get_sn_info);
 
 int
 uv_bios_mq_watchlist_alloc(unsigned long addr, unsigned int mq_size,
@@ -166,7 +160,6 @@ s64 uv_bios_freq_base(u64 clock_type, u64 *ticks_per_second)
 	return uv_bios_call(UV_BIOS_FREQ_BASE, clock_type,
 			   (u64)ticks_per_second, 0, 0, 0);
 }
-EXPORT_SYMBOL_GPL(uv_bios_freq_base);
 
 /*
  * uv_bios_set_legacy_vga_target - Set Legacy VGA I/O Target
@@ -185,7 +178,6 @@ int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus)
 	return uv_bios_call(UV_BIOS_SET_LEGACY_VGA_TARGET,
 				(u64)decode, (u64)domain, (u64)bus, 0, 0);
 }
-EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target);
 
 int uv_bios_init(void)
 {
diff --git a/arch/x86/platform/uv/uv_sysfs.c b/arch/x86/platform/uv/uv_sysfs.c
index 62214731fea5..266773e2fb37 100644
--- a/arch/x86/platform/uv/uv_sysfs.c
+++ b/arch/x86/platform/uv/uv_sysfs.c
@@ -21,7 +21,7 @@ static ssize_t partition_id_show(struct kobject *kobj,
 static ssize_t coherence_id_show(struct kobject *kobj,
 			struct kobj_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%ld\n", uv_partition_coherence_id());
+	return snprintf(buf, PAGE_SIZE, "%ld\n", sn_coherency_id);
 }
 
 static struct kobj_attribute partition_id_attr =
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index aaff9ed7ff45..fc3b757afb2c 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -307,7 +307,7 @@ int hibernate_resume_nonboot_cpu_disable(void)
 	if (ret)
 		return ret;
 	smp_ops.play_dead = resume_play_dead;
-	ret = disable_nonboot_cpus();
+	ret = freeze_secondary_cpus(0);
 	smp_ops.play_dead = play_dead;
 	return ret;
 }
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 1abe455d926a..205a9bc981b0 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -29,7 +29,7 @@ static efi_system_table_t efi_systab_xen __initdata = {
 	.fw_vendor	= EFI_INVALID_TABLE_ADDR, /* Initialized later. */
 	.fw_revision	= 0,			  /* Initialized later. */
 	.con_in_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
-	.con_in		= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.con_in		= NULL,			  /* Not used under Xen. */
 	.con_out_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
 	.con_out	= NULL, 		  /* Not used under Xen. */
 	.stderr_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 8fb8a50a28b4..f2adb63b2d7c 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -93,6 +93,7 @@ asmlinkage __visible void cpu_bringup_and_idle(void)
 	cpu_bringup();
 	boot_init_stack_canary();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+	prevent_tail_call_optimization();
 }
 
 void xen_smp_intr_free_pv(unsigned int cpu)
diff --git a/arch/xtensa/include/asm/module.h b/arch/xtensa/include/asm/vermagic.h
index 488b40c6f9b9..6d9c670e4ba9 100644
--- a/arch/xtensa/include/asm/module.h
+++ b/arch/xtensa/include/asm/vermagic.h
@@ -1,8 +1,4 @@
 /*
- * include/asm-xtensa/module.h
- *
- * This file contains the module code specific to the Xtensa architecture.
- *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
@@ -10,11 +6,12 @@
  * Copyright (C) 2001 - 2005 Tensilica Inc.
  */
 
-#ifndef _XTENSA_MODULE_H
-#define _XTENSA_MODULE_H
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
 
-#define MODULE_ARCH_VERMAGIC "xtensa-" __stringify(XCHAL_CORE_ID) " "
+#include <linux/stringify.h>
+#include <variant/core.h>
 
-#include <asm-generic/module.h>
+#define MODULE_ARCH_VERMAGIC "xtensa-" __stringify(XCHAL_CORE_ID) " "
 
-#endif	/* _XTENSA_MODULE_H */
+#endif	/* _ASM_VERMAGIC_H */
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 78ba57efd16b..3d411716d7ee 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -123,6 +123,7 @@
 #include <linux/ioprio.h>
 #include <linux/sbitmap.h>
 #include <linux/delay.h>
+#include <linux/backing-dev.h>
 
 #include "blk.h"
 #include "blk-mq.h"
@@ -4976,8 +4977,9 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
 	ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
 	switch (ioprio_class) {
 	default:
-		dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
-			"bfq: bad prio class %d\n", ioprio_class);
+		pr_err("bdi %s: bfq: bad prio class %d\n",
+				bdi_dev_name(bfqq->bfqd->queue->backing_dev_info),
+				ioprio_class);
 		/* fall through */
 	case IOPRIO_CLASS_NONE:
 		/*
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index c5dc833212e1..930212c1a512 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -496,7 +496,7 @@ const char *blkg_dev_name(struct blkcg_gq *blkg)
 {
 	/* some drivers (floppy) instantiate a queue w/o disk registered */
 	if (blkg->q->backing_dev_info->dev)
-		return dev_name(blkg->q->backing_dev_info->dev);
+		return bdi_dev_name(blkg->q->backing_dev_info);
 	return NULL;
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 7e4a1da0715e..9bfaee050c82 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -891,14 +891,11 @@ generic_make_request_checks(struct bio *bio)
 	}
 
 	/*
-	 * Non-mq queues do not honor REQ_NOWAIT, so complete a bio
-	 * with BLK_STS_AGAIN status in order to catch -EAGAIN and
-	 * to give a chance to the caller to repeat request gracefully.
+	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
+	 * if queue is not a request based queue.
 	 */
-	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) {
-		status = BLK_STS_AGAIN;
-		goto end_io;
-	}
+	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
+		goto not_supported;
 
 	if (should_fail_bio(bio))
 		goto end_io;
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index db35ee682294..7c1fe605d0d6 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -466,7 +466,7 @@ struct ioc_gq {
 	 */
 	atomic64_t			vtime;
 	atomic64_t			done_vtime;
-	atomic64_t			abs_vdebt;
+	u64				abs_vdebt;
 	u64				last_vtime;
 
 	/*
@@ -1142,7 +1142,7 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now)
 	struct iocg_wake_ctx ctx = { .iocg = iocg };
 	u64 margin_ns = (u64)(ioc->period_us *
 			      WAITQ_TIMER_MARGIN_PCT / 100) * NSEC_PER_USEC;
-	u64 abs_vdebt, vdebt, vshortage, expires, oexpires;
+	u64 vdebt, vshortage, expires, oexpires;
 	s64 vbudget;
 	u32 hw_inuse;
 
@@ -1152,18 +1152,15 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now)
 	vbudget = now->vnow - atomic64_read(&iocg->vtime);
 
 	/* pay off debt */
-	abs_vdebt = atomic64_read(&iocg->abs_vdebt);
-	vdebt = abs_cost_to_cost(abs_vdebt, hw_inuse);
+	vdebt = abs_cost_to_cost(iocg->abs_vdebt, hw_inuse);
 	if (vdebt && vbudget > 0) {
 		u64 delta = min_t(u64, vbudget, vdebt);
 		u64 abs_delta = min(cost_to_abs_cost(delta, hw_inuse),
-				    abs_vdebt);
+				    iocg->abs_vdebt);
 
 		atomic64_add(delta, &iocg->vtime);
 		atomic64_add(delta, &iocg->done_vtime);
-		atomic64_sub(abs_delta, &iocg->abs_vdebt);
-		if (WARN_ON_ONCE(atomic64_read(&iocg->abs_vdebt) < 0))
-			atomic64_set(&iocg->abs_vdebt, 0);
+		iocg->abs_vdebt -= abs_delta;
 	}
 
 	/*
@@ -1219,12 +1216,18 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost)
 	u64 expires, oexpires;
 	u32 hw_inuse;
 
+	lockdep_assert_held(&iocg->waitq.lock);
+
 	/* debt-adjust vtime */
 	current_hweight(iocg, NULL, &hw_inuse);
-	vtime += abs_cost_to_cost(atomic64_read(&iocg->abs_vdebt), hw_inuse);
+	vtime += abs_cost_to_cost(iocg->abs_vdebt, hw_inuse);
 
-	/* clear or maintain depending on the overage */
-	if (time_before_eq64(vtime, now->vnow)) {
+	/*
+	 * Clear or maintain depending on the overage. Non-zero vdebt is what
+	 * guarantees that @iocg is online and future iocg_kick_delay() will
+	 * clear use_delay. Don't leave it on when there's no vdebt.
+	 */
+	if (!iocg->abs_vdebt || time_before_eq64(vtime, now->vnow)) {
 		blkcg_clear_delay(blkg);
 		return false;
 	}
@@ -1258,9 +1261,12 @@ static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer)
 {
 	struct ioc_gq *iocg = container_of(timer, struct ioc_gq, delay_timer);
 	struct ioc_now now;
+	unsigned long flags;
 
+	spin_lock_irqsave(&iocg->waitq.lock, flags);
 	ioc_now(iocg->ioc, &now);
 	iocg_kick_delay(iocg, &now, 0);
+	spin_unlock_irqrestore(&iocg->waitq.lock, flags);
 
 	return HRTIMER_NORESTART;
 }
@@ -1368,14 +1374,13 @@ static void ioc_timer_fn(struct timer_list *timer)
 	 * should have woken up in the last period and expire idle iocgs.
 	 */
 	list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) {
-		if (!waitqueue_active(&iocg->waitq) &&
-		    !atomic64_read(&iocg->abs_vdebt) && !iocg_is_idle(iocg))
+		if (!waitqueue_active(&iocg->waitq) && iocg->abs_vdebt &&
+		    !iocg_is_idle(iocg))
 			continue;
 
 		spin_lock(&iocg->waitq.lock);
 
-		if (waitqueue_active(&iocg->waitq) ||
-		    atomic64_read(&iocg->abs_vdebt)) {
+		if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt) {
 			/* might be oversleeping vtime / hweight changes, kick */
 			iocg_kick_waitq(iocg, &now);
 			iocg_kick_delay(iocg, &now, 0);
@@ -1591,7 +1596,7 @@ skip_surplus_transfers:
 				      vrate_min, vrate_max);
 		}
 
-		trace_iocost_ioc_vrate_adj(ioc, vrate, &missed_ppm, rq_wait_pct,
+		trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct,
 					   nr_lagging, nr_shortages,
 					   nr_surpluses);
 
@@ -1600,7 +1605,7 @@ skip_surplus_transfers:
 			ioc->period_us * vrate * INUSE_MARGIN_PCT, 100);
 	} else if (ioc->busy_level != prev_busy_level || nr_lagging) {
 		trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate),
-					   &missed_ppm, rq_wait_pct, nr_lagging,
+					   missed_ppm, rq_wait_pct, nr_lagging,
 					   nr_shortages, nr_surpluses);
 	}
 
@@ -1718,28 +1723,49 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
 	 * tests are racy but the races aren't systemic - we only miss once
 	 * in a while which is fine.
 	 */
-	if (!waitqueue_active(&iocg->waitq) &&
-	    !atomic64_read(&iocg->abs_vdebt) &&
+	if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt &&
 	    time_before_eq64(vtime + cost, now.vnow)) {
 		iocg_commit_bio(iocg, bio, cost);
 		return;
 	}
 
 	/*
-	 * We're over budget.  If @bio has to be issued regardless,
-	 * remember the abs_cost instead of advancing vtime.
-	 * iocg_kick_waitq() will pay off the debt before waking more IOs.
+	 * We activated above but w/o any synchronization. Deactivation is
+	 * synchronized with waitq.lock and we won't get deactivated as long
+	 * as we're waiting or has debt, so we're good if we're activated
+	 * here. In the unlikely case that we aren't, just issue the IO.
+	 */
+	spin_lock_irq(&iocg->waitq.lock);
+
+	if (unlikely(list_empty(&iocg->active_list))) {
+		spin_unlock_irq(&iocg->waitq.lock);
+		iocg_commit_bio(iocg, bio, cost);
+		return;
+	}
+
+	/*
+	 * We're over budget. If @bio has to be issued regardless, remember
+	 * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay
+	 * off the debt before waking more IOs.
+	 *
 	 * This way, the debt is continuously paid off each period with the
-	 * actual budget available to the cgroup.  If we just wound vtime,
-	 * we would incorrectly use the current hw_inuse for the entire
-	 * amount which, for example, can lead to the cgroup staying
-	 * blocked for a long time even with substantially raised hw_inuse.
+	 * actual budget available to the cgroup. If we just wound vtime, we
+	 * would incorrectly use the current hw_inuse for the entire amount
+	 * which, for example, can lead to the cgroup staying blocked for a
+	 * long time even with substantially raised hw_inuse.
+	 *
+	 * An iocg with vdebt should stay online so that the timer can keep
+	 * deducting its vdebt and [de]activate use_delay mechanism
+	 * accordingly. We don't want to race against the timer trying to
+	 * clear them and leave @iocg inactive w/ dangling use_delay heavily
+	 * penalizing the cgroup and its descendants.
 	 */
 	if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) {
-		atomic64_add(abs_cost, &iocg->abs_vdebt);
+		iocg->abs_vdebt += abs_cost;
 		if (iocg_kick_delay(iocg, &now, cost))
 			blkcg_schedule_throttle(rqos->q,
 					(bio->bi_opf & REQ_SWAP) == REQ_SWAP);
+		spin_unlock_irq(&iocg->waitq.lock);
 		return;
 	}
 
@@ -1756,20 +1782,6 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
 	 * All waiters are on iocg->waitq and the wait states are
 	 * synchronized using waitq.lock.
 	 */
-	spin_lock_irq(&iocg->waitq.lock);
-
-	/*
-	 * We activated above but w/o any synchronization.  Deactivation is
-	 * synchronized with waitq.lock and we won't get deactivated as
-	 * long as we're waiting, so we're good if we're activated here.
-	 * In the unlikely case that we are deactivated, just issue the IO.
-	 */
-	if (unlikely(list_empty(&iocg->active_list))) {
-		spin_unlock_irq(&iocg->waitq.lock);
-		iocg_commit_bio(iocg, bio, cost);
-		return;
-	}
-
 	init_waitqueue_func_entry(&wait.wait, iocg_wake_fn);
 	wait.wait.private = current;
 	wait.bio = bio;
@@ -1801,6 +1813,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq,
 	struct ioc_now now;
 	u32 hw_inuse;
 	u64 abs_cost, cost;
+	unsigned long flags;
 
 	/* bypass if disabled or for root cgroup */
 	if (!ioc->enabled || !iocg->level)
@@ -1820,15 +1833,28 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq,
 		iocg->cursor = bio_end;
 
 	/*
-	 * Charge if there's enough vtime budget and the existing request
-	 * has cost assigned.  Otherwise, account it as debt.  See debt
-	 * handling in ioc_rqos_throttle() for details.
+	 * Charge if there's enough vtime budget and the existing request has
+	 * cost assigned.
 	 */
 	if (rq->bio && rq->bio->bi_iocost_cost &&
-	    time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow))
+	    time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) {
 		iocg_commit_bio(iocg, bio, cost);
-	else
-		atomic64_add(abs_cost, &iocg->abs_vdebt);
+		return;
+	}
+
+	/*
+	 * Otherwise, account it as debt if @iocg is online, which it should
+	 * be for the vast majority of cases. See debt handling in
+	 * ioc_rqos_throttle() for details.
+	 */
+	spin_lock_irqsave(&iocg->waitq.lock, flags);
+	if (likely(!list_empty(&iocg->active_list))) {
+		iocg->abs_vdebt += abs_cost;
+		iocg_kick_delay(iocg, &now, cost);
+	} else {
+		iocg_commit_bio(iocg, bio, cost);
+	}
+	spin_unlock_irqrestore(&iocg->waitq.lock, flags);
 }
 
 static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio)
@@ -1998,7 +2024,6 @@ static void ioc_pd_init(struct blkg_policy_data *pd)
 	iocg->ioc = ioc;
 	atomic64_set(&iocg->vtime, now.vnow);
 	atomic64_set(&iocg->done_vtime, now.vnow);
-	atomic64_set(&iocg->abs_vdebt, 0);
 	atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period));
 	INIT_LIST_HEAD(&iocg->active_list);
 	iocg->hweight_active = HWEIGHT_WHOLE;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 8e56884fd2e9..a7785df2c944 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1222,8 +1222,10 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		rq = list_first_entry(list, struct request, queuelist);
 
 		hctx = rq->mq_hctx;
-		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
+		if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) {
+			blk_mq_put_driver_tag(rq);
 			break;
+		}
 
 		if (!blk_mq_get_driver_tag(rq)) {
 			/*
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 8641ba9793c5..9cb082f38b93 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -313,7 +313,7 @@ static void scale_up(struct rq_wb *rwb)
 	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
 	rwb_wake_all(rwb);
-	rwb_trace_step(rwb, "scale up");
+	rwb_trace_step(rwb, tracepoint_string("scale up"));
 }
 
 static void scale_down(struct rq_wb *rwb, bool hard_throttle)
@@ -322,7 +322,7 @@ static void scale_down(struct rq_wb *rwb, bool hard_throttle)
 		return;
 	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
-	rwb_trace_step(rwb, "scale down");
+	rwb_trace_step(rwb, tracepoint_string("scale down"));
 }
 
 static void rwb_arm_timer(struct rq_wb *rwb)
diff --git a/block/partitions/core.c b/block/partitions/core.c
index bc1ded1331b1..9ef48a8cff86 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -496,7 +496,7 @@ int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev)
 
 	if (!disk_part_scan_enabled(disk))
 		return 0;
-	if (bdev->bd_part_count || bdev->bd_openers > 1)
+	if (bdev->bd_part_count)
 		return -EBUSY;
 	res = invalidate_partition(disk, 0);
 	if (res)
diff --git a/crypto/Kconfig b/crypto/Kconfig
index c24a47406f8f..d5daf35431e3 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -370,7 +370,6 @@ config CRYPTO_CFB
 config CRYPTO_CTR
 	tristate "CTR support"
 	select CRYPTO_SKCIPHER
-	select CRYPTO_SEQIV
 	select CRYPTO_MANAGER
 	help
 	  CTR: Counter mode
@@ -1820,7 +1819,7 @@ config CRYPTO_DRBG_HASH
 config CRYPTO_DRBG_CTR
 	bool "Enable CTR DRBG"
 	select CRYPTO_AES
-	depends on CRYPTO_CTR
+	select CRYPTO_CTR
 	help
 	  Enable the CTR DRBG variant as defined in NIST SP800-90A.
 
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 69605e21af92..92abdf675992 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -403,7 +403,7 @@ static void crypto_wait_for_test(struct crypto_larval *larval)
 	err = wait_for_completion_killable(&larval->completion);
 	WARN_ON(err);
 	if (!err)
-		crypto_probing_notify(CRYPTO_MSG_ALG_LOADED, larval);
+		crypto_notify(CRYPTO_MSG_ALG_LOADED, larval);
 
 out:
 	crypto_larval_kill(&larval->alg);
@@ -716,17 +716,27 @@ EXPORT_SYMBOL_GPL(crypto_drop_spawn);
 
 static struct crypto_alg *crypto_spawn_alg(struct crypto_spawn *spawn)
 {
-	struct crypto_alg *alg;
+	struct crypto_alg *alg = ERR_PTR(-EAGAIN);
+	struct crypto_alg *target;
+	bool shoot = false;
 
 	down_read(&crypto_alg_sem);
-	alg = spawn->alg;
-	if (!spawn->dead && !crypto_mod_get(alg)) {
-		alg->cra_flags |= CRYPTO_ALG_DYING;
-		alg = NULL;
+	if (!spawn->dead) {
+		alg = spawn->alg;
+		if (!crypto_mod_get(alg)) {
+			target = crypto_alg_get(alg);
+			shoot = true;
+			alg = ERR_PTR(-EAGAIN);
+		}
 	}
 	up_read(&crypto_alg_sem);
 
-	return alg ?: ERR_PTR(-EAGAIN);
+	if (shoot) {
+		crypto_shoot_alg(target);
+		crypto_alg_put(target);
+	}
+
+	return alg;
 }
 
 struct crypto_tfm *crypto_spawn_tfm(struct crypto_spawn *spawn, u32 type,
@@ -904,6 +914,14 @@ out:
 }
 EXPORT_SYMBOL_GPL(crypto_enqueue_request);
 
+void crypto_enqueue_request_head(struct crypto_queue *queue,
+				 struct crypto_async_request *request)
+{
+	queue->qlen++;
+	list_add(&request->list, &queue->list);
+}
+EXPORT_SYMBOL_GPL(crypto_enqueue_request_head);
+
 struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue)
 {
 	struct list_head *request;
diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c
index 22df3799a17b..087c0ad09d38 100644
--- a/crypto/algif_rng.c
+++ b/crypto/algif_rng.c
@@ -61,7 +61,7 @@ static int rng_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct rng_ctx *ctx = ask->private;
-	int err = -EFAULT;
+	int err;
 	int genlen = 0;
 	u8 result[MAXSIZE];
 
diff --git a/crypto/api.c b/crypto/api.c
index 7d71a9b10e5f..edcf690800d4 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -333,12 +333,13 @@ static unsigned int crypto_ctxsize(struct crypto_alg *alg, u32 type, u32 mask)
 	return len;
 }
 
-static void crypto_shoot_alg(struct crypto_alg *alg)
+void crypto_shoot_alg(struct crypto_alg *alg)
 {
 	down_write(&crypto_alg_sem);
 	alg->cra_flags |= CRYPTO_ALG_DYING;
 	up_write(&crypto_alg_sem);
 }
+EXPORT_SYMBOL_GPL(crypto_shoot_alg);
 
 struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type,
 				      u32 mask)
diff --git a/crypto/blake2b_generic.c b/crypto/blake2b_generic.c
index 1d262374fa4e..0ffd8d92e308 100644
--- a/crypto/blake2b_generic.c
+++ b/crypto/blake2b_generic.c
@@ -129,7 +129,9 @@ static void blake2b_compress(struct blake2b_state *S,
 	ROUND(9);
 	ROUND(10);
 	ROUND(11);
-
+#ifdef CONFIG_CC_IS_CLANG
+#pragma nounroll /* https://bugs.llvm.org/show_bug.cgi?id=45803 */
+#endif
 	for (i = 0; i < 8; ++i)
 		S->h[i] = S->h[i] ^ v[i] ^ v[i + 8];
 }
diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c
index eb029ff1e05a..3655d9d3f5df 100644
--- a/crypto/crypto_engine.c
+++ b/crypto/crypto_engine.c
@@ -22,32 +22,36 @@
  * @err: error number
  */
 static void crypto_finalize_request(struct crypto_engine *engine,
-			     struct crypto_async_request *req, int err)
+				    struct crypto_async_request *req, int err)
 {
 	unsigned long flags;
-	bool finalize_cur_req = false;
+	bool finalize_req = false;
 	int ret;
 	struct crypto_engine_ctx *enginectx;
 
-	spin_lock_irqsave(&engine->queue_lock, flags);
-	if (engine->cur_req == req)
-		finalize_cur_req = true;
-	spin_unlock_irqrestore(&engine->queue_lock, flags);
+	/*
+	 * If hardware cannot enqueue more requests
+	 * and retry mechanism is not supported
+	 * make sure we are completing the current request
+	 */
+	if (!engine->retry_support) {
+		spin_lock_irqsave(&engine->queue_lock, flags);
+		if (engine->cur_req == req) {
+			finalize_req = true;
+			engine->cur_req = NULL;
+		}
+		spin_unlock_irqrestore(&engine->queue_lock, flags);
+	}
 
-	if (finalize_cur_req) {
+	if (finalize_req || engine->retry_support) {
 		enginectx = crypto_tfm_ctx(req->tfm);
-		if (engine->cur_req_prepared &&
+		if (enginectx->op.prepare_request &&
 		    enginectx->op.unprepare_request) {
 			ret = enginectx->op.unprepare_request(engine, req);
 			if (ret)
 				dev_err(engine->dev, "failed to unprepare request\n");
 		}
-		spin_lock_irqsave(&engine->queue_lock, flags);
-		engine->cur_req = NULL;
-		engine->cur_req_prepared = false;
-		spin_unlock_irqrestore(&engine->queue_lock, flags);
 	}
-
 	req->complete(req, err);
 
 	kthread_queue_work(engine->kworker, &engine->pump_requests);
@@ -74,7 +78,7 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 	spin_lock_irqsave(&engine->queue_lock, flags);
 
 	/* Make sure we are not already running a request */
-	if (engine->cur_req)
+	if (!engine->retry_support && engine->cur_req)
 		goto out;
 
 	/* If another context is idling then defer */
@@ -108,13 +112,21 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 		goto out;
 	}
 
+start_request:
 	/* Get the fist request from the engine queue to handle */
 	backlog = crypto_get_backlog(&engine->queue);
 	async_req = crypto_dequeue_request(&engine->queue);
 	if (!async_req)
 		goto out;
 
-	engine->cur_req = async_req;
+	/*
+	 * If hardware doesn't support the retry mechanism,
+	 * keep track of the request we are processing now.
+	 * We'll need it on completion (crypto_finalize_request).
+	 */
+	if (!engine->retry_support)
+		engine->cur_req = async_req;
+
 	if (backlog)
 		backlog->complete(backlog, -EINPROGRESS);
 
@@ -130,7 +142,7 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 		ret = engine->prepare_crypt_hardware(engine);
 		if (ret) {
 			dev_err(engine->dev, "failed to prepare crypt hardware\n");
-			goto req_err;
+			goto req_err_2;
 		}
 	}
 
@@ -141,28 +153,90 @@ static void crypto_pump_requests(struct crypto_engine *engine,
 		if (ret) {
 			dev_err(engine->dev, "failed to prepare request: %d\n",
 				ret);
-			goto req_err;
+			goto req_err_2;
 		}
-		engine->cur_req_prepared = true;
 	}
 	if (!enginectx->op.do_one_request) {
 		dev_err(engine->dev, "failed to do request\n");
 		ret = -EINVAL;
-		goto req_err;
+		goto req_err_1;
 	}
+
 	ret = enginectx->op.do_one_request(engine, async_req);
-	if (ret) {
-		dev_err(engine->dev, "Failed to do one request from queue: %d\n", ret);
-		goto req_err;
+
+	/* Request unsuccessfully executed by hardware */
+	if (ret < 0) {
+		/*
+		 * If hardware queue is full (-ENOSPC), requeue request
+		 * regardless of backlog flag.
+		 * Otherwise, unprepare and complete the request.
+		 */
+		if (!engine->retry_support ||
+		    (ret != -ENOSPC)) {
+			dev_err(engine->dev,
+				"Failed to do one request from queue: %d\n",
+				ret);
+			goto req_err_1;
+		}
+		/*
+		 * If retry mechanism is supported,
+		 * unprepare current request and
+		 * enqueue it back into crypto-engine queue.
+		 */
+		if (enginectx->op.unprepare_request) {
+			ret = enginectx->op.unprepare_request(engine,
+							      async_req);
+			if (ret)
+				dev_err(engine->dev,
+					"failed to unprepare request\n");
+		}
+		spin_lock_irqsave(&engine->queue_lock, flags);
+		/*
+		 * If hardware was unable to execute request, enqueue it
+		 * back in front of crypto-engine queue, to keep the order
+		 * of requests.
+		 */
+		crypto_enqueue_request_head(&engine->queue, async_req);
+
+		kthread_queue_work(engine->kworker, &engine->pump_requests);
+		goto out;
 	}
-	return;
 
-req_err:
-	crypto_finalize_request(engine, async_req, ret);
+	goto retry;
+
+req_err_1:
+	if (enginectx->op.unprepare_request) {
+		ret = enginectx->op.unprepare_request(engine, async_req);
+		if (ret)
+			dev_err(engine->dev, "failed to unprepare request\n");
+	}
+
+req_err_2:
+	async_req->complete(async_req, ret);
+
+retry:
+	/* If retry mechanism is supported, send new requests to engine */
+	if (engine->retry_support) {
+		spin_lock_irqsave(&engine->queue_lock, flags);
+		goto start_request;
+	}
 	return;
 
 out:
 	spin_unlock_irqrestore(&engine->queue_lock, flags);
+
+	/*
+	 * Batch requests is possible only if
+	 * hardware can enqueue multiple requests
+	 */
+	if (engine->do_batch_requests) {
+		ret = engine->do_batch_requests(engine);
+		if (ret)
+			dev_err(engine->dev, "failed to do batch requests: %d\n",
+				ret);
+	}
+
+	return;
 }
 
 static void crypto_pump_work(struct kthread_work *work)
@@ -386,15 +460,27 @@ int crypto_engine_stop(struct crypto_engine *engine)
 EXPORT_SYMBOL_GPL(crypto_engine_stop);
 
 /**
- * crypto_engine_alloc_init - allocate crypto hardware engine structure and
- * initialize it.
+ * crypto_engine_alloc_init_and_set - allocate crypto hardware engine structure
+ * and initialize it by setting the maximum number of entries in the software
+ * crypto-engine queue.
  * @dev: the device attached with one hardware engine
+ * @retry_support: whether hardware has support for retry mechanism
+ * @cbk_do_batch: pointer to a callback function to be invoked when executing a
+ *                a batch of requests.
+ *                This has the form:
+ *                callback(struct crypto_engine *engine)
+ *                where:
+ *                @engine: the crypto engine structure.
  * @rt: whether this queue is set to run as a realtime task
+ * @qlen: maximum size of the crypto-engine queue
  *
  * This must be called from context that can sleep.
  * Return: the crypto engine structure on success, else NULL.
  */
-struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
+struct crypto_engine *crypto_engine_alloc_init_and_set(struct device *dev,
+						       bool retry_support,
+						       int (*cbk_do_batch)(struct crypto_engine *engine),
+						       bool rt, int qlen)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO / 2 };
 	struct crypto_engine *engine;
@@ -411,12 +497,18 @@ struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
 	engine->running = false;
 	engine->busy = false;
 	engine->idling = false;
-	engine->cur_req_prepared = false;
+	engine->retry_support = retry_support;
 	engine->priv_data = dev;
+	/*
+	 * Batch requests is possible only if
+	 * hardware has support for retry mechanism.
+	 */
+	engine->do_batch_requests = retry_support ? cbk_do_batch : NULL;
+
 	snprintf(engine->name, sizeof(engine->name),
 		 "%s-engine", dev_name(dev));
 
-	crypto_init_queue(&engine->queue, CRYPTO_ENGINE_MAX_QLEN);
+	crypto_init_queue(&engine->queue, qlen);
 	spin_lock_init(&engine->queue_lock);
 
 	engine->kworker = kthread_create_worker(0, "%s", engine->name);
@@ -433,6 +525,22 @@ struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
 
 	return engine;
 }
+EXPORT_SYMBOL_GPL(crypto_engine_alloc_init_and_set);
+
+/**
+ * crypto_engine_alloc_init - allocate crypto hardware engine structure and
+ * initialize it.
+ * @dev: the device attached with one hardware engine
+ * @rt: whether this queue is set to run as a realtime task
+ *
+ * This must be called from context that can sleep.
+ * Return: the crypto engine structure on success, else NULL.
+ */
+struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
+{
+	return crypto_engine_alloc_init_and_set(dev, false, NULL, rt,
+						CRYPTO_ENGINE_MAX_QLEN);
+}
 EXPORT_SYMBOL_GPL(crypto_engine_alloc_init);
 
 /**
diff --git a/crypto/drbg.c b/crypto/drbg.c
index b6929eb5f565..37526eb8c5d5 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1087,10 +1087,6 @@ static void drbg_async_seed(struct work_struct *work)
 	if (ret)
 		goto unlock;
 
-	/* If nonblocking pool is initialized, deactivate Jitter RNG */
-	crypto_free_rng(drbg->jent);
-	drbg->jent = NULL;
-
 	/* Set seeded to false so that if __drbg_seed fails the
 	 * next generate call will trigger a reseed.
 	 */
@@ -1168,7 +1164,23 @@ static int drbg_seed(struct drbg_state *drbg, struct drbg_string *pers,
 						   entropylen);
 			if (ret) {
 				pr_devel("DRBG: jent failed with %d\n", ret);
-				goto out;
+
+				/*
+				 * Do not treat the transient failure of the
+				 * Jitter RNG as an error that needs to be
+				 * reported. The combined number of the
+				 * maximum reseed threshold times the maximum
+				 * number of Jitter RNG transient errors is
+				 * less than the reseed threshold required by
+				 * SP800-90A allowing us to treat the
+				 * transient errors as such.
+				 *
+				 * However, we mandate that at least the first
+				 * seeding operation must succeed with the
+				 * Jitter RNG.
+				 */
+				if (!reseed || ret != -EAGAIN)
+					goto out;
 			}
 
 			drbg_string_fill(&data1, entropy, entropylen * 2);
@@ -1294,8 +1306,10 @@ static inline int drbg_alloc_state(struct drbg_state *drbg)
 	if (IS_ENABLED(CONFIG_CRYPTO_FIPS)) {
 		drbg->prev = kzalloc(drbg_sec_strength(drbg->core->flags),
 				     GFP_KERNEL);
-		if (!drbg->prev)
+		if (!drbg->prev) {
+			ret = -ENOMEM;
 			goto fini;
+		}
 		drbg->fips_primed = false;
 	}
 
@@ -1492,6 +1506,8 @@ static int drbg_prepare_hrng(struct drbg_state *drbg)
 	if (list_empty(&drbg->test_data.list))
 		return 0;
 
+	drbg->jent = crypto_alloc_rng("jitterentropy_rng", 0, 0);
+
 	INIT_WORK(&drbg->seed_work, drbg_async_seed);
 
 	drbg->random_ready.owner = THIS_MODULE;
@@ -1512,8 +1528,6 @@ static int drbg_prepare_hrng(struct drbg_state *drbg)
 		return err;
 	}
 
-	drbg->jent = crypto_alloc_rng("jitterentropy_rng", 0, 0);
-
 	/*
 	 * Require frequent reseeds until the seed source is fully
 	 * initialized.
diff --git a/crypto/essiv.c b/crypto/essiv.c
index 465a89c9d1ef..a7f45dbc4ee2 100644
--- a/crypto/essiv.c
+++ b/crypto/essiv.c
@@ -66,7 +66,6 @@ static int essiv_skcipher_setkey(struct crypto_skcipher *tfm,
 				 const u8 *key, unsigned int keylen)
 {
 	struct essiv_tfm_ctx *tctx = crypto_skcipher_ctx(tfm);
-	SHASH_DESC_ON_STACK(desc, tctx->hash);
 	u8 salt[HASH_MAX_DIGESTSIZE];
 	int err;
 
@@ -78,8 +77,7 @@ static int essiv_skcipher_setkey(struct crypto_skcipher *tfm,
 	if (err)
 		return err;
 
-	desc->tfm = tctx->hash;
-	err = crypto_shash_digest(desc, key, keylen, salt);
+	err = crypto_shash_tfm_digest(tctx->hash, key, keylen, salt);
 	if (err)
 		return err;
 
diff --git a/crypto/internal.h b/crypto/internal.h
index d5ebc60c5143..ff06a3bd1ca1 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -65,6 +65,7 @@ void crypto_alg_tested(const char *name, int err);
 void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list,
 			  struct crypto_alg *nalg);
 void crypto_remove_final(struct list_head *list);
+void crypto_shoot_alg(struct crypto_alg *alg);
 struct crypto_tfm *__crypto_alloc_tfm(struct crypto_alg *alg, u32 type,
 				      u32 mask);
 void *crypto_create_tfm(struct crypto_alg *alg,
diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c
index a5ce8f96790f..b43684c0dade 100644
--- a/crypto/jitterentropy-kcapi.c
+++ b/crypto/jitterentropy-kcapi.c
@@ -108,6 +108,7 @@ void jent_get_nstime(__u64 *out)
 struct jitterentropy {
 	spinlock_t jent_lock;
 	struct rand_data *entropy_collector;
+	unsigned int reset_cnt;
 };
 
 static int jent_kcapi_init(struct crypto_tfm *tfm)
@@ -142,7 +143,33 @@ static int jent_kcapi_random(struct crypto_rng *tfm,
 	int ret = 0;
 
 	spin_lock(&rng->jent_lock);
+
+	/* Return a permanent error in case we had too many resets in a row. */
+	if (rng->reset_cnt > (1<<10)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
 	ret = jent_read_entropy(rng->entropy_collector, rdata, dlen);
+
+	/* Reset RNG in case of health failures */
+	if (ret < -1) {
+		pr_warn_ratelimited("Reset Jitter RNG due to health test failure: %s failure\n",
+				    (ret == -2) ? "Repetition Count Test" :
+						  "Adaptive Proportion Test");
+
+		rng->reset_cnt++;
+
+		ret = -EAGAIN;
+	} else {
+		rng->reset_cnt = 0;
+
+		/* Convert the Jitter RNG error into a usable error code */
+		if (ret == -1)
+			ret = -EINVAL;
+	}
+
+out:
 	spin_unlock(&rng->jent_lock);
 
 	return ret;
diff --git a/crypto/jitterentropy.c b/crypto/jitterentropy.c
index 042157f0d28b..57f4a1ac738b 100644
--- a/crypto/jitterentropy.c
+++ b/crypto/jitterentropy.c
@@ -2,7 +2,7 @@
  * Non-physical true random number generator based on timing jitter --
  * Jitter RNG standalone code.
  *
- * Copyright Stephan Mueller <smueller@chronox.de>, 2015 - 2019
+ * Copyright Stephan Mueller <smueller@chronox.de>, 2015 - 2020
  *
  * Design
  * ======
@@ -47,7 +47,7 @@
 
 /*
  * This Jitterentropy RNG is based on the jitterentropy library
- * version 2.1.2 provided at http://www.chronox.de/jent.html
+ * version 2.2.0 provided at http://www.chronox.de/jent.html
  */
 
 #ifdef __OPTIMIZE__
@@ -83,6 +83,22 @@ struct rand_data {
 	unsigned int memblocksize; /* Size of one memory block in bytes */
 	unsigned int memaccessloops; /* Number of memory accesses per random
 				      * bit generation */
+
+	/* Repetition Count Test */
+	int rct_count;			/* Number of stuck values */
+
+	/* Adaptive Proportion Test for a significance level of 2^-30 */
+#define JENT_APT_CUTOFF		325	/* Taken from SP800-90B sec 4.4.2 */
+#define JENT_APT_WINDOW_SIZE	512	/* Data window size */
+	/* LSB of time stamp to process */
+#define JENT_APT_LSB		16
+#define JENT_APT_WORD_MASK	(JENT_APT_LSB - 1)
+	unsigned int apt_observations;	/* Number of collected observations */
+	unsigned int apt_count;		/* APT counter */
+	unsigned int apt_base;		/* APT base reference */
+	unsigned int apt_base_set:1;	/* APT base reference set? */
+
+	unsigned int health_failure:1;	/* Permanent health failure */
 };
 
 /* Flags that can be used to initialize the RNG */
@@ -98,12 +114,201 @@ struct rand_data {
 				   * variations (2nd derivation of time is
 				   * zero). */
 #define JENT_ESTUCK		8 /* Too many stuck results during init. */
+#define JENT_EHEALTH		9 /* Health test failed during initialization */
+#define JENT_ERCT		10 /* RCT failed during initialization */
+
+#include "jitterentropy.h"
 
 /***************************************************************************
- * Helper functions
+ * Adaptive Proportion Test
+ *
+ * This test complies with SP800-90B section 4.4.2.
  ***************************************************************************/
 
-#include "jitterentropy.h"
+/**
+ * Reset the APT counter
+ *
+ * @ec [in] Reference to entropy collector
+ */
+static void jent_apt_reset(struct rand_data *ec, unsigned int delta_masked)
+{
+	/* Reset APT counter */
+	ec->apt_count = 0;
+	ec->apt_base = delta_masked;
+	ec->apt_observations = 0;
+}
+
+/**
+ * Insert a new entropy event into APT
+ *
+ * @ec [in] Reference to entropy collector
+ * @delta_masked [in] Masked time delta to process
+ */
+static void jent_apt_insert(struct rand_data *ec, unsigned int delta_masked)
+{
+	/* Initialize the base reference */
+	if (!ec->apt_base_set) {
+		ec->apt_base = delta_masked;
+		ec->apt_base_set = 1;
+		return;
+	}
+
+	if (delta_masked == ec->apt_base) {
+		ec->apt_count++;
+
+		if (ec->apt_count >= JENT_APT_CUTOFF)
+			ec->health_failure = 1;
+	}
+
+	ec->apt_observations++;
+
+	if (ec->apt_observations >= JENT_APT_WINDOW_SIZE)
+		jent_apt_reset(ec, delta_masked);
+}
+
+/***************************************************************************
+ * Stuck Test and its use as Repetition Count Test
+ *
+ * The Jitter RNG uses an enhanced version of the Repetition Count Test
+ * (RCT) specified in SP800-90B section 4.4.1. Instead of counting identical
+ * back-to-back values, the input to the RCT is the counting of the stuck
+ * values during the generation of one Jitter RNG output block.
+ *
+ * The RCT is applied with an alpha of 2^{-30} compliant to FIPS 140-2 IG 9.8.
+ *
+ * During the counting operation, the Jitter RNG always calculates the RCT
+ * cut-off value of C. If that value exceeds the allowed cut-off value,
+ * the Jitter RNG output block will be calculated completely but discarded at
+ * the end. The caller of the Jitter RNG is informed with an error code.
+ ***************************************************************************/
+
+/**
+ * Repetition Count Test as defined in SP800-90B section 4.4.1
+ *
+ * @ec [in] Reference to entropy collector
+ * @stuck [in] Indicator whether the value is stuck
+ */
+static void jent_rct_insert(struct rand_data *ec, int stuck)
+{
+	/*
+	 * If we have a count less than zero, a previous RCT round identified
+	 * a failure. We will not overwrite it.
+	 */
+	if (ec->rct_count < 0)
+		return;
+
+	if (stuck) {
+		ec->rct_count++;
+
+		/*
+		 * The cutoff value is based on the following consideration:
+		 * alpha = 2^-30 as recommended in FIPS 140-2 IG 9.8.
+		 * In addition, we require an entropy value H of 1/OSR as this
+		 * is the minimum entropy required to provide full entropy.
+		 * Note, we collect 64 * OSR deltas for inserting them into
+		 * the entropy pool which should then have (close to) 64 bits
+		 * of entropy.
+		 *
+		 * Note, ec->rct_count (which equals to value B in the pseudo
+		 * code of SP800-90B section 4.4.1) starts with zero. Hence
+		 * we need to subtract one from the cutoff value as calculated
+		 * following SP800-90B.
+		 */
+		if ((unsigned int)ec->rct_count >= (31 * ec->osr)) {
+			ec->rct_count = -1;
+			ec->health_failure = 1;
+		}
+	} else {
+		ec->rct_count = 0;
+	}
+}
+
+/**
+ * Is there an RCT health test failure?
+ *
+ * @ec [in] Reference to entropy collector
+ *
+ * @return
+ * 	0 No health test failure
+ * 	1 Permanent health test failure
+ */
+static int jent_rct_failure(struct rand_data *ec)
+{
+	if (ec->rct_count < 0)
+		return 1;
+	return 0;
+}
+
+static inline __u64 jent_delta(__u64 prev, __u64 next)
+{
+#define JENT_UINT64_MAX		(__u64)(~((__u64) 0))
+	return (prev < next) ? (next - prev) :
+			       (JENT_UINT64_MAX - prev + 1 + next);
+}
+
+/**
+ * Stuck test by checking the:
+ * 	1st derivative of the jitter measurement (time delta)
+ * 	2nd derivative of the jitter measurement (delta of time deltas)
+ * 	3rd derivative of the jitter measurement (delta of delta of time deltas)
+ *
+ * All values must always be non-zero.
+ *
+ * @ec [in] Reference to entropy collector
+ * @current_delta [in] Jitter time delta
+ *
+ * @return
+ * 	0 jitter measurement not stuck (good bit)
+ * 	1 jitter measurement stuck (reject bit)
+ */
+static int jent_stuck(struct rand_data *ec, __u64 current_delta)
+{
+	__u64 delta2 = jent_delta(ec->last_delta, current_delta);
+	__u64 delta3 = jent_delta(ec->last_delta2, delta2);
+	unsigned int delta_masked = current_delta & JENT_APT_WORD_MASK;
+
+	ec->last_delta = current_delta;
+	ec->last_delta2 = delta2;
+
+	/*
+	 * Insert the result of the comparison of two back-to-back time
+	 * deltas.
+	 */
+	jent_apt_insert(ec, delta_masked);
+
+	if (!current_delta || !delta2 || !delta3) {
+		/* RCT with a stuck bit */
+		jent_rct_insert(ec, 1);
+		return 1;
+	}
+
+	/* RCT with a non-stuck bit */
+	jent_rct_insert(ec, 0);
+
+	return 0;
+}
+
+/**
+ * Report any health test failures
+ *
+ * @ec [in] Reference to entropy collector
+ *
+ * @return
+ * 	0 No health test failure
+ * 	1 Permanent health test failure
+ */
+static int jent_health_failure(struct rand_data *ec)
+{
+	/* Test is only enabled in FIPS mode */
+	if (!jent_fips_enabled())
+		return 0;
+
+	return ec->health_failure;
+}
+
+/***************************************************************************
+ * Noise sources
+ ***************************************************************************/
 
 /**
  * Update of the loop count used for the next round of
@@ -148,10 +353,6 @@ static __u64 jent_loop_shuffle(struct rand_data *ec,
 	return (shuffle + (1<<min));
 }
 
-/***************************************************************************
- * Noise sources
- ***************************************************************************/
-
 /**
  * CPU Jitter noise source -- this is the noise source based on the CPU
  *			      execution time jitter
@@ -166,18 +367,19 @@ static __u64 jent_loop_shuffle(struct rand_data *ec,
  * the CPU execution time jitter. Any change to the loop in this function
  * implies that careful retesting must be done.
  *
- * Input:
- * @ec entropy collector struct
- * @time time stamp to be injected
- * @loop_cnt if a value not equal to 0 is set, use the given value as number of
- *	     loops to perform the folding
+ * @ec [in] entropy collector struct
+ * @time [in] time stamp to be injected
+ * @loop_cnt [in] if a value not equal to 0 is set, use the given value as
+ *		  number of loops to perform the folding
+ * @stuck [in] Is the time stamp identified as stuck?
  *
  * Output:
  * updated ec->data
  *
  * @return Number of loops the folding operation is performed
  */
-static __u64 jent_lfsr_time(struct rand_data *ec, __u64 time, __u64 loop_cnt)
+static void jent_lfsr_time(struct rand_data *ec, __u64 time, __u64 loop_cnt,
+			   int stuck)
 {
 	unsigned int i;
 	__u64 j = 0;
@@ -220,9 +422,17 @@ static __u64 jent_lfsr_time(struct rand_data *ec, __u64 time, __u64 loop_cnt)
 			new ^= tmp;
 		}
 	}
-	ec->data = new;
 
-	return fold_loop_cnt;
+	/*
+	 * If the time stamp is stuck, do not finally insert the value into
+	 * the entropy pool. Although this operation should not do any harm
+	 * even when the time stamp has no entropy, SP800-90B requires that
+	 * any conditioning operation (SP800-90B considers the LFSR to be a
+	 * conditioning operation) to have an identical amount of input
+	 * data according to section 3.1.5.
+	 */
+	if (!stuck)
+		ec->data = new;
 }
 
 /**
@@ -243,16 +453,13 @@ static __u64 jent_lfsr_time(struct rand_data *ec, __u64 time, __u64 loop_cnt)
  * to reliably access either L3 or memory, the ec->mem memory must be quite
  * large which is usually not desirable.
  *
- * Input:
- * @ec Reference to the entropy collector with the memory access data -- if
- *     the reference to the memory block to be accessed is NULL, this noise
- *     source is disabled
- * @loop_cnt if a value not equal to 0 is set, use the given value as number of
- *	     loops to perform the folding
- *
- * @return Number of memory access operations
+ * @ec [in] Reference to the entropy collector with the memory access data -- if
+ *	    the reference to the memory block to be accessed is NULL, this noise
+ *	    source is disabled
+ * @loop_cnt [in] if a value not equal to 0 is set, use the given value
+ *		  number of loops to perform the LFSR
  */
-static unsigned int jent_memaccess(struct rand_data *ec, __u64 loop_cnt)
+static void jent_memaccess(struct rand_data *ec, __u64 loop_cnt)
 {
 	unsigned int wrap = 0;
 	__u64 i = 0;
@@ -262,7 +469,7 @@ static unsigned int jent_memaccess(struct rand_data *ec, __u64 loop_cnt)
 		jent_loop_shuffle(ec, MAX_ACC_LOOP_BIT, MIN_ACC_LOOP_BIT);
 
 	if (NULL == ec || NULL == ec->mem)
-		return 0;
+		return;
 	wrap = ec->memblocksize * ec->memblocks;
 
 	/*
@@ -288,43 +495,11 @@ static unsigned int jent_memaccess(struct rand_data *ec, __u64 loop_cnt)
 		ec->memlocation = ec->memlocation + ec->memblocksize - 1;
 		ec->memlocation = ec->memlocation % wrap;
 	}
-	return i;
 }
 
 /***************************************************************************
  * Start of entropy processing logic
  ***************************************************************************/
-
-/**
- * Stuck test by checking the:
- *	1st derivation of the jitter measurement (time delta)
- *	2nd derivation of the jitter measurement (delta of time deltas)
- *	3rd derivation of the jitter measurement (delta of delta of time deltas)
- *
- * All values must always be non-zero.
- *
- * Input:
- * @ec Reference to entropy collector
- * @current_delta Jitter time delta
- *
- * @return
- *	0 jitter measurement not stuck (good bit)
- *	1 jitter measurement stuck (reject bit)
- */
-static int jent_stuck(struct rand_data *ec, __u64 current_delta)
-{
-	__s64 delta2 = ec->last_delta - current_delta;
-	__s64 delta3 = delta2 - ec->last_delta2;
-
-	ec->last_delta = current_delta;
-	ec->last_delta2 = delta2;
-
-	if (!current_delta || !delta2 || !delta3)
-		return 1;
-
-	return 0;
-}
-
 /**
  * This is the heart of the entropy generation: calculate time deltas and
  * use the CPU jitter in the time deltas. The jitter is injected into the
@@ -334,8 +509,7 @@ static int jent_stuck(struct rand_data *ec, __u64 current_delta)
  *	    of this function! This can be done by calling this function
  *	    and not using its result.
  *
- * Input:
- * @entropy_collector Reference to entropy collector
+ * @ec [in] Reference to entropy collector
  *
  * @return result of stuck test
  */
@@ -343,6 +517,7 @@ static int jent_measure_jitter(struct rand_data *ec)
 {
 	__u64 time = 0;
 	__u64 current_delta = 0;
+	int stuck;
 
 	/* Invoke one noise source before time measurement to add variations */
 	jent_memaccess(ec, 0);
@@ -352,22 +527,23 @@ static int jent_measure_jitter(struct rand_data *ec)
 	 * invocation to measure the timing variations
 	 */
 	jent_get_nstime(&time);
-	current_delta = time - ec->prev_time;
+	current_delta = jent_delta(ec->prev_time, time);
 	ec->prev_time = time;
 
+	/* Check whether we have a stuck measurement. */
+	stuck = jent_stuck(ec, current_delta);
+
 	/* Now call the next noise sources which also injects the data */
-	jent_lfsr_time(ec, current_delta, 0);
+	jent_lfsr_time(ec, current_delta, 0, stuck);
 
-	/* Check whether we have a stuck measurement. */
-	return jent_stuck(ec, current_delta);
+	return stuck;
 }
 
 /**
  * Generator of one 64 bit random number
  * Function fills rand_data->data
  *
- * Input:
- * @ec Reference to entropy collector
+ * @ec [in] Reference to entropy collector
  */
 static void jent_gen_entropy(struct rand_data *ec)
 {
@@ -391,31 +567,6 @@ static void jent_gen_entropy(struct rand_data *ec)
 }
 
 /**
- * The continuous test required by FIPS 140-2 -- the function automatically
- * primes the test if needed.
- *
- * Return:
- * returns normally if FIPS test passed
- * panics the kernel if FIPS test failed
- */
-static void jent_fips_test(struct rand_data *ec)
-{
-	if (!jent_fips_enabled())
-		return;
-
-	/* prime the FIPS test */
-	if (!ec->old_data) {
-		ec->old_data = ec->data;
-		jent_gen_entropy(ec);
-	}
-
-	if (ec->data == ec->old_data)
-		jent_panic("jitterentropy: Duplicate output detected\n");
-
-	ec->old_data = ec->data;
-}
-
-/**
  * Entry function: Obtain entropy for the caller.
  *
  * This function invokes the entropy gathering logic as often to generate
@@ -425,17 +576,18 @@ static void jent_fips_test(struct rand_data *ec)
  * This function truncates the last 64 bit entropy value output to the exact
  * size specified by the caller.
  *
- * Input:
- * @ec Reference to entropy collector
- * @data pointer to buffer for storing random data -- buffer must already
- *	 exist
- * @len size of the buffer, specifying also the requested number of random
- *	in bytes
+ * @ec [in] Reference to entropy collector
+ * @data [in] pointer to buffer for storing random data -- buffer must already
+ *	      exist
+ * @len [in] size of the buffer, specifying also the requested number of random
+ *	     in bytes
  *
  * @return 0 when request is fulfilled or an error
  *
  * The following error codes can occur:
  *	-1	entropy_collector is NULL
+ *	-2	RCT failed
+ *	-3	APT test failed
  */
 int jent_read_entropy(struct rand_data *ec, unsigned char *data,
 		      unsigned int len)
@@ -449,7 +601,42 @@ int jent_read_entropy(struct rand_data *ec, unsigned char *data,
 		unsigned int tocopy;
 
 		jent_gen_entropy(ec);
-		jent_fips_test(ec);
+
+		if (jent_health_failure(ec)) {
+			int ret;
+
+			if (jent_rct_failure(ec))
+				ret = -2;
+			else
+				ret = -3;
+
+			/*
+			 * Re-initialize the noise source
+			 *
+			 * If the health test fails, the Jitter RNG remains
+			 * in failure state and will return a health failure
+			 * during next invocation.
+			 */
+			if (jent_entropy_init())
+				return ret;
+
+			/* Set APT to initial state */
+			jent_apt_reset(ec, 0);
+			ec->apt_base_set = 0;
+
+			/* Set RCT to initial state */
+			ec->rct_count = 0;
+
+			/* Re-enable Jitter RNG */
+			ec->health_failure = 0;
+
+			/*
+			 * Return the health test failure status to the
+			 * caller as the generated value is not appropriate.
+			 */
+			return ret;
+		}
+
 		if ((DATA_SIZE_BITS / 8) < len)
 			tocopy = (DATA_SIZE_BITS / 8);
 		else
@@ -513,11 +700,15 @@ int jent_entropy_init(void)
 	int i;
 	__u64 delta_sum = 0;
 	__u64 old_delta = 0;
+	unsigned int nonstuck = 0;
 	int time_backwards = 0;
 	int count_mod = 0;
 	int count_stuck = 0;
 	struct rand_data ec = { 0 };
 
+	/* Required for RCT */
+	ec.osr = 1;
+
 	/* We could perform statistical tests here, but the problem is
 	 * that we only have a few loop counts to do testing. These
 	 * loop counts may show some slight skew and we produce
@@ -539,8 +730,10 @@ int jent_entropy_init(void)
 	/*
 	 * TESTLOOPCOUNT needs some loops to identify edge systems. 100 is
 	 * definitely too little.
+	 *
+	 * SP800-90B requires at least 1024 initial test cycles.
 	 */
-#define TESTLOOPCOUNT 300
+#define TESTLOOPCOUNT 1024
 #define CLEARCACHE 100
 	for (i = 0; (TESTLOOPCOUNT + CLEARCACHE) > i; i++) {
 		__u64 time = 0;
@@ -552,13 +745,13 @@ int jent_entropy_init(void)
 		/* Invoke core entropy collection logic */
 		jent_get_nstime(&time);
 		ec.prev_time = time;
-		jent_lfsr_time(&ec, time, 0);
+		jent_lfsr_time(&ec, time, 0, 0);
 		jent_get_nstime(&time2);
 
 		/* test whether timer works */
 		if (!time || !time2)
 			return JENT_ENOTIME;
-		delta = time2 - time;
+		delta = jent_delta(time, time2);
 		/*
 		 * test whether timer is fine grained enough to provide
 		 * delta even when called shortly after each other -- this
@@ -581,6 +774,28 @@ int jent_entropy_init(void)
 
 		if (stuck)
 			count_stuck++;
+		else {
+			nonstuck++;
+
+			/*
+			 * Ensure that the APT succeeded.
+			 *
+			 * With the check below that count_stuck must be less
+			 * than 10% of the overall generated raw entropy values
+			 * it is guaranteed that the APT is invoked at
+			 * floor((TESTLOOPCOUNT * 0.9) / 64) == 14 times.
+			 */
+			if ((nonstuck % JENT_APT_WINDOW_SIZE) == 0) {
+				jent_apt_reset(&ec,
+					       delta & JENT_APT_WORD_MASK);
+				if (jent_health_failure(&ec))
+					return JENT_EHEALTH;
+			}
+		}
+
+		/* Validate RCT */
+		if (jent_rct_failure(&ec))
+			return JENT_ERCT;
 
 		/* test whether we have an increasing timer */
 		if (!(time2 > time))
diff --git a/crypto/lrw.c b/crypto/lrw.c
index 376d7ed3f1f8..5b07a7c09296 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -287,7 +287,7 @@ static void exit_tfm(struct crypto_skcipher *tfm)
 	crypto_free_skcipher(ctx->child);
 }
 
-static void free(struct skcipher_instance *inst)
+static void crypto_lrw_free(struct skcipher_instance *inst)
 {
 	crypto_drop_skcipher(skcipher_instance_ctx(inst));
 	kfree(inst);
@@ -400,12 +400,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->alg.encrypt = encrypt;
 	inst->alg.decrypt = decrypt;
 
-	inst->free = free;
+	inst->free = crypto_lrw_free;
 
 	err = skcipher_register_instance(tmpl, inst);
 	if (err) {
 err_free_inst:
-		free(inst);
+		crypto_lrw_free(inst);
 	}
 	return err;
 }
diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c
index 7c57b844c382..1d43472fecbd 100644
--- a/crypto/sha1_generic.c
+++ b/crypto/sha1_generic.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
@@ -31,10 +30,10 @@ EXPORT_SYMBOL_GPL(sha1_zero_message_hash);
 static void sha1_generic_block_fn(struct sha1_state *sst, u8 const *src,
 				  int blocks)
 {
-	u32 temp[SHA_WORKSPACE_WORDS];
+	u32 temp[SHA1_WORKSPACE_WORDS];
 
 	while (blocks--) {
-		sha_transform(sst->state, src, temp);
+		sha1_transform(sst->state, src, temp);
 		src += SHA1_BLOCK_SIZE;
 	}
 	memzero_explicit(temp, sizeof(temp));
diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c
index f2d7095d4f2d..88156e3e2a33 100644
--- a/crypto/sha256_generic.c
+++ b/crypto/sha256_generic.c
@@ -35,27 +35,31 @@ EXPORT_SYMBOL_GPL(sha256_zero_message_hash);
 
 static int crypto_sha256_init(struct shash_desc *desc)
 {
-	return sha256_init(shash_desc_ctx(desc));
+	sha256_init(shash_desc_ctx(desc));
+	return 0;
 }
 
 static int crypto_sha224_init(struct shash_desc *desc)
 {
-	return sha224_init(shash_desc_ctx(desc));
+	sha224_init(shash_desc_ctx(desc));
+	return 0;
 }
 
 int crypto_sha256_update(struct shash_desc *desc, const u8 *data,
 			  unsigned int len)
 {
-	return sha256_update(shash_desc_ctx(desc), data, len);
+	sha256_update(shash_desc_ctx(desc), data, len);
+	return 0;
 }
 EXPORT_SYMBOL(crypto_sha256_update);
 
 static int crypto_sha256_final(struct shash_desc *desc, u8 *out)
 {
 	if (crypto_shash_digestsize(desc->tfm) == SHA224_DIGEST_SIZE)
-		return sha224_final(shash_desc_ctx(desc), out);
+		sha224_final(shash_desc_ctx(desc), out);
 	else
-		return sha256_final(shash_desc_ctx(desc), out);
+		sha256_final(shash_desc_ctx(desc), out);
+	return 0;
 }
 
 int crypto_sha256_finup(struct shash_desc *desc, const u8 *data,
diff --git a/crypto/shash.c b/crypto/shash.c
index c075b26c2a1d..e6a4b5f39b8c 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -206,6 +206,22 @@ int crypto_shash_digest(struct shash_desc *desc, const u8 *data,
 }
 EXPORT_SYMBOL_GPL(crypto_shash_digest);
 
+int crypto_shash_tfm_digest(struct crypto_shash *tfm, const u8 *data,
+			    unsigned int len, u8 *out)
+{
+	SHASH_DESC_ON_STACK(desc, tfm);
+	int err;
+
+	desc->tfm = tfm;
+
+	err = crypto_shash_digest(desc, data, len, out);
+
+	shash_desc_zero(desc);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(crypto_shash_tfm_digest);
+
 static int shash_default_export(struct shash_desc *desc, void *out)
 {
 	memcpy(out, shash_desc_ctx(desc), crypto_shash_descsize(desc->tfm));
diff --git a/crypto/xts.c b/crypto/xts.c
index dbdd8af629e6..3565f3b863a6 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -322,7 +322,7 @@ static void exit_tfm(struct crypto_skcipher *tfm)
 	crypto_free_cipher(ctx->tweak);
 }
 
-static void free(struct skcipher_instance *inst)
+static void crypto_xts_free(struct skcipher_instance *inst)
 {
 	crypto_drop_skcipher(skcipher_instance_ctx(inst));
 	kfree(inst);
@@ -434,12 +434,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->alg.encrypt = encrypt;
 	inst->alg.decrypt = decrypt;
 
-	inst->free = free;
+	inst->free = crypto_xts_free;
 
 	err = skcipher_register_instance(tmpl, inst);
 	if (err) {
 err_free_inst:
-		free(inst);
+		crypto_xts_free(inst);
 	}
 	return err;
 }
diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c
index 01962c63a711..f2d0e5915dab 100644
--- a/drivers/acpi/arm64/gtdt.c
+++ b/drivers/acpi/arm64/gtdt.c
@@ -394,7 +394,7 @@ static int __init gtdt_sbsa_gwdt_init(void)
 	 */
 	ret = acpi_gtdt_init(table, &timer_count);
 	if (ret || !timer_count)
-		return ret;
+		goto out_put_gtdt;
 
 	for_each_platform_timer(platform_timer) {
 		if (is_non_secure_watchdog(platform_timer)) {
@@ -408,6 +408,8 @@ static int __init gtdt_sbsa_gwdt_init(void)
 	if (gwdt_count)
 		pr_info("found %d SBSA generic Watchdog(s).\n", gwdt_count);
 
+out_put_gtdt:
+	acpi_put_table(table);
 	return ret;
 }
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 7d04424189df..28a6b387e80e 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -299,61 +299,8 @@ out:
 	return status;
 }
 
-struct iort_workaround_oem_info {
-	char oem_id[ACPI_OEM_ID_SIZE + 1];
-	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
-	u32 oem_revision;
-};
-
-static bool apply_id_count_workaround;
-
-static struct iort_workaround_oem_info wa_info[] __initdata = {
-	{
-		.oem_id		= "HISI  ",
-		.oem_table_id	= "HIP07   ",
-		.oem_revision	= 0,
-	}, {
-		.oem_id		= "HISI  ",
-		.oem_table_id	= "HIP08   ",
-		.oem_revision	= 0,
-	}
-};
-
-static void __init
-iort_check_id_count_workaround(struct acpi_table_header *tbl)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(wa_info); i++) {
-		if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) &&
-		    !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) &&
-		    wa_info[i].oem_revision == tbl->oem_revision) {
-			apply_id_count_workaround = true;
-			pr_warn(FW_BUG "ID count for ID mapping entry is wrong, applying workaround\n");
-			break;
-		}
-	}
-}
-
-static inline u32 iort_get_map_max(struct acpi_iort_id_mapping *map)
-{
-	u32 map_max = map->input_base + map->id_count;
-
-	/*
-	 * The IORT specification revision D (Section 3, table 4, page 9) says
-	 * Number of IDs = The number of IDs in the range minus one, but the
-	 * IORT code ignored the "minus one", and some firmware did that too,
-	 * so apply a workaround here to keep compatible with both the spec
-	 * compliant and non-spec compliant firmwares.
-	 */
-	if (apply_id_count_workaround)
-		map_max--;
-
-	return map_max;
-}
-
 static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in,
-		       u32 *rid_out)
+		       u32 *rid_out, bool check_overlap)
 {
 	/* Single mapping does not care for input id */
 	if (map->flags & ACPI_IORT_ID_SINGLE_MAPPING) {
@@ -368,10 +315,37 @@ static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in,
 		return -ENXIO;
 	}
 
-	if (rid_in < map->input_base || rid_in > iort_get_map_max(map))
+	if (rid_in < map->input_base ||
+	    (rid_in > map->input_base + map->id_count))
 		return -ENXIO;
 
+	if (check_overlap) {
+		/*
+		 * We already found a mapping for this input ID at the end of
+		 * another region. If it coincides with the start of this
+		 * region, we assume the prior match was due to the off-by-1
+		 * issue mentioned below, and allow it to be superseded.
+		 * Otherwise, things are *really* broken, and we just disregard
+		 * duplicate matches entirely to retain compatibility.
+		 */
+		pr_err(FW_BUG "[map %p] conflicting mapping for input ID 0x%x\n",
+		       map, rid_in);
+		if (rid_in != map->input_base)
+			return -ENXIO;
+
+		pr_err(FW_BUG "applying workaround.\n");
+	}
+
 	*rid_out = map->output_base + (rid_in - map->input_base);
+
+	/*
+	 * Due to confusion regarding the meaning of the id_count field (which
+	 * carries the number of IDs *minus 1*), we may have to disregard this
+	 * match if it is at the end of the range, and overlaps with the start
+	 * of another one.
+	 */
+	if (map->id_count > 0 && rid_in == map->input_base + map->id_count)
+		return -EAGAIN;
 	return 0;
 }
 
@@ -414,6 +388,7 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
 static int iort_get_id_mapping_index(struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu_v3 *smmu;
+	struct acpi_iort_pmcg *pmcg;
 
 	switch (node->type) {
 	case ACPI_IORT_NODE_SMMU_V3:
@@ -441,6 +416,10 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node)
 
 		return smmu->id_mapping_index;
 	case ACPI_IORT_NODE_PMCG:
+		pmcg = (struct acpi_iort_pmcg *)node->node_data;
+		if (pmcg->overflow_gsiv || node->mapping_count == 0)
+			return -EINVAL;
+
 		return 0;
 	default:
 		return -EINVAL;
@@ -456,7 +435,8 @@ static struct acpi_iort_node *iort_node_map_id(struct acpi_iort_node *node,
 	/* Parse the ID mapping tree to find specified node type */
 	while (node) {
 		struct acpi_iort_id_mapping *map;
-		int i, index;
+		int i, index, rc = 0;
+		u32 out_ref = 0, map_id = id;
 
 		if (IORT_TYPE_MASK(node->type) & type_mask) {
 			if (id_out)
@@ -490,15 +470,18 @@ static struct acpi_iort_node *iort_node_map_id(struct acpi_iort_node *node,
 			if (i == index)
 				continue;
 
-			if (!iort_id_map(map, node->type, id, &id))
+			rc = iort_id_map(map, node->type, map_id, &id, out_ref);
+			if (!rc)
 				break;
+			if (rc == -EAGAIN)
+				out_ref = map->output_reference;
 		}
 
-		if (i == node->mapping_count)
+		if (i == node->mapping_count && !out_ref)
 			goto fail_map;
 
 		node = ACPI_ADD_PTR(struct acpi_iort_node, iort_table,
-				    map->output_reference);
+				    rc ? out_ref : map->output_reference);
 	}
 
 fail_map:
@@ -789,15 +772,6 @@ void acpi_configure_pmsi_domain(struct device *dev)
 		dev_set_msi_domain(dev, msi_domain);
 }
 
-static int __maybe_unused __get_pci_rid(struct pci_dev *pdev, u16 alias,
-					void *data)
-{
-	u32 *rid = data;
-
-	*rid = alias;
-	return 0;
-}
-
 #ifdef CONFIG_IOMMU_API
 static struct acpi_iort_node *iort_get_msi_resv_iommu(struct device *dev)
 {
@@ -1148,13 +1122,10 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	else
 		size = 1ULL << 32;
 
-	if (dev_is_pci(dev)) {
-		ret = acpi_dma_get_range(dev, &dmaaddr, &offset, &size);
-		if (ret == -ENODEV)
-			ret = rc_dma_get_range(dev, &size);
-	} else {
-		ret = nc_dma_get_range(dev, &size);
-	}
+	ret = acpi_dma_get_range(dev, &dmaaddr, &offset, &size);
+	if (ret == -ENODEV)
+		ret = dev_is_pci(dev) ? rc_dma_get_range(dev, &size)
+				      : nc_dma_get_range(dev, &size);
 
 	if (!ret) {
 		/*
@@ -1692,6 +1663,10 @@ void __init acpi_iort_init(void)
 {
 	acpi_status status;
 
+	/* iort_table will be used at runtime after the iort init,
+	 * so we don't need to call acpi_put_table() to release
+	 * the IORT table mapping.
+	 */
 	status = acpi_get_table(ACPI_SIG_IORT, 0, &iort_table);
 	if (ACPI_FAILURE(status)) {
 		if (status != AE_NOT_FOUND) {
@@ -1703,6 +1678,5 @@ void __init acpi_iort_init(void)
 		return;
 	}
 
-	iort_check_id_count_workaround(iort_table);
 	iort_init_platform_devices();
 }
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 00112cf15322..78cfc70cb320 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -88,18 +88,6 @@ static const struct dmi_system_id dmi_lid_quirks[] = {
 		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED,
 	},
 	{
-		/*
-		 * Asus T200TA, _LID keeps reporting closed after every second
-		 * openening of the lid. Causing immediate re-suspend after
-		 * opening every other open. Using LID_INIT_OPEN fixes this.
-		 */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"),
-		},
-		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
-	},
-	{
 		/* GP-electronic T701, _LID method points to a floating GPIO */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index b2263ec67b43..5832bc10aca8 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -273,13 +273,13 @@ int acpi_device_set_power(struct acpi_device *device, int state)
  end:
 	if (result) {
 		dev_warn(&device->dev, "Failed to change power state to %s\n",
-			 acpi_power_state_string(state));
+			 acpi_power_state_string(target_state));
 	} else {
 		device->power.state = target_state;
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "Device [%s] transitioned to %s\n",
 				  device->pnp.bus_id,
-				  acpi_power_state_string(state)));
+				  acpi_power_state_string(target_state)));
 	}
 
 	return result;
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index b4c0152e92aa..1af2125e17d5 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1994,23 +1994,35 @@ void acpi_ec_set_gpe_wake_mask(u8 action)
 		acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action);
 }
 
-bool acpi_ec_other_gpes_active(void)
-{
-	return acpi_any_gpe_status_set(first_ec ? first_ec->gpe : U32_MAX);
-}
-
 bool acpi_ec_dispatch_gpe(void)
 {
 	u32 ret;
 
 	if (!first_ec)
+		return acpi_any_gpe_status_set(U32_MAX);
+
+	/*
+	 * Report wakeup if the status bit is set for any enabled GPE other
+	 * than the EC one.
+	 */
+	if (acpi_any_gpe_status_set(first_ec->gpe))
+		return true;
+
+	if (ec_no_wakeup)
 		return false;
 
+	/*
+	 * Dispatch the EC GPE in-band, but do not report wakeup in any case
+	 * to allow the caller to process events properly after that.
+	 */
 	ret = acpi_dispatch_gpe(NULL, first_ec->gpe);
 	if (ret == ACPI_INTERRUPT_HANDLED) {
 		pm_pr_dbg("EC GPE dispatched\n");
-		return true;
+
+		/* Flush the event and query workqueues. */
+		acpi_ec_flush_work();
 	}
+
 	return false;
 }
 #endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index e387517d3354..43411a7457cd 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -202,7 +202,6 @@ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit);
 
 #ifdef CONFIG_PM_SLEEP
 void acpi_ec_flush_work(void);
-bool acpi_ec_other_gpes_active(void);
 bool acpi_ec_dispatch_gpe(void);
 #endif
 
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index 00a6da2121be..ed3d2182cf2c 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -322,10 +322,10 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq)
 		resource->res.data.extended_irq.polarity =
 		    link->irq.polarity;
 		if (link->irq.triggering == ACPI_EDGE_SENSITIVE)
-			resource->res.data.irq.shareable =
+			resource->res.data.extended_irq.shareable =
 			    ACPI_EXCLUSIVE;
 		else
-			resource->res.data.irq.shareable = ACPI_SHARED;
+			resource->res.data.extended_irq.shareable = ACPI_SHARED;
 		resource->res.data.extended_irq.interrupt_count = 1;
 		resource->res.data.extended_irq.interrupts[0] = irq;
 		/* ignore resource_source, it's optional */
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 4edc8a3ce40f..fd9d4e8318e9 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -980,13 +980,6 @@ static int acpi_s2idle_prepare_late(void)
 	return 0;
 }
 
-static void acpi_s2idle_sync(void)
-{
-	/* The EC driver uses special workqueues that need to be flushed. */
-	acpi_ec_flush_work();
-	acpi_os_wait_events_complete(); /* synchronize Notify handling */
-}
-
 static bool acpi_s2idle_wake(void)
 {
 	if (!acpi_sci_irq_valid())
@@ -1013,22 +1006,12 @@ static bool acpi_s2idle_wake(void)
 		if (acpi_check_wakeup_handlers())
 			return true;
 
-		/*
-		 * If the status bit is set for any enabled GPE other than the
-		 * EC one, the wakeup is regarded as a genuine one.
-		 */
-		if (acpi_ec_other_gpes_active())
+		/* Check non-EC GPE wakeups and dispatch the EC GPE. */
+		if (acpi_ec_dispatch_gpe())
 			return true;
 
 		/*
-		 * If the EC GPE status bit has not been set, the wakeup is
-		 * regarded as a spurious one.
-		 */
-		if (!acpi_ec_dispatch_gpe())
-			return false;
-
-		/*
-		 * Cancel the wakeup and process all pending events in case
+		 * Cancel the SCI wakeup and process all pending events in case
 		 * there are any wakeup ones in there.
 		 *
 		 * Note that if any non-EC GPEs are active at this point, the
@@ -1036,8 +1019,7 @@ static bool acpi_s2idle_wake(void)
 		 * should be missed by canceling the wakeup here.
 		 */
 		pm_system_cancel_wakeup();
-
-		acpi_s2idle_sync();
+		acpi_os_wait_events_complete();
 
 		/*
 		 * The SCI is in the "suspended" state now and it cannot produce
@@ -1070,7 +1052,8 @@ static void acpi_s2idle_restore(void)
 	 * of GPEs.
 	 */
 	acpi_os_wait_events_complete(); /* synchronize GPE processing */
-	acpi_s2idle_sync();
+	acpi_ec_flush_work(); /* flush the EC driver's workqueues */
+	acpi_os_wait_events_complete(); /* synchronize Notify handling */
 
 	s2idle_wakeup = false;
 
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index fe1523664816..8558b629880b 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -645,6 +645,7 @@ static void amba_device_initialize(struct amba_device *dev, const char *name)
 	dev->dev.release = amba_device_release;
 	dev->dev.bus = &amba_bustype;
 	dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
+	dev->dev.dma_parms = &dev->dma_parms;
 	dev->res.name = dev_name(&dev->dev);
 }
 
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 0101b65250cb..0c0a736eb861 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -410,6 +410,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */
 	{ PCI_VDEVICE(INTEL, 0x5ae3), board_ahci_mobile }, /* ApolloLake AHCI */
 	{ PCI_VDEVICE(INTEL, 0x34d3), board_ahci_mobile }, /* Ice Lake LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x02d3), board_ahci_mobile }, /* Comet Lake PCH-U AHCI */
 	{ PCI_VDEVICE(INTEL, 0x02d7), board_ahci_mobile }, /* Comet Lake PCH RAID */
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index a6b76cc12a66..e517bd8822a5 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -145,7 +145,7 @@ enum {
 
 	/* PORT_IDMA_CTL bits */
 	IDMA_CTL_RST_ATA	= (1 << 2),  /* hardreset ATA bus */
-	IDMA_CTL_RST_IDMA	= (1 << 5),  /* reset IDMA machinary */
+	IDMA_CTL_RST_IDMA	= (1 << 5),  /* reset IDMA machinery */
 	IDMA_CTL_GO		= (1 << 7),  /* IDMA mode go */
 	IDMA_CTL_ATA_NIEN	= (1 << 8),  /* ATA IRQ disable */
 
diff --git a/drivers/base/component.c b/drivers/base/component.c
index e97704104784..dcfbe7251dc4 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -256,7 +256,8 @@ static int try_to_bring_up_master(struct master *master,
 	ret = master->ops->bind(master->dev);
 	if (ret < 0) {
 		devres_release_group(master->dev, NULL);
-		dev_info(master->dev, "master bind failed: %d\n", ret);
+		if (ret != -EPROBE_DEFER)
+			dev_info(master->dev, "master bind failed: %d\n", ret);
 		return ret;
 	}
 
@@ -611,8 +612,9 @@ static int component_bind(struct component *component, struct master *master,
 		devres_release_group(component->dev, NULL);
 		devres_release_group(master->dev, NULL);
 
-		dev_err(master->dev, "failed to bind %s (ops %ps): %d\n",
-			dev_name(component->dev), component->ops, ret);
+		if (ret != -EPROBE_DEFER)
+			dev_err(master->dev, "failed to bind %s (ops %ps): %d\n",
+				dev_name(component->dev), component->ops, ret);
 	}
 
 	return ret;
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 89fcc0a09f94..57562e0f6308 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -365,6 +365,7 @@ struct device_link *device_link_add(struct device *consumer,
 				link->flags |= DL_FLAG_STATELESS;
 				goto reorder;
 			} else {
+				link->flags |= DL_FLAG_STATELESS;
 				goto out;
 			}
 		}
@@ -433,12 +434,16 @@ struct device_link *device_link_add(struct device *consumer,
 	    flags & DL_FLAG_PM_RUNTIME)
 		pm_runtime_resume(supplier);
 
+	list_add_tail_rcu(&link->s_node, &supplier->links.consumers);
+	list_add_tail_rcu(&link->c_node, &consumer->links.suppliers);
+
 	if (flags & DL_FLAG_SYNC_STATE_ONLY) {
 		dev_dbg(consumer,
 			"Linked as a sync state only consumer to %s\n",
 			dev_name(supplier));
 		goto out;
 	}
+
 reorder:
 	/*
 	 * Move the consumer and all of the devices depending on it to the end
@@ -449,12 +454,9 @@ reorder:
 	 */
 	device_reorder_to_tail(consumer, NULL);
 
-	list_add_tail_rcu(&link->s_node, &supplier->links.consumers);
-	list_add_tail_rcu(&link->c_node, &consumer->links.suppliers);
-
 	dev_dbg(consumer, "Linked as a consumer to %s\n", dev_name(supplier));
 
- out:
+out:
 	device_pm_unlock();
 	device_links_write_unlock();
 
@@ -829,6 +831,13 @@ static void __device_links_supplier_defer_sync(struct device *sup)
 		list_add_tail(&sup->links.defer_sync, &deferred_sync);
 }
 
+static void device_link_drop_managed(struct device_link *link)
+{
+	link->flags &= ~DL_FLAG_MANAGED;
+	WRITE_ONCE(link->status, DL_STATE_NONE);
+	kref_put(&link->kref, __device_link_del);
+}
+
 /**
  * device_links_driver_bound - Update device links after probing its driver.
  * @dev: Device to update the links for.
@@ -842,7 +851,7 @@ static void __device_links_supplier_defer_sync(struct device *sup)
  */
 void device_links_driver_bound(struct device *dev)
 {
-	struct device_link *link;
+	struct device_link *link, *ln;
 	LIST_HEAD(sync_list);
 
 	/*
@@ -882,18 +891,35 @@ void device_links_driver_bound(struct device *dev)
 	else
 		__device_links_queue_sync_state(dev, &sync_list);
 
-	list_for_each_entry(link, &dev->links.suppliers, c_node) {
+	list_for_each_entry_safe(link, ln, &dev->links.suppliers, c_node) {
+		struct device *supplier;
+
 		if (!(link->flags & DL_FLAG_MANAGED))
 			continue;
 
-		WARN_ON(link->status != DL_STATE_CONSUMER_PROBE);
-		WRITE_ONCE(link->status, DL_STATE_ACTIVE);
+		supplier = link->supplier;
+		if (link->flags & DL_FLAG_SYNC_STATE_ONLY) {
+			/*
+			 * When DL_FLAG_SYNC_STATE_ONLY is set, it means no
+			 * other DL_MANAGED_LINK_FLAGS have been set. So, it's
+			 * save to drop the managed link completely.
+			 */
+			device_link_drop_managed(link);
+		} else {
+			WARN_ON(link->status != DL_STATE_CONSUMER_PROBE);
+			WRITE_ONCE(link->status, DL_STATE_ACTIVE);
+		}
 
+		/*
+		 * This needs to be done even for the deleted
+		 * DL_FLAG_SYNC_STATE_ONLY device link in case it was the last
+		 * device link that was preventing the supplier from getting a
+		 * sync_state() call.
+		 */
 		if (defer_sync_state_count)
-			__device_links_supplier_defer_sync(link->supplier);
+			__device_links_supplier_defer_sync(supplier);
 		else
-			__device_links_queue_sync_state(link->supplier,
-							&sync_list);
+			__device_links_queue_sync_state(supplier, &sync_list);
 	}
 
 	dev->links.status = DL_DEV_DRIVER_BOUND;
@@ -903,13 +929,6 @@ void device_links_driver_bound(struct device *dev)
 	device_links_flush_sync_list(&sync_list, dev);
 }
 
-static void device_link_drop_managed(struct device_link *link)
-{
-	link->flags &= ~DL_FLAG_MANAGED;
-	WRITE_ONCE(link->status, DL_STATE_NONE);
-	kref_put(&link->kref, __device_link_del);
-}
-
 /**
  * __device_links_no_driver - Update links of a device without a driver.
  * @dev: Device without a drvier.
@@ -2370,6 +2389,11 @@ u32 fw_devlink_get_flags(void)
 	return fw_devlink_flags;
 }
 
+static bool fw_devlink_is_permissive(void)
+{
+	return fw_devlink_flags == DL_FLAG_SYNC_STATE_ONLY;
+}
+
 /**
  * device_add - add device to device hierarchy.
  * @dev: device.
@@ -2524,7 +2548,7 @@ int device_add(struct device *dev)
 	if (fw_devlink_flags && is_fwnode_dev &&
 	    fwnode_has_op(dev->fwnode, add_links)) {
 		fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev);
-		if (fw_ret == -ENODEV)
+		if (fw_ret == -ENODEV && !fw_devlink_is_permissive())
 			device_link_wait_for_mandatory_supplier(dev);
 		else if (fw_ret)
 			device_link_wait_for_optional_supplier(dev);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 06ec0e851fa1..94037be7f5d7 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -224,17 +224,9 @@ static int deferred_devs_show(struct seq_file *s, void *data)
 }
 DEFINE_SHOW_ATTRIBUTE(deferred_devs);
 
-#ifdef CONFIG_MODULES
-/*
- * In the case of modules, set the default probe timeout to
- * 30 seconds to give userland some time to load needed modules
- */
-int driver_deferred_probe_timeout = 30;
-#else
-/* In the case of !modules, no probe timeout needed */
-int driver_deferred_probe_timeout = -1;
-#endif
+int driver_deferred_probe_timeout;
 EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout);
+static DECLARE_WAIT_QUEUE_HEAD(probe_timeout_waitqueue);
 
 static int __init deferred_probe_timeout_setup(char *str)
 {
@@ -266,8 +258,8 @@ int driver_deferred_probe_check_state(struct device *dev)
 		return -ENODEV;
 	}
 
-	if (!driver_deferred_probe_timeout) {
-		dev_WARN(dev, "deferred probe timeout, ignoring dependency");
+	if (!driver_deferred_probe_timeout && initcalls_done) {
+		dev_warn(dev, "deferred probe timeout, ignoring dependency");
 		return -ETIMEDOUT;
 	}
 
@@ -284,6 +276,7 @@ static void deferred_probe_timeout_work_func(struct work_struct *work)
 
 	list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe)
 		dev_info(private->device, "deferred probe pending");
+	wake_up(&probe_timeout_waitqueue);
 }
 static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func);
 
@@ -658,6 +651,9 @@ int driver_probe_done(void)
  */
 void wait_for_device_probe(void)
 {
+	/* wait for probe timeout */
+	wait_event(probe_timeout_waitqueue, !driver_deferred_probe_timeout);
+
 	/* wait for the deferred probe workqueue to finish */
 	flush_work(&deferred_probe_work);
 
diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c
index ba9d30b28edc..a182e318bd09 100644
--- a/drivers/base/firmware_loader/fallback_table.c
+++ b/drivers/base/firmware_loader/fallback_table.c
@@ -45,5 +45,4 @@ struct ctl_table firmware_config_table[] = {
 	},
 	{ }
 };
-EXPORT_SYMBOL_GPL(firmware_config_table);
 #endif
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 10d7e818e118..50b8c0d43859 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -415,6 +415,9 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       "Node %d AnonPages:      %8lu kB\n"
 		       "Node %d Shmem:          %8lu kB\n"
 		       "Node %d KernelStack:    %8lu kB\n"
+#ifdef CONFIG_SHADOW_CALL_STACK
+		       "Node %d ShadowCallStack:%8lu kB\n"
+#endif
 		       "Node %d PageTables:     %8lu kB\n"
 		       "Node %d NFS_Unstable:   %8lu kB\n"
 		       "Node %d Bounce:         %8lu kB\n"
@@ -438,6 +441,9 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
 		       nid, K(i.sharedram),
 		       nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK_KB),
+#ifdef CONFIG_SHADOW_CALL_STACK
+		       nid, sum_zone_node_page_state(nid, NR_KERNEL_SCS_KB),
+#endif
 		       nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)),
 		       nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 		       nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index a07e28eab7d7..615c6b06b427 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -382,6 +382,8 @@ struct platform_object {
  */
 static void setup_pdev_dma_masks(struct platform_device *pdev)
 {
+	pdev->dev.dma_parms = &pdev->dma_parms;
+
 	if (!pdev->dev.coherent_dma_mask)
 		pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
 	if (!pdev->dev.dma_mask) {
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index fdd508a78ffd..0e07e17c2def 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -730,7 +730,7 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 
 	if (is_async(dev)) {
 		get_device(dev);
-		async_schedule(func, dev);
+		async_schedule_dev(func, dev);
 		return true;
 	}
 
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index e72843fe41df..089e5dc7144a 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -227,6 +227,9 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
+	if (count > (PAGE_SIZE << (MAX_ORDER - 1)))
+		count = PAGE_SIZE << (MAX_ORDER - 1);
+
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
@@ -371,6 +374,9 @@ static ssize_t regmap_reg_ranges_read_file(struct file *file,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
+	if (count > (PAGE_SIZE << (MAX_ORDER - 1)))
+		count = PAGE_SIZE << (MAX_ORDER - 1);
+
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c
index 008f8da69d97..62b95a9212ae 100644
--- a/drivers/base/regmap/regmap-i2c.c
+++ b/drivers/base/regmap/regmap-i2c.c
@@ -246,6 +246,63 @@ static const struct regmap_bus regmap_i2c_smbus_i2c_block = {
 	.max_raw_write = I2C_SMBUS_BLOCK_MAX,
 };
 
+static int regmap_i2c_smbus_i2c_write_reg16(void *context, const void *data,
+				      size_t count)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+
+	if (count < 2)
+		return -EINVAL;
+
+	count--;
+	return i2c_smbus_write_i2c_block_data(i2c, ((u8 *)data)[0], count,
+					      (u8 *)data + 1);
+}
+
+static int regmap_i2c_smbus_i2c_read_reg16(void *context, const void *reg,
+				     size_t reg_size, void *val,
+				     size_t val_size)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	int ret, count, len = val_size;
+
+	if (reg_size != 2)
+		return -EINVAL;
+
+	ret = i2c_smbus_write_byte_data(i2c, ((u16 *)reg)[0] & 0xff,
+					((u16 *)reg)[0] >> 8);
+	if (ret < 0)
+		return ret;
+
+	count = 0;
+	do {
+		/* Current Address Read */
+		ret = i2c_smbus_read_byte(i2c);
+		if (ret < 0)
+			break;
+
+		*((u8 *)val++) = ret;
+		count++;
+		len--;
+	} while (len > 0);
+
+	if (count == val_size)
+		return 0;
+	else if (ret < 0)
+		return ret;
+	else
+		return -EIO;
+}
+
+static const struct regmap_bus regmap_i2c_smbus_i2c_block_reg16 = {
+	.write = regmap_i2c_smbus_i2c_write_reg16,
+	.read = regmap_i2c_smbus_i2c_read_reg16,
+	.max_raw_read = I2C_SMBUS_BLOCK_MAX,
+	.max_raw_write = I2C_SMBUS_BLOCK_MAX,
+};
+
 static const struct regmap_bus *regmap_get_i2c_bus(struct i2c_client *i2c,
 					const struct regmap_config *config)
 {
@@ -255,6 +312,10 @@ static const struct regmap_bus *regmap_get_i2c_bus(struct i2c_client *i2c,
 		 i2c_check_functionality(i2c->adapter,
 					 I2C_FUNC_SMBUS_I2C_BLOCK))
 		return &regmap_i2c_smbus_i2c_block;
+	else if (config->val_bits == 8 && config->reg_bits == 16 &&
+		i2c_check_functionality(i2c->adapter,
+					I2C_FUNC_SMBUS_I2C_BLOCK))
+		return &regmap_i2c_smbus_i2c_block_reg16;
 	else if (config->val_bits == 16 && config->reg_bits == 8 &&
 		 i2c_check_functionality(i2c->adapter,
 					 I2C_FUNC_SMBUS_WORD_DATA))
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 3d64c9331a82..4340e1d268b6 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -541,8 +541,9 @@ static const struct irq_domain_ops regmap_domain_ops = {
 };
 
 /**
- * regmap_add_irq_chip() - Use standard regmap IRQ controller handling
+ * regmap_add_irq_chip_np() - Use standard regmap IRQ controller handling
  *
+ * @np: The device_node where the IRQ domain should be added to.
  * @map: The regmap for the device.
  * @irq: The IRQ the device uses to signal interrupts.
  * @irq_flags: The IRQF_ flags to use for the primary interrupt.
@@ -556,9 +557,10 @@ static const struct irq_domain_ops regmap_domain_ops = {
  * register cache.  The chip driver is responsible for restoring the
  * register values used by the IRQ controller over suspend and resume.
  */
-int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
-			int irq_base, const struct regmap_irq_chip *chip,
-			struct regmap_irq_chip_data **data)
+int regmap_add_irq_chip_np(struct device_node *np, struct regmap *map, int irq,
+			   int irq_flags, int irq_base,
+			   const struct regmap_irq_chip *chip,
+			   struct regmap_irq_chip_data **data)
 {
 	struct regmap_irq_chip_data *d;
 	int i;
@@ -769,12 +771,10 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
 	}
 
 	if (irq_base)
-		d->domain = irq_domain_add_legacy(map->dev->of_node,
-						  chip->num_irqs, irq_base, 0,
-						  &regmap_domain_ops, d);
+		d->domain = irq_domain_add_legacy(np, chip->num_irqs, irq_base,
+						  0, &regmap_domain_ops, d);
 	else
-		d->domain = irq_domain_add_linear(map->dev->of_node,
-						  chip->num_irqs,
+		d->domain = irq_domain_add_linear(np, chip->num_irqs,
 						  &regmap_domain_ops, d);
 	if (!d->domain) {
 		dev_err(map->dev, "Failed to create IRQ domain\n");
@@ -808,6 +808,30 @@ err_alloc:
 	kfree(d);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(regmap_add_irq_chip_np);
+
+/**
+ * regmap_add_irq_chip() - Use standard regmap IRQ controller handling
+ *
+ * @map: The regmap for the device.
+ * @irq: The IRQ the device uses to signal interrupts.
+ * @irq_flags: The IRQF_ flags to use for the primary interrupt.
+ * @irq_base: Allocate at specific IRQ number if irq_base > 0.
+ * @chip: Configuration for the interrupt controller.
+ * @data: Runtime data structure for the controller, allocated on success.
+ *
+ * Returns 0 on success or an errno on failure.
+ *
+ * This is the same as regmap_add_irq_chip_np, except that the device
+ * node of the regmap is used.
+ */
+int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
+			int irq_base, const struct regmap_irq_chip *chip,
+			struct regmap_irq_chip_data **data)
+{
+	return regmap_add_irq_chip_np(map->dev->of_node, map, irq, irq_flags,
+				      irq_base, chip, data);
+}
 EXPORT_SYMBOL_GPL(regmap_add_irq_chip);
 
 /**
@@ -875,9 +899,10 @@ static int devm_regmap_irq_chip_match(struct device *dev, void *res, void *data)
 }
 
 /**
- * devm_regmap_add_irq_chip() - Resource manager regmap_add_irq_chip()
+ * devm_regmap_add_irq_chip_np() - Resource manager regmap_add_irq_chip_np()
  *
  * @dev: The device pointer on which irq_chip belongs to.
+ * @np: The device_node where the IRQ domain should be added to.
  * @map: The regmap for the device.
  * @irq: The IRQ the device uses to signal interrupts
  * @irq_flags: The IRQF_ flags to use for the primary interrupt.
@@ -890,10 +915,11 @@ static int devm_regmap_irq_chip_match(struct device *dev, void *res, void *data)
  * The &regmap_irq_chip_data will be automatically released when the device is
  * unbound.
  */
-int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
-			     int irq_flags, int irq_base,
-			     const struct regmap_irq_chip *chip,
-			     struct regmap_irq_chip_data **data)
+int devm_regmap_add_irq_chip_np(struct device *dev, struct device_node *np,
+				struct regmap *map, int irq, int irq_flags,
+				int irq_base,
+				const struct regmap_irq_chip *chip,
+				struct regmap_irq_chip_data **data)
 {
 	struct regmap_irq_chip_data **ptr, *d;
 	int ret;
@@ -903,8 +929,8 @@ int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
 	if (!ptr)
 		return -ENOMEM;
 
-	ret = regmap_add_irq_chip(map, irq, irq_flags, irq_base,
-				  chip, &d);
+	ret = regmap_add_irq_chip_np(np, map, irq, irq_flags, irq_base,
+				     chip, &d);
 	if (ret < 0) {
 		devres_free(ptr);
 		return ret;
@@ -915,6 +941,32 @@ int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
 	*data = d;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(devm_regmap_add_irq_chip_np);
+
+/**
+ * devm_regmap_add_irq_chip() - Resource manager regmap_add_irq_chip()
+ *
+ * @dev: The device pointer on which irq_chip belongs to.
+ * @map: The regmap for the device.
+ * @irq: The IRQ the device uses to signal interrupts
+ * @irq_flags: The IRQF_ flags to use for the primary interrupt.
+ * @irq_base: Allocate at specific IRQ number if irq_base > 0.
+ * @chip: Configuration for the interrupt controller.
+ * @data: Runtime data structure for the controller, allocated on success
+ *
+ * Returns 0 on success or an errno on failure.
+ *
+ * The &regmap_irq_chip_data will be automatically released when the device is
+ * unbound.
+ */
+int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
+			     int irq_flags, int irq_base,
+			     const struct regmap_irq_chip *chip,
+			     struct regmap_irq_chip_data **data)
+{
+	return devm_regmap_add_irq_chip_np(dev, map->dev->of_node, map, irq,
+					   irq_flags, irq_base, chip, data);
+}
 EXPORT_SYMBOL_GPL(devm_regmap_add_irq_chip);
 
 /**
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 59f911e57719..c472f624382d 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -827,6 +827,7 @@ struct regmap *__regmap_init(struct device *dev,
 	} else if (!bus->read || !bus->write) {
 		map->reg_read = _regmap_bus_reg_read;
 		map->reg_write = _regmap_bus_reg_write;
+		map->reg_update_bits = bus->reg_update_bits;
 
 		map->defer_caching = false;
 		goto skip_format_initialization;
@@ -2936,6 +2937,28 @@ int regmap_update_bits_base(struct regmap *map, unsigned int reg,
 }
 EXPORT_SYMBOL_GPL(regmap_update_bits_base);
 
+/**
+ * regmap_test_bits() - Check if all specified bits are set in a register.
+ *
+ * @map: Register map to operate on
+ * @reg: Register to read from
+ * @bits: Bits to test
+ *
+ * Returns -1 if the underlying regmap_read() fails, 0 if at least one of the
+ * tested bits is not set and 1 if all tested bits are set.
+ */
+int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits)
+{
+	unsigned int val, ret;
+
+	ret = regmap_read(map, reg, &val);
+	if (ret)
+		return ret;
+
+	return (val & bits) == bits;
+}
+EXPORT_SYMBOL_GPL(regmap_test_bits);
+
 void regmap_async_complete_cb(struct regmap_async *async, int ret)
 {
 	struct regmap *map = async->map;
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
index 62b660821dbc..81b311c9d781 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk.h
@@ -85,26 +85,35 @@ struct nullb {
 	char disk_name[DISK_NAME_LEN];
 };
 
+blk_status_t null_process_cmd(struct nullb_cmd *cmd,
+			      enum req_opf op, sector_t sector,
+			      unsigned int nr_sectors);
+
 #ifdef CONFIG_BLK_DEV_ZONED
-int null_zone_init(struct nullb_device *dev);
-void null_zone_exit(struct nullb_device *dev);
+int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q);
+int null_register_zoned_dev(struct nullb *nullb);
+void null_free_zoned_dev(struct nullb_device *dev);
 int null_report_zones(struct gendisk *disk, sector_t sector,
 		      unsigned int nr_zones, report_zones_cb cb, void *data);
-blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
-				enum req_opf op, sector_t sector,
-				sector_t nr_sectors);
+blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd,
+				    enum req_opf op, sector_t sector,
+				    sector_t nr_sectors);
 size_t null_zone_valid_read_len(struct nullb *nullb,
 				sector_t sector, unsigned int len);
 #else
-static inline int null_zone_init(struct nullb_device *dev)
+static inline int null_init_zoned_dev(struct nullb_device *dev,
+				      struct request_queue *q)
 {
 	pr_err("CONFIG_BLK_DEV_ZONED not enabled\n");
 	return -EINVAL;
 }
-static inline void null_zone_exit(struct nullb_device *dev) {}
-static inline blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
-					     enum req_opf op, sector_t sector,
-					     sector_t nr_sectors)
+static inline int null_register_zoned_dev(struct nullb *nullb)
+{
+	return -ENODEV;
+}
+static inline void null_free_zoned_dev(struct nullb_device *dev) {}
+static inline blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd,
+			enum req_opf op, sector_t sector, sector_t nr_sectors)
 {
 	return BLK_STS_NOTSUPP;
 }
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 4e1c0712278e..ce9e33603a4d 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -580,7 +580,7 @@ static void null_free_dev(struct nullb_device *dev)
 	if (!dev)
 		return;
 
-	null_zone_exit(dev);
+	null_free_zoned_dev(dev);
 	badblocks_exit(&dev->badblocks);
 	kfree(dev);
 }
@@ -1276,6 +1276,25 @@ static inline void nullb_complete_cmd(struct nullb_cmd *cmd)
 	}
 }
 
+blk_status_t null_process_cmd(struct nullb_cmd *cmd,
+			      enum req_opf op, sector_t sector,
+			      unsigned int nr_sectors)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	blk_status_t ret;
+
+	if (dev->badblocks.shift != -1) {
+		ret = null_handle_badblocks(cmd, sector, nr_sectors);
+		if (ret != BLK_STS_OK)
+			return ret;
+	}
+
+	if (dev->memory_backed)
+		return null_handle_memory_backed(cmd, op);
+
+	return BLK_STS_OK;
+}
+
 static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
 				    sector_t nr_sectors, enum req_opf op)
 {
@@ -1294,17 +1313,11 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector,
 		goto out;
 	}
 
-	if (nullb->dev->badblocks.shift != -1) {
-		cmd->error = null_handle_badblocks(cmd, sector, nr_sectors);
-		if (cmd->error != BLK_STS_OK)
-			goto out;
-	}
-
-	if (dev->memory_backed)
-		cmd->error = null_handle_memory_backed(cmd, op);
-
-	if (!cmd->error && dev->zoned)
-		cmd->error = null_handle_zoned(cmd, op, sector, nr_sectors);
+	if (dev->zoned)
+		cmd->error = null_process_zoned_cmd(cmd, op,
+						    sector, nr_sectors);
+	else
+		cmd->error = null_process_cmd(cmd, op, sector, nr_sectors);
 
 out:
 	nullb_complete_cmd(cmd);
@@ -1522,6 +1535,13 @@ static void null_config_discard(struct nullb *nullb)
 {
 	if (nullb->dev->discard == false)
 		return;
+
+	if (nullb->dev->zoned) {
+		nullb->dev->discard = false;
+		pr_info("discard option is ignored in zoned mode\n");
+		return;
+	}
+
 	nullb->q->limits.discard_granularity = nullb->dev->blocksize;
 	nullb->q->limits.discard_alignment = nullb->dev->blocksize;
 	blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9);
@@ -1605,19 +1625,12 @@ static int null_gendisk_register(struct nullb *nullb)
 	disk->queue		= nullb->q;
 	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
 
-#ifdef CONFIG_BLK_DEV_ZONED
 	if (nullb->dev->zoned) {
-		if (queue_is_mq(nullb->q)) {
-			int ret = blk_revalidate_disk_zones(disk);
-			if (ret)
-				return ret;
-		} else {
-			blk_queue_chunk_sectors(nullb->q,
-					nullb->dev->zone_size_sects);
-			nullb->q->nr_zones = blkdev_nr_zones(disk);
-		}
+		int ret = null_register_zoned_dev(nullb);
+
+		if (ret)
+			return ret;
 	}
-#endif
 
 	add_disk(disk);
 	return 0;
@@ -1773,14 +1786,9 @@ static int null_add_dev(struct nullb_device *dev)
 	}
 
 	if (dev->zoned) {
-		rv = null_zone_init(dev);
+		rv = null_init_zoned_dev(dev, nullb->q);
 		if (rv)
 			goto out_cleanup_blk_queue;
-
-		nullb->q->limits.zoned = BLK_ZONED_HM;
-		blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, nullb->q);
-		blk_queue_required_elevator_features(nullb->q,
-						ELEVATOR_F_ZBD_SEQ_WRITE);
 	}
 
 	nullb->q->queuedata = nullb;
@@ -1809,8 +1817,7 @@ static int null_add_dev(struct nullb_device *dev)
 
 	return 0;
 out_cleanup_zone:
-	if (dev->zoned)
-		null_zone_exit(dev);
+	null_free_zoned_dev(dev);
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index 673618d8222a..ed5458f2d367 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -13,7 +13,7 @@ static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
 	return sect >> ilog2(dev->zone_size_sects);
 }
 
-int null_zone_init(struct nullb_device *dev)
+int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 {
 	sector_t dev_size = (sector_t)dev->size * 1024 * 1024;
 	sector_t sector = 0;
@@ -23,6 +23,10 @@ int null_zone_init(struct nullb_device *dev)
 		pr_err("zone_size must be power-of-two\n");
 		return -EINVAL;
 	}
+	if (dev->zone_size > dev->size) {
+		pr_err("Zone size larger than device capacity\n");
+		return -EINVAL;
+	}
 
 	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
 	dev->nr_zones = dev_size >>
@@ -61,10 +65,27 @@ int null_zone_init(struct nullb_device *dev)
 		sector += dev->zone_size_sects;
 	}
 
+	q->limits.zoned = BLK_ZONED_HM;
+	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
+
 	return 0;
 }
 
-void null_zone_exit(struct nullb_device *dev)
+int null_register_zoned_dev(struct nullb *nullb)
+{
+	struct request_queue *q = nullb->q;
+
+	if (queue_is_mq(q))
+		return blk_revalidate_disk_zones(nullb->disk);
+
+	blk_queue_chunk_sectors(q, nullb->dev->zone_size_sects);
+	q->nr_zones = blkdev_nr_zones(nullb->disk);
+
+	return 0;
+}
+
+void null_free_zoned_dev(struct nullb_device *dev)
 {
 	kvfree(dev->zones);
 }
@@ -126,11 +147,16 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	struct nullb_device *dev = cmd->nq->dev;
 	unsigned int zno = null_zone_no(dev, sector);
 	struct blk_zone *zone = &dev->zones[zno];
+	blk_status_t ret;
+
+	trace_nullb_zone_op(cmd, zno, zone->cond);
+
+	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+		return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
 
 	switch (zone->cond) {
 	case BLK_ZONE_COND_FULL:
 		/* Cannot write to a full zone */
-		cmd->error = BLK_STS_IOERR;
 		return BLK_STS_IOERR;
 	case BLK_ZONE_COND_EMPTY:
 	case BLK_ZONE_COND_IMP_OPEN:
@@ -143,19 +169,18 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
 			zone->cond = BLK_ZONE_COND_IMP_OPEN;
 
+		ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
+		if (ret != BLK_STS_OK)
+			return ret;
+
 		zone->wp += nr_sectors;
 		if (zone->wp == zone->start + zone->len)
 			zone->cond = BLK_ZONE_COND_FULL;
-		break;
-	case BLK_ZONE_COND_NOT_WP:
-		break;
+		return BLK_STS_OK;
 	default:
 		/* Invalid zone condition */
 		return BLK_STS_IOERR;
 	}
-
-	trace_nullb_zone_op(cmd, zno, zone->cond);
-	return BLK_STS_OK;
 }
 
 static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
@@ -216,8 +241,8 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
 	return BLK_STS_OK;
 }
 
-blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op,
-			       sector_t sector, sector_t nr_sectors)
+blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op,
+				    sector_t sector, sector_t nr_sectors)
 {
 	switch (op) {
 	case REQ_OP_WRITE:
@@ -229,6 +254,6 @@ blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op,
 	case REQ_OP_ZONE_FINISH:
 		return null_zone_mgmt(cmd, op, sector);
 	default:
-		return BLK_STS_OK;
+		return null_process_cmd(cmd, op, sector, nr_sectors);
 	}
 }
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 1e0a6b19ae0d..67d65ac785e9 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3754,11 +3754,7 @@ static int __rbd_notify_op_lock(struct rbd_device *rbd_dev,
 static void rbd_notify_op_lock(struct rbd_device *rbd_dev,
 			       enum rbd_notify_op notify_op)
 {
-	struct page **reply_pages;
-	size_t reply_len;
-
-	__rbd_notify_op_lock(rbd_dev, notify_op, &reply_pages, &reply_len);
-	ceph_release_page_vector(reply_pages, calc_pages_for(0, reply_len));
+	__rbd_notify_op_lock(rbd_dev, notify_op, NULL, NULL);
 }
 
 static void rbd_notify_acquired_lock(struct work_struct *work)
@@ -4527,6 +4523,10 @@ static void cancel_tasks_sync(struct rbd_device *rbd_dev)
 	cancel_work_sync(&rbd_dev->unlock_work);
 }
 
+/*
+ * header_rwsem must not be held to avoid a deadlock with
+ * rbd_dev_refresh() when flushing notifies.
+ */
 static void rbd_unregister_watch(struct rbd_device *rbd_dev)
 {
 	cancel_tasks_sync(rbd_dev);
@@ -6894,9 +6894,10 @@ static void rbd_print_dne(struct rbd_device *rbd_dev, bool is_snap)
 
 static void rbd_dev_image_release(struct rbd_device *rbd_dev)
 {
-	rbd_dev_unprobe(rbd_dev);
-	if (rbd_dev->opts)
+	if (!rbd_is_ro(rbd_dev))
 		rbd_unregister_watch(rbd_dev);
+
+	rbd_dev_unprobe(rbd_dev);
 	rbd_dev->image_format = 0;
 	kfree(rbd_dev->spec->image_id);
 	rbd_dev->spec->image_id = NULL;
@@ -6907,6 +6908,9 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev)
  * device.  If this image is the one being mapped (i.e., not a
  * parent), initiate a watch on its header object before using that
  * object to get detailed information about the rbd image.
+ *
+ * On success, returns with header_rwsem held for write if called
+ * with @depth == 0.
  */
 static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
 {
@@ -6936,11 +6940,14 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
 		}
 	}
 
+	if (!depth)
+		down_write(&rbd_dev->header_rwsem);
+
 	ret = rbd_dev_header_info(rbd_dev);
 	if (ret) {
 		if (ret == -ENOENT && !need_watch)
 			rbd_print_dne(rbd_dev, false);
-		goto err_out_watch;
+		goto err_out_probe;
 	}
 
 	/*
@@ -6985,10 +6992,11 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
 	return 0;
 
 err_out_probe:
-	rbd_dev_unprobe(rbd_dev);
-err_out_watch:
+	if (!depth)
+		up_write(&rbd_dev->header_rwsem);
 	if (need_watch)
 		rbd_unregister_watch(rbd_dev);
+	rbd_dev_unprobe(rbd_dev);
 err_out_format:
 	rbd_dev->image_format = 0;
 	kfree(rbd_dev->spec->image_id);
@@ -7050,12 +7058,9 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 		goto err_out_rbd_dev;
 	}
 
-	down_write(&rbd_dev->header_rwsem);
 	rc = rbd_dev_image_probe(rbd_dev, 0);
-	if (rc < 0) {
-		up_write(&rbd_dev->header_rwsem);
+	if (rc < 0)
 		goto err_out_rbd_dev;
-	}
 
 	if (rbd_dev->opts->alloc_size > rbd_dev->layout.object_size) {
 		rbd_warn(rbd_dev, "alloc_size adjusted to %u",
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index f9b1e70f1b31..9d21bf0f155e 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -15,6 +15,7 @@
 #include <linux/blk-mq.h>
 #include <linux/blk-mq-virtio.h>
 #include <linux/numa.h>
+#include <uapi/linux/virtio_ring.h>
 
 #define PART_BITS 4
 #define VQ_NAME_LEN 16
@@ -32,6 +33,15 @@ struct virtio_blk_vq {
 } ____cacheline_aligned_in_smp;
 
 struct virtio_blk {
+	/*
+	 * This mutex must be held by anything that may run after
+	 * virtblk_remove() sets vblk->vdev to NULL.
+	 *
+	 * blk-mq, virtqueue processing, and sysfs attribute code paths are
+	 * shut down before vblk->vdev is set to NULL and therefore do not need
+	 * to hold this mutex.
+	 */
+	struct mutex vdev_mutex;
 	struct virtio_device *vdev;
 
 	/* The disk structure for the kernel. */
@@ -43,6 +53,13 @@ struct virtio_blk {
 	/* Process context for config space updates */
 	struct work_struct config_work;
 
+	/*
+	 * Tracks references from block_device_operations open/release and
+	 * virtio_driver probe/remove so this object can be freed once no
+	 * longer in use.
+	 */
+	refcount_t refs;
+
 	/* What host tells us, plus 2 for header & tailer. */
 	unsigned int sg_elems;
 
@@ -294,10 +311,55 @@ out:
 	return err;
 }
 
+static void virtblk_get(struct virtio_blk *vblk)
+{
+	refcount_inc(&vblk->refs);
+}
+
+static void virtblk_put(struct virtio_blk *vblk)
+{
+	if (refcount_dec_and_test(&vblk->refs)) {
+		ida_simple_remove(&vd_index_ida, vblk->index);
+		mutex_destroy(&vblk->vdev_mutex);
+		kfree(vblk);
+	}
+}
+
+static int virtblk_open(struct block_device *bd, fmode_t mode)
+{
+	struct virtio_blk *vblk = bd->bd_disk->private_data;
+	int ret = 0;
+
+	mutex_lock(&vblk->vdev_mutex);
+
+	if (vblk->vdev)
+		virtblk_get(vblk);
+	else
+		ret = -ENXIO;
+
+	mutex_unlock(&vblk->vdev_mutex);
+	return ret;
+}
+
+static void virtblk_release(struct gendisk *disk, fmode_t mode)
+{
+	struct virtio_blk *vblk = disk->private_data;
+
+	virtblk_put(vblk);
+}
+
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
 	struct virtio_blk *vblk = bd->bd_disk->private_data;
+	int ret = 0;
+
+	mutex_lock(&vblk->vdev_mutex);
+
+	if (!vblk->vdev) {
+		ret = -ENXIO;
+		goto out;
+	}
 
 	/* see if the host passed in geometry config */
 	if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) {
@@ -313,11 +375,15 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 		geo->sectors = 1 << 5;
 		geo->cylinders = get_capacity(bd->bd_disk) >> 11;
 	}
-	return 0;
+out:
+	mutex_unlock(&vblk->vdev_mutex);
+	return ret;
 }
 
 static const struct block_device_operations virtblk_fops = {
 	.owner  = THIS_MODULE,
+	.open = virtblk_open,
+	.release = virtblk_release,
 	.getgeo = virtblk_getgeo,
 };
 
@@ -654,6 +720,10 @@ static int virtblk_probe(struct virtio_device *vdev)
 		goto out_free_index;
 	}
 
+	/* This reference is dropped in virtblk_remove(). */
+	refcount_set(&vblk->refs, 1);
+	mutex_init(&vblk->vdev_mutex);
+
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
 
@@ -819,8 +889,6 @@ out:
 static void virtblk_remove(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
-	int index = vblk->index;
-	int refc;
 
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vblk->config_work);
@@ -830,18 +898,21 @@ static void virtblk_remove(struct virtio_device *vdev)
 
 	blk_mq_free_tag_set(&vblk->tag_set);
 
+	mutex_lock(&vblk->vdev_mutex);
+
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
 
-	refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref);
+	/* Virtqueues are stopped, nothing can use vblk->vdev anymore. */
+	vblk->vdev = NULL;
+
 	put_disk(vblk->disk);
 	vdev->config->del_vqs(vdev);
 	kfree(vblk->vqs);
-	kfree(vblk);
 
-	/* Only free device id if we don't have any users */
-	if (refc == 1)
-		ida_simple_remove(&vd_index_ida, index);
+	mutex_unlock(&vblk->vdev_mutex);
+
+	virtblk_put(vblk);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 1a8564a79d8d..5ee8e3fae551 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -37,19 +37,16 @@ static void zcomp_strm_free(struct zcomp_strm *zstrm)
 	if (!IS_ERR_OR_NULL(zstrm->tfm))
 		crypto_free_comp(zstrm->tfm);
 	free_pages((unsigned long)zstrm->buffer, 1);
-	kfree(zstrm);
+	zstrm->tfm = NULL;
+	zstrm->buffer = NULL;
 }
 
 /*
- * allocate new zcomp_strm structure with ->tfm initialized by
- * backend, return NULL on error
+ * Initialize zcomp_strm structure with ->tfm initialized by backend, and
+ * ->buffer. Return a negative value on error.
  */
-static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
+static int zcomp_strm_init(struct zcomp_strm *zstrm, struct zcomp *comp)
 {
-	struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL);
-	if (!zstrm)
-		return NULL;
-
 	zstrm->tfm = crypto_alloc_comp(comp->name, 0, 0);
 	/*
 	 * allocate 2 pages. 1 for compressed data, plus 1 extra for the
@@ -58,9 +55,9 @@ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
 	zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
 	if (IS_ERR_OR_NULL(zstrm->tfm) || !zstrm->buffer) {
 		zcomp_strm_free(zstrm);
-		zstrm = NULL;
+		return -ENOMEM;
 	}
-	return zstrm;
+	return 0;
 }
 
 bool zcomp_available_algorithm(const char *comp)
@@ -113,12 +110,13 @@ ssize_t zcomp_available_show(const char *comp, char *buf)
 
 struct zcomp_strm *zcomp_stream_get(struct zcomp *comp)
 {
-	return *get_cpu_ptr(comp->stream);
+	local_lock(&comp->stream->lock);
+	return this_cpu_ptr(comp->stream);
 }
 
 void zcomp_stream_put(struct zcomp *comp)
 {
-	put_cpu_ptr(comp->stream);
+	local_unlock(&comp->stream->lock);
 }
 
 int zcomp_compress(struct zcomp_strm *zstrm,
@@ -159,17 +157,15 @@ int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zcomp *comp = hlist_entry(node, struct zcomp, node);
 	struct zcomp_strm *zstrm;
+	int ret;
 
-	if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
-		return 0;
+	zstrm = per_cpu_ptr(comp->stream, cpu);
+	local_lock_init(&zstrm->lock);
 
-	zstrm = zcomp_strm_alloc(comp);
-	if (IS_ERR_OR_NULL(zstrm)) {
+	ret = zcomp_strm_init(zstrm, comp);
+	if (ret)
 		pr_err("Can't allocate a compression stream\n");
-		return -ENOMEM;
-	}
-	*per_cpu_ptr(comp->stream, cpu) = zstrm;
-	return 0;
+	return ret;
 }
 
 int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node)
@@ -177,10 +173,8 @@ int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node)
 	struct zcomp *comp = hlist_entry(node, struct zcomp, node);
 	struct zcomp_strm *zstrm;
 
-	zstrm = *per_cpu_ptr(comp->stream, cpu);
-	if (!IS_ERR_OR_NULL(zstrm))
-		zcomp_strm_free(zstrm);
-	*per_cpu_ptr(comp->stream, cpu) = NULL;
+	zstrm = per_cpu_ptr(comp->stream, cpu);
+	zcomp_strm_free(zstrm);
 	return 0;
 }
 
@@ -188,7 +182,7 @@ static int zcomp_init(struct zcomp *comp)
 {
 	int ret;
 
-	comp->stream = alloc_percpu(struct zcomp_strm *);
+	comp->stream = alloc_percpu(struct zcomp_strm);
 	if (!comp->stream)
 		return -ENOMEM;
 
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 1806475b919d..40f6420f4b2e 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -5,8 +5,11 @@
 
 #ifndef _ZCOMP_H_
 #define _ZCOMP_H_
+#include <linux/local_lock.h>
 
 struct zcomp_strm {
+	/* The members ->buffer and ->tfm are protected by ->lock. */
+	local_lock_t lock;
 	/* compression/decompression buffer */
 	void *buffer;
 	struct crypto_comp *tfm;
@@ -14,7 +17,7 @@ struct zcomp_strm {
 
 /* dynamic per-device compression frontend */
 struct zcomp {
-	struct zcomp_strm * __percpu *stream;
+	struct zcomp_strm __percpu *stream;
 	const char *name;
 	struct hlist_node node;
 };
diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index b38359c480ea..1f8c82603179 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -291,6 +291,7 @@ int mhi_init_dev_ctxt(struct mhi_controller *mhi_cntrl)
 	}
 
 	/* Setup cmd context */
+	ret = -ENOMEM;
 	mhi_ctxt->cmd_ctxt = mhi_alloc_coherent(mhi_cntrl,
 						sizeof(*mhi_ctxt->cmd_ctxt) *
 						NR_OF_CMD_RINGS,
@@ -812,10 +813,9 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl,
 	if (!mhi_cntrl)
 		return -EINVAL;
 
-	if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put)
-		return -EINVAL;
-
-	if (!mhi_cntrl->status_cb || !mhi_cntrl->link_status)
+	if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put ||
+	    !mhi_cntrl->status_cb || !mhi_cntrl->read_reg ||
+	    !mhi_cntrl->write_reg)
 		return -EINVAL;
 
 	ret = parse_config(mhi_cntrl, config);
@@ -1101,6 +1101,7 @@ static int mhi_driver_probe(struct device *dev)
 		}
 	}
 
+	ret = -EINVAL;
 	if (dl_chan) {
 		/*
 		 * If channel supports LPM notifications then status_cb should
diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h
index 5deadfaa053a..095d95bc0e37 100644
--- a/drivers/bus/mhi/core/internal.h
+++ b/drivers/bus/mhi/core/internal.h
@@ -11,9 +11,6 @@
 
 extern struct bus_type mhi_bus_type;
 
-/* MHI MMIO register mapping */
-#define PCI_INVALID_READ(val) (val == U32_MAX)
-
 #define MHIREGLEN (0x0)
 #define MHIREGLEN_MHIREGLEN_MASK (0xFFFFFFFF)
 #define MHIREGLEN_MHIREGLEN_SHIFT (0)
diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c
index eb4256b81406..97e06cc586e4 100644
--- a/drivers/bus/mhi/core/main.c
+++ b/drivers/bus/mhi/core/main.c
@@ -18,16 +18,7 @@
 int __must_check mhi_read_reg(struct mhi_controller *mhi_cntrl,
 			      void __iomem *base, u32 offset, u32 *out)
 {
-	u32 tmp = readl(base + offset);
-
-	/* If there is any unexpected value, query the link status */
-	if (PCI_INVALID_READ(tmp) &&
-	    mhi_cntrl->link_status(mhi_cntrl))
-		return -EIO;
-
-	*out = tmp;
-
-	return 0;
+	return mhi_cntrl->read_reg(mhi_cntrl, base + offset, out);
 }
 
 int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
@@ -49,7 +40,7 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
 void mhi_write_reg(struct mhi_controller *mhi_cntrl, void __iomem *base,
 		   u32 offset, u32 val)
 {
-	writel(val, base + offset);
+	mhi_cntrl->write_reg(mhi_cntrl, base + offset, val);
 }
 
 void mhi_write_reg_field(struct mhi_controller *mhi_cntrl, void __iomem *base,
@@ -294,7 +285,7 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl)
 		    !(mhi_chan->ee_mask & BIT(mhi_cntrl->ee)))
 			continue;
 		mhi_dev = mhi_alloc_device(mhi_cntrl);
-		if (!mhi_dev)
+		if (IS_ERR(mhi_dev))
 			return;
 
 		mhi_dev->dev_type = MHI_DEVICE_XFER;
@@ -336,7 +327,8 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl)
 
 		/* Channel name is same for both UL and DL */
 		mhi_dev->chan_name = mhi_chan->name;
-		dev_set_name(&mhi_dev->dev, "%04x_%s", mhi_chan->chan,
+		dev_set_name(&mhi_dev->dev, "%s_%s",
+			     dev_name(mhi_cntrl->cntrl_dev),
 			     mhi_dev->chan_name);
 
 		/* Init wakeup source if available */
diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c
index 52690cb5c89c..dc83d65f7784 100644
--- a/drivers/bus/mhi/core/pm.c
+++ b/drivers/bus/mhi/core/pm.c
@@ -902,7 +902,11 @@ int mhi_sync_power_up(struct mhi_controller *mhi_cntrl)
 			   MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state),
 			   msecs_to_jiffies(mhi_cntrl->timeout_ms));
 
-	return (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -EIO;
+	ret = (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -ETIMEDOUT;
+	if (ret)
+		mhi_power_down(mhi_cntrl, false);
+
+	return ret;
 }
 EXPORT_SYMBOL(mhi_sync_power_up);
 
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index 9bc46da8d77a..ac00d78ee9cc 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -474,6 +474,19 @@ config HW_RANDOM_KEYSTONE
 	help
 	  This option enables Keystone's hardware random generator.
 
+config HW_RANDOM_CCTRNG
+	tristate "Arm CryptoCell True Random Number Generator support"
+	depends on HAS_IOMEM && OF
+	help
+	  Say 'Y' to enable the True Random Number Generator driver for the
+	  Arm TrustZone CryptoCell family of processors.
+	  Currently the CryptoCell 713 and 703 are supported.
+	  The driver is supported only in SoC where Trusted Execution
+	  Environment is not used.
+	  Choose 'M' to compile this driver as a module. The module
+	  will be called cctrng.
+	  If unsure, say 'N'.
+
 endif # HW_RANDOM
 
 config UML_RANDOM
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index a7801b49ce6c..2c6724735345 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -41,3 +41,4 @@ obj-$(CONFIG_HW_RANDOM_S390) += s390-trng.o
 obj-$(CONFIG_HW_RANDOM_KEYSTONE) += ks-sa-rng.o
 obj-$(CONFIG_HW_RANDOM_OPTEE) += optee-rng.o
 obj-$(CONFIG_HW_RANDOM_NPCM) += npcm-rng.o
+obj-$(CONFIG_HW_RANDOM_CCTRNG) += cctrng.o
diff --git a/drivers/char/hw_random/cctrng.c b/drivers/char/hw_random/cctrng.c
new file mode 100644
index 000000000000..619148fb2dc9
--- /dev/null
+++ b/drivers/char/hw_random/cctrng.c
@@ -0,0 +1,735 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2019-2020 ARM Limited or its affiliates. */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/hw_random.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/interrupt.h>
+#include <linux/irqreturn.h>
+#include <linux/workqueue.h>
+#include <linux/circ_buf.h>
+#include <linux/completion.h>
+#include <linux/of.h>
+#include <linux/bitfield.h>
+#include <linux/fips.h>
+
+#include "cctrng.h"
+
+#define CC_REG_LOW(name)  (name ## _BIT_SHIFT)
+#define CC_REG_HIGH(name) (CC_REG_LOW(name) + name ## _BIT_SIZE - 1)
+#define CC_GENMASK(name)  GENMASK(CC_REG_HIGH(name), CC_REG_LOW(name))
+
+#define CC_REG_FLD_GET(reg_name, fld_name, reg_val)     \
+	(FIELD_GET(CC_GENMASK(CC_ ## reg_name ## _ ## fld_name), reg_val))
+
+#define CC_HW_RESET_LOOP_COUNT 10
+#define CC_TRNG_SUSPEND_TIMEOUT 3000
+
+/* data circular buffer in words must be:
+ *  - of a power-of-2 size (limitation of circ_buf.h macros)
+ *  - at least 6, the size generated in the EHR according to HW implementation
+ */
+#define CCTRNG_DATA_BUF_WORDS 32
+
+/* The timeout for the TRNG operation should be calculated with the formula:
+ * Timeout = EHR_NUM * VN_COEFF * EHR_LENGTH * SAMPLE_CNT * SCALE_VALUE
+ * while:
+ *  - SAMPLE_CNT is input value from the characterisation process
+ *  - all the rest are constants
+ */
+#define EHR_NUM 1
+#define VN_COEFF 4
+#define EHR_LENGTH CC_TRNG_EHR_IN_BITS
+#define SCALE_VALUE 2
+#define CCTRNG_TIMEOUT(smpl_cnt) \
+	(EHR_NUM * VN_COEFF * EHR_LENGTH * smpl_cnt * SCALE_VALUE)
+
+struct cctrng_drvdata {
+	struct platform_device *pdev;
+	void __iomem *cc_base;
+	struct clk *clk;
+	struct hwrng rng;
+	u32 active_rosc;
+	/* Sampling interval for each ring oscillator:
+	 * count of ring oscillator cycles between consecutive bits sampling.
+	 * Value of 0 indicates non-valid rosc
+	 */
+	u32 smpl_ratio[CC_TRNG_NUM_OF_ROSCS];
+
+	u32 data_buf[CCTRNG_DATA_BUF_WORDS];
+	struct circ_buf circ;
+	struct work_struct compwork;
+	struct work_struct startwork;
+
+	/* pending_hw - 1 when HW is pending, 0 when it is idle */
+	atomic_t pending_hw;
+
+	/* protects against multiple concurrent consumers of data_buf */
+	spinlock_t read_lock;
+};
+
+
+/* functions for write/read CC registers */
+static inline void cc_iowrite(struct cctrng_drvdata *drvdata, u32 reg, u32 val)
+{
+	iowrite32(val, (drvdata->cc_base + reg));
+}
+static inline u32 cc_ioread(struct cctrng_drvdata *drvdata, u32 reg)
+{
+	return ioread32(drvdata->cc_base + reg);
+}
+
+
+static int cc_trng_pm_get(struct device *dev)
+{
+	int rc = 0;
+
+	rc = pm_runtime_get_sync(dev);
+
+	/* pm_runtime_get_sync() can return 1 as a valid return code */
+	return (rc == 1 ? 0 : rc);
+}
+
+static void cc_trng_pm_put_suspend(struct device *dev)
+{
+	int rc = 0;
+
+	pm_runtime_mark_last_busy(dev);
+	rc = pm_runtime_put_autosuspend(dev);
+	if (rc)
+		dev_err(dev, "pm_runtime_put_autosuspend returned %x\n", rc);
+}
+
+static int cc_trng_pm_init(struct cctrng_drvdata *drvdata)
+{
+	struct device *dev = &(drvdata->pdev->dev);
+
+	/* must be before the enabling to avoid redundant suspending */
+	pm_runtime_set_autosuspend_delay(dev, CC_TRNG_SUSPEND_TIMEOUT);
+	pm_runtime_use_autosuspend(dev);
+	/* set us as active - note we won't do PM ops until cc_trng_pm_go()! */
+	return pm_runtime_set_active(dev);
+}
+
+static void cc_trng_pm_go(struct cctrng_drvdata *drvdata)
+{
+	struct device *dev = &(drvdata->pdev->dev);
+
+	/* enable the PM module*/
+	pm_runtime_enable(dev);
+}
+
+static void cc_trng_pm_fini(struct cctrng_drvdata *drvdata)
+{
+	struct device *dev = &(drvdata->pdev->dev);
+
+	pm_runtime_disable(dev);
+}
+
+
+static inline int cc_trng_parse_sampling_ratio(struct cctrng_drvdata *drvdata)
+{
+	struct device *dev = &(drvdata->pdev->dev);
+	struct device_node *np = drvdata->pdev->dev.of_node;
+	int rc;
+	int i;
+	/* ret will be set to 0 if at least one rosc has (sampling ratio > 0) */
+	int ret = -EINVAL;
+
+	rc = of_property_read_u32_array(np, "arm,rosc-ratio",
+					drvdata->smpl_ratio,
+					CC_TRNG_NUM_OF_ROSCS);
+	if (rc) {
+		/* arm,rosc-ratio was not found in device tree */
+		return rc;
+	}
+
+	/* verify that at least one rosc has (sampling ratio > 0) */
+	for (i = 0; i < CC_TRNG_NUM_OF_ROSCS; ++i) {
+		dev_dbg(dev, "rosc %d sampling ratio %u",
+			i, drvdata->smpl_ratio[i]);
+
+		if (drvdata->smpl_ratio[i] > 0)
+			ret = 0;
+	}
+
+	return ret;
+}
+
+static int cc_trng_change_rosc(struct cctrng_drvdata *drvdata)
+{
+	struct device *dev = &(drvdata->pdev->dev);
+
+	dev_dbg(dev, "cctrng change rosc (was %d)\n", drvdata->active_rosc);
+	drvdata->active_rosc += 1;
+
+	while (drvdata->active_rosc < CC_TRNG_NUM_OF_ROSCS) {
+		if (drvdata->smpl_ratio[drvdata->active_rosc] > 0)
+			return 0;
+
+		drvdata->active_rosc += 1;
+	}
+	return -EINVAL;
+}
+
+
+static void cc_trng_enable_rnd_source(struct cctrng_drvdata *drvdata)
+{
+	u32 max_cycles;
+
+	/* Set watchdog threshold to maximal allowed time (in CPU cycles) */
+	max_cycles = CCTRNG_TIMEOUT(drvdata->smpl_ratio[drvdata->active_rosc]);
+	cc_iowrite(drvdata, CC_RNG_WATCHDOG_VAL_REG_OFFSET, max_cycles);
+
+	/* enable the RND source */
+	cc_iowrite(drvdata, CC_RND_SOURCE_ENABLE_REG_OFFSET, 0x1);
+
+	/* unmask RNG interrupts */
+	cc_iowrite(drvdata, CC_RNG_IMR_REG_OFFSET, (u32)~CC_RNG_INT_MASK);
+}
+
+
+/* increase circular data buffer index (head/tail) */
+static inline void circ_idx_inc(int *idx, int bytes)
+{
+	*idx += (bytes + 3) >> 2;
+	*idx &= (CCTRNG_DATA_BUF_WORDS - 1);
+}
+
+static inline size_t circ_buf_space(struct cctrng_drvdata *drvdata)
+{
+	return CIRC_SPACE(drvdata->circ.head,
+			  drvdata->circ.tail, CCTRNG_DATA_BUF_WORDS);
+
+}
+
+static int cctrng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	/* current implementation ignores "wait" */
+
+	struct cctrng_drvdata *drvdata = (struct cctrng_drvdata *)rng->priv;
+	struct device *dev = &(drvdata->pdev->dev);
+	u32 *buf = (u32 *)drvdata->circ.buf;
+	size_t copied = 0;
+	size_t cnt_w;
+	size_t size;
+	size_t left;
+
+	if (!spin_trylock(&drvdata->read_lock)) {
+		/* concurrent consumers from data_buf cannot be served */
+		dev_dbg_ratelimited(dev, "unable to hold lock\n");
+		return 0;
+	}
+
+	/* copy till end of data buffer (without wrap back) */
+	cnt_w = CIRC_CNT_TO_END(drvdata->circ.head,
+				drvdata->circ.tail, CCTRNG_DATA_BUF_WORDS);
+	size = min((cnt_w<<2), max);
+	memcpy(data, &(buf[drvdata->circ.tail]), size);
+	copied = size;
+	circ_idx_inc(&drvdata->circ.tail, size);
+	/* copy rest of data in data buffer */
+	left = max - copied;
+	if (left > 0) {
+		cnt_w = CIRC_CNT(drvdata->circ.head,
+				 drvdata->circ.tail, CCTRNG_DATA_BUF_WORDS);
+		size = min((cnt_w<<2), left);
+		memcpy(data, &(buf[drvdata->circ.tail]), size);
+		copied += size;
+		circ_idx_inc(&drvdata->circ.tail, size);
+	}
+
+	spin_unlock(&drvdata->read_lock);
+
+	if (circ_buf_space(drvdata) >= CC_TRNG_EHR_IN_WORDS) {
+		if (atomic_cmpxchg(&drvdata->pending_hw, 0, 1) == 0) {
+			/* re-check space in buffer to avoid potential race */
+			if (circ_buf_space(drvdata) >= CC_TRNG_EHR_IN_WORDS) {
+				/* increment device's usage counter */
+				int rc = cc_trng_pm_get(dev);
+
+				if (rc) {
+					dev_err(dev,
+						"cc_trng_pm_get returned %x\n",
+						rc);
+					return rc;
+				}
+
+				/* schedule execution of deferred work handler
+				 * for filling of data buffer
+				 */
+				schedule_work(&drvdata->startwork);
+			} else {
+				atomic_set(&drvdata->pending_hw, 0);
+			}
+		}
+	}
+
+	return copied;
+}
+
+static void cc_trng_hw_trigger(struct cctrng_drvdata *drvdata)
+{
+	u32 tmp_smpl_cnt = 0;
+	struct device *dev = &(drvdata->pdev->dev);
+
+	dev_dbg(dev, "cctrng hw trigger.\n");
+
+	/* enable the HW RND clock */
+	cc_iowrite(drvdata, CC_RNG_CLK_ENABLE_REG_OFFSET, 0x1);
+
+	/* do software reset */
+	cc_iowrite(drvdata, CC_RNG_SW_RESET_REG_OFFSET, 0x1);
+	/* in order to verify that the reset has completed,
+	 * the sample count need to be verified
+	 */
+	do {
+		/* enable the HW RND clock   */
+		cc_iowrite(drvdata, CC_RNG_CLK_ENABLE_REG_OFFSET, 0x1);
+
+		/* set sampling ratio (rng_clocks) between consecutive bits */
+		cc_iowrite(drvdata, CC_SAMPLE_CNT1_REG_OFFSET,
+			   drvdata->smpl_ratio[drvdata->active_rosc]);
+
+		/* read the sampling ratio  */
+		tmp_smpl_cnt = cc_ioread(drvdata, CC_SAMPLE_CNT1_REG_OFFSET);
+
+	} while (tmp_smpl_cnt != drvdata->smpl_ratio[drvdata->active_rosc]);
+
+	/* disable the RND source for setting new parameters in HW */
+	cc_iowrite(drvdata, CC_RND_SOURCE_ENABLE_REG_OFFSET, 0);
+
+	cc_iowrite(drvdata, CC_RNG_ICR_REG_OFFSET, 0xFFFFFFFF);
+
+	cc_iowrite(drvdata, CC_TRNG_CONFIG_REG_OFFSET, drvdata->active_rosc);
+
+	/* Debug Control register: set to 0 - no bypasses */
+	cc_iowrite(drvdata, CC_TRNG_DEBUG_CONTROL_REG_OFFSET, 0);
+
+	cc_trng_enable_rnd_source(drvdata);
+}
+
+static void cc_trng_compwork_handler(struct work_struct *w)
+{
+	u32 isr = 0;
+	u32 ehr_valid = 0;
+	struct cctrng_drvdata *drvdata =
+			container_of(w, struct cctrng_drvdata, compwork);
+	struct device *dev = &(drvdata->pdev->dev);
+	int i;
+
+	/* stop DMA and the RNG source */
+	cc_iowrite(drvdata, CC_RNG_DMA_ENABLE_REG_OFFSET, 0);
+	cc_iowrite(drvdata, CC_RND_SOURCE_ENABLE_REG_OFFSET, 0);
+
+	/* read RNG_ISR and check for errors */
+	isr = cc_ioread(drvdata, CC_RNG_ISR_REG_OFFSET);
+	ehr_valid = CC_REG_FLD_GET(RNG_ISR, EHR_VALID, isr);
+	dev_dbg(dev, "Got RNG_ISR=0x%08X (EHR_VALID=%u)\n", isr, ehr_valid);
+
+	if (fips_enabled && CC_REG_FLD_GET(RNG_ISR, CRNGT_ERR, isr)) {
+		fips_fail_notify();
+		/* FIPS error is fatal */
+		panic("Got HW CRNGT error while fips is enabled!\n");
+	}
+
+	/* Clear all pending RNG interrupts */
+	cc_iowrite(drvdata, CC_RNG_ICR_REG_OFFSET, isr);
+
+
+	if (!ehr_valid) {
+		/* in case of AUTOCORR/TIMEOUT error, try the next ROSC */
+		if (CC_REG_FLD_GET(RNG_ISR, AUTOCORR_ERR, isr) ||
+				CC_REG_FLD_GET(RNG_ISR, WATCHDOG, isr)) {
+			dev_dbg(dev, "cctrng autocorr/timeout error.\n");
+			goto next_rosc;
+		}
+
+		/* in case of VN error, ignore it */
+	}
+
+	/* read EHR data from registers */
+	for (i = 0; i < CC_TRNG_EHR_IN_WORDS; i++) {
+		/* calc word ptr in data_buf */
+		u32 *buf = (u32 *)drvdata->circ.buf;
+
+		buf[drvdata->circ.head] = cc_ioread(drvdata,
+				CC_EHR_DATA_0_REG_OFFSET + (i*sizeof(u32)));
+
+		/* EHR_DATA registers are cleared on read. In case 0 value was
+		 * returned, restart the entropy collection.
+		 */
+		if (buf[drvdata->circ.head] == 0) {
+			dev_dbg(dev, "Got 0 value in EHR. active_rosc %u\n",
+				drvdata->active_rosc);
+			goto next_rosc;
+		}
+
+		circ_idx_inc(&drvdata->circ.head, 1<<2);
+	}
+
+	atomic_set(&drvdata->pending_hw, 0);
+
+	/* continue to fill data buffer if needed */
+	if (circ_buf_space(drvdata) >= CC_TRNG_EHR_IN_WORDS) {
+		if (atomic_cmpxchg(&drvdata->pending_hw, 0, 1) == 0) {
+			/* Re-enable rnd source */
+			cc_trng_enable_rnd_source(drvdata);
+			return;
+		}
+	}
+
+	cc_trng_pm_put_suspend(dev);
+
+	dev_dbg(dev, "compwork handler done\n");
+	return;
+
+next_rosc:
+	if ((circ_buf_space(drvdata) >= CC_TRNG_EHR_IN_WORDS) &&
+			(cc_trng_change_rosc(drvdata) == 0)) {
+		/* trigger trng hw with next rosc */
+		cc_trng_hw_trigger(drvdata);
+	} else {
+		atomic_set(&drvdata->pending_hw, 0);
+		cc_trng_pm_put_suspend(dev);
+	}
+}
+
+static irqreturn_t cc_isr(int irq, void *dev_id)
+{
+	struct cctrng_drvdata *drvdata = (struct cctrng_drvdata *)dev_id;
+	struct device *dev = &(drvdata->pdev->dev);
+	u32 irr;
+
+	/* if driver suspended return, probably shared interrupt */
+	if (pm_runtime_suspended(dev))
+		return IRQ_NONE;
+
+	/* read the interrupt status */
+	irr = cc_ioread(drvdata, CC_HOST_RGF_IRR_REG_OFFSET);
+	dev_dbg(dev, "Got IRR=0x%08X\n", irr);
+
+	if (irr == 0) /* Probably shared interrupt line */
+		return IRQ_NONE;
+
+	/* clear interrupt - must be before processing events */
+	cc_iowrite(drvdata, CC_HOST_RGF_ICR_REG_OFFSET, irr);
+
+	/* RNG interrupt - most probable */
+	if (irr & CC_HOST_RNG_IRQ_MASK) {
+		/* Mask RNG interrupts - will be unmasked in deferred work */
+		cc_iowrite(drvdata, CC_RNG_IMR_REG_OFFSET, 0xFFFFFFFF);
+
+		/* We clear RNG interrupt here,
+		 * to avoid it from firing as we'll unmask RNG interrupts.
+		 */
+		cc_iowrite(drvdata, CC_HOST_RGF_ICR_REG_OFFSET,
+			   CC_HOST_RNG_IRQ_MASK);
+
+		irr &= ~CC_HOST_RNG_IRQ_MASK;
+
+		/* schedule execution of deferred work handler */
+		schedule_work(&drvdata->compwork);
+	}
+
+	if (irr) {
+		dev_dbg_ratelimited(dev,
+				"IRR includes unknown cause bits (0x%08X)\n",
+				irr);
+		/* Just warning */
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void cc_trng_startwork_handler(struct work_struct *w)
+{
+	struct cctrng_drvdata *drvdata =
+			container_of(w, struct cctrng_drvdata, startwork);
+
+	drvdata->active_rosc = 0;
+	cc_trng_hw_trigger(drvdata);
+}
+
+
+static int cc_trng_clk_init(struct cctrng_drvdata *drvdata)
+{
+	struct clk *clk;
+	struct device *dev = &(drvdata->pdev->dev);
+	int rc = 0;
+
+	clk = devm_clk_get_optional(dev, NULL);
+	if (IS_ERR(clk)) {
+		if (PTR_ERR(clk) != -EPROBE_DEFER)
+			dev_err(dev, "Error getting clock: %pe\n", clk);
+		return PTR_ERR(clk);
+	}
+	drvdata->clk = clk;
+
+	rc = clk_prepare_enable(drvdata->clk);
+	if (rc) {
+		dev_err(dev, "Failed to enable clock\n");
+		return rc;
+	}
+
+	return 0;
+}
+
+static void cc_trng_clk_fini(struct cctrng_drvdata *drvdata)
+{
+	clk_disable_unprepare(drvdata->clk);
+}
+
+
+static int cctrng_probe(struct platform_device *pdev)
+{
+	struct resource *req_mem_cc_regs = NULL;
+	struct cctrng_drvdata *drvdata;
+	struct device *dev = &pdev->dev;
+	int rc = 0;
+	u32 val;
+	int irq;
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->rng.name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL);
+	if (!drvdata->rng.name)
+		return -ENOMEM;
+
+	drvdata->rng.read = cctrng_read;
+	drvdata->rng.priv = (unsigned long)drvdata;
+	drvdata->rng.quality = CC_TRNG_QUALITY;
+
+	platform_set_drvdata(pdev, drvdata);
+	drvdata->pdev = pdev;
+
+	drvdata->circ.buf = (char *)drvdata->data_buf;
+
+	/* Get device resources */
+	/* First CC registers space */
+	req_mem_cc_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	/* Map registers space */
+	drvdata->cc_base = devm_ioremap_resource(dev, req_mem_cc_regs);
+	if (IS_ERR(drvdata->cc_base)) {
+		dev_err(dev, "Failed to ioremap registers");
+		return PTR_ERR(drvdata->cc_base);
+	}
+
+	dev_dbg(dev, "Got MEM resource (%s): %pR\n", req_mem_cc_regs->name,
+		req_mem_cc_regs);
+	dev_dbg(dev, "CC registers mapped from %pa to 0x%p\n",
+		&req_mem_cc_regs->start, drvdata->cc_base);
+
+	/* Then IRQ */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "Failed getting IRQ resource\n");
+		return irq;
+	}
+
+	/* parse sampling rate from device tree */
+	rc = cc_trng_parse_sampling_ratio(drvdata);
+	if (rc) {
+		dev_err(dev, "Failed to get legal sampling ratio for rosc\n");
+		return rc;
+	}
+
+	rc = cc_trng_clk_init(drvdata);
+	if (rc) {
+		dev_err(dev, "cc_trng_clk_init failed\n");
+		return rc;
+	}
+
+	INIT_WORK(&drvdata->compwork, cc_trng_compwork_handler);
+	INIT_WORK(&drvdata->startwork, cc_trng_startwork_handler);
+	spin_lock_init(&drvdata->read_lock);
+
+	/* register the driver isr function */
+	rc = devm_request_irq(dev, irq, cc_isr, IRQF_SHARED, "cctrng", drvdata);
+	if (rc) {
+		dev_err(dev, "Could not register to interrupt %d\n", irq);
+		goto post_clk_err;
+	}
+	dev_dbg(dev, "Registered to IRQ: %d\n", irq);
+
+	/* Clear all pending interrupts */
+	val = cc_ioread(drvdata, CC_HOST_RGF_IRR_REG_OFFSET);
+	dev_dbg(dev, "IRR=0x%08X\n", val);
+	cc_iowrite(drvdata, CC_HOST_RGF_ICR_REG_OFFSET, val);
+
+	/* unmask HOST RNG interrupt */
+	cc_iowrite(drvdata, CC_HOST_RGF_IMR_REG_OFFSET,
+		   cc_ioread(drvdata, CC_HOST_RGF_IMR_REG_OFFSET) &
+		   ~CC_HOST_RNG_IRQ_MASK);
+
+	/* init PM */
+	rc = cc_trng_pm_init(drvdata);
+	if (rc) {
+		dev_err(dev, "cc_trng_pm_init failed\n");
+		goto post_clk_err;
+	}
+
+	/* increment device's usage counter */
+	rc = cc_trng_pm_get(dev);
+	if (rc) {
+		dev_err(dev, "cc_trng_pm_get returned %x\n", rc);
+		goto post_pm_err;
+	}
+
+	/* set pending_hw to verify that HW won't be triggered from read */
+	atomic_set(&drvdata->pending_hw, 1);
+
+	/* registration of the hwrng device */
+	rc = hwrng_register(&drvdata->rng);
+	if (rc) {
+		dev_err(dev, "Could not register hwrng device.\n");
+		goto post_pm_err;
+	}
+
+	/* trigger HW to start generate data */
+	drvdata->active_rosc = 0;
+	cc_trng_hw_trigger(drvdata);
+
+	/* All set, we can allow auto-suspend */
+	cc_trng_pm_go(drvdata);
+
+	dev_info(dev, "ARM cctrng device initialized\n");
+
+	return 0;
+
+post_pm_err:
+	cc_trng_pm_fini(drvdata);
+
+post_clk_err:
+	cc_trng_clk_fini(drvdata);
+
+	return rc;
+}
+
+static int cctrng_remove(struct platform_device *pdev)
+{
+	struct cctrng_drvdata *drvdata = platform_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+
+	dev_dbg(dev, "Releasing cctrng resources...\n");
+
+	hwrng_unregister(&drvdata->rng);
+
+	cc_trng_pm_fini(drvdata);
+
+	cc_trng_clk_fini(drvdata);
+
+	dev_info(dev, "ARM cctrng device terminated\n");
+
+	return 0;
+}
+
+static int __maybe_unused cctrng_suspend(struct device *dev)
+{
+	struct cctrng_drvdata *drvdata = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "set HOST_POWER_DOWN_EN\n");
+	cc_iowrite(drvdata, CC_HOST_POWER_DOWN_EN_REG_OFFSET,
+			POWER_DOWN_ENABLE);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	return 0;
+}
+
+static bool cctrng_wait_for_reset_completion(struct cctrng_drvdata *drvdata)
+{
+	unsigned int val;
+	unsigned int i;
+
+	for (i = 0; i < CC_HW_RESET_LOOP_COUNT; i++) {
+		/* in cc7x3 NVM_IS_IDLE indicates that CC reset is
+		 *  completed and device is fully functional
+		 */
+		val = cc_ioread(drvdata, CC_NVM_IS_IDLE_REG_OFFSET);
+		if (val & BIT(CC_NVM_IS_IDLE_VALUE_BIT_SHIFT)) {
+			/* hw indicate reset completed */
+			return true;
+		}
+		/* allow scheduling other process on the processor */
+		schedule();
+	}
+	/* reset not completed */
+	return false;
+}
+
+static int __maybe_unused cctrng_resume(struct device *dev)
+{
+	struct cctrng_drvdata *drvdata = dev_get_drvdata(dev);
+	int rc;
+
+	dev_dbg(dev, "unset HOST_POWER_DOWN_EN\n");
+	/* Enables the device source clk */
+	rc = clk_prepare_enable(drvdata->clk);
+	if (rc) {
+		dev_err(dev, "failed getting clock back on. We're toast.\n");
+		return rc;
+	}
+
+	/* wait for Cryptocell reset completion */
+	if (!cctrng_wait_for_reset_completion(drvdata)) {
+		dev_err(dev, "Cryptocell reset not completed");
+		return -EBUSY;
+	}
+
+	/* unmask HOST RNG interrupt */
+	cc_iowrite(drvdata, CC_HOST_RGF_IMR_REG_OFFSET,
+		   cc_ioread(drvdata, CC_HOST_RGF_IMR_REG_OFFSET) &
+		   ~CC_HOST_RNG_IRQ_MASK);
+
+	cc_iowrite(drvdata, CC_HOST_POWER_DOWN_EN_REG_OFFSET,
+		   POWER_DOWN_DISABLE);
+
+	return 0;
+}
+
+static UNIVERSAL_DEV_PM_OPS(cctrng_pm, cctrng_suspend, cctrng_resume, NULL);
+
+static const struct of_device_id arm_cctrng_dt_match[] = {
+	{ .compatible = "arm,cryptocell-713-trng", },
+	{ .compatible = "arm,cryptocell-703-trng", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, arm_cctrng_dt_match);
+
+static struct platform_driver cctrng_driver = {
+	.driver = {
+		.name = "cctrng",
+		.of_match_table = arm_cctrng_dt_match,
+		.pm = &cctrng_pm,
+	},
+	.probe = cctrng_probe,
+	.remove = cctrng_remove,
+};
+
+static int __init cctrng_mod_init(void)
+{
+	/* Compile time assertion checks */
+	BUILD_BUG_ON(CCTRNG_DATA_BUF_WORDS < 6);
+	BUILD_BUG_ON((CCTRNG_DATA_BUF_WORDS & (CCTRNG_DATA_BUF_WORDS-1)) != 0);
+
+	return platform_driver_register(&cctrng_driver);
+}
+module_init(cctrng_mod_init);
+
+static void __exit cctrng_mod_exit(void)
+{
+	platform_driver_unregister(&cctrng_driver);
+}
+module_exit(cctrng_mod_exit);
+
+/* Module description */
+MODULE_DESCRIPTION("ARM CryptoCell TRNG Driver");
+MODULE_AUTHOR("ARM");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/char/hw_random/cctrng.h b/drivers/char/hw_random/cctrng.h
new file mode 100644
index 000000000000..1f2fde95adcb
--- /dev/null
+++ b/drivers/char/hw_random/cctrng.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019-2020 ARM Limited or its affiliates. */
+
+#include <linux/bitops.h>
+
+#define POWER_DOWN_ENABLE 0x01
+#define POWER_DOWN_DISABLE 0x00
+
+/* hwrng quality: bits of true entropy per 1024 bits of input */
+#define CC_TRNG_QUALITY	1024
+
+/* CryptoCell TRNG HW definitions */
+#define CC_TRNG_NUM_OF_ROSCS	4
+/* The number of words generated in the entropy holding register (EHR)
+ * 6 words (192 bit) according to HW implementation
+ */
+#define CC_TRNG_EHR_IN_WORDS	6
+#define CC_TRNG_EHR_IN_BITS	(CC_TRNG_EHR_IN_WORDS * BITS_PER_TYPE(u32))
+
+#define CC_HOST_RNG_IRQ_MASK BIT(CC_HOST_RGF_IRR_RNG_INT_BIT_SHIFT)
+
+/* RNG interrupt mask */
+#define CC_RNG_INT_MASK (BIT(CC_RNG_IMR_EHR_VALID_INT_MASK_BIT_SHIFT) | \
+			 BIT(CC_RNG_IMR_AUTOCORR_ERR_INT_MASK_BIT_SHIFT) | \
+			 BIT(CC_RNG_IMR_CRNGT_ERR_INT_MASK_BIT_SHIFT) | \
+			 BIT(CC_RNG_IMR_VN_ERR_INT_MASK_BIT_SHIFT) | \
+			 BIT(CC_RNG_IMR_WATCHDOG_INT_MASK_BIT_SHIFT))
+
+// --------------------------------------
+// BLOCK: RNG
+// --------------------------------------
+#define CC_RNG_IMR_REG_OFFSET	0x0100UL
+#define CC_RNG_IMR_EHR_VALID_INT_MASK_BIT_SHIFT	0x0UL
+#define CC_RNG_IMR_AUTOCORR_ERR_INT_MASK_BIT_SHIFT	0x1UL
+#define CC_RNG_IMR_CRNGT_ERR_INT_MASK_BIT_SHIFT	0x2UL
+#define CC_RNG_IMR_VN_ERR_INT_MASK_BIT_SHIFT	0x3UL
+#define CC_RNG_IMR_WATCHDOG_INT_MASK_BIT_SHIFT	0x4UL
+#define CC_RNG_ISR_REG_OFFSET	0x0104UL
+#define CC_RNG_ISR_EHR_VALID_BIT_SHIFT	0x0UL
+#define CC_RNG_ISR_EHR_VALID_BIT_SIZE	0x1UL
+#define CC_RNG_ISR_AUTOCORR_ERR_BIT_SHIFT	0x1UL
+#define CC_RNG_ISR_AUTOCORR_ERR_BIT_SIZE	0x1UL
+#define CC_RNG_ISR_CRNGT_ERR_BIT_SHIFT	0x2UL
+#define CC_RNG_ISR_CRNGT_ERR_BIT_SIZE	0x1UL
+#define CC_RNG_ISR_WATCHDOG_BIT_SHIFT	0x4UL
+#define CC_RNG_ISR_WATCHDOG_BIT_SIZE	0x1UL
+#define CC_RNG_ICR_REG_OFFSET	0x0108UL
+#define CC_TRNG_CONFIG_REG_OFFSET	0x010CUL
+#define CC_EHR_DATA_0_REG_OFFSET	0x0114UL
+#define CC_RND_SOURCE_ENABLE_REG_OFFSET	0x012CUL
+#define CC_SAMPLE_CNT1_REG_OFFSET	0x0130UL
+#define CC_TRNG_DEBUG_CONTROL_REG_OFFSET	0x0138UL
+#define CC_RNG_SW_RESET_REG_OFFSET	0x0140UL
+#define CC_RNG_CLK_ENABLE_REG_OFFSET	0x01C4UL
+#define CC_RNG_DMA_ENABLE_REG_OFFSET	0x01C8UL
+#define CC_RNG_WATCHDOG_VAL_REG_OFFSET	0x01D8UL
+// --------------------------------------
+// BLOCK: SEC_HOST_RGF
+// --------------------------------------
+#define CC_HOST_RGF_IRR_REG_OFFSET	0x0A00UL
+#define CC_HOST_RGF_IRR_RNG_INT_BIT_SHIFT	0xAUL
+#define CC_HOST_RGF_IMR_REG_OFFSET	0x0A04UL
+#define CC_HOST_RGF_ICR_REG_OFFSET	0x0A08UL
+
+#define CC_HOST_POWER_DOWN_EN_REG_OFFSET	0x0A78UL
+
+// --------------------------------------
+// BLOCK: NVM
+// --------------------------------------
+#define CC_NVM_IS_IDLE_REG_OFFSET	0x0F10UL
+#define CC_NVM_IS_IDLE_VALUE_BIT_SHIFT	0x0UL
+#define CC_NVM_IS_IDLE_VALUE_BIT_SIZE	0x1UL
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 65952393e1bb..7290c603fcb8 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -392,11 +392,8 @@ static int of_get_omap_rng_device_details(struct omap_rng_dev *priv,
 	if (of_device_is_compatible(dev->of_node, "ti,omap4-rng") ||
 	    of_device_is_compatible(dev->of_node, "inside-secure,safexcel-eip76")) {
 		irq = platform_get_irq(pdev, 0);
-		if (irq < 0) {
-			dev_err(dev, "%s: error getting IRQ resource - %d\n",
-				__func__, irq);
+		if (irq < 0)
 			return irq;
-		}
 
 		err = devm_request_irq(dev, irq, omap4_rng_irq,
 				       IRQF_TRIGGER_NONE, dev_name(dev), priv);
diff --git a/drivers/char/hw_random/optee-rng.c b/drivers/char/hw_random/optee-rng.c
index ddfbabaa5f8f..49b2e02537dd 100644
--- a/drivers/char/hw_random/optee-rng.c
+++ b/drivers/char/hw_random/optee-rng.c
@@ -226,7 +226,7 @@ static int optee_rng_probe(struct device *dev)
 		return -ENODEV;
 
 	/* Open session with hwrng Trusted App */
-	memcpy(sess_arg.uuid, rng_device->id.uuid.b, TEE_IOCTL_UUID_LEN);
+	export_uuid(sess_arg.uuid, &rng_device->id.uuid);
 	sess_arg.clnt_login = TEE_IOCTL_LOGIN_PUBLIC;
 	sess_arg.num_params = 0;
 
diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c
index 718d8c087650..79a6e47b5fbc 100644
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c
@@ -11,6 +11,7 @@
 #include <linux/virtio.h>
 #include <linux/virtio_rng.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 
 static DEFINE_IDA(rng_index_ida);
 
diff --git a/drivers/char/hw_random/xgene-rng.c b/drivers/char/hw_random/xgene-rng.c
index d7516a446987..008e6db9ce01 100644
--- a/drivers/char/hw_random/xgene-rng.c
+++ b/drivers/char/hw_random/xgene-rng.c
@@ -328,10 +328,8 @@ static int xgene_rng_probe(struct platform_device *pdev)
 		return PTR_ERR(ctx->csr_base);
 
 	rc = platform_get_irq(pdev, 0);
-	if (rc < 0) {
-		dev_err(&pdev->dev, "No IRQ resource\n");
+	if (rc < 0)
 		return rc;
-	}
 	ctx->irq = rc;
 
 	dev_dbg(&pdev->dev, "APM X-Gene RNG BASE %p ALARM IRQ %d",
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index b7145f370d3b..2704470e021d 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -1947,8 +1947,8 @@ static int ssif_adapter_handler(struct device *adev, void *opaque)
 	if (adev->type != &i2c_adapter_type)
 		return 0;
 
-	addr_info->added_client = i2c_new_device(to_i2c_adapter(adev),
-						 &addr_info->binfo);
+	addr_info->added_client = i2c_new_client_device(to_i2c_adapter(adev),
+							&addr_info->binfo);
 
 	if (!addr_info->adapter_name)
 		return 1; /* Only try the first I2C adapter by default. */
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 0d10e31fd342..cae02b2a871c 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -327,7 +327,6 @@
 #include <linux/spinlock.h>
 #include <linux/kthread.h>
 #include <linux/percpu.h>
-#include <linux/cryptohash.h>
 #include <linux/fips.h>
 #include <linux/ptrace.h>
 #include <linux/workqueue.h>
@@ -337,6 +336,7 @@
 #include <linux/completion.h>
 #include <linux/uuid.h>
 #include <crypto/chacha.h>
+#include <crypto/sha.h>
 
 #include <asm/processor.h>
 #include <linux/uaccess.h>
@@ -1397,14 +1397,14 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 		__u32 w[5];
 		unsigned long l[LONGS(20)];
 	} hash;
-	__u32 workspace[SHA_WORKSPACE_WORDS];
+	__u32 workspace[SHA1_WORKSPACE_WORDS];
 	unsigned long flags;
 
 	/*
 	 * If we have an architectural hardware random number
 	 * generator, use it for SHA's initial vector
 	 */
-	sha_init(hash.w);
+	sha1_init(hash.w);
 	for (i = 0; i < LONGS(20); i++) {
 		unsigned long v;
 		if (!arch_get_random_long(&v))
@@ -1415,7 +1415,7 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	/* Generate a hash across the pool, 16 words (512 bits) at a time */
 	spin_lock_irqsave(&r->lock, flags);
 	for (i = 0; i < r->poolinfo->poolwords; i += 16)
-		sha_transform(hash.w, (__u8 *)(r->pool + i), workspace);
+		sha1_transform(hash.w, (__u8 *)(r->pool + i), workspace);
 
 	/*
 	 * We mix the hash back into the pool to prevent backtracking
diff --git a/drivers/char/tpm/eventlog/tpm2.c b/drivers/char/tpm/eventlog/tpm2.c
index e741b1157525..37a05800980c 100644
--- a/drivers/char/tpm/eventlog/tpm2.c
+++ b/drivers/char/tpm/eventlog/tpm2.c
@@ -51,8 +51,7 @@ static void *tpm2_bios_measurements_start(struct seq_file *m, loff_t *pos)
 	int i;
 
 	event_header = addr;
-	size = sizeof(struct tcg_pcr_event) - sizeof(event_header->event)
-		+ event_header->event_size;
+	size = struct_size(event_header, event, event_header->event_size);
 
 	if (*pos == 0) {
 		if (addr + size < limit) {
@@ -98,8 +97,8 @@ static void *tpm2_bios_measurements_next(struct seq_file *m, void *v,
 	event_header = log->bios_event_log;
 
 	if (v == SEQ_START_TOKEN) {
-		event_size = sizeof(struct tcg_pcr_event) -
-			sizeof(event_header->event) + event_header->event_size;
+		event_size = struct_size(event_header, event,
+					 event_header->event_size);
 		marker = event_header;
 	} else {
 		event = v;
@@ -136,9 +135,8 @@ static int tpm2_binary_bios_measurements_show(struct seq_file *m, void *v)
 	size_t size;
 
 	if (v == SEQ_START_TOKEN) {
-		size = sizeof(struct tcg_pcr_event) -
-			sizeof(event_header->event) + event_header->event_size;
-
+		size = struct_size(event_header, event,
+				   event_header->event_size);
 		temp_ptr = event_header;
 
 		if (size > 0)
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index a438b1206fcb..1621ce818705 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -323,7 +323,7 @@ int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx,
 
 	for (i = 0; i < chip->nr_allocated_banks; i++) {
 		if (digests[i].alg_id != chip->allocated_banks[i].alg_id) {
-			rc = EINVAL;
+			rc = -EINVAL;
 			goto out;
 		}
 	}
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index 76f67b155bd5..eff1f12d981a 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -681,6 +681,7 @@ out:
 		rc = -ENODEV;
 	return rc;
 }
+EXPORT_SYMBOL_GPL(tpm2_get_cc_attrs_tbl);
 
 /**
  * tpm2_startup - turn on the TPM
diff --git a/drivers/char/tpm/tpm_ftpm_tee.c b/drivers/char/tpm/tpm_ftpm_tee.c
index 22bf553ccf9d..2491a2cb54a2 100644
--- a/drivers/char/tpm/tpm_ftpm_tee.c
+++ b/drivers/char/tpm/tpm_ftpm_tee.c
@@ -241,7 +241,7 @@ static int ftpm_tee_probe(struct platform_device *pdev)
 
 	/* Open a session with fTPM TA */
 	memset(&sess_arg, 0, sizeof(sess_arg));
-	memcpy(sess_arg.uuid, ftpm_ta_uuid.b, TEE_IOCTL_UUID_LEN);
+	export_uuid(sess_arg.uuid, &ftpm_ta_uuid);
 	sess_arg.clnt_login = TEE_IOCTL_LOGIN_PUBLIC;
 	sess_arg.num_params = 0;
 
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index 1a49db9e108e..09fe45246b8c 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2012 IBM Corporation
+ * Copyright (C) 2012-2020 IBM Corporation
  *
  * Author: Ashley Lai <ashleydlai@gmail.com>
  *
@@ -135,6 +135,64 @@ static int tpm_ibmvtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 }
 
 /**
+ * ibmvtpm_crq_send_init - Send a CRQ initialize message
+ * @ibmvtpm:	vtpm device struct
+ *
+ * Return:
+ *	0 on success.
+ *	Non-zero on failure.
+ */
+static int ibmvtpm_crq_send_init(struct ibmvtpm_dev *ibmvtpm)
+{
+	int rc;
+
+	rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD);
+	if (rc != H_SUCCESS)
+		dev_err(ibmvtpm->dev,
+			"%s failed rc=%d\n", __func__, rc);
+
+	return rc;
+}
+
+/**
+ * tpm_ibmvtpm_resume - Resume from suspend
+ *
+ * @dev:	device struct
+ *
+ * Return: Always 0.
+ */
+static int tpm_ibmvtpm_resume(struct device *dev)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
+	int rc = 0;
+
+	do {
+		if (rc)
+			msleep(100);
+		rc = plpar_hcall_norets(H_ENABLE_CRQ,
+					ibmvtpm->vdev->unit_address);
+	} while (rc == H_IN_PROGRESS || rc == H_BUSY || H_IS_LONG_BUSY(rc));
+
+	if (rc) {
+		dev_err(dev, "Error enabling ibmvtpm rc=%d\n", rc);
+		return rc;
+	}
+
+	rc = vio_enable_interrupts(ibmvtpm->vdev);
+	if (rc) {
+		dev_err(dev, "Error vio_enable_interrupts rc=%d\n", rc);
+		return rc;
+	}
+
+	rc = ibmvtpm_crq_send_init(ibmvtpm);
+	if (rc)
+		dev_err(dev, "Error send_init rc=%d\n", rc);
+
+	return rc;
+}
+
+/**
  * tpm_ibmvtpm_send() - Send a TPM command
  * @chip:	tpm chip struct
  * @buf:	buffer contains data to send
@@ -147,6 +205,7 @@ static int tpm_ibmvtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
 {
 	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
+	bool retry = true;
 	int rc, sig;
 
 	if (!ibmvtpm->rtce_buf) {
@@ -180,18 +239,27 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
 	 */
 	ibmvtpm->tpm_processing_cmd = true;
 
+again:
 	rc = ibmvtpm_send_crq(ibmvtpm->vdev,
 			IBMVTPM_VALID_CMD, VTPM_TPM_COMMAND,
 			count, ibmvtpm->rtce_dma_handle);
 	if (rc != H_SUCCESS) {
+		/*
+		 * H_CLOSED can be returned after LPM resume.  Call
+		 * tpm_ibmvtpm_resume() to re-enable the CRQ then retry
+		 * ibmvtpm_send_crq() once before failing.
+		 */
+		if (rc == H_CLOSED && retry) {
+			tpm_ibmvtpm_resume(ibmvtpm->dev);
+			retry = false;
+			goto again;
+		}
 		dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc);
-		rc = 0;
 		ibmvtpm->tpm_processing_cmd = false;
-	} else
-		rc = 0;
+	}
 
 	spin_unlock(&ibmvtpm->rtce_lock);
-	return rc;
+	return 0;
 }
 
 static void tpm_ibmvtpm_cancel(struct tpm_chip *chip)
@@ -270,26 +338,6 @@ static int ibmvtpm_crq_send_init_complete(struct ibmvtpm_dev *ibmvtpm)
 }
 
 /**
- * ibmvtpm_crq_send_init - Send a CRQ initialize message
- * @ibmvtpm:	vtpm device struct
- *
- * Return:
- *	0 on success.
- *	Non-zero on failure.
- */
-static int ibmvtpm_crq_send_init(struct ibmvtpm_dev *ibmvtpm)
-{
-	int rc;
-
-	rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD);
-	if (rc != H_SUCCESS)
-		dev_err(ibmvtpm->dev,
-			"ibmvtpm_crq_send_init failed rc=%d\n", rc);
-
-	return rc;
-}
-
-/**
  * tpm_ibmvtpm_remove - ibm vtpm remove entry point
  * @vdev:	vio device struct
  *
@@ -401,44 +449,6 @@ static int ibmvtpm_reset_crq(struct ibmvtpm_dev *ibmvtpm)
 				  ibmvtpm->crq_dma_handle, CRQ_RES_BUF_SIZE);
 }
 
-/**
- * tpm_ibmvtpm_resume - Resume from suspend
- *
- * @dev:	device struct
- *
- * Return: Always 0.
- */
-static int tpm_ibmvtpm_resume(struct device *dev)
-{
-	struct tpm_chip *chip = dev_get_drvdata(dev);
-	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
-	int rc = 0;
-
-	do {
-		if (rc)
-			msleep(100);
-		rc = plpar_hcall_norets(H_ENABLE_CRQ,
-					ibmvtpm->vdev->unit_address);
-	} while (rc == H_IN_PROGRESS || rc == H_BUSY || H_IS_LONG_BUSY(rc));
-
-	if (rc) {
-		dev_err(dev, "Error enabling ibmvtpm rc=%d\n", rc);
-		return rc;
-	}
-
-	rc = vio_enable_interrupts(ibmvtpm->vdev);
-	if (rc) {
-		dev_err(dev, "Error vio_enable_interrupts rc=%d\n", rc);
-		return rc;
-	}
-
-	rc = ibmvtpm_crq_send_init(ibmvtpm);
-	if (rc)
-		dev_err(dev, "Error send_init rc=%d\n", rc);
-
-	return rc;
-}
-
 static bool tpm_ibmvtpm_req_canceled(struct tpm_chip *chip, u8 status)
 {
 	return (status == 0);
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 27c6ca031e23..2435216bd10a 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -433,6 +433,9 @@ static void disable_interrupts(struct tpm_chip *chip)
 	u32 intmask;
 	int rc;
 
+	if (priv->irq == 0)
+		return;
+
 	rc = tpm_tis_read32(priv, TPM_INT_ENABLE(priv->locality), &intmask);
 	if (rc < 0)
 		intmask = 0;
@@ -1062,9 +1065,12 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 		if (irq) {
 			tpm_tis_probe_irq_single(chip, intmask, IRQF_SHARED,
 						 irq);
-			if (!(chip->flags & TPM_CHIP_FLAG_IRQ))
+			if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) {
 				dev_err(&chip->dev, FW_BUG
 					"TPM interrupt not working, polling instead\n");
+
+				disable_interrupts(chip);
+			}
 		} else {
 			tpm_tis_probe_irq(chip, intmask);
 		}
diff --git a/drivers/clk/clk-asm9260.c b/drivers/clk/clk-asm9260.c
index 536b59aabd2c..bacebd457e6f 100644
--- a/drivers/clk/clk-asm9260.c
+++ b/drivers/clk/clk-asm9260.c
@@ -276,7 +276,7 @@ static void __init asm9260_acc_init(struct device_node *np)
 
 	/* TODO: Convert to DT parent scheme */
 	ref_clk = of_clk_get_parent_name(np, 0);
-	hw = __clk_hw_register_fixed_rate_with_accuracy(NULL, NULL, pll_clk,
+	hw = __clk_hw_register_fixed_rate(NULL, NULL, pll_clk,
 			ref_clk, NULL, NULL, 0, rate, 0,
 			CLK_FIXED_RATE_PARENT_ACCURACY);
 
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 39c59f063aa0..2dfb30b963c4 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -3519,6 +3519,9 @@ static int __clk_core_init(struct clk_core *core)
 out:
 	clk_pm_runtime_put(core);
 unlock:
+	if (ret)
+		hlist_del_init(&core->child_node);
+
 	clk_prepare_unlock();
 
 	if (!ret)
diff --git a/drivers/clk/mmp/clk-pll.c b/drivers/clk/mmp/clk-pll.c
index 7077be293871..962014cfdc44 100644
--- a/drivers/clk/mmp/clk-pll.c
+++ b/drivers/clk/mmp/clk-pll.c
@@ -97,7 +97,7 @@ static const struct clk_ops mmp_clk_pll_ops = {
 	.recalc_rate = mmp_clk_pll_recalc_rate,
 };
 
-struct clk *mmp_clk_register_pll(char *name,
+static struct clk *mmp_clk_register_pll(char *name,
 			unsigned long default_rate,
 			void __iomem *enable_reg, u32 enable,
 			void __iomem *reg, u8 shift,
@@ -137,3 +137,34 @@ struct clk *mmp_clk_register_pll(char *name,
 
 	return clk;
 }
+
+void mmp_register_pll_clks(struct mmp_clk_unit *unit,
+			struct mmp_param_pll_clk *clks,
+			void __iomem *base, int size)
+{
+	struct clk *clk;
+	int i;
+
+	for (i = 0; i < size; i++) {
+		void __iomem *reg = NULL;
+
+		if (clks[i].offset)
+			reg = base + clks[i].offset;
+
+		clk = mmp_clk_register_pll(clks[i].name,
+					clks[i].default_rate,
+					base + clks[i].enable_offset,
+					clks[i].enable,
+					reg, clks[i].shift,
+					clks[i].input_rate,
+					base + clks[i].postdiv_offset,
+					clks[i].postdiv_shift);
+		if (IS_ERR(clk)) {
+			pr_err("%s: failed to register clock %s\n",
+			       __func__, clks[i].name);
+			continue;
+		}
+		if (clks[i].id)
+			unit->clk_table[clks[i].id] = clk;
+	}
+}
diff --git a/drivers/clk/mmp/clk.c b/drivers/clk/mmp/clk.c
index 317123641d1e..ca7d37e2c7be 100644
--- a/drivers/clk/mmp/clk.c
+++ b/drivers/clk/mmp/clk.c
@@ -176,37 +176,6 @@ void mmp_register_div_clks(struct mmp_clk_unit *unit,
 	}
 }
 
-void mmp_register_pll_clks(struct mmp_clk_unit *unit,
-			struct mmp_param_pll_clk *clks,
-			void __iomem *base, int size)
-{
-	struct clk *clk;
-	int i;
-
-	for (i = 0; i < size; i++) {
-		void __iomem *reg = NULL;
-
-		if (clks[i].offset)
-			reg = base + clks[i].offset;
-
-		clk = mmp_clk_register_pll(clks[i].name,
-					clks[i].default_rate,
-					base + clks[i].enable_offset,
-					clks[i].enable,
-					reg, clks[i].shift,
-					clks[i].input_rate,
-					base + clks[i].postdiv_offset,
-					clks[i].postdiv_shift);
-		if (IS_ERR(clk)) {
-			pr_err("%s: failed to register clock %s\n",
-			       __func__, clks[i].name);
-			continue;
-		}
-		if (clks[i].id)
-			unit->clk_table[clks[i].id] = clk;
-	}
-}
-
 void mmp_clk_add(struct mmp_clk_unit *unit, unsigned int id,
 			struct clk *clk)
 {
diff --git a/drivers/clk/mmp/clk.h b/drivers/clk/mmp/clk.h
index 971b4d6d992f..20dc1e5dd756 100644
--- a/drivers/clk/mmp/clk.h
+++ b/drivers/clk/mmp/clk.h
@@ -238,13 +238,6 @@ void mmp_register_pll_clks(struct mmp_clk_unit *unit,
 			struct mmp_param_pll_clk *clks,
 			void __iomem *base, int size);
 
-extern struct clk *mmp_clk_register_pll(char *name,
-			unsigned long default_rate,
-			void __iomem *enable_reg, u32 enable,
-			void __iomem *reg, u8 shift,
-			unsigned long input_rate,
-			void __iomem *postdiv_reg, u8 postdiv_shift);
-
 #define DEFINE_MIX_REG_INFO(w_d, s_d, w_m, s_m, fc)	\
 {							\
 	.width_div = (w_d),				\
diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 11ec6f466467..abb121f8de52 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -377,6 +377,7 @@ config SM_GCC_8150
 
 config SM_GCC_8250
 	tristate "SM8250 Global Clock Controller"
+	select QCOM_GDSC
 	help
 	  Support for the global clock controller on SM8250 devices.
 	  Say Y if you want to use peripheral devices such as UART,
diff --git a/drivers/clk/qcom/gcc-sm8150.c b/drivers/clk/qcom/gcc-sm8150.c
index ef98fdc51755..732bc7c937e6 100644
--- a/drivers/clk/qcom/gcc-sm8150.c
+++ b/drivers/clk/qcom/gcc-sm8150.c
@@ -76,8 +76,7 @@ static struct clk_alpha_pll_postdiv gpll0_out_even = {
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "gpll0_out_even",
 		.parent_data = &(const struct clk_parent_data){
-			.fw_name = "bi_tcxo",
-			.name = "bi_tcxo",
+			.hw = &gpll0.clkr.hw,
 		},
 		.num_parents = 1,
 		.ops = &clk_trion_pll_postdiv_ops,
diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c
index d17cfb7a3ff4..d7243c09cc84 100644
--- a/drivers/clk/rockchip/clk-rk3228.c
+++ b/drivers/clk/rockchip/clk-rk3228.c
@@ -156,8 +156,6 @@ PNAME(mux_i2s_out_p)		= { "i2s1_pre", "xin12m" };
 PNAME(mux_i2s2_p)		= { "i2s2_src", "i2s2_frac", "xin12m" };
 PNAME(mux_sclk_spdif_p)		= { "sclk_spdif_src", "spdif_frac", "xin12m" };
 
-PNAME(mux_aclk_gpu_pre_p)	= { "cpll_gpu", "gpll_gpu", "hdmiphy_gpu", "usb480m_gpu" };
-
 PNAME(mux_uart0_p)		= { "uart0_src", "uart0_frac", "xin24m" };
 PNAME(mux_uart1_p)		= { "uart1_src", "uart1_frac", "xin24m" };
 PNAME(mux_uart2_p)		= { "uart2_src", "uart2_frac", "xin24m" };
@@ -468,16 +466,9 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 			RK2928_CLKSEL_CON(24), 6, 10, DFLAGS,
 			RK2928_CLKGATE_CON(2), 8, GFLAGS),
 
-	GATE(0, "cpll_gpu", "cpll", 0,
-			RK2928_CLKGATE_CON(3), 13, GFLAGS),
-	GATE(0, "gpll_gpu", "gpll", 0,
-			RK2928_CLKGATE_CON(3), 13, GFLAGS),
-	GATE(0, "hdmiphy_gpu", "hdmiphy", 0,
-			RK2928_CLKGATE_CON(3), 13, GFLAGS),
-	GATE(0, "usb480m_gpu", "usb480m", 0,
+	COMPOSITE(0, "aclk_gpu_pre", mux_pll_src_4plls_p, 0,
+			RK2928_CLKSEL_CON(34), 5, 2, MFLAGS, 0, 5, DFLAGS,
 			RK2928_CLKGATE_CON(3), 13, GFLAGS),
-	COMPOSITE_NOGATE(0, "aclk_gpu_pre", mux_aclk_gpu_pre_p, 0,
-			RK2928_CLKSEL_CON(34), 5, 2, MFLAGS, 0, 5, DFLAGS),
 
 	COMPOSITE(SCLK_SPI0, "sclk_spi0", mux_pll_src_2plls_p, 0,
 			RK2928_CLKSEL_CON(25), 8, 1, MFLAGS, 0, 7, DFLAGS,
@@ -582,8 +573,8 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
 	GATE(0, "pclk_peri_noc", "pclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 2, GFLAGS),
 
 	/* PD_GPU */
-	GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 14, GFLAGS),
-	GATE(0, "aclk_gpu_noc", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 15, GFLAGS),
+	GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(7), 14, GFLAGS),
+	GATE(0, "aclk_gpu_noc", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(7), 15, GFLAGS),
 
 	/* PD_BUS */
 	GATE(0, "sclk_initmem_mbist", "aclk_cpu", 0, RK2928_CLKGATE_CON(8), 1, GFLAGS),
diff --git a/drivers/clk/sprd/sc9863a-clk.c b/drivers/clk/sprd/sc9863a-clk.c
index a0631f7756cf..2e2dfb2d48ff 100644
--- a/drivers/clk/sprd/sc9863a-clk.c
+++ b/drivers/clk/sprd/sc9863a-clk.c
@@ -1641,8 +1641,9 @@ static SPRD_SC_GATE_CLK_FW_NAME(i2c4_eb,	"i2c4-eb",	"ext-26m", 0x0,
 				0x1000, BIT(12), 0, 0);
 static SPRD_SC_GATE_CLK_FW_NAME(uart0_eb,	"uart0-eb",	"ext-26m", 0x0,
 				0x1000, BIT(13), 0, 0);
+/* uart1_eb is for console, don't gate even if unused */
 static SPRD_SC_GATE_CLK_FW_NAME(uart1_eb,	"uart1-eb",	"ext-26m", 0x0,
-				0x1000, BIT(14), 0, 0);
+				0x1000, BIT(14), CLK_IGNORE_UNUSED, 0);
 static SPRD_SC_GATE_CLK_FW_NAME(uart2_eb,	"uart2-eb",	"ext-26m", 0x0,
 				0x1000, BIT(15), 0, 0);
 static SPRD_SC_GATE_CLK_FW_NAME(uart3_eb,	"uart3-eb",	"ext-26m", 0x0,
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index 64e229ddf2a5..e931319dcc9d 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -1292,7 +1292,7 @@ static struct tegra_clk_init_table common_init_table[] __initdata = {
 	{ TEGRA124_CLK_UARTB, TEGRA124_CLK_PLL_P, 408000000, 0 },
 	{ TEGRA124_CLK_UARTC, TEGRA124_CLK_PLL_P, 408000000, 0 },
 	{ TEGRA124_CLK_UARTD, TEGRA124_CLK_PLL_P, 408000000, 0 },
-	{ TEGRA124_CLK_PLL_A, TEGRA124_CLK_CLK_MAX, 564480000, 0 },
+	{ TEGRA124_CLK_PLL_A, TEGRA124_CLK_CLK_MAX, 282240000, 0 },
 	{ TEGRA124_CLK_PLL_A_OUT0, TEGRA124_CLK_CLK_MAX, 11289600, 0 },
 	{ TEGRA124_CLK_I2S0, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 },
 	{ TEGRA124_CLK_I2S1, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 },
diff --git a/drivers/clk/ti/clk-33xx.c b/drivers/clk/ti/clk-33xx.c
index e001b9bcb6bf..7dc30dd6c8d5 100644
--- a/drivers/clk/ti/clk-33xx.c
+++ b/drivers/clk/ti/clk-33xx.c
@@ -212,7 +212,7 @@ static const struct omap_clkctrl_reg_data am3_mpu_clkctrl_regs[] __initconst = {
 };
 
 static const struct omap_clkctrl_reg_data am3_l4_rtc_clkctrl_regs[] __initconst = {
-	{ AM3_L4_RTC_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clk_32768_ck" },
+	{ AM3_L4_RTC_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clk-24mhz-clkctrl:0000:0" },
 	{ 0 },
 };
 
diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c
index 062266034d84..864c484bde1b 100644
--- a/drivers/clk/ti/clkctrl.c
+++ b/drivers/clk/ti/clkctrl.c
@@ -255,24 +255,53 @@ static struct clk_hw *_ti_omap4_clkctrl_xlate(struct of_phandle_args *clkspec,
 	return entry->clk;
 }
 
+/* Get clkctrl clock base name based on clkctrl_name or dts node */
+static const char * __init clkctrl_get_clock_name(struct device_node *np,
+						  const char *clkctrl_name,
+						  int offset, int index,
+						  bool legacy_naming)
+{
+	char *clock_name;
+
+	/* l4per-clkctrl:1234:0 style naming based on clkctrl_name */
+	if (clkctrl_name && !legacy_naming) {
+		clock_name = kasprintf(GFP_KERNEL, "%s-clkctrl:%04x:%d",
+				       clkctrl_name, offset, index);
+		strreplace(clock_name, '_', '-');
+
+		return clock_name;
+	}
+
+	/* l4per:1234:0 old style naming based on clkctrl_name */
+	if (clkctrl_name)
+		return kasprintf(GFP_KERNEL, "%s_cm:clk:%04x:%d",
+				 clkctrl_name, offset, index);
+
+	/* l4per_cm:1234:0 old style naming based on parent node name */
+	if (legacy_naming)
+		return kasprintf(GFP_KERNEL, "%pOFn:clk:%04x:%d",
+				 np->parent, offset, index);
+
+	/* l4per-clkctrl:1234:0 style naming based on node name */
+	return kasprintf(GFP_KERNEL, "%pOFn:%04x:%d", np, offset, index);
+}
+
 static int __init
 _ti_clkctrl_clk_register(struct omap_clkctrl_provider *provider,
 			 struct device_node *node, struct clk_hw *clk_hw,
 			 u16 offset, u8 bit, const char * const *parents,
-			 int num_parents, const struct clk_ops *ops)
+			 int num_parents, const struct clk_ops *ops,
+			 const char *clkctrl_name)
 {
 	struct clk_init_data init = { NULL };
 	struct clk *clk;
 	struct omap_clkctrl_clk *clkctrl_clk;
 	int ret = 0;
 
-	if (ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT)
-		init.name = kasprintf(GFP_KERNEL, "%pOFn:%pOFn:%04x:%d",
-				      node->parent, node, offset,
-				      bit);
-	else
-		init.name = kasprintf(GFP_KERNEL, "%pOFn:%04x:%d", node,
-				      offset, bit);
+	init.name = clkctrl_get_clock_name(node, clkctrl_name, offset, bit,
+					   ti_clk_get_features()->flags &
+					   TI_CLK_CLKCTRL_COMPAT);
+
 	clkctrl_clk = kzalloc(sizeof(*clkctrl_clk), GFP_KERNEL);
 	if (!init.name || !clkctrl_clk) {
 		ret = -ENOMEM;
@@ -309,7 +338,7 @@ static void __init
 _ti_clkctrl_setup_gate(struct omap_clkctrl_provider *provider,
 		       struct device_node *node, u16 offset,
 		       const struct omap_clkctrl_bit_data *data,
-		       void __iomem *reg)
+		       void __iomem *reg, const char *clkctrl_name)
 {
 	struct clk_hw_omap *clk_hw;
 
@@ -322,7 +351,7 @@ _ti_clkctrl_setup_gate(struct omap_clkctrl_provider *provider,
 
 	if (_ti_clkctrl_clk_register(provider, node, &clk_hw->hw, offset,
 				     data->bit, data->parents, 1,
-				     &omap_gate_clk_ops))
+				     &omap_gate_clk_ops, clkctrl_name))
 		kfree(clk_hw);
 }
 
@@ -330,7 +359,7 @@ static void __init
 _ti_clkctrl_setup_mux(struct omap_clkctrl_provider *provider,
 		      struct device_node *node, u16 offset,
 		      const struct omap_clkctrl_bit_data *data,
-		      void __iomem *reg)
+		      void __iomem *reg, const char *clkctrl_name)
 {
 	struct clk_omap_mux *mux;
 	int num_parents = 0;
@@ -357,7 +386,7 @@ _ti_clkctrl_setup_mux(struct omap_clkctrl_provider *provider,
 
 	if (_ti_clkctrl_clk_register(provider, node, &mux->hw, offset,
 				     data->bit, data->parents, num_parents,
-				     &ti_clk_mux_ops))
+				     &ti_clk_mux_ops, clkctrl_name))
 		kfree(mux);
 }
 
@@ -365,7 +394,7 @@ static void __init
 _ti_clkctrl_setup_div(struct omap_clkctrl_provider *provider,
 		      struct device_node *node, u16 offset,
 		      const struct omap_clkctrl_bit_data *data,
-		      void __iomem *reg)
+		      void __iomem *reg, const char *clkctrl_name)
 {
 	struct clk_omap_divider *div;
 	const struct omap_clkctrl_div_data *div_data = data->data;
@@ -393,7 +422,7 @@ _ti_clkctrl_setup_div(struct omap_clkctrl_provider *provider,
 
 	if (_ti_clkctrl_clk_register(provider, node, &div->hw, offset,
 				     data->bit, data->parents, 1,
-				     &ti_clk_divider_ops))
+				     &ti_clk_divider_ops, clkctrl_name))
 		kfree(div);
 }
 
@@ -401,7 +430,7 @@ static void __init
 _ti_clkctrl_setup_subclks(struct omap_clkctrl_provider *provider,
 			  struct device_node *node,
 			  const struct omap_clkctrl_reg_data *data,
-			  void __iomem *reg)
+			  void __iomem *reg, const char *clkctrl_name)
 {
 	const struct omap_clkctrl_bit_data *bits = data->bit_data;
 
@@ -412,17 +441,17 @@ _ti_clkctrl_setup_subclks(struct omap_clkctrl_provider *provider,
 		switch (bits->type) {
 		case TI_CLK_GATE:
 			_ti_clkctrl_setup_gate(provider, node, data->offset,
-					       bits, reg);
+					       bits, reg, clkctrl_name);
 			break;
 
 		case TI_CLK_DIVIDER:
 			_ti_clkctrl_setup_div(provider, node, data->offset,
-					      bits, reg);
+					      bits, reg, clkctrl_name);
 			break;
 
 		case TI_CLK_MUX:
 			_ti_clkctrl_setup_mux(provider, node, data->offset,
-					      bits, reg);
+					      bits, reg, clkctrl_name);
 			break;
 
 		default:
@@ -461,42 +490,10 @@ static char * __init clkctrl_get_name(struct device_node *np)
 			return name;
 		}
 	}
-	of_node_put(np);
 
 	return NULL;
 }
 
-/* Get clkctrl clock base name based on clkctrl_name or dts node */
-static const char * __init clkctrl_get_clock_name(struct device_node *np,
-						  const char *clkctrl_name,
-						  int offset, int index,
-						  bool legacy_naming)
-{
-	char *clock_name;
-
-	/* l4per-clkctrl:1234:0 style naming based on clkctrl_name */
-	if (clkctrl_name && !legacy_naming) {
-		clock_name = kasprintf(GFP_KERNEL, "%s-clkctrl:%04x:%d",
-				       clkctrl_name, offset, index);
-		strreplace(clock_name, '_', '-');
-
-		return clock_name;
-	}
-
-	/* l4per:1234:0 old style naming based on clkctrl_name */
-	if (clkctrl_name)
-		return kasprintf(GFP_KERNEL, "%s_cm:clk:%04x:%d",
-				 clkctrl_name, offset, index);
-
-	/* l4per_cm:1234:0 old style naming based on parent node name */
-	if (legacy_naming)
-		return kasprintf(GFP_KERNEL, "%pOFn:clk:%04x:%d",
-				 np->parent, offset, index);
-
-	/* l4per-clkctrl:1234:0 style naming based on node name */
-	return kasprintf(GFP_KERNEL, "%pOFn:%04x:%d", np, offset, index);
-}
-
 static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 {
 	struct omap_clkctrl_provider *provider;
@@ -664,7 +661,7 @@ clkdm_found:
 		hw->enable_reg.ptr = provider->base + reg_data->offset;
 
 		_ti_clkctrl_setup_subclks(provider, node, reg_data,
-					  hw->enable_reg.ptr);
+					  hw->enable_reg.ptr, clkctrl_name);
 
 		if (reg_data->flags & CLKF_SW_SUP)
 			hw->enable_bit = MODULEMODE_SWCTRL;
diff --git a/drivers/clk/versatile/clk-impd1.c b/drivers/clk/versatile/clk-impd1.c
index b05da8516d4c..f9f4babe3ca6 100644
--- a/drivers/clk/versatile/clk-impd1.c
+++ b/drivers/clk/versatile/clk-impd1.c
@@ -206,6 +206,7 @@ static int integrator_impd1_clk_spawn(struct device *dev,
 		return -ENODEV;
 	}
 
+	of_property_read_string(np, "clock-output-names", &name);
 	parent_name = of_clk_get_parent_name(np, 0);
 	clk = icst_clk_setup(NULL, desc, name, parent_name, map,
 			     ICST_INTEGRATOR_IM_PD1);
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index d58ce664da84..646ad385e490 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -18,6 +18,7 @@
 #include <linux/pid_namespace.h>
 
 #include <linux/cn_proc.h>
+#include <linux/local_lock.h>
 
 /*
  * Size of a cn_msg followed by a proc_event structure.  Since the
@@ -38,25 +39,31 @@ static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer)
 static atomic_t proc_event_num_listeners = ATOMIC_INIT(0);
 static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
 
-/* proc_event_counts is used as the sequence number of the netlink message */
-static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
+/* local_event.count is used as the sequence number of the netlink message */
+struct local_event {
+	local_lock_t lock;
+	__u32 count;
+};
+static DEFINE_PER_CPU(struct local_event, local_event) = {
+	.lock = INIT_LOCAL_LOCK(lock),
+};
 
 static inline void send_msg(struct cn_msg *msg)
 {
-	preempt_disable();
+	local_lock(&local_event.lock);
 
-	msg->seq = __this_cpu_inc_return(proc_event_counts) - 1;
+	msg->seq = __this_cpu_inc_return(local_event.count) - 1;
 	((struct proc_event *)msg->data)->cpu = smp_processor_id();
 
 	/*
-	 * Preemption remains disabled during send to ensure the messages are
-	 * ordered according to their sequence numbers.
+	 * local_lock() disables preemption during send to ensure the messages
+	 * are ordered according to their sequence numbers.
 	 *
 	 * If cn_netlink_send() fails, the data is not sent.
 	 */
 	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
 
-	preempt_enable();
+	local_unlock(&local_event.lock);
 }
 
 void proc_fork_connector(struct task_struct *task)
diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c
index 9dab190c49b0..aa13708c2bc3 100644
--- a/drivers/counter/104-quad-8.c
+++ b/drivers/counter/104-quad-8.c
@@ -44,6 +44,7 @@ MODULE_PARM_DESC(base, "ACCES 104-QUAD-8 base addresses");
  * @base:		base port address of the IIO device
  */
 struct quad8_iio {
+	struct mutex lock;
 	struct counter_device counter;
 	unsigned int fck_prescaler[QUAD8_NUM_COUNTERS];
 	unsigned int preset[QUAD8_NUM_COUNTERS];
@@ -123,6 +124,8 @@ static int quad8_read_raw(struct iio_dev *indio_dev,
 		/* Borrow XOR Carry effectively doubles count range */
 		*val = (borrow ^ carry) << 24;
 
+		mutex_lock(&priv->lock);
+
 		/* Reset Byte Pointer; transfer Counter to Output Latch */
 		outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP | QUAD8_RLD_CNTR_OUT,
 		     base_offset + 1);
@@ -130,6 +133,8 @@ static int quad8_read_raw(struct iio_dev *indio_dev,
 		for (i = 0; i < 3; i++)
 			*val |= (unsigned int)inb(base_offset) << (8 * i);
 
+		mutex_unlock(&priv->lock);
+
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_ENABLE:
 		*val = priv->ab_enable[chan->channel];
@@ -160,6 +165,8 @@ static int quad8_write_raw(struct iio_dev *indio_dev,
 		if ((unsigned int)val > 0xFFFFFF)
 			return -EINVAL;
 
+		mutex_lock(&priv->lock);
+
 		/* Reset Byte Pointer */
 		outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP, base_offset + 1);
 
@@ -183,12 +190,16 @@ static int quad8_write_raw(struct iio_dev *indio_dev,
 		/* Reset Error flag */
 		outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_E, base_offset + 1);
 
+		mutex_unlock(&priv->lock);
+
 		return 0;
 	case IIO_CHAN_INFO_ENABLE:
 		/* only boolean values accepted */
 		if (val < 0 || val > 1)
 			return -EINVAL;
 
+		mutex_lock(&priv->lock);
+
 		priv->ab_enable[chan->channel] = val;
 
 		ior_cfg = val | priv->preset_enable[chan->channel] << 1;
@@ -196,11 +207,18 @@ static int quad8_write_raw(struct iio_dev *indio_dev,
 		/* Load I/O control configuration */
 		outb(QUAD8_CTR_IOR | ior_cfg, base_offset + 1);
 
+		mutex_unlock(&priv->lock);
+
 		return 0;
 	case IIO_CHAN_INFO_SCALE:
+		mutex_lock(&priv->lock);
+
 		/* Quadrature scaling only available in quadrature mode */
-		if (!priv->quadrature_mode[chan->channel] && (val2 || val != 1))
+		if (!priv->quadrature_mode[chan->channel] &&
+				(val2 || val != 1)) {
+			mutex_unlock(&priv->lock);
 			return -EINVAL;
+		}
 
 		/* Only three gain states (1, 0.5, 0.25) */
 		if (val == 1 && !val2)
@@ -214,11 +232,15 @@ static int quad8_write_raw(struct iio_dev *indio_dev,
 				priv->quadrature_scale[chan->channel] = 2;
 				break;
 			default:
+				mutex_unlock(&priv->lock);
 				return -EINVAL;
 			}
-		else
+		else {
+			mutex_unlock(&priv->lock);
 			return -EINVAL;
+		}
 
+		mutex_unlock(&priv->lock);
 		return 0;
 	}
 
@@ -255,6 +277,8 @@ static ssize_t quad8_write_preset(struct iio_dev *indio_dev, uintptr_t private,
 	if (preset > 0xFFFFFF)
 		return -EINVAL;
 
+	mutex_lock(&priv->lock);
+
 	priv->preset[chan->channel] = preset;
 
 	/* Reset Byte Pointer */
@@ -264,6 +288,8 @@ static ssize_t quad8_write_preset(struct iio_dev *indio_dev, uintptr_t private,
 	for (i = 0; i < 3; i++)
 		outb(preset >> (8 * i), base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -293,6 +319,8 @@ static ssize_t quad8_write_set_to_preset_on_index(struct iio_dev *indio_dev,
 	/* Preset enable is active low in Input/Output Control register */
 	preset_enable = !preset_enable;
 
+	mutex_lock(&priv->lock);
+
 	priv->preset_enable[chan->channel] = preset_enable;
 
 	ior_cfg = priv->ab_enable[chan->channel] |
@@ -301,6 +329,8 @@ static ssize_t quad8_write_set_to_preset_on_index(struct iio_dev *indio_dev,
 	/* Load I/O control configuration to Input / Output Control Register */
 	outb(QUAD8_CTR_IOR | ior_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -358,6 +388,8 @@ static int quad8_set_count_mode(struct iio_dev *indio_dev,
 	unsigned int mode_cfg = cnt_mode << 1;
 	const int base_offset = priv->base + 2 * chan->channel + 1;
 
+	mutex_lock(&priv->lock);
+
 	priv->count_mode[chan->channel] = cnt_mode;
 
 	/* Add quadrature mode configuration */
@@ -367,6 +399,8 @@ static int quad8_set_count_mode(struct iio_dev *indio_dev,
 	/* Load mode configuration to Counter Mode Register */
 	outb(QUAD8_CTR_CMR | mode_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -394,19 +428,26 @@ static int quad8_set_synchronous_mode(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, unsigned int synchronous_mode)
 {
 	struct quad8_iio *const priv = iio_priv(indio_dev);
-	const unsigned int idr_cfg = synchronous_mode |
-		priv->index_polarity[chan->channel] << 1;
 	const int base_offset = priv->base + 2 * chan->channel + 1;
+	unsigned int idr_cfg = synchronous_mode;
+
+	mutex_lock(&priv->lock);
+
+	idr_cfg |= priv->index_polarity[chan->channel] << 1;
 
 	/* Index function must be non-synchronous in non-quadrature mode */
-	if (synchronous_mode && !priv->quadrature_mode[chan->channel])
+	if (synchronous_mode && !priv->quadrature_mode[chan->channel]) {
+		mutex_unlock(&priv->lock);
 		return -EINVAL;
+	}
 
 	priv->synchronous_mode[chan->channel] = synchronous_mode;
 
 	/* Load Index Control configuration to Index Control Register */
 	outb(QUAD8_CTR_IDR | idr_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -434,8 +475,12 @@ static int quad8_set_quadrature_mode(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, unsigned int quadrature_mode)
 {
 	struct quad8_iio *const priv = iio_priv(indio_dev);
-	unsigned int mode_cfg = priv->count_mode[chan->channel] << 1;
 	const int base_offset = priv->base + 2 * chan->channel + 1;
+	unsigned int mode_cfg;
+
+	mutex_lock(&priv->lock);
+
+	mode_cfg = priv->count_mode[chan->channel] << 1;
 
 	if (quadrature_mode)
 		mode_cfg |= (priv->quadrature_scale[chan->channel] + 1) << 3;
@@ -453,6 +498,8 @@ static int quad8_set_quadrature_mode(struct iio_dev *indio_dev,
 	/* Load mode configuration to Counter Mode Register */
 	outb(QUAD8_CTR_CMR | mode_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -480,15 +527,20 @@ static int quad8_set_index_polarity(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, unsigned int index_polarity)
 {
 	struct quad8_iio *const priv = iio_priv(indio_dev);
-	const unsigned int idr_cfg = priv->synchronous_mode[chan->channel] |
-		index_polarity << 1;
 	const int base_offset = priv->base + 2 * chan->channel + 1;
+	unsigned int idr_cfg = index_polarity << 1;
+
+	mutex_lock(&priv->lock);
+
+	idr_cfg |= priv->synchronous_mode[chan->channel];
 
 	priv->index_polarity[chan->channel] = index_polarity;
 
 	/* Load Index Control configuration to Index Control Register */
 	outb(QUAD8_CTR_IDR | idr_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -589,7 +641,7 @@ static int quad8_signal_read(struct counter_device *counter,
 static int quad8_count_read(struct counter_device *counter,
 	struct counter_count *count, unsigned long *val)
 {
-	const struct quad8_iio *const priv = counter->priv;
+	struct quad8_iio *const priv = counter->priv;
 	const int base_offset = priv->base + 2 * count->id;
 	unsigned int flags;
 	unsigned int borrow;
@@ -603,6 +655,8 @@ static int quad8_count_read(struct counter_device *counter,
 	/* Borrow XOR Carry effectively doubles count range */
 	*val = (unsigned long)(borrow ^ carry) << 24;
 
+	mutex_lock(&priv->lock);
+
 	/* Reset Byte Pointer; transfer Counter to Output Latch */
 	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP | QUAD8_RLD_CNTR_OUT,
 	     base_offset + 1);
@@ -610,13 +664,15 @@ static int quad8_count_read(struct counter_device *counter,
 	for (i = 0; i < 3; i++)
 		*val |= (unsigned long)inb(base_offset) << (8 * i);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
 static int quad8_count_write(struct counter_device *counter,
 	struct counter_count *count, unsigned long val)
 {
-	const struct quad8_iio *const priv = counter->priv;
+	struct quad8_iio *const priv = counter->priv;
 	const int base_offset = priv->base + 2 * count->id;
 	int i;
 
@@ -624,6 +680,8 @@ static int quad8_count_write(struct counter_device *counter,
 	if (val > 0xFFFFFF)
 		return -EINVAL;
 
+	mutex_lock(&priv->lock);
+
 	/* Reset Byte Pointer */
 	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP, base_offset + 1);
 
@@ -647,6 +705,8 @@ static int quad8_count_write(struct counter_device *counter,
 	/* Reset Error flag */
 	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_E, base_offset + 1);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -667,13 +727,13 @@ static enum counter_count_function quad8_count_functions_list[] = {
 static int quad8_function_get(struct counter_device *counter,
 	struct counter_count *count, size_t *function)
 {
-	const struct quad8_iio *const priv = counter->priv;
+	struct quad8_iio *const priv = counter->priv;
 	const int id = count->id;
-	const unsigned int quadrature_mode = priv->quadrature_mode[id];
-	const unsigned int scale = priv->quadrature_scale[id];
 
-	if (quadrature_mode)
-		switch (scale) {
+	mutex_lock(&priv->lock);
+
+	if (priv->quadrature_mode[id])
+		switch (priv->quadrature_scale[id]) {
 		case 0:
 			*function = QUAD8_COUNT_FUNCTION_QUADRATURE_X1;
 			break;
@@ -687,6 +747,8 @@ static int quad8_function_get(struct counter_device *counter,
 	else
 		*function = QUAD8_COUNT_FUNCTION_PULSE_DIRECTION;
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -697,10 +759,15 @@ static int quad8_function_set(struct counter_device *counter,
 	const int id = count->id;
 	unsigned int *const quadrature_mode = priv->quadrature_mode + id;
 	unsigned int *const scale = priv->quadrature_scale + id;
-	unsigned int mode_cfg = priv->count_mode[id] << 1;
 	unsigned int *const synchronous_mode = priv->synchronous_mode + id;
-	const unsigned int idr_cfg = priv->index_polarity[id] << 1;
 	const int base_offset = priv->base + 2 * id + 1;
+	unsigned int mode_cfg;
+	unsigned int idr_cfg;
+
+	mutex_lock(&priv->lock);
+
+	mode_cfg = priv->count_mode[id] << 1;
+	idr_cfg = priv->index_polarity[id] << 1;
 
 	if (function == QUAD8_COUNT_FUNCTION_PULSE_DIRECTION) {
 		*quadrature_mode = 0;
@@ -736,6 +803,8 @@ static int quad8_function_set(struct counter_device *counter,
 	/* Load mode configuration to Counter Mode Register */
 	outb(QUAD8_CTR_CMR | mode_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -852,15 +921,20 @@ static int quad8_index_polarity_set(struct counter_device *counter,
 {
 	struct quad8_iio *const priv = counter->priv;
 	const size_t channel_id = signal->id - 16;
-	const unsigned int idr_cfg = priv->synchronous_mode[channel_id] |
-		index_polarity << 1;
 	const int base_offset = priv->base + 2 * channel_id + 1;
+	unsigned int idr_cfg = index_polarity << 1;
+
+	mutex_lock(&priv->lock);
+
+	idr_cfg |= priv->synchronous_mode[channel_id];
 
 	priv->index_polarity[channel_id] = index_polarity;
 
 	/* Load Index Control configuration to Index Control Register */
 	outb(QUAD8_CTR_IDR | idr_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -887,19 +961,26 @@ static int quad8_synchronous_mode_set(struct counter_device *counter,
 {
 	struct quad8_iio *const priv = counter->priv;
 	const size_t channel_id = signal->id - 16;
-	const unsigned int idr_cfg = synchronous_mode |
-		priv->index_polarity[channel_id] << 1;
 	const int base_offset = priv->base + 2 * channel_id + 1;
+	unsigned int idr_cfg = synchronous_mode;
+
+	mutex_lock(&priv->lock);
+
+	idr_cfg |= priv->index_polarity[channel_id] << 1;
 
 	/* Index function must be non-synchronous in non-quadrature mode */
-	if (synchronous_mode && !priv->quadrature_mode[channel_id])
+	if (synchronous_mode && !priv->quadrature_mode[channel_id]) {
+		mutex_unlock(&priv->lock);
 		return -EINVAL;
+	}
 
 	priv->synchronous_mode[channel_id] = synchronous_mode;
 
 	/* Load Index Control configuration to Index Control Register */
 	outb(QUAD8_CTR_IDR | idr_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -964,6 +1045,8 @@ static int quad8_count_mode_set(struct counter_device *counter,
 		break;
 	}
 
+	mutex_lock(&priv->lock);
+
 	priv->count_mode[count->id] = cnt_mode;
 
 	/* Set count mode configuration value */
@@ -976,6 +1059,8 @@ static int quad8_count_mode_set(struct counter_device *counter,
 	/* Load mode configuration to Counter Mode Register */
 	outb(QUAD8_CTR_CMR | mode_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return 0;
 }
 
@@ -1017,6 +1102,8 @@ static ssize_t quad8_count_enable_write(struct counter_device *counter,
 	if (err)
 		return err;
 
+	mutex_lock(&priv->lock);
+
 	priv->ab_enable[count->id] = ab_enable;
 
 	ior_cfg = ab_enable | priv->preset_enable[count->id] << 1;
@@ -1024,6 +1111,8 @@ static ssize_t quad8_count_enable_write(struct counter_device *counter,
 	/* Load I/O control configuration */
 	outb(QUAD8_CTR_IOR | ior_cfg, base_offset + 1);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -1052,14 +1141,28 @@ static ssize_t quad8_count_preset_read(struct counter_device *counter,
 	return sprintf(buf, "%u\n", priv->preset[count->id]);
 }
 
+static void quad8_preset_register_set(struct quad8_iio *quad8iio, int id,
+		unsigned int preset)
+{
+	const unsigned int base_offset = quad8iio->base + 2 * id;
+	int i;
+
+	quad8iio->preset[id] = preset;
+
+	/* Reset Byte Pointer */
+	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP, base_offset + 1);
+
+	/* Set Preset Register */
+	for (i = 0; i < 3; i++)
+		outb(preset >> (8 * i), base_offset);
+}
+
 static ssize_t quad8_count_preset_write(struct counter_device *counter,
 	struct counter_count *count, void *private, const char *buf, size_t len)
 {
 	struct quad8_iio *const priv = counter->priv;
-	const int base_offset = priv->base + 2 * count->id;
 	unsigned int preset;
 	int ret;
-	int i;
 
 	ret = kstrtouint(buf, 0, &preset);
 	if (ret)
@@ -1069,14 +1172,11 @@ static ssize_t quad8_count_preset_write(struct counter_device *counter,
 	if (preset > 0xFFFFFF)
 		return -EINVAL;
 
-	priv->preset[count->id] = preset;
+	mutex_lock(&priv->lock);
 
-	/* Reset Byte Pointer */
-	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP, base_offset + 1);
+	quad8_preset_register_set(priv, count->id, preset);
 
-	/* Set Preset Register */
-	for (i = 0; i < 3; i++)
-		outb(preset >> (8 * i), base_offset);
+	mutex_unlock(&priv->lock);
 
 	return len;
 }
@@ -1084,15 +1184,20 @@ static ssize_t quad8_count_preset_write(struct counter_device *counter,
 static ssize_t quad8_count_ceiling_read(struct counter_device *counter,
 	struct counter_count *count, void *private, char *buf)
 {
-	const struct quad8_iio *const priv = counter->priv;
+	struct quad8_iio *const priv = counter->priv;
+
+	mutex_lock(&priv->lock);
 
 	/* Range Limit and Modulo-N count modes use preset value as ceiling */
 	switch (priv->count_mode[count->id]) {
 	case 1:
 	case 3:
-		return quad8_count_preset_read(counter, count, private, buf);
+		mutex_unlock(&priv->lock);
+		return sprintf(buf, "%u\n", priv->preset[count->id]);
 	}
 
+	mutex_unlock(&priv->lock);
+
 	/* By default 0x1FFFFFF (25 bits unsigned) is maximum count */
 	return sprintf(buf, "33554431\n");
 }
@@ -1101,15 +1206,29 @@ static ssize_t quad8_count_ceiling_write(struct counter_device *counter,
 	struct counter_count *count, void *private, const char *buf, size_t len)
 {
 	struct quad8_iio *const priv = counter->priv;
+	unsigned int ceiling;
+	int ret;
+
+	ret = kstrtouint(buf, 0, &ceiling);
+	if (ret)
+		return ret;
+
+	/* Only 24-bit values are supported */
+	if (ceiling > 0xFFFFFF)
+		return -EINVAL;
+
+	mutex_lock(&priv->lock);
 
 	/* Range Limit and Modulo-N count modes use preset value as ceiling */
 	switch (priv->count_mode[count->id]) {
 	case 1:
 	case 3:
-		return quad8_count_preset_write(counter, count, private, buf,
-						len);
+		quad8_preset_register_set(priv, count->id, ceiling);
+		break;
 	}
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -1137,6 +1256,8 @@ static ssize_t quad8_count_preset_enable_write(struct counter_device *counter,
 	/* Preset enable is active low in Input/Output Control register */
 	preset_enable = !preset_enable;
 
+	mutex_lock(&priv->lock);
+
 	priv->preset_enable[count->id] = preset_enable;
 
 	ior_cfg = priv->ab_enable[count->id] | (unsigned int)preset_enable << 1;
@@ -1144,6 +1265,8 @@ static ssize_t quad8_count_preset_enable_write(struct counter_device *counter,
 	/* Load I/O control configuration to Input / Output Control Register */
 	outb(QUAD8_CTR_IOR | ior_cfg, base_offset);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -1429,6 +1552,9 @@ static int quad8_probe(struct device *dev, unsigned int id)
 	quad8iio->counter.priv = quad8iio;
 	quad8iio->base = base[id];
 
+	/* Initialize mutex */
+	mutex_init(&quad8iio->lock);
+
 	/* Reset all counters and disable interrupt function */
 	outb(QUAD8_CHAN_OP_RESET_COUNTERS, base[id] + QUAD8_REG_CHAN_OP);
 	/* Set initial configuration for all counters */
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 4d1e25d1ced1..4d3429b2058f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1059,7 +1059,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 
 	update_turbo_state();
 	if (global.turbo_disabled) {
-		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
+		pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n");
 		mutex_unlock(&intel_pstate_limits_lock);
 		mutex_unlock(&intel_pstate_driver_lock);
 		return -EPERM;
diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
index 8ba4f9c81dac..5d9d0fedcb06 100644
--- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
+++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c
@@ -537,10 +537,8 @@ static int sun8i_ss_probe(struct platform_device *pdev)
 		return err;
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(ss->dev, "Cannot get SecuritySystem IRQ\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	ss->reset = devm_reset_control_get(&pdev->dev, NULL);
 	if (IS_ERR(ss->reset)) {
diff --git a/drivers/crypto/amlogic/amlogic-gxl-core.c b/drivers/crypto/amlogic/amlogic-gxl-core.c
index 9d4ead2f7ebb..411857fad8ba 100644
--- a/drivers/crypto/amlogic/amlogic-gxl-core.c
+++ b/drivers/crypto/amlogic/amlogic-gxl-core.c
@@ -253,10 +253,8 @@ static int meson_crypto_probe(struct platform_device *pdev)
 	mc->irqs = devm_kcalloc(mc->dev, MAXFLOW, sizeof(int), GFP_KERNEL);
 	for (i = 0; i < MAXFLOW; i++) {
 		mc->irqs[i] = platform_get_irq(pdev, i);
-		if (mc->irqs[i] < 0) {
-			dev_err(mc->dev, "Cannot get IRQ for flow %d\n", i);
+		if (mc->irqs[i] < 0)
 			return mc->irqs[i];
-		}
 
 		err = devm_request_irq(&pdev->dev, mc->irqs[i], meson_irq_handler, 0,
 				       "gxl-crypto", mc);
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index e536e2a6bbd8..75ccf41a7cb9 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -31,7 +31,6 @@
 #include <linux/of_device.h>
 #include <linux/delay.h>
 #include <linux/crypto.h>
-#include <linux/cryptohash.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/algapi.h>
 #include <crypto/sha.h>
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index fcf1effc7661..62ba0325a618 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -2239,16 +2239,12 @@ artpec6_crypto_hash_set_key(struct crypto_ahash *tfm,
 	blocksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm));
 
 	if (keylen > blocksize) {
-		SHASH_DESC_ON_STACK(hdesc, tfm_ctx->child_hash);
-
-		hdesc->tfm = tfm_ctx->child_hash;
-
 		tfm_ctx->hmac_key_length = blocksize;
-		ret = crypto_shash_digest(hdesc, key, keylen,
-					  tfm_ctx->hmac_key);
+
+		ret = crypto_shash_tfm_digest(tfm_ctx->child_hash, key, keylen,
+					      tfm_ctx->hmac_key);
 		if (ret)
 			return ret;
-
 	} else {
 		memcpy(tfm_ctx->hmac_key, key, keylen);
 		tfm_ctx->hmac_key_length = keylen;
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index c8b9408541a9..a353217a0d33 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -308,9 +308,9 @@ static int handle_skcipher_req(struct iproc_reqctx_s *rctx)
 	    container_of(areq, struct skcipher_request, base);
 	struct iproc_ctx_s *ctx = rctx->ctx;
 	struct spu_cipher_parms cipher_parms;
-	int err = 0;
-	unsigned int chunksize = 0;	/* Num bytes of request to submit */
-	int remaining = 0;	/* Bytes of request still to process */
+	int err;
+	unsigned int chunksize;	/* Num bytes of request to submit */
+	int remaining;	/* Bytes of request still to process */
 	int chunk_start;	/* Beginning of data for current SPU msg */
 
 	/* IV or ctr value to use in this SPU msg */
@@ -698,7 +698,7 @@ static int handle_ahash_req(struct iproc_reqctx_s *rctx)
 
 	/* number of bytes still to be hashed in this req */
 	unsigned int nbytes_to_hash = 0;
-	int err = 0;
+	int err;
 	unsigned int chunksize = 0;	/* length of hash carry + new data */
 	/*
 	 * length of new data, not from hash carry, to be submitted in
@@ -1664,7 +1664,7 @@ static void spu_rx_callback(struct mbox_client *cl, void *msg)
 	struct spu_hw *spu = &iproc_priv.spu;
 	struct brcm_message *mssg = msg;
 	struct iproc_reqctx_s *rctx;
-	int err = 0;
+	int err;
 
 	rctx = mssg->ctx;
 	if (unlikely(!rctx)) {
@@ -1967,7 +1967,7 @@ static int ahash_enqueue(struct ahash_request *req)
 	struct iproc_reqctx_s *rctx = ahash_request_ctx(req);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct iproc_ctx_s *ctx = crypto_ahash_ctx(tfm);
-	int err = 0;
+	int err;
 	const char *alg_name;
 
 	flow_log("ahash_enqueue() nbytes:%u\n", req->nbytes);
@@ -2299,7 +2299,7 @@ ahash_finup_exit:
 
 static int ahash_digest(struct ahash_request *req)
 {
-	int err = 0;
+	int err;
 
 	flow_log("ahash_digest() nbytes:%u\n", req->nbytes);
 
@@ -4436,7 +4436,7 @@ static int spu_mb_init(struct device *dev)
 	for (i = 0; i < iproc_priv.spu.num_chan; i++) {
 		iproc_priv.mbox[i] = mbox_request_channel(mcl, i);
 		if (IS_ERR(iproc_priv.mbox[i])) {
-			err = (int)PTR_ERR(iproc_priv.mbox[i]);
+			err = PTR_ERR(iproc_priv.mbox[i]);
 			dev_err(dev,
 				"Mbox channel %d request failed with err %d",
 				i, err);
@@ -4717,21 +4717,20 @@ static int spu_dt_read(struct platform_device *pdev)
 
 	matched_spu_type = of_device_get_match_data(dev);
 	if (!matched_spu_type) {
-		dev_err(&pdev->dev, "Failed to match device\n");
+		dev_err(dev, "Failed to match device\n");
 		return -ENODEV;
 	}
 
 	spu->spu_type = matched_spu_type->type;
 	spu->spu_subtype = matched_spu_type->subtype;
 
-	i = 0;
 	for (i = 0; (i < MAX_SPUS) && ((spu_ctrl_regs =
 		platform_get_resource(pdev, IORESOURCE_MEM, i)) != NULL); i++) {
 
 		spu->reg_vbase[i] = devm_ioremap_resource(dev, spu_ctrl_regs);
 		if (IS_ERR(spu->reg_vbase[i])) {
 			err = PTR_ERR(spu->reg_vbase[i]);
-			dev_err(&pdev->dev, "Failed to map registers: %d\n",
+			dev_err(dev, "Failed to map registers: %d\n",
 				err);
 			spu->reg_vbase[i] = NULL;
 			return err;
@@ -4747,7 +4746,7 @@ static int bcm_spu_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct spu_hw *spu = &iproc_priv.spu;
-	int err = 0;
+	int err;
 
 	iproc_priv.pdev  = pdev;
 	platform_set_drvdata(iproc_priv.pdev,
@@ -4757,7 +4756,7 @@ static int bcm_spu_probe(struct platform_device *pdev)
 	if (err < 0)
 		goto failure;
 
-	err = spu_mb_init(&pdev->dev);
+	err = spu_mb_init(dev);
 	if (err < 0)
 		goto failure;
 
@@ -4766,7 +4765,7 @@ static int bcm_spu_probe(struct platform_device *pdev)
 	else if (spu->spu_type == SPU_TYPE_SPU2)
 		iproc_priv.bcm_hdr_len = 0;
 
-	spu_functions_register(&pdev->dev, spu->spu_type, spu->spu_subtype);
+	spu_functions_register(dev, spu->spu_type, spu->spu_subtype);
 
 	spu_counters_init();
 
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index b7bb7c30adeb..b2f9882bc010 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -963,10 +963,12 @@ static void aead_crypt_done(struct device *jrdev, u32 *desc, u32 err,
 	struct caam_drv_private_jr *jrp = dev_get_drvdata(jrdev);
 	struct aead_edesc *edesc;
 	int ecode = 0;
+	bool has_bklog;
 
 	dev_dbg(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
 
 	edesc = rctx->edesc;
+	has_bklog = edesc->bklog;
 
 	if (err)
 		ecode = caam_jr_strstatus(jrdev, err);
@@ -979,7 +981,7 @@ static void aead_crypt_done(struct device *jrdev, u32 *desc, u32 err,
 	 * If no backlog flag, the completion of the request is done
 	 * by CAAM, not crypto engine.
 	 */
-	if (!edesc->bklog)
+	if (!has_bklog)
 		aead_request_complete(req, ecode);
 	else
 		crypto_finalize_aead_request(jrp->engine, req, ecode);
@@ -995,10 +997,12 @@ static void skcipher_crypt_done(struct device *jrdev, u32 *desc, u32 err,
 	struct caam_drv_private_jr *jrp = dev_get_drvdata(jrdev);
 	int ivsize = crypto_skcipher_ivsize(skcipher);
 	int ecode = 0;
+	bool has_bklog;
 
 	dev_dbg(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
 
 	edesc = rctx->edesc;
+	has_bklog = edesc->bklog;
 	if (err)
 		ecode = caam_jr_strstatus(jrdev, err);
 
@@ -1028,7 +1032,7 @@ static void skcipher_crypt_done(struct device *jrdev, u32 *desc, u32 err,
 	 * If no backlog flag, the completion of the request is done
 	 * by CAAM, not crypto engine.
 	 */
-	if (!edesc->bklog)
+	if (!has_bklog)
 		skcipher_request_complete(req, ecode);
 	else
 		crypto_finalize_skcipher_request(jrp->engine, req, ecode);
@@ -1711,7 +1715,7 @@ static struct skcipher_edesc *skcipher_edesc_alloc(struct skcipher_request *req,
 
 	if (ivsize || mapped_dst_nents > 1)
 		sg_to_sec4_set_last(edesc->sec4_sg + dst_sg_idx +
-				    mapped_dst_nents);
+				    mapped_dst_nents - 1 + !!ivsize);
 
 	if (sec4_sg_bytes) {
 		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 943bc0296267..27ff4a3d037e 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -583,10 +583,12 @@ static inline void ahash_done_cpy(struct device *jrdev, u32 *desc, u32 err,
 	struct caam_hash_state *state = ahash_request_ctx(req);
 	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
 	int ecode = 0;
+	bool has_bklog;
 
 	dev_dbg(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
 
 	edesc = state->edesc;
+	has_bklog = edesc->bklog;
 
 	if (err)
 		ecode = caam_jr_strstatus(jrdev, err);
@@ -603,7 +605,7 @@ static inline void ahash_done_cpy(struct device *jrdev, u32 *desc, u32 err,
 	 * If no backlog flag, the completion of the request is done
 	 * by CAAM, not crypto engine.
 	 */
-	if (!edesc->bklog)
+	if (!has_bklog)
 		req->base.complete(&req->base, ecode);
 	else
 		crypto_finalize_hash_request(jrp->engine, req, ecode);
@@ -632,10 +634,12 @@ static inline void ahash_done_switch(struct device *jrdev, u32 *desc, u32 err,
 	struct caam_hash_state *state = ahash_request_ctx(req);
 	int digestsize = crypto_ahash_digestsize(ahash);
 	int ecode = 0;
+	bool has_bklog;
 
 	dev_dbg(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
 
 	edesc = state->edesc;
+	has_bklog = edesc->bklog;
 	if (err)
 		ecode = caam_jr_strstatus(jrdev, err);
 
@@ -663,7 +667,7 @@ static inline void ahash_done_switch(struct device *jrdev, u32 *desc, u32 err,
 	 * If no backlog flag, the completion of the request is done
 	 * by CAAM, not crypto engine.
 	 */
-	if (!edesc->bklog)
+	if (!has_bklog)
 		req->base.complete(&req->base, ecode);
 	else
 		crypto_finalize_hash_request(jrp->engine, req, ecode);
diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
index 4fcae37a2e33..2e44d685618f 100644
--- a/drivers/crypto/caam/caampkc.c
+++ b/drivers/crypto/caam/caampkc.c
@@ -121,11 +121,13 @@ static void rsa_pub_done(struct device *dev, u32 *desc, u32 err, void *context)
 	struct caam_drv_private_jr *jrp = dev_get_drvdata(dev);
 	struct rsa_edesc *edesc;
 	int ecode = 0;
+	bool has_bklog;
 
 	if (err)
 		ecode = caam_jr_strstatus(dev, err);
 
 	edesc = req_ctx->edesc;
+	has_bklog = edesc->bklog;
 
 	rsa_pub_unmap(dev, edesc, req);
 	rsa_io_unmap(dev, edesc, req);
@@ -135,7 +137,7 @@ static void rsa_pub_done(struct device *dev, u32 *desc, u32 err, void *context)
 	 * If no backlog flag, the completion of the request is done
 	 * by CAAM, not crypto engine.
 	 */
-	if (!edesc->bklog)
+	if (!has_bklog)
 		akcipher_request_complete(req, ecode);
 	else
 		crypto_finalize_akcipher_request(jrp->engine, req, ecode);
@@ -152,11 +154,13 @@ static void rsa_priv_f_done(struct device *dev, u32 *desc, u32 err,
 	struct caam_rsa_req_ctx *req_ctx = akcipher_request_ctx(req);
 	struct rsa_edesc *edesc;
 	int ecode = 0;
+	bool has_bklog;
 
 	if (err)
 		ecode = caam_jr_strstatus(dev, err);
 
 	edesc = req_ctx->edesc;
+	has_bklog = edesc->bklog;
 
 	switch (key->priv_form) {
 	case FORM1:
@@ -176,7 +180,7 @@ static void rsa_priv_f_done(struct device *dev, u32 *desc, u32 err,
 	 * If no backlog flag, the completion of the request is done
 	 * by CAAM, not crypto engine.
 	 */
-	if (!edesc->bklog)
+	if (!has_bklog)
 		akcipher_request_complete(req, ecode);
 	else
 		crypto_finalize_akcipher_request(jrp->engine, req, ecode);
diff --git a/drivers/crypto/cavium/nitrox/nitrox_main.c b/drivers/crypto/cavium/nitrox/nitrox_main.c
index e91be9b8b083..788c6607078b 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_main.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_main.c
@@ -346,7 +346,7 @@ static void nitrox_pf_sw_cleanup(struct nitrox_device *ndev)
 }
 
 /**
- * nitrox_bist_check - Check NITORX BIST registers status
+ * nitrox_bist_check - Check NITROX BIST registers status
  * @ndev: NITROX device
  */
 static int nitrox_bist_check(struct nitrox_device *ndev)
diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig
index e0a8bd15aa74..32268e239bf1 100644
--- a/drivers/crypto/ccp/Kconfig
+++ b/drivers/crypto/ccp/Kconfig
@@ -10,10 +10,9 @@ config CRYPTO_DEV_CCP_DD
 config CRYPTO_DEV_SP_CCP
 	bool "Cryptographic Coprocessor device"
 	default y
-	depends on CRYPTO_DEV_CCP_DD
+	depends on CRYPTO_DEV_CCP_DD && DMADEVICES
 	select HW_RANDOM
 	select DMA_ENGINE
-	select DMADEVICES
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	help
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 474e6f1a6a84..b0cc2bd73af8 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -272,9 +272,6 @@ static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 {
 	struct ccp_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
 	struct crypto_shash *shash = ctx->u.sha.hmac_tfm;
-
-	SHASH_DESC_ON_STACK(sdesc, shash);
-
 	unsigned int block_size = crypto_shash_blocksize(shash);
 	unsigned int digest_size = crypto_shash_digestsize(shash);
 	int i, ret;
@@ -289,10 +286,8 @@ static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 
 	if (key_len > block_size) {
 		/* Must hash the input key */
-		sdesc->tfm = shash;
-
-		ret = crypto_shash_digest(sdesc, key, key_len,
-					  ctx->u.sha.key);
+		ret = crypto_shash_tfm_digest(shash, key, key_len,
+					      ctx->u.sha.key);
 		if (ret)
 			return -EINVAL;
 
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index 896f190b9a50..439cd737076e 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -20,6 +20,7 @@
 #include <linux/hw_random.h>
 #include <linux/ccp.h>
 #include <linux/firmware.h>
+#include <linux/gfp.h>
 
 #include <asm/smp.h>
 
@@ -44,6 +45,14 @@ MODULE_PARM_DESC(psp_probe_timeout, " default timeout value, in seconds, during
 static bool psp_dead;
 static int psp_timeout;
 
+/* Trusted Memory Region (TMR):
+ *   The TMR is a 1MB area that must be 1MB aligned.  Use the page allocator
+ *   to allocate the memory, which will return aligned memory for the specified
+ *   allocation order.
+ */
+#define SEV_ES_TMR_SIZE		(1024 * 1024)
+static void *sev_es_tmr;
+
 static inline bool sev_version_greater_or_equal(u8 maj, u8 min)
 {
 	struct sev_device *sev = psp_master->sev_data;
@@ -214,6 +223,20 @@ static int __sev_platform_init_locked(int *error)
 	if (sev->state == SEV_STATE_INIT)
 		return 0;
 
+	if (sev_es_tmr) {
+		u64 tmr_pa;
+
+		/*
+		 * Do not include the encryption mask on the physical
+		 * address of the TMR (firmware should clear it anyway).
+		 */
+		tmr_pa = __pa(sev_es_tmr);
+
+		sev->init_cmd_buf.flags |= SEV_INIT_FLAGS_SEV_ES;
+		sev->init_cmd_buf.tmr_address = tmr_pa;
+		sev->init_cmd_buf.tmr_len = SEV_ES_TMR_SIZE;
+	}
+
 	rc = __sev_do_cmd_locked(SEV_CMD_INIT, &sev->init_cmd_buf, error);
 	if (rc)
 		return rc;
@@ -1012,6 +1035,7 @@ EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user);
 void sev_pci_init(void)
 {
 	struct sev_device *sev = psp_master->sev_data;
+	struct page *tmr_page;
 	int error, rc;
 
 	if (!sev)
@@ -1041,6 +1065,16 @@ void sev_pci_init(void)
 	    sev_update_firmware(sev->dev) == 0)
 		sev_get_api_version();
 
+	/* Obtain the TMR memory area for SEV-ES use */
+	tmr_page = alloc_pages(GFP_KERNEL, get_order(SEV_ES_TMR_SIZE));
+	if (tmr_page) {
+		sev_es_tmr = page_address(tmr_page);
+	} else {
+		sev_es_tmr = NULL;
+		dev_warn(sev->dev,
+			 "SEV: TMR allocation failed, SEV-ES support unavailable\n");
+	}
+
 	/* Initialize the platform */
 	rc = sev_platform_init(&error);
 	if (rc && (error == SEV_RET_SECURE_DATA_INVALID)) {
@@ -1075,4 +1109,13 @@ void sev_pci_exit(void)
 		return;
 
 	sev_platform_shutdown(NULL);
+
+	if (sev_es_tmr) {
+		/* The TMR area was encrypted, flush it from the cache */
+		wbinvd_on_all_cpus();
+
+		free_pages((unsigned long)sev_es_tmr,
+			   get_order(SEV_ES_TMR_SIZE));
+		sev_es_tmr = NULL;
+	}
 }
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index a84335328f37..872ea3ff1c6b 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -427,12 +427,9 @@ static int cc_cipher_setkey(struct crypto_skcipher *sktfm, const u8 *key,
 		int key_len = keylen >> 1;
 		int err;
 
-		SHASH_DESC_ON_STACK(desc, ctx_p->shash_tfm);
-
-		desc->tfm = ctx_p->shash_tfm;
-
-		err = crypto_shash_digest(desc, ctx_p->user.key, key_len,
-					  ctx_p->user.key + key_len);
+		err = crypto_shash_tfm_digest(ctx_p->shash_tfm,
+					      ctx_p->user.key, key_len,
+					      ctx_p->user.key + key_len);
 		if (err) {
 			dev_err(dev, "Failed to hash ESSIV key.\n");
 			return err;
diff --git a/drivers/crypto/ccree/cc_debugfs.c b/drivers/crypto/ccree/cc_debugfs.c
index c454afce7781..7083767602fc 100644
--- a/drivers/crypto/ccree/cc_debugfs.c
+++ b/drivers/crypto/ccree/cc_debugfs.c
@@ -26,7 +26,7 @@ static struct debugfs_reg32 ver_sig_regs[] = {
 	{ .name = "VERSION" }, /* Must be 1st */
 };
 
-static struct debugfs_reg32 pid_cid_regs[] = {
+static const struct debugfs_reg32 pid_cid_regs[] = {
 	CC_DEBUG_REG(PERIPHERAL_ID_0),
 	CC_DEBUG_REG(PERIPHERAL_ID_1),
 	CC_DEBUG_REG(PERIPHERAL_ID_2),
@@ -38,7 +38,7 @@ static struct debugfs_reg32 pid_cid_regs[] = {
 	CC_DEBUG_REG(COMPONENT_ID_3),
 };
 
-static struct debugfs_reg32 debug_regs[] = {
+static const struct debugfs_reg32 debug_regs[] = {
 	CC_DEBUG_REG(HOST_IRR),
 	CC_DEBUG_REG(HOST_POWER_DOWN_EN),
 	CC_DEBUG_REG(AXIM_MON_ERR),
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index c29b80dd30d8..caf1136e7ef9 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -44,7 +44,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/crypto.h>
-#include <linux/cryptohash.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/highmem.h>
@@ -1757,7 +1756,7 @@ static int chcr_ahash_final(struct ahash_request *req)
 	struct uld_ctx *u_ctx = ULD_CTX(h_ctx(rtfm));
 	struct chcr_context *ctx = h_ctx(rtfm);
 	u8 bs = crypto_tfm_alg_blocksize(crypto_ahash_tfm(rtfm));
-	int error = -EINVAL;
+	int error;
 	unsigned int cpu;
 
 	cpu = get_cpu();
diff --git a/drivers/crypto/chelsio/chcr_ipsec.c b/drivers/crypto/chelsio/chcr_ipsec.c
index 9fd3b9d1ec2f..25bf6d963066 100644
--- a/drivers/crypto/chelsio/chcr_ipsec.c
+++ b/drivers/crypto/chelsio/chcr_ipsec.c
@@ -40,7 +40,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/crypto.h>
-#include <linux/cryptohash.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/highmem.h>
diff --git a/drivers/crypto/chelsio/chcr_ktls.c b/drivers/crypto/chelsio/chcr_ktls.c
index cd1769ecdc1c..43d9e2420110 100644
--- a/drivers/crypto/chelsio/chcr_ktls.c
+++ b/drivers/crypto/chelsio/chcr_ktls.c
@@ -120,12 +120,10 @@ out:
 static int chcr_ktls_update_connection_state(struct chcr_ktls_info *tx_info,
 					     int new_state)
 {
-	unsigned long flags;
-
 	/* This function can be called from both rx (interrupt context) and tx
 	 * queue contexts.
 	 */
-	spin_lock_irqsave(&tx_info->lock, flags);
+	spin_lock_bh(&tx_info->lock);
 	switch (tx_info->connection_state) {
 	case KTLS_CONN_CLOSED:
 		tx_info->connection_state = new_state;
@@ -169,7 +167,7 @@ static int chcr_ktls_update_connection_state(struct chcr_ktls_info *tx_info,
 		pr_err("unknown KTLS connection state\n");
 		break;
 	}
-	spin_unlock_irqrestore(&tx_info->lock, flags);
+	spin_unlock_bh(&tx_info->lock);
 
 	return tx_info->connection_state;
 }
@@ -675,41 +673,14 @@ int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input)
 	return 0;
 }
 
-/*
- * chcr_write_cpl_set_tcb_ulp: update tcb values.
- * TCB is responsible to create tcp headers, so all the related values
- * should be correctly updated.
- * @tx_info - driver specific tls info.
- * @q - tx queue on which packet is going out.
- * @tid - TCB identifier.
- * @pos - current index where should we start writing.
- * @word - TCB word.
- * @mask - TCB word related mask.
- * @val - TCB word related value.
- * @reply - set 1 if looking for TP response.
- * return - next position to write.
- */
-static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info,
-					struct sge_eth_txq *q, u32 tid,
-					void *pos, u16 word, u64 mask,
+static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info,
+					u32 tid, void *pos, u16 word, u64 mask,
 					u64 val, u32 reply)
 {
 	struct cpl_set_tcb_field_core *cpl;
 	struct ulptx_idata *idata;
 	struct ulp_txpkt *txpkt;
-	void *save_pos = NULL;
-	u8 buf[48] = {0};
-	int left;
 
-	left = (void *)q->q.stat - pos;
-	if (unlikely(left < CHCR_SET_TCB_FIELD_LEN)) {
-		if (!left) {
-			pos = q->q.desc;
-		} else {
-			save_pos = pos;
-			pos = buf;
-		}
-	}
 	/* ULP_TXPKT */
 	txpkt = pos;
 	txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0));
@@ -734,18 +705,54 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info,
 	idata = (struct ulptx_idata *)(cpl + 1);
 	idata->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_NOOP));
 	idata->len = htonl(0);
+	pos = idata + 1;
 
-	if (save_pos) {
-		pos = chcr_copy_to_txd(buf, &q->q, save_pos,
-				       CHCR_SET_TCB_FIELD_LEN);
-	} else {
-		/* check again if we are at the end of the queue */
-		if (left == CHCR_SET_TCB_FIELD_LEN)
+	return pos;
+}
+
+
+/*
+ * chcr_write_cpl_set_tcb_ulp: update tcb values.
+ * TCB is responsible to create tcp headers, so all the related values
+ * should be correctly updated.
+ * @tx_info - driver specific tls info.
+ * @q - tx queue on which packet is going out.
+ * @tid - TCB identifier.
+ * @pos - current index where should we start writing.
+ * @word - TCB word.
+ * @mask - TCB word related mask.
+ * @val - TCB word related value.
+ * @reply - set 1 if looking for TP response.
+ * return - next position to write.
+ */
+static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info,
+					struct sge_eth_txq *q, u32 tid,
+					void *pos, u16 word, u64 mask,
+					u64 val, u32 reply)
+{
+	int left = (void *)q->q.stat - pos;
+
+	if (unlikely(left < CHCR_SET_TCB_FIELD_LEN)) {
+		if (!left) {
 			pos = q->q.desc;
-		else
-			pos = idata + 1;
+		} else {
+			u8 buf[48] = {0};
+
+			__chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word,
+						     mask, val, reply);
+
+			return chcr_copy_to_txd(buf, &q->q, pos,
+						CHCR_SET_TCB_FIELD_LEN);
+		}
 	}
 
+	pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word,
+					   mask, val, reply);
+
+	/* check again if we are at the end of the queue */
+	if (left == CHCR_SET_TCB_FIELD_LEN)
+		pos = q->q.desc;
+
 	return pos;
 }
 
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index dccef3a2908b..e1401d9cc756 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -682,7 +682,7 @@ int chtls_push_frames(struct chtls_sock *csk, int comp)
 				make_tx_data_wr(sk, skb, immdlen, len,
 						credits_needed, completion);
 			tp->snd_nxt += len;
-			tp->lsndtime = tcp_time_stamp(tp);
+			tp->lsndtime = tcp_jiffies32;
 			if (completion)
 				ULP_SKB_CB(skb)->flags &= ~ULPCB_FLAG_NEED_HDR;
 		} else {
diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig
index f09c6cf7823e..9c3b3ca815e6 100644
--- a/drivers/crypto/hisilicon/Kconfig
+++ b/drivers/crypto/hisilicon/Kconfig
@@ -29,6 +29,7 @@ config CRYPTO_DEV_HISI_SEC2
 	depends on PCI && PCI_MSI
 	depends on UACCE || UACCE=n
 	depends on ARM64 || (COMPILE_TEST && 64BIT)
+	depends on ACPI
 	help
 	  Support for HiSilicon SEC Engine of version 2 in crypto subsystem.
 	  It provides AES, SM4, and 3DES algorithms with ECB
@@ -42,6 +43,7 @@ config CRYPTO_DEV_HISI_QM
 	depends on ARM64 || COMPILE_TEST
 	depends on PCI && PCI_MSI
 	depends on UACCE || UACCE=n
+	depends on ACPI
 	help
 	  HiSilicon accelerator engines use a common queue management
 	  interface. Specific engine driver may use this module.
@@ -52,6 +54,7 @@ config CRYPTO_DEV_HISI_ZIP
 	depends on ARM64 || (COMPILE_TEST && 64BIT)
 	depends on !CPU_BIG_ENDIAN || COMPILE_TEST
 	depends on UACCE || UACCE=n
+	depends on ACPI
 	select CRYPTO_DEV_HISI_QM
 	help
 	  Support for HiSilicon ZIP Driver
@@ -61,6 +64,7 @@ config CRYPTO_DEV_HISI_HPRE
 	depends on PCI && PCI_MSI
 	depends on UACCE || UACCE=n
 	depends on ARM64 || (COMPILE_TEST && 64BIT)
+	depends on ACPI
 	select CRYPTO_DEV_HISI_QM
 	select CRYPTO_DH
 	select CRYPTO_RSA
diff --git a/drivers/crypto/hisilicon/hpre/hpre.h b/drivers/crypto/hisilicon/hpre/hpre.h
index 03d512ec6336..ed730d173e95 100644
--- a/drivers/crypto/hisilicon/hpre/hpre.h
+++ b/drivers/crypto/hisilicon/hpre/hpre.h
@@ -25,6 +25,17 @@ enum hpre_ctrl_dbgfs_file {
 	HPRE_DEBUG_FILE_NUM,
 };
 
+enum hpre_dfx_dbgfs_file {
+	HPRE_SEND_CNT,
+	HPRE_RECV_CNT,
+	HPRE_SEND_FAIL_CNT,
+	HPRE_SEND_BUSY_CNT,
+	HPRE_OVER_THRHLD_CNT,
+	HPRE_OVERTIME_THRHLD,
+	HPRE_INVALID_REQ_CNT,
+	HPRE_DFX_FILE_NUM
+};
+
 #define HPRE_DEBUGFS_FILE_NUM    (HPRE_DEBUG_FILE_NUM + HPRE_CLUSTERS_NUM - 1)
 
 struct hpre_debugfs_file {
@@ -34,6 +45,11 @@ struct hpre_debugfs_file {
 	struct hpre_debug *debug;
 };
 
+struct hpre_dfx {
+	atomic64_t value;
+	enum hpre_dfx_dbgfs_file type;
+};
+
 /*
  * One HPRE controller has one PF and multiple VFs, some global configurations
  * which PF has need this structure.
@@ -41,13 +57,13 @@ struct hpre_debugfs_file {
  */
 struct hpre_debug {
 	struct dentry *debug_root;
+	struct hpre_dfx dfx[HPRE_DFX_FILE_NUM];
 	struct hpre_debugfs_file files[HPRE_DEBUGFS_FILE_NUM];
 };
 
 struct hpre {
 	struct hisi_qm qm;
 	struct hpre_debug debug;
-	u32 num_vfs;
 	unsigned long status;
 };
 
diff --git a/drivers/crypto/hisilicon/hpre/hpre_crypto.c b/drivers/crypto/hisilicon/hpre/hpre_crypto.c
index 65425250b2e9..7b5cb27d473d 100644
--- a/drivers/crypto/hisilicon/hpre/hpre_crypto.c
+++ b/drivers/crypto/hisilicon/hpre/hpre_crypto.c
@@ -10,6 +10,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/fips.h>
 #include <linux/module.h>
+#include <linux/time.h>
 #include "hpre.h"
 
 struct hpre_ctx;
@@ -32,6 +33,9 @@ struct hpre_ctx;
 #define HPRE_SQE_DONE_SHIFT	30
 #define HPRE_DH_MAX_P_SZ	512
 
+#define HPRE_DFX_SEC_TO_US	1000000
+#define HPRE_DFX_US_TO_NS	1000
+
 typedef void (*hpre_cb)(struct hpre_ctx *ctx, void *sqe);
 
 struct hpre_rsa_ctx {
@@ -68,6 +72,7 @@ struct hpre_dh_ctx {
 struct hpre_ctx {
 	struct hisi_qp *qp;
 	struct hpre_asym_request **req_list;
+	struct hpre *hpre;
 	spinlock_t req_lock;
 	unsigned int key_sz;
 	bool crt_g2_mode;
@@ -90,6 +95,7 @@ struct hpre_asym_request {
 	int err;
 	int req_id;
 	hpre_cb cb;
+	struct timespec64 req_time;
 };
 
 static DEFINE_MUTEX(hpre_alg_lock);
@@ -119,6 +125,7 @@ static void hpre_free_req_id(struct hpre_ctx *ctx, int req_id)
 static int hpre_add_req_to_ctx(struct hpre_asym_request *hpre_req)
 {
 	struct hpre_ctx *ctx;
+	struct hpre_dfx *dfx;
 	int id;
 
 	ctx = hpre_req->ctx;
@@ -129,6 +136,10 @@ static int hpre_add_req_to_ctx(struct hpre_asym_request *hpre_req)
 	ctx->req_list[id] = hpre_req;
 	hpre_req->req_id = id;
 
+	dfx = ctx->hpre->debug.dfx;
+	if (atomic64_read(&dfx[HPRE_OVERTIME_THRHLD].value))
+		ktime_get_ts64(&hpre_req->req_time);
+
 	return id;
 }
 
@@ -309,12 +320,16 @@ static int hpre_alg_res_post_hf(struct hpre_ctx *ctx, struct hpre_sqe *sqe,
 
 static int hpre_ctx_set(struct hpre_ctx *ctx, struct hisi_qp *qp, int qlen)
 {
+	struct hpre *hpre;
+
 	if (!ctx || !qp || qlen < 0)
 		return -EINVAL;
 
 	spin_lock_init(&ctx->req_lock);
 	ctx->qp = qp;
 
+	hpre = container_of(ctx->qp->qm, struct hpre, qm);
+	ctx->hpre = hpre;
 	ctx->req_list = kcalloc(qlen, sizeof(void *), GFP_KERNEL);
 	if (!ctx->req_list)
 		return -ENOMEM;
@@ -337,38 +352,80 @@ static void hpre_ctx_clear(struct hpre_ctx *ctx, bool is_clear_all)
 	ctx->key_sz = 0;
 }
 
+static bool hpre_is_bd_timeout(struct hpre_asym_request *req,
+			       u64 overtime_thrhld)
+{
+	struct timespec64 reply_time;
+	u64 time_use_us;
+
+	ktime_get_ts64(&reply_time);
+	time_use_us = (reply_time.tv_sec - req->req_time.tv_sec) *
+		HPRE_DFX_SEC_TO_US +
+		(reply_time.tv_nsec - req->req_time.tv_nsec) /
+		HPRE_DFX_US_TO_NS;
+
+	if (time_use_us <= overtime_thrhld)
+		return false;
+
+	return true;
+}
+
 static void hpre_dh_cb(struct hpre_ctx *ctx, void *resp)
 {
+	struct hpre_dfx *dfx = ctx->hpre->debug.dfx;
 	struct hpre_asym_request *req;
 	struct kpp_request *areq;
+	u64 overtime_thrhld;
 	int ret;
 
 	ret = hpre_alg_res_post_hf(ctx, resp, (void **)&req);
 	areq = req->areq.dh;
 	areq->dst_len = ctx->key_sz;
+
+	overtime_thrhld = atomic64_read(&dfx[HPRE_OVERTIME_THRHLD].value);
+	if (overtime_thrhld && hpre_is_bd_timeout(req, overtime_thrhld))
+		atomic64_inc(&dfx[HPRE_OVER_THRHLD_CNT].value);
+
 	hpre_hw_data_clr_all(ctx, req, areq->dst, areq->src);
 	kpp_request_complete(areq, ret);
+	atomic64_inc(&dfx[HPRE_RECV_CNT].value);
 }
 
 static void hpre_rsa_cb(struct hpre_ctx *ctx, void *resp)
 {
+	struct hpre_dfx *dfx = ctx->hpre->debug.dfx;
 	struct hpre_asym_request *req;
 	struct akcipher_request *areq;
+	u64 overtime_thrhld;
 	int ret;
 
 	ret = hpre_alg_res_post_hf(ctx, resp, (void **)&req);
+
+	overtime_thrhld = atomic64_read(&dfx[HPRE_OVERTIME_THRHLD].value);
+	if (overtime_thrhld && hpre_is_bd_timeout(req, overtime_thrhld))
+		atomic64_inc(&dfx[HPRE_OVER_THRHLD_CNT].value);
+
 	areq = req->areq.rsa;
 	areq->dst_len = ctx->key_sz;
 	hpre_hw_data_clr_all(ctx, req, areq->dst, areq->src);
 	akcipher_request_complete(areq, ret);
+	atomic64_inc(&dfx[HPRE_RECV_CNT].value);
 }
 
 static void hpre_alg_cb(struct hisi_qp *qp, void *resp)
 {
 	struct hpre_ctx *ctx = qp->qp_ctx;
+	struct hpre_dfx *dfx = ctx->hpre->debug.dfx;
 	struct hpre_sqe *sqe = resp;
+	struct hpre_asym_request *req = ctx->req_list[le16_to_cpu(sqe->tag)];
 
-	ctx->req_list[le16_to_cpu(sqe->tag)]->cb(ctx, resp);
+
+	if (unlikely(!req)) {
+		atomic64_inc(&dfx[HPRE_INVALID_REQ_CNT].value);
+		return;
+	}
+
+	req->cb(ctx, resp);
 }
 
 static int hpre_ctx_init(struct hpre_ctx *ctx)
@@ -436,6 +493,29 @@ static int hpre_msg_request_set(struct hpre_ctx *ctx, void *req, bool is_rsa)
 	return 0;
 }
 
+static int hpre_send(struct hpre_ctx *ctx, struct hpre_sqe *msg)
+{
+	struct hpre_dfx *dfx = ctx->hpre->debug.dfx;
+	int ctr = 0;
+	int ret;
+
+	do {
+		atomic64_inc(&dfx[HPRE_SEND_CNT].value);
+		ret = hisi_qp_send(ctx->qp, msg);
+		if (ret != -EBUSY)
+			break;
+		atomic64_inc(&dfx[HPRE_SEND_BUSY_CNT].value);
+	} while (ctr++ < HPRE_TRY_SEND_TIMES);
+
+	if (likely(!ret))
+		return ret;
+
+	if (ret != -EBUSY)
+		atomic64_inc(&dfx[HPRE_SEND_FAIL_CNT].value);
+
+	return ret;
+}
+
 #ifdef CONFIG_CRYPTO_DH
 static int hpre_dh_compute_value(struct kpp_request *req)
 {
@@ -444,7 +524,6 @@ static int hpre_dh_compute_value(struct kpp_request *req)
 	void *tmp = kpp_request_ctx(req);
 	struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
 	struct hpre_sqe *msg = &hpre_req->req;
-	int ctr = 0;
 	int ret;
 
 	ret = hpre_msg_request_set(ctx, req, false);
@@ -465,11 +544,9 @@ static int hpre_dh_compute_value(struct kpp_request *req)
 		msg->dw0 = cpu_to_le32(le32_to_cpu(msg->dw0) | HPRE_ALG_DH_G2);
 	else
 		msg->dw0 = cpu_to_le32(le32_to_cpu(msg->dw0) | HPRE_ALG_DH);
-	do {
-		ret = hisi_qp_send(ctx->qp, msg);
-	} while (ret == -EBUSY && ctr++ < HPRE_TRY_SEND_TIMES);
 
 	/* success */
+	ret = hpre_send(ctx, msg);
 	if (likely(!ret))
 		return -EINPROGRESS;
 
@@ -647,7 +724,6 @@ static int hpre_rsa_enc(struct akcipher_request *req)
 	void *tmp = akcipher_request_ctx(req);
 	struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
 	struct hpre_sqe *msg = &hpre_req->req;
-	int ctr = 0;
 	int ret;
 
 	/* For 512 and 1536 bits key size, use soft tfm instead */
@@ -677,11 +753,8 @@ static int hpre_rsa_enc(struct akcipher_request *req)
 	if (unlikely(ret))
 		goto clear_all;
 
-	do {
-		ret = hisi_qp_send(ctx->qp, msg);
-	} while (ret == -EBUSY && ctr++ < HPRE_TRY_SEND_TIMES);
-
 	/* success */
+	ret = hpre_send(ctx, msg);
 	if (likely(!ret))
 		return -EINPROGRESS;
 
@@ -699,7 +772,6 @@ static int hpre_rsa_dec(struct akcipher_request *req)
 	void *tmp = akcipher_request_ctx(req);
 	struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
 	struct hpre_sqe *msg = &hpre_req->req;
-	int ctr = 0;
 	int ret;
 
 	/* For 512 and 1536 bits key size, use soft tfm instead */
@@ -736,11 +808,8 @@ static int hpre_rsa_dec(struct akcipher_request *req)
 	if (unlikely(ret))
 		goto clear_all;
 
-	do {
-		ret = hisi_qp_send(ctx->qp, msg);
-	} while (ret == -EBUSY && ctr++ < HPRE_TRY_SEND_TIMES);
-
 	/* success */
+	ret = hpre_send(ctx, msg);
 	if (likely(!ret))
 		return -EINPROGRESS;
 
diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c
index 88be53bf4a38..a3ee127a70e3 100644
--- a/drivers/crypto/hisilicon/hpre/hpre_main.c
+++ b/drivers/crypto/hisilicon/hpre/hpre_main.c
@@ -59,10 +59,6 @@
 #define HPRE_HAC_ECC2_CNT		0x301a08
 #define HPRE_HAC_INT_STATUS		0x301800
 #define HPRE_HAC_SOURCE_INT		0x301600
-#define MASTER_GLOBAL_CTRL_SHUTDOWN	1
-#define MASTER_TRANS_RETURN_RW		3
-#define HPRE_MASTER_TRANS_RETURN	0x300150
-#define HPRE_MASTER_GLOBAL_CTRL		0x300000
 #define HPRE_CLSTR_ADDR_INTRVL		0x1000
 #define HPRE_CLUSTER_INQURY		0x100
 #define HPRE_CLSTR_ADDR_INQRY_RSLT	0x104
@@ -80,7 +76,16 @@
 #define HPRE_BD_USR_MASK		0x3
 #define HPRE_CLUSTER_CORE_MASK		0xf
 
+#define HPRE_AM_OOO_SHUTDOWN_ENB	0x301044
+#define HPRE_AM_OOO_SHUTDOWN_ENABLE	BIT(0)
+#define HPRE_WR_MSI_PORT		BIT(2)
+
+#define HPRE_CORE_ECC_2BIT_ERR		BIT(1)
+#define HPRE_OOO_ECC_2BIT_ERR		BIT(5)
+
 #define HPRE_VIA_MSI_DSM		1
+#define HPRE_SQE_MASK_OFFSET		8
+#define HPRE_SQE_MASK_LEN		24
 
 static struct hisi_qm_list hpre_devices;
 static const char hpre_name[] = "hisi_hpre";
@@ -131,7 +136,7 @@ static const u64 hpre_cluster_offsets[] = {
 		HPRE_CLSTR_BASE + HPRE_CLUSTER3 * HPRE_CLSTR_ADDR_INTRVL,
 };
 
-static struct debugfs_reg32 hpre_cluster_dfx_regs[] = {
+static const struct debugfs_reg32 hpre_cluster_dfx_regs[] = {
 	{"CORES_EN_STATUS          ",  HPRE_CORE_EN_OFFSET},
 	{"CORES_INI_CFG              ",  HPRE_CORE_INI_CFG_OFFSET},
 	{"CORES_INI_STATUS         ",  HPRE_CORE_INI_STATUS_OFFSET},
@@ -139,7 +144,7 @@ static struct debugfs_reg32 hpre_cluster_dfx_regs[] = {
 	{"CORES_IS_SCHD               ",  HPRE_CORE_IS_SCHD_OFFSET},
 };
 
-static struct debugfs_reg32 hpre_com_dfx_regs[] = {
+static const struct debugfs_reg32 hpre_com_dfx_regs[] = {
 	{"READ_CLR_EN          ",  HPRE_CTRL_CNT_CLR_CE},
 	{"AXQOS                   ",  HPRE_VFG_AXQOS},
 	{"AWUSR_CFG              ",  HPRE_AWUSR_FP_CFG},
@@ -156,44 +161,38 @@ static struct debugfs_reg32 hpre_com_dfx_regs[] = {
 	{"INT_STATUS               ",  HPRE_INT_STATUS},
 };
 
-static int hpre_pf_q_num_set(const char *val, const struct kernel_param *kp)
-{
-	struct pci_dev *pdev;
-	u32 n, q_num;
-	u8 rev_id;
-	int ret;
-
-	if (!val)
-		return -EINVAL;
-
-	pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, HPRE_PCI_DEVICE_ID, NULL);
-	if (!pdev) {
-		q_num = HPRE_QUEUE_NUM_V2;
-		pr_info("No device found currently, suppose queue number is %d\n",
-			q_num);
-	} else {
-		rev_id = pdev->revision;
-		if (rev_id != QM_HW_V2)
-			return -EINVAL;
-
-		q_num = HPRE_QUEUE_NUM_V2;
-	}
-
-	ret = kstrtou32(val, 10, &n);
-	if (ret != 0 || n == 0 || n > q_num)
-		return -EINVAL;
+static const char *hpre_dfx_files[HPRE_DFX_FILE_NUM] = {
+	"send_cnt",
+	"recv_cnt",
+	"send_fail_cnt",
+	"send_busy_cnt",
+	"over_thrhld_cnt",
+	"overtime_thrhld",
+	"invalid_req_cnt"
+};
 
-	return param_set_int(val, kp);
+static int pf_q_num_set(const char *val, const struct kernel_param *kp)
+{
+	return q_num_set(val, kp, HPRE_PCI_DEVICE_ID);
 }
 
 static const struct kernel_param_ops hpre_pf_q_num_ops = {
-	.set = hpre_pf_q_num_set,
+	.set = pf_q_num_set,
 	.get = param_get_int,
 };
 
-static u32 hpre_pf_q_num = HPRE_PF_DEF_Q_NUM;
-module_param_cb(hpre_pf_q_num, &hpre_pf_q_num_ops, &hpre_pf_q_num, 0444);
-MODULE_PARM_DESC(hpre_pf_q_num, "Number of queues in PF of CS(1-1024)");
+static u32 pf_q_num = HPRE_PF_DEF_Q_NUM;
+module_param_cb(pf_q_num, &hpre_pf_q_num_ops, &pf_q_num, 0444);
+MODULE_PARM_DESC(pf_q_num, "Number of queues in PF of CS(1-1024)");
+
+static const struct kernel_param_ops vfs_num_ops = {
+	.set = vfs_num_set,
+	.get = param_get_int,
+};
+
+static u32 vfs_num;
+module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444);
+MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)");
 
 struct hisi_qp *hpre_create_qp(void)
 {
@@ -232,9 +231,8 @@ static int hpre_cfg_by_dsm(struct hisi_qm *qm)
 	return 0;
 }
 
-static int hpre_set_user_domain_and_cache(struct hpre *hpre)
+static int hpre_set_user_domain_and_cache(struct hisi_qm *qm)
 {
-	struct hisi_qm *qm = &hpre->qm;
 	struct device *dev = &qm->pdev->dev;
 	unsigned long offset;
 	int ret, i;
@@ -324,17 +322,34 @@ static void hpre_cnt_regs_clear(struct hisi_qm *qm)
 
 static void hpre_hw_error_disable(struct hisi_qm *qm)
 {
+	u32 val;
+
 	/* disable hpre hw error interrupts */
 	writel(HPRE_CORE_INT_DISABLE, qm->io_base + HPRE_INT_MASK);
+
+	/* disable HPRE block master OOO when m-bit error occur */
+	val = readl(qm->io_base + HPRE_AM_OOO_SHUTDOWN_ENB);
+	val &= ~HPRE_AM_OOO_SHUTDOWN_ENABLE;
+	writel(val, qm->io_base + HPRE_AM_OOO_SHUTDOWN_ENB);
 }
 
 static void hpre_hw_error_enable(struct hisi_qm *qm)
 {
+	u32 val;
+
+	/* clear HPRE hw error source if having */
+	writel(HPRE_CORE_INT_DISABLE, qm->io_base + HPRE_HAC_SOURCE_INT);
+
 	/* enable hpre hw error interrupts */
 	writel(HPRE_CORE_INT_ENABLE, qm->io_base + HPRE_INT_MASK);
 	writel(HPRE_HAC_RAS_CE_ENABLE, qm->io_base + HPRE_RAS_CE_ENB);
 	writel(HPRE_HAC_RAS_NFE_ENABLE, qm->io_base + HPRE_RAS_NFE_ENB);
 	writel(HPRE_HAC_RAS_FE_ENABLE, qm->io_base + HPRE_RAS_FE_ENB);
+
+	/* enable HPRE block master OOO when m-bit error occur */
+	val = readl(qm->io_base + HPRE_AM_OOO_SHUTDOWN_ENB);
+	val |= HPRE_AM_OOO_SHUTDOWN_ENABLE;
+	writel(val, qm->io_base + HPRE_AM_OOO_SHUTDOWN_ENB);
 }
 
 static inline struct hisi_qm *hpre_file_to_qm(struct hpre_debugfs_file *file)
@@ -354,9 +369,7 @@ static u32 hpre_current_qm_read(struct hpre_debugfs_file *file)
 static int hpre_current_qm_write(struct hpre_debugfs_file *file, u32 val)
 {
 	struct hisi_qm *qm = hpre_file_to_qm(file);
-	struct hpre_debug *debug = file->debug;
-	struct hpre *hpre = container_of(debug, struct hpre, debug);
-	u32 num_vfs = hpre->num_vfs;
+	u32 num_vfs = qm->vfs_num;
 	u32 vfq_num, tmp;
 
 
@@ -523,6 +536,33 @@ static const struct file_operations hpre_ctrl_debug_fops = {
 	.write = hpre_ctrl_debug_write,
 };
 
+static int hpre_debugfs_atomic64_get(void *data, u64 *val)
+{
+	struct hpre_dfx *dfx_item = data;
+
+	*val = atomic64_read(&dfx_item->value);
+
+	return 0;
+}
+
+static int hpre_debugfs_atomic64_set(void *data, u64 val)
+{
+	struct hpre_dfx *dfx_item = data;
+	struct hpre_dfx *hpre_dfx = dfx_item - HPRE_OVERTIME_THRHLD;
+
+	if (val)
+		return -EINVAL;
+
+	if (dfx_item->type == HPRE_OVERTIME_THRHLD)
+		atomic64_set(&hpre_dfx[HPRE_OVER_THRHLD_CNT].value, 0);
+	atomic64_set(&dfx_item->value, val);
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(hpre_atomic64_ops, hpre_debugfs_atomic64_get,
+			 hpre_debugfs_atomic64_set, "%llu\n");
+
 static int hpre_create_debugfs_file(struct hpre_debug *dbg, struct dentry *dir,
 				    enum hpre_ctrl_dbgfs_file type, int indx)
 {
@@ -620,6 +660,22 @@ static int hpre_ctrl_debug_init(struct hpre_debug *debug)
 	return hpre_cluster_debugfs_init(debug);
 }
 
+static void hpre_dfx_debug_init(struct hpre_debug *debug)
+{
+	struct hpre *hpre = container_of(debug, struct hpre, debug);
+	struct hpre_dfx *dfx = hpre->debug.dfx;
+	struct hisi_qm *qm = &hpre->qm;
+	struct dentry *parent;
+	int i;
+
+	parent = debugfs_create_dir("hpre_dfx", qm->debug.debug_root);
+	for (i = 0; i < HPRE_DFX_FILE_NUM; i++) {
+		dfx[i].type = i;
+		debugfs_create_file(hpre_dfx_files[i], 0644, parent, &dfx[i],
+				    &hpre_atomic64_ops);
+	}
+}
+
 static int hpre_debugfs_init(struct hpre *hpre)
 {
 	struct hisi_qm *qm = &hpre->qm;
@@ -629,6 +685,8 @@ static int hpre_debugfs_init(struct hpre *hpre)
 
 	dir = debugfs_create_dir(dev_name(dev), hpre_debugfs_root);
 	qm->debug.debug_root = dir;
+	qm->debug.sqe_mask_offset = HPRE_SQE_MASK_OFFSET;
+	qm->debug.sqe_mask_len = HPRE_SQE_MASK_LEN;
 
 	ret = hisi_qm_debug_init(qm);
 	if (ret)
@@ -640,6 +698,9 @@ static int hpre_debugfs_init(struct hpre *hpre)
 		if (ret)
 			goto failed_to_create;
 	}
+
+	hpre_dfx_debug_init(&hpre->debug);
+
 	return 0;
 
 failed_to_create:
@@ -654,32 +715,27 @@ static void hpre_debugfs_exit(struct hpre *hpre)
 	debugfs_remove_recursive(qm->debug.debug_root);
 }
 
-static int hpre_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev)
+static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 {
-	enum qm_hw_ver rev_id;
-
-	rev_id = hisi_qm_get_hw_version(pdev);
-	if (rev_id < 0)
-		return -ENODEV;
-
-	if (rev_id == QM_HW_V1) {
+	if (pdev->revision == QM_HW_V1) {
 		pci_warn(pdev, "HPRE version 1 is not supported!\n");
 		return -EINVAL;
 	}
 
 	qm->pdev = pdev;
-	qm->ver = rev_id;
+	qm->ver = pdev->revision;
 	qm->sqe_size = HPRE_SQE_SIZE;
 	qm->dev_name = hpre_name;
+
 	qm->fun_type = (pdev->device == HPRE_PCI_DEVICE_ID) ?
-		       QM_HW_PF : QM_HW_VF;
-	if (pdev->is_physfn) {
+			QM_HW_PF : QM_HW_VF;
+	if (qm->fun_type == QM_HW_PF) {
 		qm->qp_base = HPRE_PF_DEF_Q_BASE;
-		qm->qp_num = hpre_pf_q_num;
+		qm->qp_num = pf_q_num;
+		qm->qm_list = &hpre_devices;
 	}
-	qm->use_dma_api = true;
 
-	return 0;
+	return hisi_qm_init(qm);
 }
 
 static void hpre_log_hw_error(struct hisi_qm *qm, u32 err_sts)
@@ -693,8 +749,6 @@ static void hpre_log_hw_error(struct hisi_qm *qm, u32 err_sts)
 				 err->msg, err->int_msk);
 		err++;
 	}
-
-	writel(err_sts, qm->io_base + HPRE_HAC_SOURCE_INT);
 }
 
 static u32 hpre_get_hw_err_status(struct hisi_qm *qm)
@@ -702,16 +756,38 @@ static u32 hpre_get_hw_err_status(struct hisi_qm *qm)
 	return readl(qm->io_base + HPRE_HAC_INT_STATUS);
 }
 
+static void hpre_clear_hw_err_status(struct hisi_qm *qm, u32 err_sts)
+{
+	writel(err_sts, qm->io_base + HPRE_HAC_SOURCE_INT);
+}
+
+static void hpre_open_axi_master_ooo(struct hisi_qm *qm)
+{
+	u32 value;
+
+	value = readl(qm->io_base + HPRE_AM_OOO_SHUTDOWN_ENB);
+	writel(value & ~HPRE_AM_OOO_SHUTDOWN_ENABLE,
+	       HPRE_ADDR(qm, HPRE_AM_OOO_SHUTDOWN_ENB));
+	writel(value | HPRE_AM_OOO_SHUTDOWN_ENABLE,
+	       HPRE_ADDR(qm, HPRE_AM_OOO_SHUTDOWN_ENB));
+}
+
 static const struct hisi_qm_err_ini hpre_err_ini = {
+	.hw_init		= hpre_set_user_domain_and_cache,
 	.hw_err_enable		= hpre_hw_error_enable,
 	.hw_err_disable		= hpre_hw_error_disable,
 	.get_dev_hw_err_status	= hpre_get_hw_err_status,
+	.clear_dev_hw_err_status = hpre_clear_hw_err_status,
 	.log_dev_hw_err		= hpre_log_hw_error,
+	.open_axi_master_ooo	= hpre_open_axi_master_ooo,
 	.err_info		= {
 		.ce			= QM_BASE_CE,
 		.nfe			= QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT,
 		.fe			= 0,
-		.msi			= QM_DB_RANDOM_INVALID,
+		.ecc_2bits_mask		= HPRE_CORE_ECC_2BIT_ERR |
+					  HPRE_OOO_ECC_2BIT_ERR,
+		.msi_wr_port		= HPRE_WR_MSI_PORT,
+		.acpi_rst		= "HRST",
 	}
 };
 
@@ -722,7 +798,7 @@ static int hpre_pf_probe_init(struct hpre *hpre)
 
 	qm->ctrl_qp_num = HPRE_QUEUE_NUM_V2;
 
-	ret = hpre_set_user_domain_and_cache(hpre);
+	ret = hpre_set_user_domain_and_cache(qm);
 	if (ret)
 		return ret;
 
@@ -732,6 +808,20 @@ static int hpre_pf_probe_init(struct hpre *hpre)
 	return 0;
 }
 
+static int hpre_probe_init(struct hpre *hpre)
+{
+	struct hisi_qm *qm = &hpre->qm;
+	int ret;
+
+	if (qm->fun_type == QM_HW_PF) {
+		ret = hpre_pf_probe_init(hpre);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct hisi_qm *qm;
@@ -742,26 +832,17 @@ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!hpre)
 		return -ENOMEM;
 
-	pci_set_drvdata(pdev, hpre);
-
 	qm = &hpre->qm;
-	ret = hpre_qm_pre_init(qm, pdev);
-	if (ret)
-		return ret;
-
-	ret = hisi_qm_init(qm);
-	if (ret)
+	ret = hpre_qm_init(qm, pdev);
+	if (ret) {
+		pci_err(pdev, "Failed to init HPRE QM (%d)!\n", ret);
 		return ret;
+	}
 
-	if (pdev->is_physfn) {
-		ret = hpre_pf_probe_init(hpre);
-		if (ret)
-			goto err_with_qm_init;
-	} else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V2) {
-		/* v2 starts to support get vft by mailbox */
-		ret = hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num);
-		if (ret)
-			goto err_with_qm_init;
+	ret = hpre_probe_init(hpre);
+	if (ret) {
+		pci_err(pdev, "Failed to probe (%d)!\n", ret);
+		goto err_with_qm_init;
 	}
 
 	ret = hisi_qm_start(qm);
@@ -779,8 +860,18 @@ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		pci_err(pdev, "fail to register algs to crypto!\n");
 		goto err_with_qm_start;
 	}
+
+	if (qm->fun_type == QM_HW_PF && vfs_num) {
+		ret = hisi_qm_sriov_enable(pdev, vfs_num);
+		if (ret < 0)
+			goto err_with_crypto_register;
+	}
+
 	return 0;
 
+err_with_crypto_register:
+	hpre_algs_unregister();
+
 err_with_qm_start:
 	hisi_qm_del_from_list(qm, &hpre_devices);
 	hisi_qm_stop(qm);
@@ -794,107 +885,6 @@ err_with_qm_init:
 	return ret;
 }
 
-static int hpre_vf_q_assign(struct hpre *hpre, int num_vfs)
-{
-	struct hisi_qm *qm = &hpre->qm;
-	u32 qp_num = qm->qp_num;
-	int q_num, remain_q_num, i;
-	u32 q_base = qp_num;
-	int ret;
-
-	if (!num_vfs)
-		return -EINVAL;
-
-	remain_q_num = qm->ctrl_qp_num - qp_num;
-
-	/* If remaining queues are not enough, return error. */
-	if (remain_q_num < num_vfs)
-		return -EINVAL;
-
-	q_num = remain_q_num / num_vfs;
-	for (i = 1; i <= num_vfs; i++) {
-		if (i == num_vfs)
-			q_num += remain_q_num % num_vfs;
-		ret = hisi_qm_set_vft(qm, i, q_base, (u32)q_num);
-		if (ret)
-			return ret;
-		q_base += q_num;
-	}
-
-	return 0;
-}
-
-static int hpre_clear_vft_config(struct hpre *hpre)
-{
-	struct hisi_qm *qm = &hpre->qm;
-	u32 num_vfs = hpre->num_vfs;
-	int ret;
-	u32 i;
-
-	for (i = 1; i <= num_vfs; i++) {
-		ret = hisi_qm_set_vft(qm, i, 0, 0);
-		if (ret)
-			return ret;
-	}
-	hpre->num_vfs = 0;
-
-	return 0;
-}
-
-static int hpre_sriov_enable(struct pci_dev *pdev, int max_vfs)
-{
-	struct hpre *hpre = pci_get_drvdata(pdev);
-	int pre_existing_vfs, num_vfs, ret;
-
-	pre_existing_vfs = pci_num_vf(pdev);
-	if (pre_existing_vfs) {
-		pci_err(pdev,
-			"Can't enable VF. Please disable pre-enabled VFs!\n");
-		return 0;
-	}
-
-	num_vfs = min_t(int, max_vfs, HPRE_VF_NUM);
-	ret = hpre_vf_q_assign(hpre, num_vfs);
-	if (ret) {
-		pci_err(pdev, "Can't assign queues for VF!\n");
-		return ret;
-	}
-
-	hpre->num_vfs = num_vfs;
-
-	ret = pci_enable_sriov(pdev, num_vfs);
-	if (ret) {
-		pci_err(pdev, "Can't enable VF!\n");
-		hpre_clear_vft_config(hpre);
-		return ret;
-	}
-
-	return num_vfs;
-}
-
-static int hpre_sriov_disable(struct pci_dev *pdev)
-{
-	struct hpre *hpre = pci_get_drvdata(pdev);
-
-	if (pci_vfs_assigned(pdev)) {
-		pci_err(pdev, "Failed to disable VFs while VFs are assigned!\n");
-		return -EPERM;
-	}
-
-	/* remove in hpre_pci_driver will be called to free VF resources */
-	pci_disable_sriov(pdev);
-
-	return hpre_clear_vft_config(hpre);
-}
-
-static int hpre_sriov_configure(struct pci_dev *pdev, int num_vfs)
-{
-	if (num_vfs)
-		return hpre_sriov_enable(pdev, num_vfs);
-	else
-		return hpre_sriov_disable(pdev);
-}
-
 static void hpre_remove(struct pci_dev *pdev)
 {
 	struct hpre *hpre = pci_get_drvdata(pdev);
@@ -903,8 +893,8 @@ static void hpre_remove(struct pci_dev *pdev)
 
 	hpre_algs_unregister();
 	hisi_qm_del_from_list(qm, &hpre_devices);
-	if (qm->fun_type == QM_HW_PF && hpre->num_vfs != 0) {
-		ret = hpre_sriov_disable(pdev);
+	if (qm->fun_type == QM_HW_PF && qm->vfs_num) {
+		ret = hisi_qm_sriov_disable(pdev);
 		if (ret) {
 			pci_err(pdev, "Disable SRIOV fail!\n");
 			return;
@@ -924,6 +914,9 @@ static void hpre_remove(struct pci_dev *pdev)
 
 static const struct pci_error_handlers hpre_err_handler = {
 	.error_detected		= hisi_qm_dev_err_detected,
+	.slot_reset		= hisi_qm_dev_slot_reset,
+	.reset_prepare		= hisi_qm_reset_prepare,
+	.reset_done		= hisi_qm_reset_done,
 };
 
 static struct pci_driver hpre_pci_driver = {
@@ -931,7 +924,7 @@ static struct pci_driver hpre_pci_driver = {
 	.id_table		= hpre_dev_ids,
 	.probe			= hpre_probe,
 	.remove			= hpre_remove,
-	.sriov_configure	= hpre_sriov_configure,
+	.sriov_configure	= hisi_qm_sriov_configure,
 	.err_handler		= &hpre_err_handler,
 };
 
diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index f795fb557630..9bb263cec6c3 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -1,9 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 HiSilicon Limited. */
 #include <asm/page.h>
+#include <linux/acpi.h>
+#include <linux/aer.h>
 #include <linux/bitmap.h>
 #include <linux/debugfs.h>
 #include <linux/dma-mapping.h>
+#include <linux/idr.h>
 #include <linux/io.h>
 #include <linux/irqreturn.h>
 #include <linux/log2.h>
@@ -53,6 +56,7 @@
 #define QM_SQ_TYPE_SHIFT		8
 
 #define QM_SQ_TYPE_MASK			GENMASK(3, 0)
+#define QM_SQ_TAIL_IDX(sqc)		((le16_to_cpu((sqc)->w11) >> 6) & 0x1)
 
 /* cqc shift */
 #define QM_CQ_HOP_NUM_SHIFT		0
@@ -64,6 +68,7 @@
 
 #define QM_CQE_PHASE(cqe)		(le16_to_cpu((cqe)->w7) & 0x1)
 #define QM_QC_CQE_SIZE			4
+#define QM_CQ_TAIL_IDX(cqc)		((le16_to_cpu((cqc)->w11) >> 6) & 0x1)
 
 /* eqc shift */
 #define QM_EQE_AEQE_SIZE		(2UL << 12)
@@ -122,9 +127,11 @@
 #define QM_DFX_CNT_CLR_CE		0x100118
 
 #define QM_ABNORMAL_INT_SOURCE		0x100000
+#define QM_ABNORMAL_INT_SOURCE_CLR	GENMASK(12, 0)
 #define QM_ABNORMAL_INT_MASK		0x100004
 #define QM_ABNORMAL_INT_MASK_VALUE	0x1fff
 #define QM_ABNORMAL_INT_STATUS		0x100008
+#define QM_ABNORMAL_INT_SET		0x10000c
 #define QM_ABNORMAL_INF00		0x100010
 #define QM_FIFO_OVERFLOW_TYPE		0xc0
 #define QM_FIFO_OVERFLOW_TYPE_SHIFT	6
@@ -140,6 +147,27 @@
 #define QM_RAS_CE_TIMES_PER_IRQ		1
 #define QM_RAS_MSI_INT_SEL		0x1040f4
 
+#define QM_DEV_RESET_FLAG		0
+#define QM_RESET_WAIT_TIMEOUT		400
+#define QM_PEH_VENDOR_ID		0x1000d8
+#define ACC_VENDOR_ID_VALUE		0x5a5a
+#define QM_PEH_DFX_INFO0		0x1000fc
+#define ACC_PEH_SRIOV_CTRL_VF_MSE_SHIFT	3
+#define ACC_PEH_MSI_DISABLE		GENMASK(31, 0)
+#define ACC_MASTER_GLOBAL_CTRL_SHUTDOWN	0x1
+#define ACC_MASTER_TRANS_RETURN_RW	3
+#define ACC_MASTER_TRANS_RETURN		0x300150
+#define ACC_MASTER_GLOBAL_CTRL		0x300000
+#define ACC_AM_CFG_PORT_WR_EN		0x30001c
+#define QM_RAS_NFE_MBIT_DISABLE		~QM_ECC_MBIT
+#define ACC_AM_ROB_ECC_INT_STS		0x300104
+#define ACC_ROB_ECC_ERR_MULTPL		BIT(1)
+
+#define POLL_PERIOD			10
+#define POLL_TIMEOUT			1000
+#define WAIT_PERIOD_US_MAX		200
+#define WAIT_PERIOD_US_MIN		100
+#define MAX_WAIT_COUNTS			1000
 #define QM_CACHE_WB_START		0x204
 #define QM_CACHE_WB_DONE		0x208
 
@@ -147,7 +175,12 @@
 #define QM_SQE_DATA_ALIGN_MASK		GENMASK(6, 0)
 #define QMC_ALIGN(sz)			ALIGN(sz, 32)
 
+#define QM_DBG_READ_LEN		256
+#define QM_DBG_WRITE_LEN		1024
 #define QM_DBG_TMP_BUF_LEN		22
+#define QM_PCI_COMMAND_INVALID		~0
+
+#define QM_SQE_ADDR_MASK		GENMASK(7, 0)
 
 #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \
 	(((hop_num) << QM_CQ_HOP_NUM_SHIFT)	| \
@@ -190,6 +223,12 @@ enum vft_type {
 	CQC_VFT,
 };
 
+enum acc_err_result {
+	ACC_ERR_NONE,
+	ACC_ERR_NEED_RESET,
+	ACC_ERR_RECOVERED,
+};
+
 struct qm_cqe {
 	__le32 rsvd0;
 	__le16 cmd_id;
@@ -284,10 +323,22 @@ struct hisi_qm_hw_ops {
 		      u8 cmd, u16 index, u8 priority);
 	u32 (*get_irq_num)(struct hisi_qm *qm);
 	int (*debug_init)(struct hisi_qm *qm);
-	void (*hw_error_init)(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe,
-			      u32 msi);
+	void (*hw_error_init)(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe);
 	void (*hw_error_uninit)(struct hisi_qm *qm);
-	pci_ers_result_t (*hw_error_handle)(struct hisi_qm *qm);
+	enum acc_err_result (*hw_error_handle)(struct hisi_qm *qm);
+};
+
+struct qm_dfx_item {
+	const char *name;
+	u32 offset;
+};
+
+static struct qm_dfx_item qm_dfx_files[] = {
+	{"err_irq", offsetof(struct qm_dfx, err_irq_cnt)},
+	{"aeq_irq", offsetof(struct qm_dfx, aeq_irq_cnt)},
+	{"abnormal_irq", offsetof(struct qm_dfx, abnormal_irq_cnt)},
+	{"create_qp_err", offsetof(struct qm_dfx, create_qp_err_cnt)},
+	{"mb_err", offsetof(struct qm_dfx, mb_err_cnt)},
 };
 
 static const char * const qm_debug_file_name[] = {
@@ -325,6 +376,93 @@ static const char * const qm_fifo_overflow[] = {
 	"cq", "eq", "aeq",
 };
 
+static const char * const qm_s[] = {
+	"init", "start", "close", "stop",
+};
+
+static const char * const qp_s[] = {
+	"none", "init", "start", "stop", "close",
+};
+
+static bool qm_avail_state(struct hisi_qm *qm, enum qm_state new)
+{
+	enum qm_state curr = atomic_read(&qm->status.flags);
+	bool avail = false;
+
+	switch (curr) {
+	case QM_INIT:
+		if (new == QM_START || new == QM_CLOSE)
+			avail = true;
+		break;
+	case QM_START:
+		if (new == QM_STOP)
+			avail = true;
+		break;
+	case QM_STOP:
+		if (new == QM_CLOSE || new == QM_START)
+			avail = true;
+		break;
+	default:
+		break;
+	}
+
+	dev_dbg(&qm->pdev->dev, "change qm state from %s to %s\n",
+		qm_s[curr], qm_s[new]);
+
+	if (!avail)
+		dev_warn(&qm->pdev->dev, "Can not change qm state from %s to %s\n",
+			 qm_s[curr], qm_s[new]);
+
+	return avail;
+}
+
+static bool qm_qp_avail_state(struct hisi_qm *qm, struct hisi_qp *qp,
+			      enum qp_state new)
+{
+	enum qm_state qm_curr = atomic_read(&qm->status.flags);
+	enum qp_state qp_curr = 0;
+	bool avail = false;
+
+	if (qp)
+		qp_curr = atomic_read(&qp->qp_status.flags);
+
+	switch (new) {
+	case QP_INIT:
+		if (qm_curr == QM_START || qm_curr == QM_INIT)
+			avail = true;
+		break;
+	case QP_START:
+		if ((qm_curr == QM_START && qp_curr == QP_INIT) ||
+		    (qm_curr == QM_START && qp_curr == QP_STOP))
+			avail = true;
+		break;
+	case QP_STOP:
+		if ((qm_curr == QM_START && qp_curr == QP_START) ||
+		    (qp_curr == QP_INIT))
+			avail = true;
+		break;
+	case QP_CLOSE:
+		if ((qm_curr == QM_START && qp_curr == QP_INIT) ||
+		    (qm_curr == QM_START && qp_curr == QP_STOP) ||
+		    (qm_curr == QM_STOP && qp_curr == QP_STOP)  ||
+		    (qm_curr == QM_STOP && qp_curr == QP_INIT))
+			avail = true;
+		break;
+	default:
+		break;
+	}
+
+	dev_dbg(&qm->pdev->dev, "change qp state from %s to %s in QM %s\n",
+		qp_s[qp_curr], qp_s[new], qm_s[qm_curr]);
+
+	if (!avail)
+		dev_warn(&qm->pdev->dev,
+			 "Can not change qp state from %s to %s in QM %s\n",
+			 qp_s[qp_curr], qp_s[new], qm_s[qm_curr]);
+
+	return avail;
+}
+
 /* return 0 mailbox ready, -ETIMEDOUT hardware timeout */
 static int qm_wait_mb_ready(struct hisi_qm *qm)
 {
@@ -393,6 +531,8 @@ static int qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue,
 busy_unlock:
 	mutex_unlock(&qm->mailbox_lock);
 
+	if (ret)
+		atomic64_inc(&qm->debug.dfx.mb_err_cnt);
 	return ret;
 }
 
@@ -460,7 +600,7 @@ static struct hisi_qp *qm_to_hisi_qp(struct hisi_qm *qm, struct qm_eqe *eqe)
 {
 	u16 cqn = le32_to_cpu(eqe->dw0) & QM_EQE_CQN_MASK;
 
-	return qm->qp_array[cqn];
+	return &qm->qp_array[cqn];
 }
 
 static void qm_cq_head_update(struct hisi_qp *qp)
@@ -510,8 +650,7 @@ static void qm_work_process(struct work_struct *work)
 	while (QM_EQE_PHASE(eqe) == qm->status.eqc_phase) {
 		eqe_num++;
 		qp = qm_to_hisi_qp(qm, eqe);
-		if (qp)
-			qm_poll_qp(qp, qm);
+		qm_poll_qp(qp, qm);
 
 		if (qm->status.eq_head == QM_Q_DEPTH - 1) {
 			qm->status.eqc_phase = !qm->status.eqc_phase;
@@ -551,6 +690,7 @@ static irqreturn_t qm_irq(int irq, void *data)
 	if (readl(qm->io_base + QM_VF_EQ_INT_SOURCE))
 		return do_qm_irq(irq, data);
 
+	atomic64_inc(&qm->debug.dfx.err_irq_cnt);
 	dev_err(&qm->pdev->dev, "invalid int source\n");
 	qm_db(qm, 0, QM_DOORBELL_CMD_EQ, qm->status.eq_head, 0);
 
@@ -563,6 +703,7 @@ static irqreturn_t qm_aeq_irq(int irq, void *data)
 	struct qm_aeqe *aeqe = qm->aeqe + qm->status.aeq_head;
 	u32 type;
 
+	atomic64_inc(&qm->debug.dfx.aeq_irq_cnt);
 	if (!readl(qm->io_base + QM_VF_AEQ_INT_SOURCE))
 		return IRQ_NONE;
 
@@ -590,79 +731,20 @@ static irqreturn_t qm_aeq_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t qm_abnormal_irq(int irq, void *data)
-{
-	const struct hisi_qm_hw_error *err = qm_hw_error;
-	struct hisi_qm *qm = data;
-	struct device *dev = &qm->pdev->dev;
-	u32 error_status, tmp;
-
-	/* read err sts */
-	tmp = readl(qm->io_base + QM_ABNORMAL_INT_STATUS);
-	error_status = qm->msi_mask & tmp;
-
-	while (err->msg) {
-		if (err->int_msk & error_status)
-			dev_err(dev, "%s [error status=0x%x] found\n",
-				err->msg, err->int_msk);
-
-		err++;
-	}
-
-	/* clear err sts */
-	writel(error_status, qm->io_base + QM_ABNORMAL_INT_SOURCE);
-
-	return IRQ_HANDLED;
-}
-
-static int qm_irq_register(struct hisi_qm *qm)
-{
-	struct pci_dev *pdev = qm->pdev;
-	int ret;
-
-	ret = request_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR),
-			  qm_irq, IRQF_SHARED, qm->dev_name, qm);
-	if (ret)
-		return ret;
-
-	if (qm->ver == QM_HW_V2) {
-		ret = request_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR),
-				  qm_aeq_irq, IRQF_SHARED, qm->dev_name, qm);
-		if (ret)
-			goto err_aeq_irq;
-
-		if (qm->fun_type == QM_HW_PF) {
-			ret = request_irq(pci_irq_vector(pdev,
-					  QM_ABNORMAL_EVENT_IRQ_VECTOR),
-					  qm_abnormal_irq, IRQF_SHARED,
-					  qm->dev_name, qm);
-			if (ret)
-				goto err_abonormal_irq;
-		}
-	}
-
-	return 0;
-
-err_abonormal_irq:
-	free_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR), qm);
-err_aeq_irq:
-	free_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR), qm);
-	return ret;
-}
-
 static void qm_irq_unregister(struct hisi_qm *qm)
 {
 	struct pci_dev *pdev = qm->pdev;
 
 	free_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR), qm);
 
-	if (qm->ver == QM_HW_V2) {
-		free_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR), qm);
+	if (qm->ver == QM_HW_V1)
+		return;
+
+	free_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR), qm);
 
-		if (qm->fun_type == QM_HW_PF)
-			free_irq(pci_irq_vector(pdev,
-				 QM_ABNORMAL_EVENT_IRQ_VECTOR), qm);
-	}
+	if (qm->fun_type == QM_HW_PF)
+		free_irq(pci_irq_vector(pdev,
+			 QM_ABNORMAL_EVENT_IRQ_VECTOR), qm);
 }
 
 static void qm_init_qp_status(struct hisi_qp *qp)
@@ -672,7 +754,7 @@ static void qm_init_qp_status(struct hisi_qp *qp)
 	qp_status->sq_tail = 0;
 	qp_status->cq_head = 0;
 	qp_status->cqc_phase = true;
-	qp_status->flags = 0;
+	atomic_set(&qp_status->flags, 0);
 }
 
 static void qm_vft_data_cfg(struct hisi_qm *qm, enum vft_type type, u32 base,
@@ -683,36 +765,26 @@ static void qm_vft_data_cfg(struct hisi_qm *qm, enum vft_type type, u32 base,
 	if (number > 0) {
 		switch (type) {
 		case SQC_VFT:
-			switch (qm->ver) {
-			case QM_HW_V1:
+			if (qm->ver == QM_HW_V1) {
 				tmp = QM_SQC_VFT_BUF_SIZE	|
 				      QM_SQC_VFT_SQC_SIZE	|
 				      QM_SQC_VFT_INDEX_NUMBER	|
 				      QM_SQC_VFT_VALID		|
 				      (u64)base << QM_SQC_VFT_START_SQN_SHIFT;
-				break;
-			case QM_HW_V2:
+			} else {
 				tmp = (u64)base << QM_SQC_VFT_START_SQN_SHIFT |
 				      QM_SQC_VFT_VALID |
 				      (u64)(number - 1) << QM_SQC_VFT_SQN_SHIFT;
-				break;
-			case QM_HW_UNKNOWN:
-				break;
 			}
 			break;
 		case CQC_VFT:
-			switch (qm->ver) {
-			case QM_HW_V1:
+			if (qm->ver == QM_HW_V1) {
 				tmp = QM_CQC_VFT_BUF_SIZE	|
 				      QM_CQC_VFT_SQC_SIZE	|
 				      QM_CQC_VFT_INDEX_NUMBER	|
 				      QM_CQC_VFT_VALID;
-				break;
-			case QM_HW_V2:
+			} else {
 				tmp = QM_CQC_VFT_VALID;
-				break;
-			case QM_HW_UNKNOWN:
-				break;
 			}
 			break;
 		}
@@ -986,6 +1058,473 @@ static const struct file_operations qm_regs_fops = {
 	.release = single_release,
 };
 
+static ssize_t qm_cmd_read(struct file *filp, char __user *buffer,
+			   size_t count, loff_t *pos)
+{
+	char buf[QM_DBG_READ_LEN];
+	int len;
+
+	if (*pos)
+		return 0;
+
+	if (count < QM_DBG_READ_LEN)
+		return -ENOSPC;
+
+	len = snprintf(buf, QM_DBG_READ_LEN, "%s\n",
+		       "Please echo help to cmd to get help information");
+
+	if (copy_to_user(buffer, buf, len))
+		return -EFAULT;
+
+	return (*pos = len);
+}
+
+static void *qm_ctx_alloc(struct hisi_qm *qm, size_t ctx_size,
+			  dma_addr_t *dma_addr)
+{
+	struct device *dev = &qm->pdev->dev;
+	void *ctx_addr;
+
+	ctx_addr = kzalloc(ctx_size, GFP_KERNEL);
+	if (!ctx_addr)
+		return ERR_PTR(-ENOMEM);
+
+	*dma_addr = dma_map_single(dev, ctx_addr, ctx_size, DMA_FROM_DEVICE);
+	if (dma_mapping_error(dev, *dma_addr)) {
+		dev_err(dev, "DMA mapping error!\n");
+		kfree(ctx_addr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return ctx_addr;
+}
+
+static void qm_ctx_free(struct hisi_qm *qm, size_t ctx_size,
+			const void *ctx_addr, dma_addr_t *dma_addr)
+{
+	struct device *dev = &qm->pdev->dev;
+
+	dma_unmap_single(dev, *dma_addr, ctx_size, DMA_FROM_DEVICE);
+	kfree(ctx_addr);
+}
+
+static int dump_show(struct hisi_qm *qm, void *info,
+		     unsigned int info_size, char *info_name)
+{
+	struct device *dev = &qm->pdev->dev;
+	u8 *info_buf, *info_curr = info;
+	u32 i;
+#define BYTE_PER_DW	4
+
+	info_buf = kzalloc(info_size, GFP_KERNEL);
+	if (!info_buf)
+		return -ENOMEM;
+
+	for (i = 0; i < info_size; i++, info_curr++) {
+		if (i % BYTE_PER_DW == 0)
+			info_buf[i + 3UL] = *info_curr;
+		else if (i % BYTE_PER_DW == 1)
+			info_buf[i + 1UL] = *info_curr;
+		else if (i % BYTE_PER_DW == 2)
+			info_buf[i - 1] = *info_curr;
+		else if (i % BYTE_PER_DW == 3)
+			info_buf[i - 3] = *info_curr;
+	}
+
+	dev_info(dev, "%s DUMP\n", info_name);
+	for (i = 0; i < info_size; i += BYTE_PER_DW) {
+		pr_info("DW%d: %02X%02X %02X%02X\n", i / BYTE_PER_DW,
+			info_buf[i], info_buf[i + 1UL],
+			info_buf[i + 2UL], info_buf[i + 3UL]);
+	}
+
+	kfree(info_buf);
+
+	return 0;
+}
+
+static int qm_dump_sqc_raw(struct hisi_qm *qm, dma_addr_t dma_addr, u16 qp_id)
+{
+	return qm_mb(qm, QM_MB_CMD_SQC, dma_addr, qp_id, 1);
+}
+
+static int qm_dump_cqc_raw(struct hisi_qm *qm, dma_addr_t dma_addr, u16 qp_id)
+{
+	return qm_mb(qm, QM_MB_CMD_CQC, dma_addr, qp_id, 1);
+}
+
+static int qm_sqc_dump(struct hisi_qm *qm, const char *s)
+{
+	struct device *dev = &qm->pdev->dev;
+	struct qm_sqc *sqc, *sqc_curr;
+	dma_addr_t sqc_dma;
+	u32 qp_id;
+	int ret;
+
+	if (!s)
+		return -EINVAL;
+
+	ret = kstrtou32(s, 0, &qp_id);
+	if (ret || qp_id >= qm->qp_num) {
+		dev_err(dev, "Please input qp num (0-%d)", qm->qp_num - 1);
+		return -EINVAL;
+	}
+
+	sqc = qm_ctx_alloc(qm, sizeof(*sqc), &sqc_dma);
+	if (IS_ERR(sqc))
+		return PTR_ERR(sqc);
+
+	ret = qm_dump_sqc_raw(qm, sqc_dma, qp_id);
+	if (ret) {
+		down_read(&qm->qps_lock);
+		if (qm->sqc) {
+			sqc_curr = qm->sqc + qp_id;
+
+			ret = dump_show(qm, sqc_curr, sizeof(*sqc),
+					"SOFT SQC");
+			if (ret)
+				dev_info(dev, "Show soft sqc failed!\n");
+		}
+		up_read(&qm->qps_lock);
+
+		goto err_free_ctx;
+	}
+
+	ret = dump_show(qm, sqc, sizeof(*sqc), "SQC");
+	if (ret)
+		dev_info(dev, "Show hw sqc failed!\n");
+
+err_free_ctx:
+	qm_ctx_free(qm, sizeof(*sqc), sqc, &sqc_dma);
+	return ret;
+}
+
+static int qm_cqc_dump(struct hisi_qm *qm, const char *s)
+{
+	struct device *dev = &qm->pdev->dev;
+	struct qm_cqc *cqc, *cqc_curr;
+	dma_addr_t cqc_dma;
+	u32 qp_id;
+	int ret;
+
+	if (!s)
+		return -EINVAL;
+
+	ret = kstrtou32(s, 0, &qp_id);
+	if (ret || qp_id >= qm->qp_num) {
+		dev_err(dev, "Please input qp num (0-%d)", qm->qp_num - 1);
+		return -EINVAL;
+	}
+
+	cqc = qm_ctx_alloc(qm, sizeof(*cqc), &cqc_dma);
+	if (IS_ERR(cqc))
+		return PTR_ERR(cqc);
+
+	ret = qm_dump_cqc_raw(qm, cqc_dma, qp_id);
+	if (ret) {
+		down_read(&qm->qps_lock);
+		if (qm->cqc) {
+			cqc_curr = qm->cqc + qp_id;
+
+			ret = dump_show(qm, cqc_curr, sizeof(*cqc),
+					"SOFT CQC");
+			if (ret)
+				dev_info(dev, "Show soft cqc failed!\n");
+		}
+		up_read(&qm->qps_lock);
+
+		goto err_free_ctx;
+	}
+
+	ret = dump_show(qm, cqc, sizeof(*cqc), "CQC");
+	if (ret)
+		dev_info(dev, "Show hw cqc failed!\n");
+
+err_free_ctx:
+	qm_ctx_free(qm, sizeof(*cqc), cqc, &cqc_dma);
+	return ret;
+}
+
+static int qm_eqc_aeqc_dump(struct hisi_qm *qm, char *s, size_t size,
+			    int cmd, char *name)
+{
+	struct device *dev = &qm->pdev->dev;
+	dma_addr_t xeqc_dma;
+	void *xeqc;
+	int ret;
+
+	if (strsep(&s, " ")) {
+		dev_err(dev, "Please do not input extra characters!\n");
+		return -EINVAL;
+	}
+
+	xeqc = qm_ctx_alloc(qm, size, &xeqc_dma);
+	if (IS_ERR(xeqc))
+		return PTR_ERR(xeqc);
+
+	ret = qm_mb(qm, cmd, xeqc_dma, 0, 1);
+	if (ret)
+		goto err_free_ctx;
+
+	ret = dump_show(qm, xeqc, size, name);
+	if (ret)
+		dev_info(dev, "Show hw %s failed!\n", name);
+
+err_free_ctx:
+	qm_ctx_free(qm, size, xeqc, &xeqc_dma);
+	return ret;
+}
+
+static int q_dump_param_parse(struct hisi_qm *qm, char *s,
+			      u32 *e_id, u32 *q_id)
+{
+	struct device *dev = &qm->pdev->dev;
+	unsigned int qp_num = qm->qp_num;
+	char *presult;
+	int ret;
+
+	presult = strsep(&s, " ");
+	if (!presult) {
+		dev_err(dev, "Please input qp number!\n");
+		return -EINVAL;
+	}
+
+	ret = kstrtou32(presult, 0, q_id);
+	if (ret || *q_id >= qp_num) {
+		dev_err(dev, "Please input qp num (0-%d)", qp_num - 1);
+		return -EINVAL;
+	}
+
+	presult = strsep(&s, " ");
+	if (!presult) {
+		dev_err(dev, "Please input sqe number!\n");
+		return -EINVAL;
+	}
+
+	ret = kstrtou32(presult, 0, e_id);
+	if (ret || *e_id >= QM_Q_DEPTH) {
+		dev_err(dev, "Please input sqe num (0-%d)", QM_Q_DEPTH - 1);
+		return -EINVAL;
+	}
+
+	if (strsep(&s, " ")) {
+		dev_err(dev, "Please do not input extra characters!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int qm_sq_dump(struct hisi_qm *qm, char *s)
+{
+	struct device *dev = &qm->pdev->dev;
+	void *sqe, *sqe_curr;
+	struct hisi_qp *qp;
+	u32 qp_id, sqe_id;
+	int ret;
+
+	ret = q_dump_param_parse(qm, s, &sqe_id, &qp_id);
+	if (ret)
+		return ret;
+
+	sqe = kzalloc(qm->sqe_size * QM_Q_DEPTH, GFP_KERNEL);
+	if (!sqe)
+		return -ENOMEM;
+
+	qp = &qm->qp_array[qp_id];
+	memcpy(sqe, qp->sqe, qm->sqe_size * QM_Q_DEPTH);
+	sqe_curr = sqe + (u32)(sqe_id * qm->sqe_size);
+	memset(sqe_curr + qm->debug.sqe_mask_offset, QM_SQE_ADDR_MASK,
+	       qm->debug.sqe_mask_len);
+
+	ret = dump_show(qm, sqe_curr, qm->sqe_size, "SQE");
+	if (ret)
+		dev_info(dev, "Show sqe failed!\n");
+
+	kfree(sqe);
+
+	return ret;
+}
+
+static int qm_cq_dump(struct hisi_qm *qm, char *s)
+{
+	struct device *dev = &qm->pdev->dev;
+	struct qm_cqe *cqe_curr;
+	struct hisi_qp *qp;
+	u32 qp_id, cqe_id;
+	int ret;
+
+	ret = q_dump_param_parse(qm, s, &cqe_id, &qp_id);
+	if (ret)
+		return ret;
+
+	qp = &qm->qp_array[qp_id];
+	cqe_curr = qp->cqe + cqe_id;
+	ret = dump_show(qm, cqe_curr, sizeof(struct qm_cqe), "CQE");
+	if (ret)
+		dev_info(dev, "Show cqe failed!\n");
+
+	return ret;
+}
+
+static int qm_eq_aeq_dump(struct hisi_qm *qm, const char *s,
+			  size_t size, char *name)
+{
+	struct device *dev = &qm->pdev->dev;
+	void *xeqe;
+	u32 xeqe_id;
+	int ret;
+
+	if (!s)
+		return -EINVAL;
+
+	ret = kstrtou32(s, 0, &xeqe_id);
+	if (ret || xeqe_id >= QM_Q_DEPTH) {
+		dev_err(dev, "Please input aeqe num (0-%d)", QM_Q_DEPTH - 1);
+		return -EINVAL;
+	}
+
+	down_read(&qm->qps_lock);
+
+	if (qm->eqe && !strcmp(name, "EQE")) {
+		xeqe = qm->eqe + xeqe_id;
+	} else if (qm->aeqe && !strcmp(name, "AEQE")) {
+		xeqe = qm->aeqe + xeqe_id;
+	} else {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
+	ret = dump_show(qm, xeqe, size, name);
+	if (ret)
+		dev_info(dev, "Show %s failed!\n", name);
+
+err_unlock:
+	up_read(&qm->qps_lock);
+	return ret;
+}
+
+static int qm_dbg_help(struct hisi_qm *qm, char *s)
+{
+	struct device *dev = &qm->pdev->dev;
+
+	if (strsep(&s, " ")) {
+		dev_err(dev, "Please do not input extra characters!\n");
+		return -EINVAL;
+	}
+
+	dev_info(dev, "available commands:\n");
+	dev_info(dev, "sqc <num>\n");
+	dev_info(dev, "cqc <num>\n");
+	dev_info(dev, "eqc\n");
+	dev_info(dev, "aeqc\n");
+	dev_info(dev, "sq <num> <e>\n");
+	dev_info(dev, "cq <num> <e>\n");
+	dev_info(dev, "eq <e>\n");
+	dev_info(dev, "aeq <e>\n");
+
+	return 0;
+}
+
+static int qm_cmd_write_dump(struct hisi_qm *qm, const char *cmd_buf)
+{
+	struct device *dev = &qm->pdev->dev;
+	char *presult, *s;
+	int ret;
+
+	s = kstrdup(cmd_buf, GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	presult = strsep(&s, " ");
+	if (!presult) {
+		kfree(s);
+		return -EINVAL;
+	}
+
+	if (!strcmp(presult, "sqc"))
+		ret = qm_sqc_dump(qm, s);
+	else if (!strcmp(presult, "cqc"))
+		ret = qm_cqc_dump(qm, s);
+	else if (!strcmp(presult, "eqc"))
+		ret = qm_eqc_aeqc_dump(qm, s, sizeof(struct qm_eqc),
+				       QM_MB_CMD_EQC, "EQC");
+	else if (!strcmp(presult, "aeqc"))
+		ret = qm_eqc_aeqc_dump(qm, s, sizeof(struct qm_aeqc),
+				       QM_MB_CMD_AEQC, "AEQC");
+	else if (!strcmp(presult, "sq"))
+		ret = qm_sq_dump(qm, s);
+	else if (!strcmp(presult, "cq"))
+		ret = qm_cq_dump(qm, s);
+	else if (!strcmp(presult, "eq"))
+		ret = qm_eq_aeq_dump(qm, s, sizeof(struct qm_eqe), "EQE");
+	else if (!strcmp(presult, "aeq"))
+		ret = qm_eq_aeq_dump(qm, s, sizeof(struct qm_aeqe), "AEQE");
+	else if (!strcmp(presult, "help"))
+		ret = qm_dbg_help(qm, s);
+	else
+		ret = -EINVAL;
+
+	if (ret)
+		dev_info(dev, "Please echo help\n");
+
+	kfree(s);
+
+	return ret;
+}
+
+static ssize_t qm_cmd_write(struct file *filp, const char __user *buffer,
+			    size_t count, loff_t *pos)
+{
+	struct hisi_qm *qm = filp->private_data;
+	char *cmd_buf, *cmd_buf_tmp;
+	int ret;
+
+	if (*pos)
+		return 0;
+
+	/* Judge if the instance is being reset. */
+	if (unlikely(atomic_read(&qm->status.flags) == QM_STOP))
+		return 0;
+
+	if (count > QM_DBG_WRITE_LEN)
+		return -ENOSPC;
+
+	cmd_buf = kzalloc(count + 1, GFP_KERNEL);
+	if (!cmd_buf)
+		return -ENOMEM;
+
+	if (copy_from_user(cmd_buf, buffer, count)) {
+		kfree(cmd_buf);
+		return -EFAULT;
+	}
+
+	cmd_buf[count] = '\0';
+
+	cmd_buf_tmp = strchr(cmd_buf, '\n');
+	if (cmd_buf_tmp) {
+		*cmd_buf_tmp = '\0';
+		count = cmd_buf_tmp - cmd_buf + 1;
+	}
+
+	ret = qm_cmd_write_dump(qm, cmd_buf);
+	if (ret) {
+		kfree(cmd_buf);
+		return ret;
+	}
+
+	kfree(cmd_buf);
+
+	return count;
+}
+
+static const struct file_operations qm_cmd_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = qm_cmd_read,
+	.write = qm_cmd_write,
+};
+
 static int qm_create_debugfs_file(struct hisi_qm *qm, enum qm_debug_file index)
 {
 	struct dentry *qm_d = qm->debug.qm_d;
@@ -1001,20 +1540,21 @@ static int qm_create_debugfs_file(struct hisi_qm *qm, enum qm_debug_file index)
 	return 0;
 }
 
-static void qm_hw_error_init_v1(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe,
-				u32 msi)
+static void qm_hw_error_init_v1(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe)
 {
 	writel(QM_ABNORMAL_INT_MASK_VALUE, qm->io_base + QM_ABNORMAL_INT_MASK);
 }
 
-static void qm_hw_error_init_v2(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe,
-				u32 msi)
+static void qm_hw_error_init_v2(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe)
 {
-	u32 irq_enable = ce | nfe | fe | msi;
+	u32 irq_enable = ce | nfe | fe;
 	u32 irq_unmask = ~irq_enable;
 
 	qm->error_mask = ce | nfe | fe;
-	qm->msi_mask = msi;
+
+	/* clear QM hw residual error source */
+	writel(QM_ABNORMAL_INT_SOURCE_CLR,
+	       qm->io_base + QM_ABNORMAL_INT_SOURCE);
 
 	/* configure error type */
 	writel(ce, qm->io_base + QM_RAS_CE_ENABLE);
@@ -1022,9 +1562,6 @@ static void qm_hw_error_init_v2(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe,
 	writel(nfe, qm->io_base + QM_RAS_NFE_ENABLE);
 	writel(fe, qm->io_base + QM_RAS_FE_ENABLE);
 
-	/* use RAS irq default, so only set QM_RAS_MSI_INT_SEL for MSI */
-	writel(msi, qm->io_base + QM_RAS_MSI_INT_SEL);
-
 	irq_unmask &= readl(qm->io_base + QM_ABNORMAL_INT_MASK);
 	writel(irq_unmask, qm->io_base + QM_ABNORMAL_INT_MASK);
 }
@@ -1071,7 +1608,7 @@ static void qm_log_hw_error(struct hisi_qm *qm, u32 error_status)
 	}
 }
 
-static pci_ers_result_t qm_hw_error_handle_v2(struct hisi_qm *qm)
+static enum acc_err_result qm_hw_error_handle_v2(struct hisi_qm *qm)
 {
 	u32 error_status, tmp;
 
@@ -1080,15 +1617,20 @@ static pci_ers_result_t qm_hw_error_handle_v2(struct hisi_qm *qm)
 	error_status = qm->error_mask & tmp;
 
 	if (error_status) {
-		qm_log_hw_error(qm, error_status);
+		if (error_status & QM_ECC_MBIT)
+			qm->err_status.is_qm_ecc_mbit = true;
 
-		/* clear err sts */
-		writel(error_status, qm->io_base + QM_ABNORMAL_INT_SOURCE);
+		qm_log_hw_error(qm, error_status);
+		if (error_status == QM_DB_RANDOM_INVALID) {
+			writel(error_status, qm->io_base +
+			       QM_ABNORMAL_INT_SOURCE);
+			return ACC_ERR_RECOVERED;
+		}
 
-		return PCI_ERS_RESULT_NEED_RESET;
+		return ACC_ERR_NEED_RESET;
 	}
 
-	return PCI_ERS_RESULT_RECOVERED;
+	return ACC_ERR_RECOVERED;
 }
 
 static const struct hisi_qm_hw_ops qm_hw_ops_v1 = {
@@ -1117,68 +1659,61 @@ static void *qm_get_avail_sqe(struct hisi_qp *qp)
 	return qp->sqe + sq_tail * qp->qm->sqe_size;
 }
 
-/**
- * hisi_qm_create_qp() - Create a queue pair from qm.
- * @qm: The qm we create a qp from.
- * @alg_type: Accelerator specific algorithm type in sqc.
- *
- * return created qp, -EBUSY if all qps in qm allocated, -ENOMEM if allocating
- * qp memory fails.
- */
-struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type)
+static struct hisi_qp *qm_create_qp_nolock(struct hisi_qm *qm, u8 alg_type)
 {
 	struct device *dev = &qm->pdev->dev;
 	struct hisi_qp *qp;
-	int qp_id, ret;
-
-	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
-	if (!qp)
-		return ERR_PTR(-ENOMEM);
+	int qp_id;
 
-	write_lock(&qm->qps_lock);
+	if (!qm_qp_avail_state(qm, NULL, QP_INIT))
+		return ERR_PTR(-EPERM);
 
-	qp_id = find_first_zero_bit(qm->qp_bitmap, qm->qp_num);
-	if (qp_id >= qm->qp_num) {
-		write_unlock(&qm->qps_lock);
-		dev_info(&qm->pdev->dev, "QM all queues are busy!\n");
-		ret = -EBUSY;
-		goto err_free_qp;
+	if (qm->qp_in_used == qm->qp_num) {
+		dev_info_ratelimited(dev, "All %u queues of QM are busy!\n",
+				     qm->qp_num);
+		atomic64_inc(&qm->debug.dfx.create_qp_err_cnt);
+		return ERR_PTR(-EBUSY);
 	}
-	set_bit(qp_id, qm->qp_bitmap);
-	qm->qp_array[qp_id] = qp;
-	qm->qp_in_used++;
 
-	write_unlock(&qm->qps_lock);
-
-	qp->qm = qm;
+	qp_id = idr_alloc_cyclic(&qm->qp_idr, NULL, 0, qm->qp_num, GFP_ATOMIC);
+	if (qp_id < 0) {
+		dev_info_ratelimited(dev, "All %u queues of QM are busy!\n",
+				    qm->qp_num);
+		atomic64_inc(&qm->debug.dfx.create_qp_err_cnt);
+		return ERR_PTR(-EBUSY);
+	}
 
-	if (qm->use_dma_api) {
-		qp->qdma.size = qm->sqe_size * QM_Q_DEPTH +
-				sizeof(struct qm_cqe) * QM_Q_DEPTH;
-		qp->qdma.va = dma_alloc_coherent(dev, qp->qdma.size,
-						 &qp->qdma.dma, GFP_KERNEL);
-		if (!qp->qdma.va) {
-			ret = -ENOMEM;
-			goto err_clear_bit;
-		}
+	qp = &qm->qp_array[qp_id];
 
-		dev_dbg(dev, "allocate qp dma buf(va=%pK, dma=%pad, size=%zx)\n",
-			qp->qdma.va, &qp->qdma.dma, qp->qdma.size);
-	}
+	memset(qp->cqe, 0, sizeof(struct qm_cqe) * QM_Q_DEPTH);
 
+	qp->event_cb = NULL;
+	qp->req_cb = NULL;
 	qp->qp_id = qp_id;
 	qp->alg_type = alg_type;
+	qm->qp_in_used++;
+	atomic_set(&qp->qp_status.flags, QP_INIT);
 
 	return qp;
+}
+
+/**
+ * hisi_qm_create_qp() - Create a queue pair from qm.
+ * @qm: The qm we create a qp from.
+ * @alg_type: Accelerator specific algorithm type in sqc.
+ *
+ * return created qp, -EBUSY if all qps in qm allocated, -ENOMEM if allocating
+ * qp memory fails.
+ */
+struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type)
+{
+	struct hisi_qp *qp;
 
-err_clear_bit:
-	write_lock(&qm->qps_lock);
-	qm->qp_array[qp_id] = NULL;
-	clear_bit(qp_id, qm->qp_bitmap);
-	write_unlock(&qm->qps_lock);
-err_free_qp:
-	kfree(qp);
-	return ERR_PTR(ret);
+	down_write(&qm->qps_lock);
+	qp = qm_create_qp_nolock(qm, alg_type);
+	up_write(&qm->qps_lock);
+
+	return qp;
 }
 EXPORT_SYMBOL_GPL(hisi_qm_create_qp);
 
@@ -1191,19 +1726,18 @@ EXPORT_SYMBOL_GPL(hisi_qm_create_qp);
 void hisi_qm_release_qp(struct hisi_qp *qp)
 {
 	struct hisi_qm *qm = qp->qm;
-	struct qm_dma *qdma = &qp->qdma;
-	struct device *dev = &qm->pdev->dev;
 
-	if (qm->use_dma_api && qdma->va)
-		dma_free_coherent(dev, qdma->size, qdma->va, qdma->dma);
+	down_write(&qm->qps_lock);
+
+	if (!qm_qp_avail_state(qm, qp, QP_CLOSE)) {
+		up_write(&qm->qps_lock);
+		return;
+	}
 
-	write_lock(&qm->qps_lock);
-	qm->qp_array[qp->qp_id] = NULL;
-	clear_bit(qp->qp_id, qm->qp_bitmap);
 	qm->qp_in_used--;
-	write_unlock(&qm->qps_lock);
+	idr_remove(&qm->qp_idr, qp->qp_id);
 
-	kfree(qp);
+	up_write(&qm->qps_lock);
 }
 EXPORT_SYMBOL_GPL(hisi_qm_release_qp);
 
@@ -1234,7 +1768,7 @@ static int qm_qp_ctx_cfg(struct hisi_qp *qp, int qp_id, int pasid)
 	if (ver == QM_HW_V1) {
 		sqc->dw3 = cpu_to_le32(QM_MK_SQC_DW3_V1(0, 0, 0, qm->sqe_size));
 		sqc->w8 = cpu_to_le16(QM_Q_DEPTH - 1);
-	} else if (ver == QM_HW_V2) {
+	} else {
 		sqc->dw3 = cpu_to_le32(QM_MK_SQC_DW3_V2(qm->sqe_size));
 		sqc->w8 = 0; /* rand_qc */
 	}
@@ -1261,7 +1795,7 @@ static int qm_qp_ctx_cfg(struct hisi_qp *qp, int qp_id, int pasid)
 	if (ver == QM_HW_V1) {
 		cqc->dw3 = cpu_to_le32(QM_MK_CQC_DW3_V1(0, 0, 0, 4));
 		cqc->w8 = cpu_to_le16(QM_Q_DEPTH - 1);
-	} else if (ver == QM_HW_V2) {
+	} else {
 		cqc->dw3 = cpu_to_le32(QM_MK_CQC_DW3_V2(4));
 		cqc->w8 = 0;
 	}
@@ -1274,6 +1808,27 @@ static int qm_qp_ctx_cfg(struct hisi_qp *qp, int qp_id, int pasid)
 	return ret;
 }
 
+static int qm_start_qp_nolock(struct hisi_qp *qp, unsigned long arg)
+{
+	struct hisi_qm *qm = qp->qm;
+	struct device *dev = &qm->pdev->dev;
+	int qp_id = qp->qp_id;
+	int pasid = arg;
+	int ret;
+
+	if (!qm_qp_avail_state(qm, qp, QP_START))
+		return -EPERM;
+
+	ret = qm_qp_ctx_cfg(qp, qp_id, pasid);
+	if (ret)
+		return ret;
+
+	atomic_set(&qp->qp_status.flags, QP_START);
+	dev_dbg(dev, "queue %d started\n", qp_id);
+
+	return 0;
+}
+
 /**
  * hisi_qm_start_qp() - Start a qp into running.
  * @qp: The qp we want to start to run.
@@ -1285,48 +1840,112 @@ static int qm_qp_ctx_cfg(struct hisi_qp *qp, int qp_id, int pasid)
 int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg)
 {
 	struct hisi_qm *qm = qp->qm;
-	struct device *dev = &qm->pdev->dev;
-	enum qm_hw_ver ver = qm->ver;
-	int qp_id = qp->qp_id;
-	int pasid = arg;
-	size_t off = 0;
 	int ret;
 
-#define QP_INIT_BUF(qp, type, size) do { \
-	(qp)->type = ((qp)->qdma.va + (off)); \
-	(qp)->type##_dma = (qp)->qdma.dma + (off); \
-	off += (size); \
-} while (0)
+	down_write(&qm->qps_lock);
+	ret = qm_start_qp_nolock(qp, arg);
+	up_write(&qm->qps_lock);
 
-	if (!qp->qdma.dma) {
-		dev_err(dev, "cannot get qm dma buffer\n");
-		return -EINVAL;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_start_qp);
+
+/**
+ * Determine whether the queue is cleared by judging the tail pointers of
+ * sq and cq.
+ */
+static int qm_drain_qp(struct hisi_qp *qp)
+{
+	size_t size = sizeof(struct qm_sqc) + sizeof(struct qm_cqc);
+	struct hisi_qm *qm = qp->qm;
+	struct device *dev = &qm->pdev->dev;
+	struct qm_sqc *sqc;
+	struct qm_cqc *cqc;
+	dma_addr_t dma_addr;
+	int ret = 0, i = 0;
+	void *addr;
+
+	/*
+	 * No need to judge if ECC multi-bit error occurs because the
+	 * master OOO will be blocked.
+	 */
+	if (qm->err_status.is_qm_ecc_mbit || qm->err_status.is_dev_ecc_mbit)
+		return 0;
+
+	addr = qm_ctx_alloc(qm, size, &dma_addr);
+	if (IS_ERR(addr)) {
+		dev_err(dev, "Failed to alloc ctx for sqc and cqc!\n");
+		return -ENOMEM;
 	}
 
-	/* sq need 128 bytes alignment */
-	if (qp->qdma.dma & QM_SQE_DATA_ALIGN_MASK) {
-		dev_err(dev, "qm sq is not aligned to 128 byte\n");
-		return -EINVAL;
+	while (++i) {
+		ret = qm_dump_sqc_raw(qm, dma_addr, qp->qp_id);
+		if (ret) {
+			dev_err_ratelimited(dev, "Failed to dump sqc!\n");
+			break;
+		}
+		sqc = addr;
+
+		ret = qm_dump_cqc_raw(qm, (dma_addr + sizeof(struct qm_sqc)),
+				      qp->qp_id);
+		if (ret) {
+			dev_err_ratelimited(dev, "Failed to dump cqc!\n");
+			break;
+		}
+		cqc = addr + sizeof(struct qm_sqc);
+
+		if ((sqc->tail == cqc->tail) &&
+		    (QM_SQ_TAIL_IDX(sqc) == QM_CQ_TAIL_IDX(cqc)))
+			break;
+
+		if (i == MAX_WAIT_COUNTS) {
+			dev_err(dev, "Fail to empty queue %u!\n", qp->qp_id);
+			ret = -EBUSY;
+			break;
+		}
+
+		usleep_range(WAIT_PERIOD_US_MIN, WAIT_PERIOD_US_MAX);
 	}
 
-	QP_INIT_BUF(qp, sqe, qm->sqe_size * QM_Q_DEPTH);
-	QP_INIT_BUF(qp, cqe, sizeof(struct qm_cqe) * QM_Q_DEPTH);
+	qm_ctx_free(qm, size, addr, &dma_addr);
 
-	dev_dbg(dev, "init qp buffer(v%d):\n"
-		     " sqe	(%pK, %lx)\n"
-		     " cqe	(%pK, %lx)\n",
-		     ver, qp->sqe, (unsigned long)qp->sqe_dma,
-		     qp->cqe, (unsigned long)qp->cqe_dma);
+	return ret;
+}
 
-	ret = qm_qp_ctx_cfg(qp, qp_id, pasid);
+static int qm_stop_qp_nolock(struct hisi_qp *qp)
+{
+	struct device *dev = &qp->qm->pdev->dev;
+	int ret;
+
+	/*
+	 * It is allowed to stop and release qp when reset, If the qp is
+	 * stopped when reset but still want to be released then, the
+	 * is_resetting flag should be set negative so that this qp will not
+	 * be restarted after reset.
+	 */
+	if (atomic_read(&qp->qp_status.flags) == QP_STOP) {
+		qp->is_resetting = false;
+		return 0;
+	}
+
+	if (!qm_qp_avail_state(qp->qm, qp, QP_STOP))
+		return -EPERM;
+
+	atomic_set(&qp->qp_status.flags, QP_STOP);
+
+	ret = qm_drain_qp(qp);
 	if (ret)
-		return ret;
+		dev_err(dev, "Failed to drain out data for stopping!\n");
 
-	dev_dbg(dev, "queue %d started\n", qp_id);
+	if (qp->qm->wq)
+		flush_workqueue(qp->qm->wq);
+	else
+		flush_work(&qp->qm->work);
+
+	dev_dbg(dev, "stop queue %u!", qp->qp_id);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(hisi_qm_start_qp);
 
 /**
  * hisi_qm_stop_qp() - Stop a qp in qm.
@@ -1336,27 +1955,13 @@ EXPORT_SYMBOL_GPL(hisi_qm_start_qp);
  */
 int hisi_qm_stop_qp(struct hisi_qp *qp)
 {
-	struct device *dev = &qp->qm->pdev->dev;
-	int i = 0;
-
-	/* it is stopped */
-	if (test_bit(QP_STOP, &qp->qp_status.flags))
-		return 0;
-
-	while (atomic_read(&qp->qp_status.used)) {
-		i++;
-		msleep(20);
-		if (i == 10) {
-			dev_err(dev, "Cannot drain out data for stopping, Force to stop!\n");
-			return 0;
-		}
-	}
-
-	set_bit(QP_STOP, &qp->qp_status.flags);
+	int ret;
 
-	dev_dbg(dev, "stop queue %u!", qp->qp_id);
+	down_write(&qp->qm->qps_lock);
+	ret = qm_stop_qp_nolock(qp);
+	up_write(&qp->qm->qps_lock);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(hisi_qm_stop_qp);
 
@@ -1367,6 +1972,13 @@ EXPORT_SYMBOL_GPL(hisi_qm_stop_qp);
  *
  * This function will return -EBUSY if qp is currently full, and -EAGAIN
  * if qp related qm is resetting.
+ *
+ * Note: This function may run with qm_irq_thread and ACC reset at same time.
+ *       It has no race with qm_irq_thread. However, during hisi_qp_send, ACC
+ *       reset may happen, we have no lock here considering performance. This
+ *       causes current qm_db sending fail or can not receive sended sqe. QM
+ *       sync/async receive function should handle the error sqe. ACC reset
+ *       done function should clear used sqe to 0.
  */
 int hisi_qp_send(struct hisi_qp *qp, const void *msg)
 {
@@ -1375,7 +1987,9 @@ int hisi_qp_send(struct hisi_qp *qp, const void *msg)
 	u16 sq_tail_next = (sq_tail + 1) % QM_Q_DEPTH;
 	void *sqe = qm_get_avail_sqe(qp);
 
-	if (unlikely(test_bit(QP_STOP, &qp->qp_status.flags))) {
+	if (unlikely(atomic_read(&qp->qp_status.flags) == QP_STOP ||
+		     atomic_read(&qp->qm->status.flags) == QM_STOP ||
+		     qp->is_resetting)) {
 		dev_info(&qp->qm->pdev->dev, "QP is stopped or resetting\n");
 		return -EAGAIN;
 	}
@@ -1397,12 +2011,13 @@ static void hisi_qm_cache_wb(struct hisi_qm *qm)
 {
 	unsigned int val;
 
-	if (qm->ver == QM_HW_V2) {
-		writel(0x1, qm->io_base + QM_CACHE_WB_START);
-		if (readl_relaxed_poll_timeout(qm->io_base + QM_CACHE_WB_DONE,
-					       val, val & BIT(0), 10, 1000))
-			dev_err(&qm->pdev->dev, "QM writeback sqc cache fail!\n");
-	}
+	if (qm->ver == QM_HW_V1)
+		return;
+
+	writel(0x1, qm->io_base + QM_CACHE_WB_START);
+	if (readl_relaxed_poll_timeout(qm->io_base + QM_CACHE_WB_DONE,
+					    val, val & BIT(0), 10, 1000))
+		dev_err(&qm->pdev->dev, "QM writeback sqc cache fail!\n");
 }
 
 static void qm_qp_event_notifier(struct hisi_qp *qp)
@@ -1412,16 +2027,7 @@ static void qm_qp_event_notifier(struct hisi_qp *qp)
 
 static int hisi_qm_get_available_instances(struct uacce_device *uacce)
 {
-	int i, ret;
-	struct hisi_qm *qm = uacce->priv;
-
-	read_lock(&qm->qps_lock);
-	for (i = 0, ret = 0; i < qm->qp_num; i++)
-		if (!qm->qp_array[i])
-			ret++;
-	read_unlock(&qm->qps_lock);
-
-	return ret;
+	return hisi_qm_get_free_qp_num(uacce->priv);
 }
 
 static int hisi_qm_uacce_get_queue(struct uacce_device *uacce,
@@ -1468,12 +2074,12 @@ static int hisi_qm_uacce_mmap(struct uacce_queue *q,
 
 	switch (qfr->type) {
 	case UACCE_QFRT_MMIO:
-		if (qm->ver == QM_HW_V2) {
-			if (sz > PAGE_SIZE * (QM_DOORBELL_PAGE_NR +
-			    QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE))
+		if (qm->ver == QM_HW_V1) {
+			if (sz > PAGE_SIZE * QM_DOORBELL_PAGE_NR)
 				return -EINVAL;
 		} else {
-			if (sz > PAGE_SIZE * QM_DOORBELL_PAGE_NR)
+			if (sz > PAGE_SIZE * (QM_DOORBELL_PAGE_NR +
+			    QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE))
 				return -EINVAL;
 		}
 
@@ -1519,9 +2125,9 @@ static int qm_set_sqctype(struct uacce_queue *q, u16 type)
 	struct hisi_qm *qm = q->uacce->priv;
 	struct hisi_qp *qp = q->priv;
 
-	write_lock(&qm->qps_lock);
+	down_write(&qm->qps_lock);
 	qp->alg_type = type;
-	write_unlock(&qm->qps_lock);
+	up_write(&qm->qps_lock);
 
 	return 0;
 }
@@ -1623,107 +2229,121 @@ int hisi_qm_get_free_qp_num(struct hisi_qm *qm)
 {
 	int ret;
 
-	read_lock(&qm->qps_lock);
+	down_read(&qm->qps_lock);
 	ret = qm->qp_num - qm->qp_in_used;
-	read_unlock(&qm->qps_lock);
+	up_read(&qm->qps_lock);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(hisi_qm_get_free_qp_num);
 
-/**
- * hisi_qm_init() - Initialize configures about qm.
- * @qm: The qm needing init.
- *
- * This function init qm, then we can call hisi_qm_start to put qm into work.
- */
-int hisi_qm_init(struct hisi_qm *qm)
+static void hisi_qp_memory_uninit(struct hisi_qm *qm, int num)
 {
-	struct pci_dev *pdev = qm->pdev;
-	struct device *dev = &pdev->dev;
-	unsigned int num_vec;
-	int ret;
+	struct device *dev = &qm->pdev->dev;
+	struct qm_dma *qdma;
+	int i;
 
-	switch (qm->ver) {
-	case QM_HW_V1:
-		qm->ops = &qm_hw_ops_v1;
-		break;
-	case QM_HW_V2:
-		qm->ops = &qm_hw_ops_v2;
-		break;
-	default:
-		return -EINVAL;
+	for (i = num - 1; i >= 0; i--) {
+		qdma = &qm->qp_array[i].qdma;
+		dma_free_coherent(dev, qdma->size, qdma->va, qdma->dma);
 	}
 
-	ret = qm_alloc_uacce(qm);
-	if (ret < 0)
-		dev_warn(&pdev->dev, "fail to alloc uacce (%d)\n", ret);
+	kfree(qm->qp_array);
+}
 
-	ret = pci_enable_device_mem(pdev);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to enable device mem!\n");
-		goto err_remove_uacce;
-	}
+static int hisi_qp_memory_init(struct hisi_qm *qm, size_t dma_size, int id)
+{
+	struct device *dev = &qm->pdev->dev;
+	size_t off = qm->sqe_size * QM_Q_DEPTH;
+	struct hisi_qp *qp;
 
-	ret = pci_request_mem_regions(pdev, qm->dev_name);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to request mem regions!\n");
-		goto err_disable_pcidev;
-	}
+	qp = &qm->qp_array[id];
+	qp->qdma.va = dma_alloc_coherent(dev, dma_size, &qp->qdma.dma,
+					 GFP_KERNEL);
+	if (!qp->qdma.va)
+		return -ENOMEM;
 
-	qm->phys_base = pci_resource_start(pdev, PCI_BAR_2);
-	qm->phys_size = pci_resource_len(qm->pdev, PCI_BAR_2);
-	qm->io_base = ioremap(qm->phys_base, qm->phys_size);
-	if (!qm->io_base) {
-		ret = -EIO;
-		goto err_release_mem_regions;
-	}
+	qp->sqe = qp->qdma.va;
+	qp->sqe_dma = qp->qdma.dma;
+	qp->cqe = qp->qdma.va + off;
+	qp->cqe_dma = qp->qdma.dma + off;
+	qp->qdma.size = dma_size;
+	qp->qm = qm;
+	qp->qp_id = id;
 
-	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
-	if (ret < 0)
-		goto err_iounmap;
-	pci_set_master(pdev);
+	return 0;
+}
 
-	if (!qm->ops->get_irq_num) {
-		ret = -EOPNOTSUPP;
-		goto err_iounmap;
+static int hisi_qm_memory_init(struct hisi_qm *qm)
+{
+	struct device *dev = &qm->pdev->dev;
+	size_t qp_dma_size, off = 0;
+	int i, ret = 0;
+
+#define QM_INIT_BUF(qm, type, num) do { \
+	(qm)->type = ((qm)->qdma.va + (off)); \
+	(qm)->type##_dma = (qm)->qdma.dma + (off); \
+	off += QMC_ALIGN(sizeof(struct qm_##type) * (num)); \
+} while (0)
+
+	idr_init(&qm->qp_idr);
+	qm->qdma.size = QMC_ALIGN(sizeof(struct qm_eqe) * QM_Q_DEPTH) +
+			QMC_ALIGN(sizeof(struct qm_aeqe) * QM_Q_DEPTH) +
+			QMC_ALIGN(sizeof(struct qm_sqc) * qm->qp_num) +
+			QMC_ALIGN(sizeof(struct qm_cqc) * qm->qp_num);
+	qm->qdma.va = dma_alloc_coherent(dev, qm->qdma.size, &qm->qdma.dma,
+					 GFP_ATOMIC);
+	dev_dbg(dev, "allocate qm dma buf size=%zx)\n", qm->qdma.size);
+	if (!qm->qdma.va)
+		return -ENOMEM;
+
+	QM_INIT_BUF(qm, eqe, QM_Q_DEPTH);
+	QM_INIT_BUF(qm, aeqe, QM_Q_DEPTH);
+	QM_INIT_BUF(qm, sqc, qm->qp_num);
+	QM_INIT_BUF(qm, cqc, qm->qp_num);
+
+	qm->qp_array = kcalloc(qm->qp_num, sizeof(struct hisi_qp), GFP_KERNEL);
+	if (!qm->qp_array) {
+		ret = -ENOMEM;
+		goto err_alloc_qp_array;
 	}
-	num_vec = qm->ops->get_irq_num(qm);
-	ret = pci_alloc_irq_vectors(pdev, num_vec, num_vec, PCI_IRQ_MSI);
-	if (ret < 0) {
-		dev_err(dev, "Failed to enable MSI vectors!\n");
-		goto err_iounmap;
+
+	/* one more page for device or qp statuses */
+	qp_dma_size = qm->sqe_size * QM_Q_DEPTH +
+		      sizeof(struct qm_cqe) * QM_Q_DEPTH;
+	qp_dma_size = PAGE_ALIGN(qp_dma_size);
+	for (i = 0; i < qm->qp_num; i++) {
+		ret = hisi_qp_memory_init(qm, qp_dma_size, i);
+		if (ret)
+			goto err_init_qp_mem;
+
+		dev_dbg(dev, "allocate qp dma buf size=%zx)\n", qp_dma_size);
 	}
 
-	ret = qm_irq_register(qm);
-	if (ret)
-		goto err_free_irq_vectors;
+	return ret;
 
-	qm->qp_in_used = 0;
-	mutex_init(&qm->mailbox_lock);
-	rwlock_init(&qm->qps_lock);
-	INIT_WORK(&qm->work, qm_work_process);
+err_init_qp_mem:
+	hisi_qp_memory_uninit(qm, i);
+err_alloc_qp_array:
+	dma_free_coherent(dev, qm->qdma.size, qm->qdma.va, qm->qdma.dma);
 
-	dev_dbg(dev, "init qm %s with %s\n", pdev->is_physfn ? "pf" : "vf",
-		qm->use_dma_api ? "dma api" : "iommu api");
+	return ret;
+}
 
-	return 0;
+static void hisi_qm_pre_init(struct hisi_qm *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
 
-err_free_irq_vectors:
-	pci_free_irq_vectors(pdev);
-err_iounmap:
-	iounmap(qm->io_base);
-err_release_mem_regions:
-	pci_release_mem_regions(pdev);
-err_disable_pcidev:
-	pci_disable_device(pdev);
-err_remove_uacce:
-	uacce_remove(qm->uacce);
-	qm->uacce = NULL;
+	if (qm->ver == QM_HW_V1)
+		qm->ops = &qm_hw_ops_v1;
+	else
+		qm->ops = &qm_hw_ops_v2;
 
-	return ret;
+	pci_set_drvdata(pdev, qm);
+	mutex_init(&qm->mailbox_lock);
+	init_rwsem(&qm->qps_lock);
+	qm->qp_in_used = 0;
 }
-EXPORT_SYMBOL_GPL(hisi_qm_init);
 
 /**
  * hisi_qm_uninit() - Uninitialize qm.
@@ -1736,10 +2356,20 @@ void hisi_qm_uninit(struct hisi_qm *qm)
 	struct pci_dev *pdev = qm->pdev;
 	struct device *dev = &pdev->dev;
 
+	down_write(&qm->qps_lock);
+
+	if (!qm_avail_state(qm, QM_CLOSE)) {
+		up_write(&qm->qps_lock);
+		return;
+	}
+
 	uacce_remove(qm->uacce);
 	qm->uacce = NULL;
 
-	if (qm->use_dma_api && qm->qdma.va) {
+	hisi_qp_memory_uninit(qm, qm->qp_num);
+	idr_destroy(&qm->qp_idr);
+
+	if (qm->qdma.va) {
 		hisi_qm_cache_wb(qm);
 		dma_free_coherent(dev, qm->qdma.size,
 				  qm->qdma.va, qm->qdma.dma);
@@ -1751,6 +2381,8 @@ void hisi_qm_uninit(struct hisi_qm *qm)
 	iounmap(qm->io_base);
 	pci_release_mem_regions(pdev);
 	pci_disable_device(pdev);
+
+	up_write(&qm->qps_lock);
 }
 EXPORT_SYMBOL_GPL(hisi_qm_uninit);
 
@@ -1781,12 +2413,6 @@ int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number)
 EXPORT_SYMBOL_GPL(hisi_qm_get_vft);
 
 /**
- * hisi_qm_set_vft() - Set "virtual function table" for a qm.
- * @fun_num: Number of operated function.
- * @qm: The qm in which to set vft, alway in a PF.
- * @base: The base number of queue in vft.
- * @number: The number of queues in vft. 0 means invalid vft.
- *
  * This function is alway called in PF driver, it is used to assign queues
  * among PF and VFs.
  *
@@ -1794,7 +2420,7 @@ EXPORT_SYMBOL_GPL(hisi_qm_get_vft);
  * Assign queues A~B to VF: hisi_qm_set_vft(qm, 2, A, B - A + 1)
  * (VF function number 0x2)
  */
-int hisi_qm_set_vft(struct hisi_qm *qm, u32 fun_num, u32 base,
+static int hisi_qm_set_vft(struct hisi_qm *qm, u32 fun_num, u32 base,
 		    u32 number)
 {
 	u32 max_q_num = qm->ctrl_qp_num;
@@ -1805,7 +2431,6 @@ int hisi_qm_set_vft(struct hisi_qm *qm, u32 fun_num, u32 base,
 
 	return qm_set_sqc_cqc_vft(qm, fun_num, base, number);
 }
-EXPORT_SYMBOL_GPL(hisi_qm_set_vft);
 
 static void qm_init_eq_aeq_status(struct hisi_qm *qm)
 {
@@ -1872,22 +2497,10 @@ static int qm_eq_ctx_cfg(struct hisi_qm *qm)
 
 static int __hisi_qm_start(struct hisi_qm *qm)
 {
-	struct pci_dev *pdev = qm->pdev;
-	struct device *dev = &pdev->dev;
-	size_t off = 0;
 	int ret;
 
-#define QM_INIT_BUF(qm, type, num) do { \
-	(qm)->type = ((qm)->qdma.va + (off)); \
-	(qm)->type##_dma = (qm)->qdma.dma + (off); \
-	off += QMC_ALIGN(sizeof(struct qm_##type) * (num)); \
-} while (0)
-
 	WARN_ON(!qm->qdma.dma);
 
-	if (qm->qp_num == 0)
-		return -EINVAL;
-
 	if (qm->fun_type == QM_HW_PF) {
 		ret = qm_dev_mem_reset(qm);
 		if (ret)
@@ -1898,21 +2511,6 @@ static int __hisi_qm_start(struct hisi_qm *qm)
 			return ret;
 	}
 
-	QM_INIT_BUF(qm, eqe, QM_Q_DEPTH);
-	QM_INIT_BUF(qm, aeqe, QM_Q_DEPTH);
-	QM_INIT_BUF(qm, sqc, qm->qp_num);
-	QM_INIT_BUF(qm, cqc, qm->qp_num);
-
-	dev_dbg(dev, "init qm buffer:\n"
-		     " eqe	(%pK, %lx)\n"
-		     " aeqe	(%pK, %lx)\n"
-		     " sqc	(%pK, %lx)\n"
-		     " cqc	(%pK, %lx)\n",
-		     qm->eqe, (unsigned long)qm->eqe_dma,
-		     qm->aeqe, (unsigned long)qm->aeqe_dma,
-		     qm->sqc, (unsigned long)qm->sqc_dma,
-		     qm->cqc, (unsigned long)qm->cqc_dma);
-
 	ret = qm_eq_ctx_cfg(qm);
 	if (ret)
 		return ret;
@@ -1940,43 +2538,102 @@ static int __hisi_qm_start(struct hisi_qm *qm)
 int hisi_qm_start(struct hisi_qm *qm)
 {
 	struct device *dev = &qm->pdev->dev;
+	int ret = 0;
+
+	down_write(&qm->qps_lock);
+
+	if (!qm_avail_state(qm, QM_START)) {
+		up_write(&qm->qps_lock);
+		return -EPERM;
+	}
 
 	dev_dbg(dev, "qm start with %d queue pairs\n", qm->qp_num);
 
 	if (!qm->qp_num) {
 		dev_err(dev, "qp_num should not be 0\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_unlock;
 	}
 
-	if (!qm->qp_bitmap) {
-		qm->qp_bitmap = devm_kcalloc(dev, BITS_TO_LONGS(qm->qp_num),
-					     sizeof(long), GFP_KERNEL);
-		qm->qp_array = devm_kcalloc(dev, qm->qp_num,
-					    sizeof(struct hisi_qp *),
-					    GFP_KERNEL);
-		if (!qm->qp_bitmap || !qm->qp_array)
-			return -ENOMEM;
+	ret = __hisi_qm_start(qm);
+	if (!ret)
+		atomic_set(&qm->status.flags, QM_START);
+
+err_unlock:
+	up_write(&qm->qps_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_start);
+
+static int qm_restart(struct hisi_qm *qm)
+{
+	struct device *dev = &qm->pdev->dev;
+	struct hisi_qp *qp;
+	int ret, i;
+
+	ret = hisi_qm_start(qm);
+	if (ret < 0)
+		return ret;
+
+	down_write(&qm->qps_lock);
+	for (i = 0; i < qm->qp_num; i++) {
+		qp = &qm->qp_array[i];
+		if (atomic_read(&qp->qp_status.flags) == QP_STOP &&
+		    qp->is_resetting == true) {
+			ret = qm_start_qp_nolock(qp, 0);
+			if (ret < 0) {
+				dev_err(dev, "Failed to start qp%d!\n", i);
+
+				up_write(&qm->qps_lock);
+				return ret;
+			}
+			qp->is_resetting = false;
+		}
 	}
+	up_write(&qm->qps_lock);
 
-	if (!qm->use_dma_api) {
-		dev_dbg(&qm->pdev->dev, "qm delay start\n");
-		return 0;
-	} else if (!qm->qdma.va) {
-		qm->qdma.size = QMC_ALIGN(sizeof(struct qm_eqe) * QM_Q_DEPTH) +
-				QMC_ALIGN(sizeof(struct qm_aeqe) * QM_Q_DEPTH) +
-				QMC_ALIGN(sizeof(struct qm_sqc) * qm->qp_num) +
-				QMC_ALIGN(sizeof(struct qm_cqc) * qm->qp_num);
-		qm->qdma.va = dma_alloc_coherent(dev, qm->qdma.size,
-						 &qm->qdma.dma, GFP_KERNEL);
-		dev_dbg(dev, "allocate qm dma buf(va=%pK, dma=%pad, size=%zx)\n",
-			qm->qdma.va, &qm->qdma.dma, qm->qdma.size);
-		if (!qm->qdma.va)
-			return -ENOMEM;
+	return 0;
+}
+
+/* Stop started qps in reset flow */
+static int qm_stop_started_qp(struct hisi_qm *qm)
+{
+	struct device *dev = &qm->pdev->dev;
+	struct hisi_qp *qp;
+	int i, ret;
+
+	for (i = 0; i < qm->qp_num; i++) {
+		qp = &qm->qp_array[i];
+		if (qp && atomic_read(&qp->qp_status.flags) == QP_START) {
+			qp->is_resetting = true;
+			ret = qm_stop_qp_nolock(qp);
+			if (ret < 0) {
+				dev_err(dev, "Failed to stop qp%d!\n", i);
+				return ret;
+			}
+		}
 	}
 
-	return __hisi_qm_start(qm);
+	return 0;
+}
+
+/**
+ * This function clears all queues memory in a qm. Reset of accelerator can
+ * use this to clear queues.
+ */
+static void qm_clear_queues(struct hisi_qm *qm)
+{
+	struct hisi_qp *qp;
+	int i;
+
+	for (i = 0; i < qm->qp_num; i++) {
+		qp = &qm->qp_array[i];
+		if (qp->is_resetting)
+			memset(qp->qdma.va, 0, qp->qdma.size);
+	}
+
+	memset(qm->qdma.va, 0, qm->qdma.size);
 }
-EXPORT_SYMBOL_GPL(hisi_qm_start);
 
 /**
  * hisi_qm_stop() - Stop a qm.
@@ -1988,43 +2645,98 @@ EXPORT_SYMBOL_GPL(hisi_qm_start);
  */
 int hisi_qm_stop(struct hisi_qm *qm)
 {
-	struct device *dev;
-	struct hisi_qp *qp;
-	int ret = 0, i;
+	struct device *dev = &qm->pdev->dev;
+	int ret = 0;
 
-	if (!qm || !qm->pdev) {
-		WARN_ON(1);
-		return -EINVAL;
+	down_write(&qm->qps_lock);
+
+	if (!qm_avail_state(qm, QM_STOP)) {
+		ret = -EPERM;
+		goto err_unlock;
 	}
 
-	dev = &qm->pdev->dev;
+	if (qm->status.stop_reason == QM_SOFT_RESET ||
+	    qm->status.stop_reason == QM_FLR) {
+		ret = qm_stop_started_qp(qm);
+		if (ret < 0) {
+			dev_err(dev, "Failed to stop started qp!\n");
+			goto err_unlock;
+		}
+	}
 
 	/* Mask eq and aeq irq */
 	writel(0x1, qm->io_base + QM_VF_EQ_INT_MASK);
 	writel(0x1, qm->io_base + QM_VF_AEQ_INT_MASK);
 
-	/* Stop all qps belong to this qm */
-	for (i = 0; i < qm->qp_num; i++) {
-		qp = qm->qp_array[i];
-		if (qp) {
-			ret = hisi_qm_stop_qp(qp);
-			if (ret < 0) {
-				dev_err(dev, "Failed to stop qp%d!\n", i);
-				return -EBUSY;
-			}
-		}
-	}
-
 	if (qm->fun_type == QM_HW_PF) {
 		ret = hisi_qm_set_vft(qm, 0, 0, 0);
-		if (ret < 0)
+		if (ret < 0) {
 			dev_err(dev, "Failed to set vft!\n");
+			ret = -EBUSY;
+			goto err_unlock;
+		}
 	}
 
+	qm_clear_queues(qm);
+	atomic_set(&qm->status.flags, QM_STOP);
+
+err_unlock:
+	up_write(&qm->qps_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(hisi_qm_stop);
 
+static ssize_t qm_status_read(struct file *filp, char __user *buffer,
+			      size_t count, loff_t *pos)
+{
+	struct hisi_qm *qm = filp->private_data;
+	char buf[QM_DBG_READ_LEN];
+	int val, cp_len, len;
+
+	if (*pos)
+		return 0;
+
+	if (count < QM_DBG_READ_LEN)
+		return -ENOSPC;
+
+	val = atomic_read(&qm->status.flags);
+	len = snprintf(buf, QM_DBG_READ_LEN, "%s\n", qm_s[val]);
+	if (!len)
+		return -EFAULT;
+
+	cp_len = copy_to_user(buffer, buf, len);
+	if (cp_len)
+		return -EFAULT;
+
+	return (*pos = len);
+}
+
+static const struct file_operations qm_status_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = qm_status_read,
+};
+
+static int qm_debugfs_atomic64_set(void *data, u64 val)
+{
+	if (val)
+		return -EINVAL;
+
+	atomic64_set((atomic64_t *)data, 0);
+
+	return 0;
+}
+
+static int qm_debugfs_atomic64_get(void *data, u64 *val)
+{
+	*val = atomic64_read((atomic64_t *)data);
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(qm_atomic64_ops, qm_debugfs_atomic64_get,
+			 qm_debugfs_atomic64_set, "%llu\n");
+
 /**
  * hisi_qm_debug_init() - Initialize qm related debugfs files.
  * @qm: The qm for which we want to add debugfs files.
@@ -2033,7 +2745,9 @@ EXPORT_SYMBOL_GPL(hisi_qm_stop);
  */
 int hisi_qm_debug_init(struct hisi_qm *qm)
 {
+	struct qm_dfx *dfx = &qm->debug.dfx;
 	struct dentry *qm_d;
+	void *data;
 	int i, ret;
 
 	qm_d = debugfs_create_dir("qm", qm->debug.debug_root);
@@ -2047,7 +2761,20 @@ int hisi_qm_debug_init(struct hisi_qm *qm)
 				goto failed_to_create;
 			}
 
-	debugfs_create_file("qm_regs", 0444, qm->debug.qm_d, qm, &qm_regs_fops);
+	debugfs_create_file("regs", 0444, qm->debug.qm_d, qm, &qm_regs_fops);
+
+	debugfs_create_file("cmd", 0444, qm->debug.qm_d, qm, &qm_cmd_fops);
+
+	debugfs_create_file("status", 0444, qm->debug.qm_d, qm,
+			&qm_status_fops);
+	for (i = 0; i < ARRAY_SIZE(qm_dfx_files); i++) {
+		data = (atomic64_t *)((uintptr_t)dfx + qm_dfx_files[i].offset);
+		debugfs_create_file(qm_dfx_files[i].name,
+			0644,
+			qm_d,
+			data,
+			&qm_atomic64_ops);
+	}
 
 	return 0;
 
@@ -2095,8 +2822,7 @@ static void qm_hw_error_init(struct hisi_qm *qm)
 		return;
 	}
 
-	qm->ops->hw_error_init(qm, err_info->ce, err_info->nfe,
-			       err_info->fe, err_info->msi);
+	qm->ops->hw_error_init(qm, err_info->ce, err_info->nfe, err_info->fe);
 }
 
 static void qm_hw_error_uninit(struct hisi_qm *qm)
@@ -2109,36 +2835,17 @@ static void qm_hw_error_uninit(struct hisi_qm *qm)
 	qm->ops->hw_error_uninit(qm);
 }
 
-static pci_ers_result_t qm_hw_error_handle(struct hisi_qm *qm)
+static enum acc_err_result qm_hw_error_handle(struct hisi_qm *qm)
 {
 	if (!qm->ops->hw_error_handle) {
 		dev_err(&qm->pdev->dev, "QM doesn't support hw error report!\n");
-		return PCI_ERS_RESULT_NONE;
+		return ACC_ERR_NONE;
 	}
 
 	return qm->ops->hw_error_handle(qm);
 }
 
 /**
- * hisi_qm_get_hw_version() - Get hardware version of a qm.
- * @pdev: The device which hardware version we want to get.
- *
- * This function gets the hardware version of a qm. Return QM_HW_UNKNOWN
- * if the hardware version is not supported.
- */
-enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev)
-{
-	switch (pdev->revision) {
-	case QM_HW_V1:
-	case QM_HW_V2:
-		return pdev->revision;
-	default:
-		return QM_HW_UNKNOWN;
-	}
-}
-EXPORT_SYMBOL_GPL(hisi_qm_get_hw_version);
-
-/**
  * hisi_qm_dev_err_init() - Initialize device error configuration.
  * @qm: The qm for which we want to do error initialization.
  *
@@ -2299,34 +3006,163 @@ err:
 }
 EXPORT_SYMBOL_GPL(hisi_qm_alloc_qps_node);
 
-static pci_ers_result_t qm_dev_err_handle(struct hisi_qm *qm)
+static int qm_vf_q_assign(struct hisi_qm *qm, u32 num_vfs)
+{
+	u32 remain_q_num, q_num, i, j;
+	u32 q_base = qm->qp_num;
+	int ret;
+
+	if (!num_vfs)
+		return -EINVAL;
+
+	remain_q_num = qm->ctrl_qp_num - qm->qp_num;
+
+	/* If remain queues not enough, return error. */
+	if (qm->ctrl_qp_num < qm->qp_num || remain_q_num < num_vfs)
+		return -EINVAL;
+
+	q_num = remain_q_num / num_vfs;
+	for (i = 1; i <= num_vfs; i++) {
+		if (i == num_vfs)
+			q_num += remain_q_num % num_vfs;
+		ret = hisi_qm_set_vft(qm, i, q_base, q_num);
+		if (ret) {
+			for (j = i; j > 0; j--)
+				hisi_qm_set_vft(qm, j, 0, 0);
+			return ret;
+		}
+		q_base += q_num;
+	}
+
+	return 0;
+}
+
+static int qm_clear_vft_config(struct hisi_qm *qm)
+{
+	int ret;
+	u32 i;
+
+	for (i = 1; i <= qm->vfs_num; i++) {
+		ret = hisi_qm_set_vft(qm, i, 0, 0);
+		if (ret)
+			return ret;
+	}
+	qm->vfs_num = 0;
+
+	return 0;
+}
+
+/**
+ * hisi_qm_sriov_enable() - enable virtual functions
+ * @pdev: the PCIe device
+ * @max_vfs: the number of virtual functions to enable
+ *
+ * Returns the number of enabled VFs. If there are VFs enabled already or
+ * max_vfs is more than the total number of device can be enabled, returns
+ * failure.
+ */
+int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs)
+{
+	struct hisi_qm *qm = pci_get_drvdata(pdev);
+	int pre_existing_vfs, num_vfs, total_vfs, ret;
+
+	total_vfs = pci_sriov_get_totalvfs(pdev);
+	pre_existing_vfs = pci_num_vf(pdev);
+	if (pre_existing_vfs) {
+		pci_err(pdev, "%d VFs already enabled. Please disable pre-enabled VFs!\n",
+			pre_existing_vfs);
+		return 0;
+	}
+
+	num_vfs = min_t(int, max_vfs, total_vfs);
+	ret = qm_vf_q_assign(qm, num_vfs);
+	if (ret) {
+		pci_err(pdev, "Can't assign queues for VF!\n");
+		return ret;
+	}
+
+	qm->vfs_num = num_vfs;
+
+	ret = pci_enable_sriov(pdev, num_vfs);
+	if (ret) {
+		pci_err(pdev, "Can't enable VF!\n");
+		qm_clear_vft_config(qm);
+		return ret;
+	}
+
+	pci_info(pdev, "VF enabled, vfs_num(=%d)!\n", num_vfs);
+
+	return num_vfs;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_sriov_enable);
+
+/**
+ * hisi_qm_sriov_disable - disable virtual functions
+ * @pdev: the PCI device
+ *
+ * Return failure if there are VFs assigned already.
+ */
+int hisi_qm_sriov_disable(struct pci_dev *pdev)
+{
+	struct hisi_qm *qm = pci_get_drvdata(pdev);
+
+	if (pci_vfs_assigned(pdev)) {
+		pci_err(pdev, "Failed to disable VFs as VFs are assigned!\n");
+		return -EPERM;
+	}
+
+	/* remove in hpre_pci_driver will be called to free VF resources */
+	pci_disable_sriov(pdev);
+	return qm_clear_vft_config(qm);
+}
+EXPORT_SYMBOL_GPL(hisi_qm_sriov_disable);
+
+/**
+ * hisi_qm_sriov_configure - configure the number of VFs
+ * @pdev: The PCI device
+ * @num_vfs: The number of VFs need enabled
+ *
+ * Enable SR-IOV according to num_vfs, 0 means disable.
+ */
+int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	if (num_vfs == 0)
+		return hisi_qm_sriov_disable(pdev);
+	else
+		return hisi_qm_sriov_enable(pdev, num_vfs);
+}
+EXPORT_SYMBOL_GPL(hisi_qm_sriov_configure);
+
+static enum acc_err_result qm_dev_err_handle(struct hisi_qm *qm)
 {
 	u32 err_sts;
 
 	if (!qm->err_ini->get_dev_hw_err_status) {
 		dev_err(&qm->pdev->dev, "Device doesn't support get hw error status!\n");
-		return PCI_ERS_RESULT_NONE;
+		return ACC_ERR_NONE;
 	}
 
 	/* get device hardware error status */
 	err_sts = qm->err_ini->get_dev_hw_err_status(qm);
 	if (err_sts) {
+		if (err_sts & qm->err_ini->err_info.ecc_2bits_mask)
+			qm->err_status.is_dev_ecc_mbit = true;
+
 		if (!qm->err_ini->log_dev_hw_err) {
 			dev_err(&qm->pdev->dev, "Device doesn't support log hw error!\n");
-			return PCI_ERS_RESULT_NEED_RESET;
+			return ACC_ERR_NEED_RESET;
 		}
 
 		qm->err_ini->log_dev_hw_err(qm, err_sts);
-		return PCI_ERS_RESULT_NEED_RESET;
+		return ACC_ERR_NEED_RESET;
 	}
 
-	return PCI_ERS_RESULT_RECOVERED;
+	return ACC_ERR_RECOVERED;
 }
 
-static pci_ers_result_t qm_process_dev_error(struct pci_dev *pdev)
+static enum acc_err_result qm_process_dev_error(struct hisi_qm *qm)
 {
-	struct hisi_qm *qm = pci_get_drvdata(pdev);
-	pci_ers_result_t qm_ret, dev_ret;
+	enum acc_err_result qm_ret, dev_ret;
 
 	/* log qm error */
 	qm_ret = qm_hw_error_handle(qm);
@@ -2334,9 +3170,9 @@ static pci_ers_result_t qm_process_dev_error(struct pci_dev *pdev)
 	/* log device error */
 	dev_ret = qm_dev_err_handle(qm);
 
-	return (qm_ret == PCI_ERS_RESULT_NEED_RESET ||
-		dev_ret == PCI_ERS_RESULT_NEED_RESET) ?
-		PCI_ERS_RESULT_NEED_RESET : PCI_ERS_RESULT_RECOVERED;
+	return (qm_ret == ACC_ERR_NEED_RESET ||
+		dev_ret == ACC_ERR_NEED_RESET) ?
+		ACC_ERR_NEED_RESET : ACC_ERR_RECOVERED;
 }
 
 /**
@@ -2350,6 +3186,9 @@ static pci_ers_result_t qm_process_dev_error(struct pci_dev *pdev)
 pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev,
 					  pci_channel_state_t state)
 {
+	struct hisi_qm *qm = pci_get_drvdata(pdev);
+	enum acc_err_result ret;
+
 	if (pdev->is_virtfn)
 		return PCI_ERS_RESULT_NONE;
 
@@ -2357,10 +3196,756 @@ pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev,
 	if (state == pci_channel_io_perm_failure)
 		return PCI_ERS_RESULT_DISCONNECT;
 
-	return qm_process_dev_error(pdev);
+	ret = qm_process_dev_error(qm);
+	if (ret == ACC_ERR_NEED_RESET)
+		return PCI_ERS_RESULT_NEED_RESET;
+
+	return PCI_ERS_RESULT_RECOVERED;
 }
 EXPORT_SYMBOL_GPL(hisi_qm_dev_err_detected);
 
+static int qm_get_hw_error_status(struct hisi_qm *qm)
+{
+	return readl(qm->io_base + QM_ABNORMAL_INT_STATUS);
+}
+
+static int qm_check_req_recv(struct hisi_qm *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	int ret;
+	u32 val;
+
+	writel(ACC_VENDOR_ID_VALUE, qm->io_base + QM_PEH_VENDOR_ID);
+	ret = readl_relaxed_poll_timeout(qm->io_base + QM_PEH_VENDOR_ID, val,
+					 (val == ACC_VENDOR_ID_VALUE),
+					 POLL_PERIOD, POLL_TIMEOUT);
+	if (ret) {
+		dev_err(&pdev->dev, "Fails to read QM reg!\n");
+		return ret;
+	}
+
+	writel(PCI_VENDOR_ID_HUAWEI, qm->io_base + QM_PEH_VENDOR_ID);
+	ret = readl_relaxed_poll_timeout(qm->io_base + QM_PEH_VENDOR_ID, val,
+					 (val == PCI_VENDOR_ID_HUAWEI),
+					 POLL_PERIOD, POLL_TIMEOUT);
+	if (ret)
+		dev_err(&pdev->dev, "Fails to read QM reg in the second time!\n");
+
+	return ret;
+}
+
+static int qm_set_pf_mse(struct hisi_qm *qm, bool set)
+{
+	struct pci_dev *pdev = qm->pdev;
+	u16 cmd;
+	int i;
+
+	pci_read_config_word(pdev, PCI_COMMAND, &cmd);
+	if (set)
+		cmd |= PCI_COMMAND_MEMORY;
+	else
+		cmd &= ~PCI_COMMAND_MEMORY;
+
+	pci_write_config_word(pdev, PCI_COMMAND, cmd);
+	for (i = 0; i < MAX_WAIT_COUNTS; i++) {
+		pci_read_config_word(pdev, PCI_COMMAND, &cmd);
+		if (set == ((cmd & PCI_COMMAND_MEMORY) >> 1))
+			return 0;
+
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int qm_set_vf_mse(struct hisi_qm *qm, bool set)
+{
+	struct pci_dev *pdev = qm->pdev;
+	u16 sriov_ctrl;
+	int pos;
+	int i;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
+	pci_read_config_word(pdev, pos + PCI_SRIOV_CTRL, &sriov_ctrl);
+	if (set)
+		sriov_ctrl |= PCI_SRIOV_CTRL_MSE;
+	else
+		sriov_ctrl &= ~PCI_SRIOV_CTRL_MSE;
+	pci_write_config_word(pdev, pos + PCI_SRIOV_CTRL, sriov_ctrl);
+
+	for (i = 0; i < MAX_WAIT_COUNTS; i++) {
+		pci_read_config_word(pdev, pos + PCI_SRIOV_CTRL, &sriov_ctrl);
+		if (set == (sriov_ctrl & PCI_SRIOV_CTRL_MSE) >>
+		    ACC_PEH_SRIOV_CTRL_VF_MSE_SHIFT)
+			return 0;
+
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int qm_set_msi(struct hisi_qm *qm, bool set)
+{
+	struct pci_dev *pdev = qm->pdev;
+
+	if (set) {
+		pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_MASK_64,
+				       0);
+	} else {
+		pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_MASK_64,
+				       ACC_PEH_MSI_DISABLE);
+		if (qm->err_status.is_qm_ecc_mbit ||
+		    qm->err_status.is_dev_ecc_mbit)
+			return 0;
+
+		mdelay(1);
+		if (readl(qm->io_base + QM_PEH_DFX_INFO0))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int qm_vf_reset_prepare(struct hisi_qm *qm)
+{
+	struct hisi_qm_list *qm_list = qm->qm_list;
+	int stop_reason = qm->status.stop_reason;
+	struct pci_dev *pdev = qm->pdev;
+	struct pci_dev *virtfn;
+	struct hisi_qm *vf_qm;
+	int ret = 0;
+
+	mutex_lock(&qm_list->lock);
+	list_for_each_entry(vf_qm, &qm_list->list, list) {
+		virtfn = vf_qm->pdev;
+		if (virtfn == pdev)
+			continue;
+
+		if (pci_physfn(virtfn) == pdev) {
+			vf_qm->status.stop_reason = stop_reason;
+			ret = hisi_qm_stop(vf_qm);
+			if (ret)
+				goto stop_fail;
+		}
+	}
+
+stop_fail:
+	mutex_unlock(&qm_list->lock);
+	return ret;
+}
+
+static int qm_reset_prepare_ready(struct hisi_qm *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	struct hisi_qm *pf_qm = pci_get_drvdata(pci_physfn(pdev));
+	int delay = 0;
+
+	/* All reset requests need to be queued for processing */
+	while (test_and_set_bit(QM_DEV_RESET_FLAG, &pf_qm->reset_flag)) {
+		msleep(++delay);
+		if (delay > QM_RESET_WAIT_TIMEOUT)
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int qm_controller_reset_prepare(struct hisi_qm *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	int ret;
+
+	ret = qm_reset_prepare_ready(qm);
+	if (ret) {
+		pci_err(pdev, "Controller reset not ready!\n");
+		return ret;
+	}
+
+	if (qm->vfs_num) {
+		ret = qm_vf_reset_prepare(qm);
+		if (ret) {
+			pci_err(pdev, "Fails to stop VFs!\n");
+			return ret;
+		}
+	}
+
+	qm->status.stop_reason = QM_SOFT_RESET;
+	ret = hisi_qm_stop(qm);
+	if (ret) {
+		pci_err(pdev, "Fails to stop QM!\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm)
+{
+	u32 nfe_enb = 0;
+
+	if (!qm->err_status.is_dev_ecc_mbit &&
+	    qm->err_status.is_qm_ecc_mbit &&
+	    qm->err_ini->close_axi_master_ooo) {
+
+		qm->err_ini->close_axi_master_ooo(qm);
+
+	} else if (qm->err_status.is_dev_ecc_mbit &&
+		   !qm->err_status.is_qm_ecc_mbit &&
+		   !qm->err_ini->close_axi_master_ooo) {
+
+		nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE);
+		writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE,
+		       qm->io_base + QM_RAS_NFE_ENABLE);
+		writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET);
+	}
+}
+
+static int qm_soft_reset(struct hisi_qm *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	int ret;
+	u32 val;
+
+	/* Ensure all doorbells and mailboxes received by QM */
+	ret = qm_check_req_recv(qm);
+	if (ret)
+		return ret;
+
+	if (qm->vfs_num) {
+		ret = qm_set_vf_mse(qm, false);
+		if (ret) {
+			pci_err(pdev, "Fails to disable vf MSE bit.\n");
+			return ret;
+		}
+	}
+
+	ret = qm_set_msi(qm, false);
+	if (ret) {
+		pci_err(pdev, "Fails to disable PEH MSI bit.\n");
+		return ret;
+	}
+
+	qm_dev_ecc_mbit_handle(qm);
+
+	/* OOO register set and check */
+	writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN,
+	       qm->io_base + ACC_MASTER_GLOBAL_CTRL);
+
+	/* If bus lock, reset chip */
+	ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN,
+					 val,
+					 (val == ACC_MASTER_TRANS_RETURN_RW),
+					 POLL_PERIOD, POLL_TIMEOUT);
+	if (ret) {
+		pci_emerg(pdev, "Bus lock! Please reset system.\n");
+		return ret;
+	}
+
+	ret = qm_set_pf_mse(qm, false);
+	if (ret) {
+		pci_err(pdev, "Fails to disable pf MSE bit.\n");
+		return ret;
+	}
+
+	/* The reset related sub-control registers are not in PCI BAR */
+	if (ACPI_HANDLE(&pdev->dev)) {
+		unsigned long long value = 0;
+		acpi_status s;
+
+		s = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
+					  qm->err_ini->err_info.acpi_rst,
+					  NULL, &value);
+		if (ACPI_FAILURE(s)) {
+			pci_err(pdev, "NO controller reset method!\n");
+			return -EIO;
+		}
+
+		if (value) {
+			pci_err(pdev, "Reset step %llu failed!\n", value);
+			return -EIO;
+		}
+	} else {
+		pci_err(pdev, "No reset method!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int qm_vf_reset_done(struct hisi_qm *qm)
+{
+	struct hisi_qm_list *qm_list = qm->qm_list;
+	struct pci_dev *pdev = qm->pdev;
+	struct pci_dev *virtfn;
+	struct hisi_qm *vf_qm;
+	int ret = 0;
+
+	mutex_lock(&qm_list->lock);
+	list_for_each_entry(vf_qm, &qm_list->list, list) {
+		virtfn = vf_qm->pdev;
+		if (virtfn == pdev)
+			continue;
+
+		if (pci_physfn(virtfn) == pdev) {
+			ret = qm_restart(vf_qm);
+			if (ret)
+				goto restart_fail;
+		}
+	}
+
+restart_fail:
+	mutex_unlock(&qm_list->lock);
+	return ret;
+}
+
+static int qm_get_dev_err_status(struct hisi_qm *qm)
+{
+	return qm->err_ini->get_dev_hw_err_status(qm);
+}
+
+static int qm_dev_hw_init(struct hisi_qm *qm)
+{
+	return qm->err_ini->hw_init(qm);
+}
+
+static void qm_restart_prepare(struct hisi_qm *qm)
+{
+	u32 value;
+
+	if (!qm->err_status.is_qm_ecc_mbit &&
+	    !qm->err_status.is_dev_ecc_mbit)
+		return;
+
+	/* temporarily close the OOO port used for PEH to write out MSI */
+	value = readl(qm->io_base + ACC_AM_CFG_PORT_WR_EN);
+	writel(value & ~qm->err_ini->err_info.msi_wr_port,
+	       qm->io_base + ACC_AM_CFG_PORT_WR_EN);
+
+	/* clear dev ecc 2bit error source if having */
+	value = qm_get_dev_err_status(qm) &
+		qm->err_ini->err_info.ecc_2bits_mask;
+	if (value && qm->err_ini->clear_dev_hw_err_status)
+		qm->err_ini->clear_dev_hw_err_status(qm, value);
+
+	/* clear QM ecc mbit error source */
+	writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SOURCE);
+
+	/* clear AM Reorder Buffer ecc mbit source */
+	writel(ACC_ROB_ECC_ERR_MULTPL, qm->io_base + ACC_AM_ROB_ECC_INT_STS);
+
+	if (qm->err_ini->open_axi_master_ooo)
+		qm->err_ini->open_axi_master_ooo(qm);
+}
+
+static void qm_restart_done(struct hisi_qm *qm)
+{
+	u32 value;
+
+	if (!qm->err_status.is_qm_ecc_mbit &&
+	    !qm->err_status.is_dev_ecc_mbit)
+		return;
+
+	/* open the OOO port for PEH to write out MSI */
+	value = readl(qm->io_base + ACC_AM_CFG_PORT_WR_EN);
+	value |= qm->err_ini->err_info.msi_wr_port;
+	writel(value, qm->io_base + ACC_AM_CFG_PORT_WR_EN);
+
+	qm->err_status.is_qm_ecc_mbit = false;
+	qm->err_status.is_dev_ecc_mbit = false;
+}
+
+static int qm_controller_reset_done(struct hisi_qm *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	int ret;
+
+	ret = qm_set_msi(qm, true);
+	if (ret) {
+		pci_err(pdev, "Fails to enable PEH MSI bit!\n");
+		return ret;
+	}
+
+	ret = qm_set_pf_mse(qm, true);
+	if (ret) {
+		pci_err(pdev, "Fails to enable pf MSE bit!\n");
+		return ret;
+	}
+
+	if (qm->vfs_num) {
+		ret = qm_set_vf_mse(qm, true);
+		if (ret) {
+			pci_err(pdev, "Fails to enable vf MSE bit!\n");
+			return ret;
+		}
+	}
+
+	ret = qm_dev_hw_init(qm);
+	if (ret) {
+		pci_err(pdev, "Failed to init device\n");
+		return ret;
+	}
+
+	qm_restart_prepare(qm);
+
+	ret = qm_restart(qm);
+	if (ret) {
+		pci_err(pdev, "Failed to start QM!\n");
+		return ret;
+	}
+
+	if (qm->vfs_num) {
+		ret = qm_vf_q_assign(qm, qm->vfs_num);
+		if (ret) {
+			pci_err(pdev, "Failed to assign queue!\n");
+			return ret;
+		}
+	}
+
+	ret = qm_vf_reset_done(qm);
+	if (ret) {
+		pci_err(pdev, "Failed to start VFs!\n");
+		return -EPERM;
+	}
+
+	hisi_qm_dev_err_init(qm);
+	qm_restart_done(qm);
+
+	clear_bit(QM_DEV_RESET_FLAG, &qm->reset_flag);
+
+	return 0;
+}
+
+static int qm_controller_reset(struct hisi_qm *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	int ret;
+
+	pci_info(pdev, "Controller resetting...\n");
+
+	ret = qm_controller_reset_prepare(qm);
+	if (ret)
+		return ret;
+
+	ret = qm_soft_reset(qm);
+	if (ret) {
+		pci_err(pdev, "Controller reset failed (%d)\n", ret);
+		return ret;
+	}
+
+	ret = qm_controller_reset_done(qm);
+	if (ret)
+		return ret;
+
+	pci_info(pdev, "Controller reset complete\n");
+
+	return 0;
+}
+
+/**
+ * hisi_qm_dev_slot_reset() - slot reset
+ * @pdev: the PCIe device
+ *
+ * This function offers QM relate PCIe device reset interface. Drivers which
+ * use QM can use this function as slot_reset in its struct pci_error_handlers.
+ */
+pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev)
+{
+	struct hisi_qm *qm = pci_get_drvdata(pdev);
+	int ret;
+
+	if (pdev->is_virtfn)
+		return PCI_ERS_RESULT_RECOVERED;
+
+	pci_aer_clear_nonfatal_status(pdev);
+
+	/* reset pcie device controller */
+	ret = qm_controller_reset(qm);
+	if (ret) {
+		pci_err(pdev, "Controller reset failed (%d)\n", ret);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_dev_slot_reset);
+
+/* check the interrupt is ecc-mbit error or not */
+static int qm_check_dev_error(struct hisi_qm *qm)
+{
+	int ret;
+
+	if (qm->fun_type == QM_HW_VF)
+		return 0;
+
+	ret = qm_get_hw_error_status(qm) & QM_ECC_MBIT;
+	if (ret)
+		return ret;
+
+	return (qm_get_dev_err_status(qm) &
+		qm->err_ini->err_info.ecc_2bits_mask);
+}
+
+void hisi_qm_reset_prepare(struct pci_dev *pdev)
+{
+	struct hisi_qm *pf_qm = pci_get_drvdata(pci_physfn(pdev));
+	struct hisi_qm *qm = pci_get_drvdata(pdev);
+	u32 delay = 0;
+	int ret;
+
+	hisi_qm_dev_err_uninit(pf_qm);
+
+	/*
+	 * Check whether there is an ECC mbit error, If it occurs, need to
+	 * wait for soft reset to fix it.
+	 */
+	while (qm_check_dev_error(pf_qm)) {
+		msleep(++delay);
+		if (delay > QM_RESET_WAIT_TIMEOUT)
+			return;
+	}
+
+	ret = qm_reset_prepare_ready(qm);
+	if (ret) {
+		pci_err(pdev, "FLR not ready!\n");
+		return;
+	}
+
+	if (qm->vfs_num) {
+		ret = qm_vf_reset_prepare(qm);
+		if (ret) {
+			pci_err(pdev, "Failed to prepare reset, ret = %d.\n",
+				ret);
+			return;
+		}
+	}
+
+	ret = hisi_qm_stop(qm);
+	if (ret) {
+		pci_err(pdev, "Failed to stop QM, ret = %d.\n", ret);
+		return;
+	}
+
+	pci_info(pdev, "FLR resetting...\n");
+}
+EXPORT_SYMBOL_GPL(hisi_qm_reset_prepare);
+
+static bool qm_flr_reset_complete(struct pci_dev *pdev)
+{
+	struct pci_dev *pf_pdev = pci_physfn(pdev);
+	struct hisi_qm *qm = pci_get_drvdata(pf_pdev);
+	u32 id;
+
+	pci_read_config_dword(qm->pdev, PCI_COMMAND, &id);
+	if (id == QM_PCI_COMMAND_INVALID) {
+		pci_err(pdev, "Device can not be used!\n");
+		return false;
+	}
+
+	clear_bit(QM_DEV_RESET_FLAG, &qm->reset_flag);
+
+	return true;
+}
+
+void hisi_qm_reset_done(struct pci_dev *pdev)
+{
+	struct hisi_qm *pf_qm = pci_get_drvdata(pci_physfn(pdev));
+	struct hisi_qm *qm = pci_get_drvdata(pdev);
+	int ret;
+
+	hisi_qm_dev_err_init(pf_qm);
+
+	ret = qm_restart(qm);
+	if (ret) {
+		pci_err(pdev, "Failed to start QM, ret = %d.\n", ret);
+		goto flr_done;
+	}
+
+	if (qm->fun_type == QM_HW_PF) {
+		ret = qm_dev_hw_init(qm);
+		if (ret) {
+			pci_err(pdev, "Failed to init PF, ret = %d.\n", ret);
+			goto flr_done;
+		}
+
+		if (!qm->vfs_num)
+			goto flr_done;
+
+		ret = qm_vf_q_assign(qm, qm->vfs_num);
+		if (ret) {
+			pci_err(pdev, "Failed to assign VFs, ret = %d.\n", ret);
+			goto flr_done;
+		}
+
+		ret = qm_vf_reset_done(qm);
+		if (ret) {
+			pci_err(pdev, "Failed to start VFs, ret = %d.\n", ret);
+			goto flr_done;
+		}
+	}
+
+flr_done:
+	if (qm_flr_reset_complete(pdev))
+		pci_info(pdev, "FLR reset complete\n");
+}
+EXPORT_SYMBOL_GPL(hisi_qm_reset_done);
+
+static irqreturn_t qm_abnormal_irq(int irq, void *data)
+{
+	struct hisi_qm *qm = data;
+	enum acc_err_result ret;
+
+	atomic64_inc(&qm->debug.dfx.abnormal_irq_cnt);
+	ret = qm_process_dev_error(qm);
+	if (ret == ACC_ERR_NEED_RESET)
+		schedule_work(&qm->rst_work);
+
+	return IRQ_HANDLED;
+}
+
+static int qm_irq_register(struct hisi_qm *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	int ret;
+
+	ret = request_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR),
+			  qm_irq, IRQF_SHARED, qm->dev_name, qm);
+	if (ret)
+		return ret;
+
+	if (qm->ver != QM_HW_V1) {
+		ret = request_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR),
+				  qm_aeq_irq, IRQF_SHARED, qm->dev_name, qm);
+		if (ret)
+			goto err_aeq_irq;
+
+		if (qm->fun_type == QM_HW_PF) {
+			ret = request_irq(pci_irq_vector(pdev,
+					  QM_ABNORMAL_EVENT_IRQ_VECTOR),
+					  qm_abnormal_irq, IRQF_SHARED,
+					  qm->dev_name, qm);
+			if (ret)
+				goto err_abonormal_irq;
+		}
+	}
+
+	return 0;
+
+err_abonormal_irq:
+	free_irq(pci_irq_vector(pdev, QM_AEQ_EVENT_IRQ_VECTOR), qm);
+err_aeq_irq:
+	free_irq(pci_irq_vector(pdev, QM_EQ_EVENT_IRQ_VECTOR), qm);
+	return ret;
+}
+
+static void hisi_qm_controller_reset(struct work_struct *rst_work)
+{
+	struct hisi_qm *qm = container_of(rst_work, struct hisi_qm, rst_work);
+	int ret;
+
+	/* reset pcie device controller */
+	ret = qm_controller_reset(qm);
+	if (ret)
+		dev_err(&qm->pdev->dev, "controller reset failed (%d)\n", ret);
+
+}
+
+/**
+ * hisi_qm_init() - Initialize configures about qm.
+ * @qm: The qm needing init.
+ *
+ * This function init qm, then we can call hisi_qm_start to put qm into work.
+ */
+int hisi_qm_init(struct hisi_qm *qm)
+{
+	struct pci_dev *pdev = qm->pdev;
+	struct device *dev = &pdev->dev;
+	unsigned int num_vec;
+	int ret;
+
+	hisi_qm_pre_init(qm);
+
+	ret = qm_alloc_uacce(qm);
+	if (ret < 0)
+		dev_warn(&pdev->dev, "fail to alloc uacce (%d)\n", ret);
+
+	ret = pci_enable_device_mem(pdev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to enable device mem!\n");
+		goto err_remove_uacce;
+	}
+
+	ret = pci_request_mem_regions(pdev, qm->dev_name);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to request mem regions!\n");
+		goto err_disable_pcidev;
+	}
+
+	qm->phys_base = pci_resource_start(pdev, PCI_BAR_2);
+	qm->phys_size = pci_resource_len(qm->pdev, PCI_BAR_2);
+	qm->io_base = ioremap(qm->phys_base, qm->phys_size);
+	if (!qm->io_base) {
+		ret = -EIO;
+		goto err_release_mem_regions;
+	}
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (ret < 0)
+		goto err_iounmap;
+	pci_set_master(pdev);
+
+	if (!qm->ops->get_irq_num) {
+		ret = -EOPNOTSUPP;
+		goto err_iounmap;
+	}
+	num_vec = qm->ops->get_irq_num(qm);
+	ret = pci_alloc_irq_vectors(pdev, num_vec, num_vec, PCI_IRQ_MSI);
+	if (ret < 0) {
+		dev_err(dev, "Failed to enable MSI vectors!\n");
+		goto err_iounmap;
+	}
+
+	ret = qm_irq_register(qm);
+	if (ret)
+		goto err_free_irq_vectors;
+
+	if (qm->fun_type == QM_HW_VF && qm->ver != QM_HW_V1) {
+		/* v2 starts to support get vft by mailbox */
+		ret = hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num);
+		if (ret)
+			goto err_irq_unregister;
+	}
+
+	ret = hisi_qm_memory_init(qm);
+	if (ret)
+		goto err_irq_unregister;
+
+	INIT_WORK(&qm->work, qm_work_process);
+	if (qm->fun_type == QM_HW_PF)
+		INIT_WORK(&qm->rst_work, hisi_qm_controller_reset);
+
+	atomic_set(&qm->status.flags, QM_INIT);
+
+	return 0;
+
+err_irq_unregister:
+	qm_irq_unregister(qm);
+err_free_irq_vectors:
+	pci_free_irq_vectors(pdev);
+err_iounmap:
+	iounmap(qm->io_base);
+err_release_mem_regions:
+	pci_release_mem_regions(pdev);
+err_disable_pcidev:
+	pci_disable_device(pdev);
+err_remove_uacce:
+	uacce_remove(qm->uacce);
+	qm->uacce = NULL;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_init);
+
+
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Zhou Wang <wangzhou1@hisilicon.com>");
 MODULE_DESCRIPTION("HiSilicon Accelerator queue manager driver");
diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h
index ec5b6f48db6c..0a351de8d838 100644
--- a/drivers/crypto/hisilicon/qm.h
+++ b/drivers/crypto/hisilicon/qm.h
@@ -8,6 +8,10 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 
+#define QM_QNUM_V1			4096
+#define QM_QNUM_V2			1024
+#define QM_MAX_VFS_NUM_V2		63
+
 /* qm user domain */
 #define QM_ARUSER_M_CFG_1		0x100088
 #define AXUSER_SNOOP_ENABLE		BIT(30)
@@ -70,7 +74,7 @@
 
 #define QM_BASE_NFE	(QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \
 			 QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \
-			 QM_OF_FIFO_OF)
+			 QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID)
 #define QM_BASE_CE			QM_ECC_1BIT
 
 #define QM_Q_DEPTH			1024
@@ -80,14 +84,31 @@
 /* page number for queue file region */
 #define QM_DOORBELL_PAGE_NR		1
 
+enum qm_stop_reason {
+	QM_NORMAL,
+	QM_SOFT_RESET,
+	QM_FLR,
+};
+
+enum qm_state {
+	QM_INIT = 0,
+	QM_START,
+	QM_CLOSE,
+	QM_STOP,
+};
+
 enum qp_state {
+	QP_INIT = 1,
+	QP_START,
 	QP_STOP,
+	QP_CLOSE,
 };
 
 enum qm_hw_ver {
 	QM_HW_UNKNOWN = -1,
 	QM_HW_V1 = 0x20,
 	QM_HW_V2 = 0x21,
+	QM_HW_V3 = 0x30,
 };
 
 enum qm_fun_type {
@@ -101,6 +122,14 @@ enum qm_debug_file {
 	DEBUG_FILE_NUM,
 };
 
+struct qm_dfx {
+	atomic64_t err_irq_cnt;
+	atomic64_t aeq_irq_cnt;
+	atomic64_t abnormal_irq_cnt;
+	atomic64_t create_qp_err_cnt;
+	atomic64_t mb_err_cnt;
+};
+
 struct debugfs_file {
 	enum qm_debug_file index;
 	struct mutex lock;
@@ -109,6 +138,9 @@ struct debugfs_file {
 
 struct qm_debug {
 	u32 curr_qm_qp_num;
+	u32 sqe_mask_offset;
+	u32 sqe_mask_len;
+	struct qm_dfx dfx;
 	struct dentry *debug_root;
 	struct dentry *qm_d;
 	struct debugfs_file files[DEBUG_FILE_NUM];
@@ -125,22 +157,34 @@ struct hisi_qm_status {
 	bool eqc_phase;
 	u32 aeq_head;
 	bool aeqc_phase;
-	unsigned long flags;
+	atomic_t flags;
+	int stop_reason;
 };
 
 struct hisi_qm;
 
 struct hisi_qm_err_info {
+	char *acpi_rst;
+	u32 msi_wr_port;
+	u32 ecc_2bits_mask;
 	u32 ce;
 	u32 nfe;
 	u32 fe;
-	u32 msi;
+};
+
+struct hisi_qm_err_status {
+	u32 is_qm_ecc_mbit;
+	u32 is_dev_ecc_mbit;
 };
 
 struct hisi_qm_err_ini {
+	int (*hw_init)(struct hisi_qm *qm);
 	void (*hw_err_enable)(struct hisi_qm *qm);
 	void (*hw_err_disable)(struct hisi_qm *qm);
 	u32 (*get_dev_hw_err_status)(struct hisi_qm *qm);
+	void (*clear_dev_hw_err_status)(struct hisi_qm *qm, u32 err_sts);
+	void (*open_axi_master_ooo)(struct hisi_qm *qm);
+	void (*close_axi_master_ooo)(struct hisi_qm *qm);
 	void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts);
 	struct hisi_qm_err_info err_info;
 };
@@ -161,7 +205,9 @@ struct hisi_qm {
 	u32 qp_num;
 	u32 qp_in_used;
 	u32 ctrl_qp_num;
+	u32 vfs_num;
 	struct list_head list;
+	struct hisi_qm_list *qm_list;
 
 	struct qm_dma qdma;
 	struct qm_sqc *sqc;
@@ -175,10 +221,12 @@ struct hisi_qm {
 
 	struct hisi_qm_status status;
 	const struct hisi_qm_err_ini *err_ini;
+	struct hisi_qm_err_status err_status;
+	unsigned long reset_flag;
 
-	rwlock_t qps_lock;
-	unsigned long *qp_bitmap;
-	struct hisi_qp **qp_array;
+	struct rw_semaphore qps_lock;
+	struct idr qp_idr;
+	struct hisi_qp *qp_array;
 
 	struct mutex mailbox_lock;
 
@@ -187,13 +235,12 @@ struct hisi_qm {
 	struct qm_debug debug;
 
 	u32 error_mask;
-	u32 msi_mask;
 
 	struct workqueue_struct *wq;
 	struct work_struct work;
+	struct work_struct rst_work;
 
 	const char *algs;
-	bool use_dma_api;
 	bool use_sva;
 	resource_size_t phys_base;
 	resource_size_t phys_size;
@@ -205,7 +252,7 @@ struct hisi_qp_status {
 	u16 sq_tail;
 	u16 cq_head;
 	bool cqc_phase;
-	unsigned long flags;
+	atomic_t flags;
 };
 
 struct hisi_qp_ops {
@@ -230,10 +277,58 @@ struct hisi_qp {
 	void (*event_cb)(struct hisi_qp *qp);
 
 	struct hisi_qm *qm;
+	bool is_resetting;
 	u16 pasid;
 	struct uacce_queue *uacce_q;
 };
 
+static inline int q_num_set(const char *val, const struct kernel_param *kp,
+			    unsigned int device)
+{
+	struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI,
+					      device, NULL);
+	u32 n, q_num;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+
+	if (!pdev) {
+		q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2);
+		pr_info("No device found currently, suppose queue number is %d\n",
+			q_num);
+	} else {
+		if (pdev->revision == QM_HW_V1)
+			q_num = QM_QNUM_V1;
+		else
+			q_num = QM_QNUM_V2;
+	}
+
+	ret = kstrtou32(val, 10, &n);
+	if (ret || !n || n > q_num)
+		return -EINVAL;
+
+	return param_set_int(val, kp);
+}
+
+static inline int vfs_num_set(const char *val, const struct kernel_param *kp)
+{
+	u32 n;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+
+	ret = kstrtou32(val, 10, &n);
+	if (ret < 0)
+		return ret;
+
+	if (n > QM_MAX_VFS_NUM_V2)
+		return -EINVAL;
+
+	return param_set_int(val, kp);
+}
+
 static inline void hisi_qm_init_list(struct hisi_qm_list *qm_list)
 {
 	INIT_LIST_HEAD(&qm_list->list);
@@ -267,14 +362,19 @@ void hisi_qm_release_qp(struct hisi_qp *qp);
 int hisi_qp_send(struct hisi_qp *qp, const void *msg);
 int hisi_qm_get_free_qp_num(struct hisi_qm *qm);
 int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number);
-int hisi_qm_set_vft(struct hisi_qm *qm, u32 fun_num, u32 base, u32 number);
 int hisi_qm_debug_init(struct hisi_qm *qm);
 enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev);
 void hisi_qm_debug_regs_clear(struct hisi_qm *qm);
+int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs);
+int hisi_qm_sriov_disable(struct pci_dev *pdev);
+int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs);
 void hisi_qm_dev_err_init(struct hisi_qm *qm);
 void hisi_qm_dev_err_uninit(struct hisi_qm *qm);
 pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev,
 					  pci_channel_state_t state);
+pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev);
+void hisi_qm_reset_prepare(struct pci_dev *pdev);
+void hisi_qm_reset_done(struct pci_dev *pdev);
 
 struct hisi_acc_sgl_pool;
 struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h
index 3598fa17beb2..7b64aca704d6 100644
--- a/drivers/crypto/hisilicon/sec2/sec.h
+++ b/drivers/crypto/hisilicon/sec2/sec.h
@@ -160,6 +160,10 @@ struct sec_debug_file {
 struct sec_dfx {
 	atomic64_t send_cnt;
 	atomic64_t recv_cnt;
+	atomic64_t send_busy_cnt;
+	atomic64_t err_bd_cnt;
+	atomic64_t invalid_req_cnt;
+	atomic64_t done_flag_cnt;
 };
 
 struct sec_debug {
@@ -172,7 +176,6 @@ struct sec_dev {
 	struct sec_debug debug;
 	u32 ctx_q_num;
 	bool iommu_used;
-	u32 num_vfs;
 	unsigned long status;
 };
 
diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c
index 7f1c6a31b82f..64614a9bdf21 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.c
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c
@@ -148,6 +148,7 @@ static int sec_aead_verify(struct sec_req *req)
 static void sec_req_cb(struct hisi_qp *qp, void *resp)
 {
 	struct sec_qp_ctx *qp_ctx = qp->qp_ctx;
+	struct sec_dfx *dfx = &qp_ctx->ctx->sec->debug.dfx;
 	struct sec_sqe *bd = resp;
 	struct sec_ctx *ctx;
 	struct sec_req *req;
@@ -157,11 +158,16 @@ static void sec_req_cb(struct hisi_qp *qp, void *resp)
 
 	type = bd->type_cipher_auth & SEC_TYPE_MASK;
 	if (unlikely(type != SEC_BD_TYPE2)) {
+		atomic64_inc(&dfx->err_bd_cnt);
 		pr_err("err bd type [%d]\n", type);
 		return;
 	}
 
 	req = qp_ctx->req_list[le16_to_cpu(bd->type2.tag)];
+	if (unlikely(!req)) {
+		atomic64_inc(&dfx->invalid_req_cnt);
+		return;
+	}
 	req->err_type = bd->type2.error_type;
 	ctx = req->ctx;
 	done = le16_to_cpu(bd->type2.done_flag) & SEC_DONE_MASK;
@@ -174,12 +180,13 @@ static void sec_req_cb(struct hisi_qp *qp, void *resp)
 			"err_type[%d],done[%d],flag[%d]\n",
 			req->err_type, done, flag);
 		err = -EIO;
+		atomic64_inc(&dfx->done_flag_cnt);
 	}
 
 	if (ctx->alg_type == SEC_AEAD && !req->c_req.encrypt)
 		err = sec_aead_verify(req);
 
-	atomic64_inc(&ctx->sec->debug.dfx.recv_cnt);
+	atomic64_inc(&dfx->recv_cnt);
 
 	ctx->req_op->buf_unmap(ctx, req);
 
@@ -200,10 +207,12 @@ static int sec_bd_send(struct sec_ctx *ctx, struct sec_req *req)
 		return -ENOBUFS;
 
 	if (!ret) {
-		if (req->fake_busy)
+		if (req->fake_busy) {
+			atomic64_inc(&ctx->sec->debug.dfx.send_busy_cnt);
 			ret = -EBUSY;
-		else
+		} else {
 			ret = -EINPROGRESS;
+		}
 	}
 
 	return ret;
@@ -832,7 +841,6 @@ static int sec_aead_auth_set_key(struct sec_auth_ctx *ctx,
 				 struct crypto_authenc_keys *keys)
 {
 	struct crypto_shash *hash_tfm = ctx->hash_tfm;
-	SHASH_DESC_ON_STACK(shash, hash_tfm);
 	int blocksize, ret;
 
 	if (!keys->authkeylen) {
@@ -842,8 +850,8 @@ static int sec_aead_auth_set_key(struct sec_auth_ctx *ctx,
 
 	blocksize = crypto_shash_blocksize(hash_tfm);
 	if (keys->authkeylen > blocksize) {
-		ret = crypto_shash_digest(shash, keys->authkey,
-					  keys->authkeylen, ctx->a_key);
+		ret = crypto_shash_tfm_digest(hash_tfm, keys->authkey,
+					      keys->authkeylen, ctx->a_key);
 		if (ret) {
 			pr_err("hisi_sec2: aead auth digest error!\n");
 			return -EINVAL;
diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c
index 1f54ebe164b6..a4cb58b54b25 100644
--- a/drivers/crypto/hisilicon/sec2/sec_main.c
+++ b/drivers/crypto/hisilicon/sec2/sec_main.c
@@ -80,6 +80,9 @@
 #define SEC_VF_CNT_MASK			0xffffffc0
 #define SEC_DBGFS_VAL_MAX_LEN		20
 
+#define SEC_SQE_MASK_OFFSET		64
+#define SEC_SQE_MASK_LEN		48
+
 #define SEC_ADDR(qm, offset) ((qm)->io_base + (offset) + \
 			     SEC_ENGINE_PF_CFG_OFF + SEC_ACC_COMMON_REG_OFF)
 
@@ -88,6 +91,11 @@ struct sec_hw_error {
 	const char *msg;
 };
 
+struct sec_dfx_item {
+	const char *name;
+	u32 offset;
+};
+
 static const char sec_name[] = "hisi_sec2";
 static struct dentry *sec_debugfs_root;
 static struct hisi_qm_list sec_devices;
@@ -110,7 +118,16 @@ static const char * const sec_dbg_file_name[] = {
 	[SEC_CLEAR_ENABLE] = "clear_enable",
 };
 
-static struct debugfs_reg32 sec_dfx_regs[] = {
+static struct sec_dfx_item sec_dfx_labels[] = {
+	{"send_cnt", offsetof(struct sec_dfx, send_cnt)},
+	{"recv_cnt", offsetof(struct sec_dfx, recv_cnt)},
+	{"send_busy_cnt", offsetof(struct sec_dfx, send_busy_cnt)},
+	{"err_bd_cnt", offsetof(struct sec_dfx, err_bd_cnt)},
+	{"invalid_req_cnt", offsetof(struct sec_dfx, invalid_req_cnt)},
+	{"done_flag_cnt", offsetof(struct sec_dfx, done_flag_cnt)},
+};
+
+static const struct debugfs_reg32 sec_dfx_regs[] = {
 	{"SEC_PF_ABNORMAL_INT_SOURCE    ",  0x301010},
 	{"SEC_SAA_EN                    ",  0x301270},
 	{"SEC_BD_LATENCY_MIN            ",  0x301600},
@@ -136,45 +153,14 @@ static struct debugfs_reg32 sec_dfx_regs[] = {
 
 static int sec_pf_q_num_set(const char *val, const struct kernel_param *kp)
 {
-	struct pci_dev *pdev;
-	u32 n, q_num;
-	u8 rev_id;
-	int ret;
-
-	if (!val)
-		return -EINVAL;
-
-	pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI,
-			      SEC_PF_PCI_DEVICE_ID, NULL);
-	if (!pdev) {
-		q_num = min_t(u32, SEC_QUEUE_NUM_V1, SEC_QUEUE_NUM_V2);
-		pr_info("No device, suppose queue number is %d!\n", q_num);
-	} else {
-		rev_id = pdev->revision;
-
-		switch (rev_id) {
-		case QM_HW_V1:
-			q_num = SEC_QUEUE_NUM_V1;
-			break;
-		case QM_HW_V2:
-			q_num = SEC_QUEUE_NUM_V2;
-			break;
-		default:
-			return -EINVAL;
-		}
-	}
-
-	ret = kstrtou32(val, 10, &n);
-	if (ret || !n || n > q_num)
-		return -EINVAL;
-
-	return param_set_int(val, kp);
+	return q_num_set(val, kp, SEC_PF_PCI_DEVICE_ID);
 }
 
 static const struct kernel_param_ops sec_pf_q_num_ops = {
 	.set = sec_pf_q_num_set,
 	.get = param_get_int,
 };
+
 static u32 pf_q_num = SEC_PF_DEF_Q_NUM;
 module_param_cb(pf_q_num, &sec_pf_q_num_ops, &pf_q_num, 0444);
 MODULE_PARM_DESC(pf_q_num, "Number of queues in PF(v1 0-4096, v2 0-1024)");
@@ -207,6 +193,15 @@ static u32 ctx_q_num = SEC_CTX_Q_NUM_DEF;
 module_param_cb(ctx_q_num, &sec_ctx_q_num_ops, &ctx_q_num, 0444);
 MODULE_PARM_DESC(ctx_q_num, "Queue num in ctx (24 default, 2, 4, ..., 32)");
 
+static const struct kernel_param_ops vfs_num_ops = {
+	.set = vfs_num_set,
+	.get = param_get_int,
+};
+
+static u32 vfs_num;
+module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444);
+MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)");
+
 void sec_destroy_qps(struct hisi_qp **qps, int qp_num)
 {
 	hisi_qm_free_qps(qps, qp_num);
@@ -240,9 +235,8 @@ static const struct pci_device_id sec_dev_ids[] = {
 };
 MODULE_DEVICE_TABLE(pci, sec_dev_ids);
 
-static u8 sec_get_endian(struct sec_dev *sec)
+static u8 sec_get_endian(struct hisi_qm *qm)
 {
-	struct hisi_qm *qm = &sec->qm;
 	u32 reg;
 
 	/*
@@ -270,9 +264,8 @@ static u8 sec_get_endian(struct sec_dev *sec)
 		return SEC_64BE;
 }
 
-static int sec_engine_init(struct sec_dev *sec)
+static int sec_engine_init(struct hisi_qm *qm)
 {
-	struct hisi_qm *qm = &sec->qm;
 	int ret;
 	u32 reg;
 
@@ -315,7 +308,7 @@ static int sec_engine_init(struct sec_dev *sec)
 
 	/* config endian */
 	reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG));
-	reg |= sec_get_endian(sec);
+	reg |= sec_get_endian(qm);
 	writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG));
 
 	/* Enable sm4 xts mode multiple iv */
@@ -325,10 +318,8 @@ static int sec_engine_init(struct sec_dev *sec)
 	return 0;
 }
 
-static int sec_set_user_domain_and_cache(struct sec_dev *sec)
+static int sec_set_user_domain_and_cache(struct hisi_qm *qm)
 {
-	struct hisi_qm *qm = &sec->qm;
-
 	/* qm user domain */
 	writel(AXUSER_BASE, qm->io_base + QM_ARUSER_M_CFG_1);
 	writel(ARUSER_M_CFG_ENABLE, qm->io_base + QM_ARUSER_M_CFG_ENABLE);
@@ -349,7 +340,7 @@ static int sec_set_user_domain_and_cache(struct sec_dev *sec)
 	       CQC_CACHE_WB_ENABLE | FIELD_PREP(SQC_CACHE_WB_THRD, 1) |
 	       FIELD_PREP(CQC_CACHE_WB_THRD, 1), qm->io_base + QM_CACHE_CTL);
 
-	return sec_engine_init(sec);
+	return sec_engine_init(qm);
 }
 
 /* sec_debug_regs_clear() - clear the sec debug regs */
@@ -424,23 +415,22 @@ static u32 sec_current_qm_read(struct sec_debug_file *file)
 static int sec_current_qm_write(struct sec_debug_file *file, u32 val)
 {
 	struct hisi_qm *qm = file->qm;
-	struct sec_dev *sec = container_of(qm, struct sec_dev, qm);
 	u32 vfq_num;
 	u32 tmp;
 
-	if (val > sec->num_vfs)
+	if (val > qm->vfs_num)
 		return -EINVAL;
 
 	/* According PF or VF Dev ID to calculation curr_qm_qp_num and store */
 	if (!val) {
 		qm->debug.curr_qm_qp_num = qm->qp_num;
 	} else {
-		vfq_num = (qm->ctrl_qp_num - qm->qp_num) / sec->num_vfs;
+		vfq_num = (qm->ctrl_qp_num - qm->qp_num) / qm->vfs_num;
 
-		if (val == sec->num_vfs)
+		if (val == qm->vfs_num)
 			qm->debug.curr_qm_qp_num =
 				qm->ctrl_qp_num - qm->qp_num -
-				(sec->num_vfs - 1) * vfq_num;
+				(qm->vfs_num - 1) * vfq_num;
 		else
 			qm->debug.curr_qm_qp_num = vfq_num;
 	}
@@ -570,10 +560,22 @@ static const struct file_operations sec_dbg_fops = {
 static int sec_debugfs_atomic64_get(void *data, u64 *val)
 {
 	*val = atomic64_read((atomic64_t *)data);
+
+	return 0;
+}
+
+static int sec_debugfs_atomic64_set(void *data, u64 val)
+{
+	if (val)
+		return -EINVAL;
+
+	atomic64_set((atomic64_t *)data, 0);
+
 	return 0;
 }
+
 DEFINE_DEBUGFS_ATTRIBUTE(sec_atomic64_ops, sec_debugfs_atomic64_get,
-			 NULL, "%lld\n");
+			 sec_debugfs_atomic64_set, "%lld\n");
 
 static int sec_core_debug_init(struct sec_dev *sec)
 {
@@ -582,6 +584,7 @@ static int sec_core_debug_init(struct sec_dev *sec)
 	struct sec_dfx *dfx = &sec->debug.dfx;
 	struct debugfs_regset32 *regset;
 	struct dentry *tmp_d;
+	int i;
 
 	tmp_d = debugfs_create_dir("sec_dfx", sec->qm.debug.debug_root);
 
@@ -593,13 +596,15 @@ static int sec_core_debug_init(struct sec_dev *sec)
 	regset->nregs = ARRAY_SIZE(sec_dfx_regs);
 	regset->base = qm->io_base;
 
-	debugfs_create_regset32("regs", 0444, tmp_d, regset);
-
-	debugfs_create_file("send_cnt", 0444, tmp_d,
-			    &dfx->send_cnt, &sec_atomic64_ops);
+	if (qm->pdev->device == SEC_PF_PCI_DEVICE_ID)
+		debugfs_create_regset32("regs", 0444, tmp_d, regset);
 
-	debugfs_create_file("recv_cnt", 0444, tmp_d,
-			    &dfx->recv_cnt, &sec_atomic64_ops);
+	for (i = 0; i < ARRAY_SIZE(sec_dfx_labels); i++) {
+		atomic64_t *data = (atomic64_t *)((uintptr_t)dfx +
+					sec_dfx_labels[i].offset);
+		debugfs_create_file(sec_dfx_labels[i].name, 0644,
+				   tmp_d, data, &sec_atomic64_ops);
+	}
 
 	return 0;
 }
@@ -630,6 +635,9 @@ static int sec_debugfs_init(struct sec_dev *sec)
 
 	qm->debug.debug_root = debugfs_create_dir(dev_name(dev),
 						  sec_debugfs_root);
+
+	qm->debug.sqe_mask_offset = SEC_SQE_MASK_OFFSET;
+	qm->debug.sqe_mask_len = SEC_SQE_MASK_LEN;
 	ret = hisi_qm_debug_init(qm);
 	if (ret)
 		goto failed_to_create;
@@ -675,8 +683,6 @@ static void sec_log_hw_error(struct hisi_qm *qm, u32 err_sts)
 		}
 		errs++;
 	}
-
-	writel(err_sts, qm->io_base + SEC_CORE_INT_SOURCE);
 }
 
 static u32 sec_get_hw_err_status(struct hisi_qm *qm)
@@ -684,17 +690,36 @@ static u32 sec_get_hw_err_status(struct hisi_qm *qm)
 	return readl(qm->io_base + SEC_CORE_INT_STATUS);
 }
 
+static void sec_clear_hw_err_status(struct hisi_qm *qm, u32 err_sts)
+{
+	writel(err_sts, qm->io_base + SEC_CORE_INT_SOURCE);
+}
+
+static void sec_open_axi_master_ooo(struct hisi_qm *qm)
+{
+	u32 val;
+
+	val = readl(SEC_ADDR(qm, SEC_CONTROL_REG));
+	writel(val & SEC_AXI_SHUTDOWN_DISABLE, SEC_ADDR(qm, SEC_CONTROL_REG));
+	writel(val | SEC_AXI_SHUTDOWN_ENABLE, SEC_ADDR(qm, SEC_CONTROL_REG));
+}
+
 static const struct hisi_qm_err_ini sec_err_ini = {
+	.hw_init		= sec_set_user_domain_and_cache,
 	.hw_err_enable		= sec_hw_error_enable,
 	.hw_err_disable		= sec_hw_error_disable,
 	.get_dev_hw_err_status	= sec_get_hw_err_status,
+	.clear_dev_hw_err_status = sec_clear_hw_err_status,
 	.log_dev_hw_err		= sec_log_hw_error,
+	.open_axi_master_ooo	= sec_open_axi_master_ooo,
 	.err_info		= {
 		.ce			= QM_BASE_CE,
 		.nfe			= QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT |
 					  QM_ACC_WB_NOT_READY_TIMEOUT,
 		.fe			= 0,
-		.msi			= QM_DB_RANDOM_INVALID,
+		.ecc_2bits_mask		= SEC_CORE_INT_STATUS_M_ECC,
+		.msi_wr_port		= BIT(0),
+		.acpi_rst		= "SRST",
 	}
 };
 
@@ -703,22 +728,14 @@ static int sec_pf_probe_init(struct sec_dev *sec)
 	struct hisi_qm *qm = &sec->qm;
 	int ret;
 
-	switch (qm->ver) {
-	case QM_HW_V1:
+	if (qm->ver == QM_HW_V1)
 		qm->ctrl_qp_num = SEC_QUEUE_NUM_V1;
-		break;
-
-	case QM_HW_V2:
+	else
 		qm->ctrl_qp_num = SEC_QUEUE_NUM_V2;
-		break;
-
-	default:
-		return -EINVAL;
-	}
 
 	qm->err_ini = &sec_err_ini;
 
-	ret = sec_set_user_domain_and_cache(sec);
+	ret = sec_set_user_domain_and_cache(qm);
 	if (ret)
 		return ret;
 
@@ -730,32 +747,30 @@ static int sec_pf_probe_init(struct sec_dev *sec)
 
 static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 {
-	enum qm_hw_ver rev_id;
-
-	rev_id = hisi_qm_get_hw_version(pdev);
-	if (rev_id == QM_HW_UNKNOWN)
-		return -ENODEV;
+	int ret;
 
 	qm->pdev = pdev;
-	qm->ver = rev_id;
-
+	qm->ver = pdev->revision;
 	qm->sqe_size = SEC_SQE_SIZE;
 	qm->dev_name = sec_name;
+
 	qm->fun_type = (pdev->device == SEC_PF_PCI_DEVICE_ID) ?
 			QM_HW_PF : QM_HW_VF;
-	qm->use_dma_api = true;
-
-	return hisi_qm_init(qm);
-}
-
-static void sec_qm_uninit(struct hisi_qm *qm)
-{
-	hisi_qm_uninit(qm);
-}
-
-static int sec_probe_init(struct hisi_qm *qm, struct sec_dev *sec)
-{
-	int ret;
+	if (qm->fun_type == QM_HW_PF) {
+		qm->qp_base = SEC_PF_DEF_Q_BASE;
+		qm->qp_num = pf_q_num;
+		qm->debug.curr_qm_qp_num = pf_q_num;
+		qm->qm_list = &sec_devices;
+	} else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V1) {
+		/*
+		 * have no way to get qm configure in VM in v1 hardware,
+		 * so currently force PF to uses SEC_PF_DEF_Q_NUM, and force
+		 * to trigger only one VF in v1 hardware.
+		 * v2 hardware has no such problem.
+		 */
+		qm->qp_base = SEC_PF_DEF_Q_NUM;
+		qm->qp_num = SEC_QUEUE_NUM_V1 - SEC_PF_DEF_Q_NUM;
+	}
 
 	/*
 	 * WQ_HIGHPRI: SEC request must be low delayed,
@@ -763,47 +778,38 @@ static int sec_probe_init(struct hisi_qm *qm, struct sec_dev *sec)
 	 * WQ_UNBOUND: SEC task is likely with long
 	 * running CPU intensive workloads.
 	 */
-	qm->wq = alloc_workqueue("%s", WQ_HIGHPRI |
-		WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus(),
-		pci_name(qm->pdev));
+	qm->wq = alloc_workqueue("%s", WQ_HIGHPRI | WQ_MEM_RECLAIM |
+				 WQ_UNBOUND, num_online_cpus(),
+				 pci_name(qm->pdev));
 	if (!qm->wq) {
 		pci_err(qm->pdev, "fail to alloc workqueue\n");
 		return -ENOMEM;
 	}
 
-	if (qm->fun_type == QM_HW_PF) {
-		qm->qp_base = SEC_PF_DEF_Q_BASE;
-		qm->qp_num = pf_q_num;
-		qm->debug.curr_qm_qp_num = pf_q_num;
+	ret = hisi_qm_init(qm);
+	if (ret)
+		destroy_workqueue(qm->wq);
+
+	return ret;
+}
 
+static void sec_qm_uninit(struct hisi_qm *qm)
+{
+	hisi_qm_uninit(qm);
+}
+
+static int sec_probe_init(struct sec_dev *sec)
+{
+	struct hisi_qm *qm = &sec->qm;
+	int ret;
+
+	if (qm->fun_type == QM_HW_PF) {
 		ret = sec_pf_probe_init(sec);
 		if (ret)
-			goto err_probe_uninit;
-	} else if (qm->fun_type == QM_HW_VF) {
-		/*
-		 * have no way to get qm configure in VM in v1 hardware,
-		 * so currently force PF to uses SEC_PF_DEF_Q_NUM, and force
-		 * to trigger only one VF in v1 hardware.
-		 * v2 hardware has no such problem.
-		 */
-		if (qm->ver == QM_HW_V1) {
-			qm->qp_base = SEC_PF_DEF_Q_NUM;
-			qm->qp_num = SEC_QUEUE_NUM_V1 - SEC_PF_DEF_Q_NUM;
-		} else if (qm->ver == QM_HW_V2) {
-			/* v2 starts to support get vft by mailbox */
-			ret = hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num);
-			if (ret)
-				goto err_probe_uninit;
-		}
-	} else {
-		ret = -ENODEV;
-		goto err_probe_uninit;
+			return ret;
 	}
 
 	return 0;
-err_probe_uninit:
-	destroy_workqueue(qm->wq);
-	return ret;
 }
 
 static void sec_probe_uninit(struct hisi_qm *qm)
@@ -840,20 +846,17 @@ static int sec_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!sec)
 		return -ENOMEM;
 
-	pci_set_drvdata(pdev, sec);
-
-	sec->ctx_q_num = ctx_q_num;
-	sec_iommu_used_check(sec);
-
 	qm = &sec->qm;
-
 	ret = sec_qm_init(qm, pdev);
 	if (ret) {
-		pci_err(pdev, "Failed to pre init qm!\n");
+		pci_err(pdev, "Failed to init SEC QM (%d)!\n", ret);
 		return ret;
 	}
 
-	ret = sec_probe_init(qm, sec);
+	sec->ctx_q_num = ctx_q_num;
+	sec_iommu_used_check(sec);
+
+	ret = sec_probe_init(sec);
 	if (ret) {
 		pci_err(pdev, "Failed to probe!\n");
 		goto err_qm_uninit;
@@ -877,8 +880,17 @@ static int sec_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_remove_from_list;
 	}
 
+	if (qm->fun_type == QM_HW_PF && vfs_num) {
+		ret = hisi_qm_sriov_enable(pdev, vfs_num);
+		if (ret < 0)
+			goto err_crypto_unregister;
+	}
+
 	return 0;
 
+err_crypto_unregister:
+	sec_unregister_from_crypto();
+
 err_remove_from_list:
 	hisi_qm_del_from_list(qm, &sec_devices);
 	sec_debugfs_exit(sec);
@@ -893,110 +905,6 @@ err_qm_uninit:
 	return ret;
 }
 
-/* now we only support equal assignment */
-static int sec_vf_q_assign(struct sec_dev *sec, u32 num_vfs)
-{
-	struct hisi_qm *qm = &sec->qm;
-	u32 qp_num = qm->qp_num;
-	u32 q_base = qp_num;
-	u32 q_num, remain_q_num;
-	int i, j, ret;
-
-	if (!num_vfs)
-		return -EINVAL;
-
-	remain_q_num = qm->ctrl_qp_num - qp_num;
-	q_num = remain_q_num / num_vfs;
-
-	for (i = 1; i <= num_vfs; i++) {
-		if (i == num_vfs)
-			q_num += remain_q_num % num_vfs;
-		ret = hisi_qm_set_vft(qm, i, q_base, q_num);
-		if (ret) {
-			for (j = i; j > 0; j--)
-				hisi_qm_set_vft(qm, j, 0, 0);
-			return ret;
-		}
-		q_base += q_num;
-	}
-
-	return 0;
-}
-
-static int sec_clear_vft_config(struct sec_dev *sec)
-{
-	struct hisi_qm *qm = &sec->qm;
-	u32 num_vfs = sec->num_vfs;
-	int ret;
-	u32 i;
-
-	for (i = 1; i <= num_vfs; i++) {
-		ret = hisi_qm_set_vft(qm, i, 0, 0);
-		if (ret)
-			return ret;
-	}
-
-	sec->num_vfs = 0;
-
-	return 0;
-}
-
-static int sec_sriov_enable(struct pci_dev *pdev, int max_vfs)
-{
-	struct sec_dev *sec = pci_get_drvdata(pdev);
-	int pre_existing_vfs, ret;
-	u32 num_vfs;
-
-	pre_existing_vfs = pci_num_vf(pdev);
-
-	if (pre_existing_vfs) {
-		pci_err(pdev, "Can't enable VF. Please disable at first!\n");
-		return 0;
-	}
-
-	num_vfs = min_t(u32, max_vfs, SEC_VF_NUM);
-
-	ret = sec_vf_q_assign(sec, num_vfs);
-	if (ret) {
-		pci_err(pdev, "Can't assign queues for VF!\n");
-		return ret;
-	}
-
-	sec->num_vfs = num_vfs;
-
-	ret = pci_enable_sriov(pdev, num_vfs);
-	if (ret) {
-		pci_err(pdev, "Can't enable VF!\n");
-		sec_clear_vft_config(sec);
-		return ret;
-	}
-
-	return num_vfs;
-}
-
-static int sec_sriov_disable(struct pci_dev *pdev)
-{
-	struct sec_dev *sec = pci_get_drvdata(pdev);
-
-	if (pci_vfs_assigned(pdev)) {
-		pci_err(pdev, "Can't disable VFs while VFs are assigned!\n");
-		return -EPERM;
-	}
-
-	/* remove in sec_pci_driver will be called to free VF resources */
-	pci_disable_sriov(pdev);
-
-	return sec_clear_vft_config(sec);
-}
-
-static int sec_sriov_configure(struct pci_dev *pdev, int num_vfs)
-{
-	if (num_vfs)
-		return sec_sriov_enable(pdev, num_vfs);
-	else
-		return sec_sriov_disable(pdev);
-}
-
 static void sec_remove(struct pci_dev *pdev)
 {
 	struct sec_dev *sec = pci_get_drvdata(pdev);
@@ -1006,8 +914,8 @@ static void sec_remove(struct pci_dev *pdev)
 
 	hisi_qm_del_from_list(qm, &sec_devices);
 
-	if (qm->fun_type == QM_HW_PF && sec->num_vfs)
-		(void)sec_sriov_disable(pdev);
+	if (qm->fun_type == QM_HW_PF && qm->vfs_num)
+		hisi_qm_sriov_disable(pdev);
 
 	sec_debugfs_exit(sec);
 
@@ -1023,6 +931,9 @@ static void sec_remove(struct pci_dev *pdev)
 
 static const struct pci_error_handlers sec_err_handler = {
 	.error_detected = hisi_qm_dev_err_detected,
+	.slot_reset =  hisi_qm_dev_slot_reset,
+	.reset_prepare		= hisi_qm_reset_prepare,
+	.reset_done		= hisi_qm_reset_done,
 };
 
 static struct pci_driver sec_pci_driver = {
@@ -1031,7 +942,7 @@ static struct pci_driver sec_pci_driver = {
 	.probe = sec_probe,
 	.remove = sec_remove,
 	.err_handler = &sec_err_handler,
-	.sriov_configure = sec_sriov_configure,
+	.sriov_configure = hisi_qm_sriov_configure,
 };
 
 static void sec_register_debugfs(void)
diff --git a/drivers/crypto/hisilicon/zip/zip.h b/drivers/crypto/hisilicon/zip/zip.h
index 82dc6f867171..f3ed4c0e5493 100644
--- a/drivers/crypto/hisilicon/zip/zip.h
+++ b/drivers/crypto/hisilicon/zip/zip.h
@@ -28,12 +28,20 @@ enum hisi_zip_error_type {
 	HZIP_NC_ERR = 0x0d,
 };
 
+struct hisi_zip_dfx {
+	atomic64_t send_cnt;
+	atomic64_t recv_cnt;
+	atomic64_t send_busy_cnt;
+	atomic64_t err_bd_cnt;
+};
+
 struct hisi_zip_ctrl;
 
 struct hisi_zip {
 	struct hisi_qm qm;
 	struct list_head list;
 	struct hisi_zip_ctrl *ctrl;
+	struct hisi_zip_dfx dfx;
 };
 
 struct hisi_zip_sqe {
diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c
index 369ec3220574..c73707c2e539 100644
--- a/drivers/crypto/hisilicon/zip/zip_crypto.c
+++ b/drivers/crypto/hisilicon/zip/zip_crypto.c
@@ -64,7 +64,6 @@ struct hisi_zip_req_q {
 
 struct hisi_zip_qp_ctx {
 	struct hisi_qp *qp;
-	struct hisi_zip_sqe zip_sqe;
 	struct hisi_zip_req_q req_q;
 	struct hisi_acc_sgl_pool *sgl_pool;
 	struct hisi_zip *zip_dev;
@@ -333,6 +332,7 @@ static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data)
 {
 	struct hisi_zip_sqe *sqe = data;
 	struct hisi_zip_qp_ctx *qp_ctx = qp->qp_ctx;
+	struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx;
 	struct hisi_zip_req_q *req_q = &qp_ctx->req_q;
 	struct hisi_zip_req *req = req_q->q + sqe->tag;
 	struct acomp_req *acomp_req = req->req;
@@ -340,12 +340,14 @@ static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data)
 	u32 status, dlen, head_size;
 	int err = 0;
 
+	atomic64_inc(&dfx->recv_cnt);
 	status = sqe->dw3 & HZIP_BD_STATUS_M;
 
 	if (status != 0 && status != HZIP_NC_ERR) {
 		dev_err(dev, "%scompress fail in qp%u: %u, output: %u\n",
 			(qp->alg_type == 0) ? "" : "de", qp->qp_id, status,
 			sqe->produced);
+		atomic64_inc(&dfx->err_bd_cnt);
 		err = -EIO;
 	}
 	dlen = sqe->produced;
@@ -484,11 +486,12 @@ static struct hisi_zip_req *hisi_zip_create_req(struct acomp_req *req,
 static int hisi_zip_do_work(struct hisi_zip_req *req,
 			    struct hisi_zip_qp_ctx *qp_ctx)
 {
-	struct hisi_zip_sqe *zip_sqe = &qp_ctx->zip_sqe;
 	struct acomp_req *a_req = req->req;
 	struct hisi_qp *qp = qp_ctx->qp;
 	struct device *dev = &qp->qm->pdev->dev;
 	struct hisi_acc_sgl_pool *pool = qp_ctx->sgl_pool;
+	struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx;
+	struct hisi_zip_sqe zip_sqe;
 	dma_addr_t input;
 	dma_addr_t output;
 	int ret;
@@ -511,15 +514,18 @@ static int hisi_zip_do_work(struct hisi_zip_req *req,
 	}
 	req->dma_dst = output;
 
-	hisi_zip_fill_sqe(zip_sqe, qp->req_type, input, output, a_req->slen,
+	hisi_zip_fill_sqe(&zip_sqe, qp->req_type, input, output, a_req->slen,
 			  a_req->dlen, req->sskip, req->dskip);
-	hisi_zip_config_buf_type(zip_sqe, HZIP_SGL);
-	hisi_zip_config_tag(zip_sqe, req->req_id);
+	hisi_zip_config_buf_type(&zip_sqe, HZIP_SGL);
+	hisi_zip_config_tag(&zip_sqe, req->req_id);
 
 	/* send command to start a task */
-	ret = hisi_qp_send(qp, zip_sqe);
-	if (ret < 0)
+	atomic64_inc(&dfx->send_cnt);
+	ret = hisi_qp_send(qp, &zip_sqe);
+	if (ret < 0) {
+		atomic64_inc(&dfx->send_busy_cnt);
 		goto err_unmap_output;
+	}
 
 	return -EINPROGRESS;
 
diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c
index fcc85d2dbd07..2229a21ae7c8 100644
--- a/drivers/crypto/hisilicon/zip/zip_main.c
+++ b/drivers/crypto/hisilicon/zip/zip_main.c
@@ -62,6 +62,7 @@
 
 #define HZIP_CORE_INT_SOURCE		0x3010A0
 #define HZIP_CORE_INT_MASK_REG		0x3010A4
+#define HZIP_CORE_INT_SET		0x3010A8
 #define HZIP_CORE_INT_STATUS		0x3010AC
 #define HZIP_CORE_INT_STATUS_M_ECC	BIT(1)
 #define HZIP_CORE_SRAM_ECC_ERR_INFO	0x301148
@@ -83,8 +84,13 @@
 
 #define HZIP_SOFT_CTRL_CNT_CLR_CE	0x301000
 #define SOFT_CTRL_CNT_CLR_CE_BIT	BIT(0)
+#define HZIP_SOFT_CTRL_ZIP_CONTROL	0x30100C
+#define HZIP_AXI_SHUTDOWN_ENABLE	BIT(14)
+#define HZIP_WR_PORT			BIT(11)
 
 #define HZIP_BUF_SIZE			22
+#define HZIP_SQE_MASK_OFFSET		64
+#define HZIP_SQE_MASK_LEN		48
 
 static const char hisi_zip_name[] = "hisi_zip";
 static struct dentry *hzip_debugfs_root;
@@ -95,6 +101,18 @@ struct hisi_zip_hw_error {
 	const char *msg;
 };
 
+struct zip_dfx_item {
+	const char *name;
+	u32 offset;
+};
+
+static struct zip_dfx_item zip_dfx_files[] = {
+	{"send_cnt", offsetof(struct hisi_zip_dfx, send_cnt)},
+	{"recv_cnt", offsetof(struct hisi_zip_dfx, recv_cnt)},
+	{"send_busy_cnt", offsetof(struct hisi_zip_dfx, send_busy_cnt)},
+	{"err_bd_cnt", offsetof(struct hisi_zip_dfx, err_bd_cnt)},
+};
+
 static const struct hisi_zip_hw_error zip_hw_error[] = {
 	{ .int_msk = BIT(0), .msg = "zip_ecc_1bitt_err" },
 	{ .int_msk = BIT(1), .msg = "zip_ecc_2bit_err" },
@@ -134,7 +152,6 @@ struct ctrl_debug_file {
  * Just relevant for PF.
  */
 struct hisi_zip_ctrl {
-	u32 num_vfs;
 	struct hisi_zip *hisi_zip;
 	struct dentry *debug_root;
 	struct ctrl_debug_file files[HZIP_DEBUG_FILE_NUM];
@@ -162,7 +179,7 @@ static const u64 core_offsets[] = {
 	[HZIP_DECOMP_CORE5] = 0x309000,
 };
 
-static struct debugfs_reg32 hzip_dfx_regs[] = {
+static const struct debugfs_reg32 hzip_dfx_regs[] = {
 	{"HZIP_GET_BD_NUM                ",  0x00ull},
 	{"HZIP_GET_RIGHT_BD              ",  0x04ull},
 	{"HZIP_GET_ERROR_BD              ",  0x08ull},
@@ -189,38 +206,7 @@ static struct debugfs_reg32 hzip_dfx_regs[] = {
 
 static int pf_q_num_set(const char *val, const struct kernel_param *kp)
 {
-	struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI,
-					      PCI_DEVICE_ID_ZIP_PF, NULL);
-	u32 n, q_num;
-	u8 rev_id;
-	int ret;
-
-	if (!val)
-		return -EINVAL;
-
-	if (!pdev) {
-		q_num = min_t(u32, HZIP_QUEUE_NUM_V1, HZIP_QUEUE_NUM_V2);
-		pr_info("No device found currently, suppose queue number is %d\n",
-			q_num);
-	} else {
-		rev_id = pdev->revision;
-		switch (rev_id) {
-		case QM_HW_V1:
-			q_num = HZIP_QUEUE_NUM_V1;
-			break;
-		case QM_HW_V2:
-			q_num = HZIP_QUEUE_NUM_V2;
-			break;
-		default:
-			return -EINVAL;
-		}
-	}
-
-	ret = kstrtou32(val, 10, &n);
-	if (ret != 0 || n > q_num || n == 0)
-		return -EINVAL;
-
-	return param_set_int(val, kp);
+	return q_num_set(val, kp, PCI_DEVICE_ID_ZIP_PF);
 }
 
 static const struct kernel_param_ops pf_q_num_ops = {
@@ -232,9 +218,14 @@ static u32 pf_q_num = HZIP_PF_DEF_Q_NUM;
 module_param_cb(pf_q_num, &pf_q_num_ops, &pf_q_num, 0444);
 MODULE_PARM_DESC(pf_q_num, "Number of queues in PF(v1 1-4096, v2 1-1024)");
 
+static const struct kernel_param_ops vfs_num_ops = {
+	.set = vfs_num_set,
+	.get = param_get_int,
+};
+
 static u32 vfs_num;
-module_param(vfs_num, uint, 0444);
-MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63)");
+module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444);
+MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)");
 
 static const struct pci_device_id hisi_zip_dev_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_ZIP_PF) },
@@ -250,9 +241,9 @@ int zip_create_qps(struct hisi_qp **qps, int qp_num)
 	return hisi_qm_alloc_qps_node(&zip_devices, qp_num, 0, node, qps);
 }
 
-static void hisi_zip_set_user_domain_and_cache(struct hisi_zip *hisi_zip)
+static int hisi_zip_set_user_domain_and_cache(struct hisi_qm *qm)
 {
-	void __iomem *base = hisi_zip->qm.io_base;
+	void __iomem *base = qm->io_base;
 
 	/* qm user domain */
 	writel(AXUSER_BASE, base + QM_ARUSER_M_CFG_1);
@@ -279,7 +270,7 @@ static void hisi_zip_set_user_domain_and_cache(struct hisi_zip *hisi_zip)
 	writel(AXUSER_BASE, base + HZIP_SGL_RUSER_32_63);
 	writel(AXUSER_BASE, base + HZIP_BD_WUSER_32_63);
 
-	if (hisi_zip->qm.use_sva) {
+	if (qm->use_sva) {
 		writel(AXUSER_BASE | AXUSER_SSV, base + HZIP_DATA_RUSER_32_63);
 		writel(AXUSER_BASE | AXUSER_SSV, base + HZIP_DATA_WUSER_32_63);
 	} else {
@@ -295,10 +286,14 @@ static void hisi_zip_set_user_domain_and_cache(struct hisi_zip *hisi_zip)
 	writel(SQC_CACHE_ENABLE | CQC_CACHE_ENABLE | SQC_CACHE_WB_ENABLE |
 	       CQC_CACHE_WB_ENABLE | FIELD_PREP(SQC_CACHE_WB_THRD, 1) |
 	       FIELD_PREP(CQC_CACHE_WB_THRD, 1), base + QM_CACHE_CTL);
+
+	return 0;
 }
 
 static void hisi_zip_hw_error_enable(struct hisi_qm *qm)
 {
+	u32 val;
+
 	if (qm->ver == QM_HW_V1) {
 		writel(HZIP_CORE_INT_MASK_ALL,
 		       qm->io_base + HZIP_CORE_INT_MASK_REG);
@@ -317,12 +312,24 @@ static void hisi_zip_hw_error_enable(struct hisi_qm *qm)
 
 	/* enable ZIP hw error interrupts */
 	writel(0, qm->io_base + HZIP_CORE_INT_MASK_REG);
+
+	/* enable ZIP block master OOO when m-bit error occur */
+	val = readl(qm->io_base + HZIP_SOFT_CTRL_ZIP_CONTROL);
+	val = val | HZIP_AXI_SHUTDOWN_ENABLE;
+	writel(val, qm->io_base + HZIP_SOFT_CTRL_ZIP_CONTROL);
 }
 
 static void hisi_zip_hw_error_disable(struct hisi_qm *qm)
 {
+	u32 val;
+
 	/* disable ZIP hw error interrupts */
 	writel(HZIP_CORE_INT_MASK_ALL, qm->io_base + HZIP_CORE_INT_MASK_REG);
+
+	/* disable ZIP block master OOO when m-bit error occur */
+	val = readl(qm->io_base + HZIP_SOFT_CTRL_ZIP_CONTROL);
+	val = val & ~HZIP_AXI_SHUTDOWN_ENABLE;
+	writel(val, qm->io_base + HZIP_SOFT_CTRL_ZIP_CONTROL);
 }
 
 static inline struct hisi_qm *file_to_qm(struct ctrl_debug_file *file)
@@ -342,21 +349,20 @@ static u32 current_qm_read(struct ctrl_debug_file *file)
 static int current_qm_write(struct ctrl_debug_file *file, u32 val)
 {
 	struct hisi_qm *qm = file_to_qm(file);
-	struct hisi_zip_ctrl *ctrl = file->ctrl;
 	u32 vfq_num;
 	u32 tmp;
 
-	if (val > ctrl->num_vfs)
+	if (val > qm->vfs_num)
 		return -EINVAL;
 
 	/* Calculate curr_qm_qp_num and store */
 	if (val == 0) {
 		qm->debug.curr_qm_qp_num = qm->qp_num;
 	} else {
-		vfq_num = (qm->ctrl_qp_num - qm->qp_num) / ctrl->num_vfs;
-		if (val == ctrl->num_vfs)
+		vfq_num = (qm->ctrl_qp_num - qm->qp_num) / qm->vfs_num;
+		if (val == qm->vfs_num)
 			qm->debug.curr_qm_qp_num = qm->ctrl_qp_num -
-				qm->qp_num - (ctrl->num_vfs - 1) * vfq_num;
+				qm->qp_num - (qm->vfs_num - 1) * vfq_num;
 		else
 			qm->debug.curr_qm_qp_num = vfq_num;
 	}
@@ -477,6 +483,27 @@ static const struct file_operations ctrl_debug_fops = {
 	.write = ctrl_debug_write,
 };
 
+
+static int zip_debugfs_atomic64_set(void *data, u64 val)
+{
+	if (val)
+		return -EINVAL;
+
+	atomic64_set((atomic64_t *)data, 0);
+
+	return 0;
+}
+
+static int zip_debugfs_atomic64_get(void *data, u64 *val)
+{
+	*val = atomic64_read((atomic64_t *)data);
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(zip_atomic64_ops, zip_debugfs_atomic64_get,
+			 zip_debugfs_atomic64_set, "%llu\n");
+
 static int hisi_zip_core_debug_init(struct hisi_zip_ctrl *ctrl)
 {
 	struct hisi_zip *hisi_zip = ctrl->hisi_zip;
@@ -508,6 +535,25 @@ static int hisi_zip_core_debug_init(struct hisi_zip_ctrl *ctrl)
 	return 0;
 }
 
+static void hisi_zip_dfx_debug_init(struct hisi_qm *qm)
+{
+	struct hisi_zip *zip = container_of(qm, struct hisi_zip, qm);
+	struct hisi_zip_dfx *dfx = &zip->dfx;
+	struct dentry *tmp_dir;
+	void *data;
+	int i;
+
+	tmp_dir = debugfs_create_dir("zip_dfx", qm->debug.debug_root);
+	for (i = 0; i < ARRAY_SIZE(zip_dfx_files); i++) {
+		data = (atomic64_t *)((uintptr_t)dfx + zip_dfx_files[i].offset);
+		debugfs_create_file(zip_dfx_files[i].name,
+			0644,
+			tmp_dir,
+			data,
+			&zip_atomic64_ops);
+	}
+}
+
 static int hisi_zip_ctrl_debug_init(struct hisi_zip_ctrl *ctrl)
 {
 	int i;
@@ -534,6 +580,8 @@ static int hisi_zip_debugfs_init(struct hisi_zip *hisi_zip)
 
 	dev_d = debugfs_create_dir(dev_name(dev), hzip_debugfs_root);
 
+	qm->debug.sqe_mask_offset = HZIP_SQE_MASK_OFFSET;
+	qm->debug.sqe_mask_len = HZIP_SQE_MASK_LEN;
 	qm->debug.debug_root = dev_d;
 	ret = hisi_qm_debug_init(qm);
 	if (ret)
@@ -546,6 +594,8 @@ static int hisi_zip_debugfs_init(struct hisi_zip *hisi_zip)
 			goto failed_to_create;
 	}
 
+	hisi_zip_dfx_debug_init(qm);
+
 	return 0;
 
 failed_to_create:
@@ -598,8 +648,6 @@ static void hisi_zip_log_hw_error(struct hisi_qm *qm, u32 err_sts)
 		}
 		err++;
 	}
-
-	writel(err_sts, qm->io_base + HZIP_CORE_INT_SOURCE);
 }
 
 static u32 hisi_zip_get_hw_err_status(struct hisi_qm *qm)
@@ -607,17 +655,55 @@ static u32 hisi_zip_get_hw_err_status(struct hisi_qm *qm)
 	return readl(qm->io_base + HZIP_CORE_INT_STATUS);
 }
 
+static void hisi_zip_clear_hw_err_status(struct hisi_qm *qm, u32 err_sts)
+{
+	writel(err_sts, qm->io_base + HZIP_CORE_INT_SOURCE);
+}
+
+static void hisi_zip_open_axi_master_ooo(struct hisi_qm *qm)
+{
+	u32 val;
+
+	val = readl(qm->io_base + HZIP_SOFT_CTRL_ZIP_CONTROL);
+
+	writel(val & ~HZIP_AXI_SHUTDOWN_ENABLE,
+	       qm->io_base + HZIP_SOFT_CTRL_ZIP_CONTROL);
+
+	writel(val | HZIP_AXI_SHUTDOWN_ENABLE,
+	       qm->io_base + HZIP_SOFT_CTRL_ZIP_CONTROL);
+}
+
+static void hisi_zip_close_axi_master_ooo(struct hisi_qm *qm)
+{
+	u32 nfe_enb;
+
+	/* Disable ECC Mbit error report. */
+	nfe_enb = readl(qm->io_base + HZIP_CORE_INT_RAS_NFE_ENB);
+	writel(nfe_enb & ~HZIP_CORE_INT_STATUS_M_ECC,
+	       qm->io_base + HZIP_CORE_INT_RAS_NFE_ENB);
+
+	/* Inject zip ECC Mbit error to block master ooo. */
+	writel(HZIP_CORE_INT_STATUS_M_ECC,
+	       qm->io_base + HZIP_CORE_INT_SET);
+}
+
 static const struct hisi_qm_err_ini hisi_zip_err_ini = {
+	.hw_init		= hisi_zip_set_user_domain_and_cache,
 	.hw_err_enable		= hisi_zip_hw_error_enable,
 	.hw_err_disable		= hisi_zip_hw_error_disable,
 	.get_dev_hw_err_status	= hisi_zip_get_hw_err_status,
+	.clear_dev_hw_err_status = hisi_zip_clear_hw_err_status,
 	.log_dev_hw_err		= hisi_zip_log_hw_error,
+	.open_axi_master_ooo	= hisi_zip_open_axi_master_ooo,
+	.close_axi_master_ooo	= hisi_zip_close_axi_master_ooo,
 	.err_info		= {
 		.ce			= QM_BASE_CE,
 		.nfe			= QM_BASE_NFE |
 					  QM_ACC_WB_NOT_READY_TIMEOUT,
 		.fe			= 0,
-		.msi			= QM_DB_RANDOM_INVALID,
+		.ecc_2bits_mask		= HZIP_CORE_INT_STATUS_M_ECC,
+		.msi_wr_port		= HZIP_WR_PORT,
+		.acpi_rst		= "ZRST",
 	}
 };
 
@@ -633,177 +719,85 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip)
 	hisi_zip->ctrl = ctrl;
 	ctrl->hisi_zip = hisi_zip;
 
-	switch (qm->ver) {
-	case QM_HW_V1:
+	if (qm->ver == QM_HW_V1)
 		qm->ctrl_qp_num = HZIP_QUEUE_NUM_V1;
-		break;
-
-	case QM_HW_V2:
+	else
 		qm->ctrl_qp_num = HZIP_QUEUE_NUM_V2;
-		break;
-
-	default:
-		return -EINVAL;
-	}
 
 	qm->err_ini = &hisi_zip_err_ini;
 
-	hisi_zip_set_user_domain_and_cache(hisi_zip);
+	hisi_zip_set_user_domain_and_cache(qm);
 	hisi_qm_dev_err_init(qm);
 	hisi_zip_debug_regs_clear(hisi_zip);
 
 	return 0;
 }
 
-/* Currently we only support equal assignment */
-static int hisi_zip_vf_q_assign(struct hisi_zip *hisi_zip, int num_vfs)
+static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 {
-	struct hisi_qm *qm = &hisi_zip->qm;
-	u32 qp_num = qm->qp_num;
-	u32 q_base = qp_num;
-	u32 q_num, remain_q_num, i;
-	int ret;
-
-	if (!num_vfs)
-		return -EINVAL;
-
-	remain_q_num = qm->ctrl_qp_num - qp_num;
-	if (remain_q_num < num_vfs)
-		return -EINVAL;
+	qm->pdev = pdev;
+	qm->ver = pdev->revision;
+	qm->algs = "zlib\ngzip";
+	qm->sqe_size = HZIP_SQE_SIZE;
+	qm->dev_name = hisi_zip_name;
 
-	q_num = remain_q_num / num_vfs;
-	for (i = 1; i <= num_vfs; i++) {
-		if (i == num_vfs)
-			q_num += remain_q_num % num_vfs;
-		ret = hisi_qm_set_vft(qm, i, q_base, q_num);
-		if (ret)
-			return ret;
-		q_base += q_num;
+	qm->fun_type = (pdev->device == PCI_DEVICE_ID_ZIP_PF) ?
+			QM_HW_PF : QM_HW_VF;
+	if (qm->fun_type == QM_HW_PF) {
+		qm->qp_base = HZIP_PF_DEF_Q_BASE;
+		qm->qp_num = pf_q_num;
+		qm->qm_list = &zip_devices;
+	} else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V1) {
+		/*
+		 * have no way to get qm configure in VM in v1 hardware,
+		 * so currently force PF to uses HZIP_PF_DEF_Q_NUM, and force
+		 * to trigger only one VF in v1 hardware.
+		 *
+		 * v2 hardware has no such problem.
+		 */
+		qm->qp_base = HZIP_PF_DEF_Q_NUM;
+		qm->qp_num = HZIP_QUEUE_NUM_V1 - HZIP_PF_DEF_Q_NUM;
 	}
 
-	return 0;
+	return hisi_qm_init(qm);
 }
 
-static int hisi_zip_clear_vft_config(struct hisi_zip *hisi_zip)
+static int hisi_zip_probe_init(struct hisi_zip *hisi_zip)
 {
-	struct hisi_zip_ctrl *ctrl = hisi_zip->ctrl;
 	struct hisi_qm *qm = &hisi_zip->qm;
-	u32 i, num_vfs = ctrl->num_vfs;
 	int ret;
 
-	for (i = 1; i <= num_vfs; i++) {
-		ret = hisi_qm_set_vft(qm, i, 0, 0);
+	if (qm->fun_type == QM_HW_PF) {
+		ret = hisi_zip_pf_probe_init(hisi_zip);
 		if (ret)
 			return ret;
 	}
 
-	ctrl->num_vfs = 0;
-
 	return 0;
 }
 
-static int hisi_zip_sriov_enable(struct pci_dev *pdev, int max_vfs)
-{
-	struct hisi_zip *hisi_zip = pci_get_drvdata(pdev);
-	int pre_existing_vfs, num_vfs, ret;
-
-	pre_existing_vfs = pci_num_vf(pdev);
-
-	if (pre_existing_vfs) {
-		dev_err(&pdev->dev,
-			"Can't enable VF. Please disable pre-enabled VFs!\n");
-		return 0;
-	}
-
-	num_vfs = min_t(int, max_vfs, HZIP_VF_NUM);
-
-	ret = hisi_zip_vf_q_assign(hisi_zip, num_vfs);
-	if (ret) {
-		dev_err(&pdev->dev, "Can't assign queues for VF!\n");
-		return ret;
-	}
-
-	hisi_zip->ctrl->num_vfs = num_vfs;
-
-	ret = pci_enable_sriov(pdev, num_vfs);
-	if (ret) {
-		dev_err(&pdev->dev, "Can't enable VF!\n");
-		hisi_zip_clear_vft_config(hisi_zip);
-		return ret;
-	}
-
-	return num_vfs;
-}
-
-static int hisi_zip_sriov_disable(struct pci_dev *pdev)
-{
-	struct hisi_zip *hisi_zip = pci_get_drvdata(pdev);
-
-	if (pci_vfs_assigned(pdev)) {
-		dev_err(&pdev->dev,
-			"Can't disable VFs while VFs are assigned!\n");
-		return -EPERM;
-	}
-
-	/* remove in hisi_zip_pci_driver will be called to free VF resources */
-	pci_disable_sriov(pdev);
-
-	return hisi_zip_clear_vft_config(hisi_zip);
-}
-
 static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct hisi_zip *hisi_zip;
-	enum qm_hw_ver rev_id;
 	struct hisi_qm *qm;
 	int ret;
 
-	rev_id = hisi_qm_get_hw_version(pdev);
-	if (rev_id == QM_HW_UNKNOWN)
-		return -EINVAL;
-
 	hisi_zip = devm_kzalloc(&pdev->dev, sizeof(*hisi_zip), GFP_KERNEL);
 	if (!hisi_zip)
 		return -ENOMEM;
-	pci_set_drvdata(pdev, hisi_zip);
 
 	qm = &hisi_zip->qm;
-	qm->use_dma_api = true;
-	qm->pdev = pdev;
-	qm->ver = rev_id;
 
-	qm->algs = "zlib\ngzip";
-	qm->sqe_size = HZIP_SQE_SIZE;
-	qm->dev_name = hisi_zip_name;
-	qm->fun_type = (pdev->device == PCI_DEVICE_ID_ZIP_PF) ? QM_HW_PF :
-								QM_HW_VF;
-	ret = hisi_qm_init(qm);
+	ret = hisi_zip_qm_init(qm, pdev);
 	if (ret) {
-		dev_err(&pdev->dev, "Failed to init qm!\n");
+		pci_err(pdev, "Failed to init ZIP QM (%d)!\n", ret);
 		return ret;
 	}
 
-	if (qm->fun_type == QM_HW_PF) {
-		ret = hisi_zip_pf_probe_init(hisi_zip);
-		if (ret)
-			return ret;
-
-		qm->qp_base = HZIP_PF_DEF_Q_BASE;
-		qm->qp_num = pf_q_num;
-	} else if (qm->fun_type == QM_HW_VF) {
-		/*
-		 * have no way to get qm configure in VM in v1 hardware,
-		 * so currently force PF to uses HZIP_PF_DEF_Q_NUM, and force
-		 * to trigger only one VF in v1 hardware.
-		 *
-		 * v2 hardware has no such problem.
-		 */
-		if (qm->ver == QM_HW_V1) {
-			qm->qp_base = HZIP_PF_DEF_Q_NUM;
-			qm->qp_num = HZIP_QUEUE_NUM_V1 - HZIP_PF_DEF_Q_NUM;
-		} else if (qm->ver == QM_HW_V2)
-			/* v2 starts to support get vft by mailbox */
-			hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num);
+	ret = hisi_zip_probe_init(hisi_zip);
+	if (ret) {
+		pci_err(pdev, "Failed to probe (%d)!\n", ret);
+		goto err_qm_uninit;
 	}
 
 	ret = hisi_qm_start(qm);
@@ -823,7 +817,7 @@ static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	if (qm->fun_type == QM_HW_PF && vfs_num > 0) {
-		ret = hisi_zip_sriov_enable(pdev, vfs_num);
+		ret = hisi_qm_sriov_enable(pdev, vfs_num);
 		if (ret < 0)
 			goto err_remove_from_list;
 	}
@@ -836,15 +830,8 @@ err_remove_from_list:
 	hisi_qm_stop(qm);
 err_qm_uninit:
 	hisi_qm_uninit(qm);
-	return ret;
-}
 
-static int hisi_zip_sriov_configure(struct pci_dev *pdev, int num_vfs)
-{
-	if (num_vfs == 0)
-		return hisi_zip_sriov_disable(pdev);
-	else
-		return hisi_zip_sriov_enable(pdev, num_vfs);
+	return ret;
 }
 
 static void hisi_zip_remove(struct pci_dev *pdev)
@@ -852,8 +839,8 @@ static void hisi_zip_remove(struct pci_dev *pdev)
 	struct hisi_zip *hisi_zip = pci_get_drvdata(pdev);
 	struct hisi_qm *qm = &hisi_zip->qm;
 
-	if (qm->fun_type == QM_HW_PF && hisi_zip->ctrl->num_vfs != 0)
-		hisi_zip_sriov_disable(pdev);
+	if (qm->fun_type == QM_HW_PF && qm->vfs_num)
+		hisi_qm_sriov_disable(pdev);
 
 	hisi_zip_debugfs_exit(hisi_zip);
 	hisi_qm_stop(qm);
@@ -865,6 +852,9 @@ static void hisi_zip_remove(struct pci_dev *pdev)
 
 static const struct pci_error_handlers hisi_zip_err_handler = {
 	.error_detected	= hisi_qm_dev_err_detected,
+	.slot_reset	= hisi_qm_dev_slot_reset,
+	.reset_prepare	= hisi_qm_reset_prepare,
+	.reset_done	= hisi_qm_reset_done,
 };
 
 static struct pci_driver hisi_zip_pci_driver = {
@@ -873,7 +863,7 @@ static struct pci_driver hisi_zip_pci_driver = {
 	.probe			= hisi_zip_probe,
 	.remove			= hisi_zip_remove,
 	.sriov_configure	= IS_ENABLED(CONFIG_PCI_IOV) ?
-					hisi_zip_sriov_configure : NULL,
+					hisi_qm_sriov_configure : NULL,
 	.err_handler		= &hisi_zip_err_handler,
 };
 
diff --git a/drivers/crypto/marvell/octeontx/otx_cptpf_main.c b/drivers/crypto/marvell/octeontx/otx_cptpf_main.c
index 200fb3303db0..34bb3063eb70 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptpf_main.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptpf_main.c
@@ -79,13 +79,13 @@ static int otx_cpt_device_init(struct otx_cpt_device *cpt)
 	/* Check BIST status */
 	bist = (u64)otx_cpt_check_bist_status(cpt);
 	if (bist) {
-		dev_err(dev, "RAM BIST failed with code 0x%llx", bist);
+		dev_err(dev, "RAM BIST failed with code 0x%llx\n", bist);
 		return -ENODEV;
 	}
 
 	bist = otx_cpt_check_exe_bist_status(cpt);
 	if (bist) {
-		dev_err(dev, "Engine BIST failed with code 0x%llx", bist);
+		dev_err(dev, "Engine BIST failed with code 0x%llx\n", bist);
 		return -ENODEV;
 	}
 
diff --git a/drivers/crypto/marvell/octeontx/otx_cptpf_mbox.c b/drivers/crypto/marvell/octeontx/otx_cptpf_mbox.c
index a6774232e9a3..a9e3de65875a 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptpf_mbox.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptpf_mbox.c
@@ -63,11 +63,11 @@ static void dump_mbox_msg(struct otx_cpt_mbox *mbox_msg, int vf_id)
 	hex_dump_to_buffer(mbox_msg, sizeof(struct otx_cpt_mbox), 16, 8,
 			   raw_data_str, OTX_CPT_MAX_MBOX_DATA_STR_SIZE, false);
 	if (vf_id >= 0)
-		pr_debug("MBOX opcode %s received from VF%d raw_data %s",
+		pr_debug("MBOX opcode %s received from VF%d raw_data %s\n",
 			 get_mbox_opcode_str(mbox_msg->msg), vf_id,
 			 raw_data_str);
 	else
-		pr_debug("MBOX opcode %s received from PF raw_data %s",
+		pr_debug("MBOX opcode %s received from PF raw_data %s\n",
 			 get_mbox_opcode_str(mbox_msg->msg), raw_data_str);
 }
 
@@ -140,20 +140,20 @@ static int otx_cpt_bind_vq_to_grp(struct otx_cpt_device *cpt, u8 q, u8 grp)
 	struct otx_cpt_ucode *ucode;
 
 	if (q >= cpt->max_vfs) {
-		dev_err(dev, "Requested queue %d is > than maximum avail %d",
+		dev_err(dev, "Requested queue %d is > than maximum avail %d\n",
 			q, cpt->max_vfs);
 		return -EINVAL;
 	}
 
 	if (grp >= OTX_CPT_MAX_ENGINE_GROUPS) {
-		dev_err(dev, "Requested group %d is > than maximum avail %d",
+		dev_err(dev, "Requested group %d is > than maximum avail %d\n",
 			grp, OTX_CPT_MAX_ENGINE_GROUPS);
 		return -EINVAL;
 	}
 
 	eng_grp = &cpt->eng_grps.grp[grp];
 	if (!eng_grp->is_enabled) {
-		dev_err(dev, "Requested engine group %d is disabled", grp);
+		dev_err(dev, "Requested engine group %d is disabled\n", grp);
 		return -EINVAL;
 	}
 
@@ -212,7 +212,7 @@ static void otx_cpt_handle_mbox_intr(struct otx_cpt_device *cpt, int vf)
 		vftype = otx_cpt_bind_vq_to_grp(cpt, vf, (u8)mbx.data);
 		if ((vftype != OTX_CPT_AE_TYPES) &&
 		    (vftype != OTX_CPT_SE_TYPES)) {
-			dev_err(dev, "VF%d binding to eng group %llu failed",
+			dev_err(dev, "VF%d binding to eng group %llu failed\n",
 				vf, mbx.data);
 			otx_cptpf_mbox_send_nack(cpt, vf, &mbx);
 		} else {
diff --git a/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c b/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c
index d04baa319592..fec8f3b9b112 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptpf_ucode.c
@@ -62,7 +62,7 @@ static struct otx_cpt_bitmap get_cores_bmap(struct device *dev,
 	int i;
 
 	if (eng_grp->g->engs_num > OTX_CPT_MAX_ENGINES) {
-		dev_err(dev, "unsupported number of engines %d on octeontx",
+		dev_err(dev, "unsupported number of engines %d on octeontx\n",
 			eng_grp->g->engs_num);
 		return bmap;
 	}
@@ -78,7 +78,7 @@ static struct otx_cpt_bitmap get_cores_bmap(struct device *dev,
 	}
 
 	if (!found)
-		dev_err(dev, "No engines reserved for engine group %d",
+		dev_err(dev, "No engines reserved for engine group %d\n",
 			eng_grp->idx);
 	return bmap;
 }
@@ -306,7 +306,7 @@ static int process_tar_file(struct device *dev,
 	ucode_size = ntohl(ucode_hdr->code_length) * 2;
 	if (!ucode_size || (size < round_up(ucode_size, 16) +
 	    sizeof(struct otx_cpt_ucode_hdr) + OTX_CPT_UCODE_SIGN_LEN)) {
-		dev_err(dev, "Ucode %s invalid size", filename);
+		dev_err(dev, "Ucode %s invalid size\n", filename);
 		return -EINVAL;
 	}
 
@@ -379,18 +379,18 @@ static void print_tar_dbg_info(struct tar_arch_info_t *tar_arch,
 {
 	struct tar_ucode_info_t *curr;
 
-	pr_debug("Tar archive filename %s", tar_filename);
-	pr_debug("Tar archive pointer %p, size %ld", tar_arch->fw->data,
+	pr_debug("Tar archive filename %s\n", tar_filename);
+	pr_debug("Tar archive pointer %p, size %ld\n", tar_arch->fw->data,
 		 tar_arch->fw->size);
 	list_for_each_entry(curr, &tar_arch->ucodes, list) {
-		pr_debug("Ucode filename %s", curr->ucode.filename);
-		pr_debug("Ucode version string %s", curr->ucode.ver_str);
-		pr_debug("Ucode version %d.%d.%d.%d",
+		pr_debug("Ucode filename %s\n", curr->ucode.filename);
+		pr_debug("Ucode version string %s\n", curr->ucode.ver_str);
+		pr_debug("Ucode version %d.%d.%d.%d\n",
 			 curr->ucode.ver_num.nn, curr->ucode.ver_num.xx,
 			 curr->ucode.ver_num.yy, curr->ucode.ver_num.zz);
-		pr_debug("Ucode type (%d) %s", curr->ucode.type,
+		pr_debug("Ucode type (%d) %s\n", curr->ucode.type,
 			 get_ucode_type_str(curr->ucode.type));
-		pr_debug("Ucode size %d", curr->ucode.size);
+		pr_debug("Ucode size %d\n", curr->ucode.size);
 		pr_debug("Ucode ptr %p\n", curr->ucode_ptr);
 	}
 }
@@ -417,14 +417,14 @@ static struct tar_arch_info_t *load_tar_archive(struct device *dev,
 		goto release_tar_arch;
 
 	if (tar_arch->fw->size < TAR_BLOCK_LEN) {
-		dev_err(dev, "Invalid tar archive %s ", tar_filename);
+		dev_err(dev, "Invalid tar archive %s\n", tar_filename);
 		goto release_tar_arch;
 	}
 
 	tar_size = tar_arch->fw->size;
 	tar_blk = (struct tar_blk_t *) tar_arch->fw->data;
 	if (strncmp(tar_blk->hdr.magic, TAR_MAGIC, TAR_MAGIC_LEN - 1)) {
-		dev_err(dev, "Unsupported format of tar archive %s",
+		dev_err(dev, "Unsupported format of tar archive %s\n",
 			tar_filename);
 		goto release_tar_arch;
 	}
@@ -437,7 +437,7 @@ static struct tar_arch_info_t *load_tar_archive(struct device *dev,
 
 		if (tar_offs + cur_size > tar_size ||
 		    tar_offs + 2*TAR_BLOCK_LEN > tar_size) {
-			dev_err(dev, "Invalid tar archive %s ", tar_filename);
+			dev_err(dev, "Invalid tar archive %s\n", tar_filename);
 			goto release_tar_arch;
 		}
 
@@ -458,7 +458,7 @@ static struct tar_arch_info_t *load_tar_archive(struct device *dev,
 
 		/* Check for the end of the archive */
 		if (tar_offs + 2*TAR_BLOCK_LEN > tar_size) {
-			dev_err(dev, "Invalid tar archive %s ", tar_filename);
+			dev_err(dev, "Invalid tar archive %s\n", tar_filename);
 			goto release_tar_arch;
 		}
 
@@ -563,13 +563,13 @@ static void print_engs_info(struct otx_cpt_eng_grp_info *eng_grp,
 
 static void print_ucode_dbg_info(struct otx_cpt_ucode *ucode)
 {
-	pr_debug("Ucode info");
-	pr_debug("Ucode version string %s", ucode->ver_str);
-	pr_debug("Ucode version %d.%d.%d.%d", ucode->ver_num.nn,
+	pr_debug("Ucode info\n");
+	pr_debug("Ucode version string %s\n", ucode->ver_str);
+	pr_debug("Ucode version %d.%d.%d.%d\n", ucode->ver_num.nn,
 		 ucode->ver_num.xx, ucode->ver_num.yy, ucode->ver_num.zz);
-	pr_debug("Ucode type %s", get_ucode_type_str(ucode->type));
-	pr_debug("Ucode size %d", ucode->size);
-	pr_debug("Ucode virt address %16.16llx", (u64)ucode->align_va);
+	pr_debug("Ucode type %s\n", get_ucode_type_str(ucode->type));
+	pr_debug("Ucode size %d\n", ucode->size);
+	pr_debug("Ucode virt address %16.16llx\n", (u64)ucode->align_va);
 	pr_debug("Ucode phys address %16.16llx\n", ucode->align_dma);
 }
 
@@ -600,19 +600,19 @@ static void print_dbg_info(struct device *dev,
 	u32 mask[4];
 	int i, j;
 
-	pr_debug("Engine groups global info");
-	pr_debug("max SE %d, max AE %d",
+	pr_debug("Engine groups global info\n");
+	pr_debug("max SE %d, max AE %d\n",
 		 eng_grps->avail.max_se_cnt, eng_grps->avail.max_ae_cnt);
-	pr_debug("free SE %d", eng_grps->avail.se_cnt);
-	pr_debug("free AE %d", eng_grps->avail.ae_cnt);
+	pr_debug("free SE %d\n", eng_grps->avail.se_cnt);
+	pr_debug("free AE %d\n", eng_grps->avail.ae_cnt);
 
 	for (i = 0; i < OTX_CPT_MAX_ENGINE_GROUPS; i++) {
 		grp = &eng_grps->grp[i];
-		pr_debug("engine_group%d, state %s", i, grp->is_enabled ?
+		pr_debug("engine_group%d, state %s\n", i, grp->is_enabled ?
 			 "enabled" : "disabled");
 		if (grp->is_enabled) {
 			mirrored_grp = &eng_grps->grp[grp->mirror.idx];
-			pr_debug("Ucode0 filename %s, version %s",
+			pr_debug("Ucode0 filename %s, version %s\n",
 				 grp->mirror.is_ena ?
 				 mirrored_grp->ucode[0].filename :
 				 grp->ucode[0].filename,
@@ -626,18 +626,18 @@ static void print_dbg_info(struct device *dev,
 			if (engs->type) {
 				print_engs_info(grp, engs_info,
 						2*OTX_CPT_UCODE_NAME_LENGTH, j);
-				pr_debug("Slot%d: %s", j, engs_info);
+				pr_debug("Slot%d: %s\n", j, engs_info);
 				bitmap_to_arr32(mask, engs->bmap,
 						eng_grps->engs_num);
-				pr_debug("Mask:  %8.8x %8.8x %8.8x %8.8x",
+				pr_debug("Mask: %8.8x %8.8x %8.8x %8.8x\n",
 					 mask[3], mask[2], mask[1], mask[0]);
 			} else
-				pr_debug("Slot%d not used", j);
+				pr_debug("Slot%d not used\n", j);
 		}
 		if (grp->is_enabled) {
 			cpt_print_engines_mask(grp, dev, engs_mask,
 					       OTX_CPT_UCODE_NAME_LENGTH);
-			pr_debug("Cmask: %s", engs_mask);
+			pr_debug("Cmask: %s\n", engs_mask);
 		}
 	}
 }
@@ -766,7 +766,7 @@ static int check_engines_availability(struct device *dev,
 
 	if (avail_cnt < req_eng->count) {
 		dev_err(dev,
-			"Error available %s engines %d < than requested %d",
+			"Error available %s engines %d < than requested %d\n",
 			get_eng_type_str(req_eng->type),
 			avail_cnt, req_eng->count);
 		return -EBUSY;
@@ -867,7 +867,7 @@ static int copy_ucode_to_dma_mem(struct device *dev,
 				       OTX_CPT_UCODE_ALIGNMENT,
 				       &ucode->dma, GFP_KERNEL);
 	if (!ucode->va) {
-		dev_err(dev, "Unable to allocate space for microcode");
+		dev_err(dev, "Unable to allocate space for microcode\n");
 		return -ENOMEM;
 	}
 	ucode->align_va = PTR_ALIGN(ucode->va, OTX_CPT_UCODE_ALIGNMENT);
@@ -905,15 +905,15 @@ static int ucode_load(struct device *dev, struct otx_cpt_ucode *ucode,
 	ucode->size = ntohl(ucode_hdr->code_length) * 2;
 	if (!ucode->size || (fw->size < round_up(ucode->size, 16)
 	    + sizeof(struct otx_cpt_ucode_hdr) + OTX_CPT_UCODE_SIGN_LEN)) {
-		dev_err(dev, "Ucode %s invalid size", ucode_filename);
+		dev_err(dev, "Ucode %s invalid size\n", ucode_filename);
 		ret = -EINVAL;
 		goto release_fw;
 	}
 
 	ret = get_ucode_type(ucode_hdr, &ucode->type);
 	if (ret) {
-		dev_err(dev, "Microcode %s unknown type 0x%x", ucode->filename,
-			ucode->type);
+		dev_err(dev, "Microcode %s unknown type 0x%x\n",
+			ucode->filename, ucode->type);
 		goto release_fw;
 	}
 
@@ -1083,7 +1083,7 @@ static int eng_grp_update_masks(struct device *dev,
 			break;
 
 		default:
-			dev_err(dev, "Invalid engine type %d", engs->type);
+			dev_err(dev, "Invalid engine type %d\n", engs->type);
 			return -EINVAL;
 		}
 
@@ -1142,13 +1142,14 @@ static int delete_engine_group(struct device *dev,
 		return -EINVAL;
 
 	if (eng_grp->mirror.ref_count) {
-		dev_err(dev, "Can't delete engine_group%d as it is used by:",
+		dev_err(dev, "Can't delete engine_group%d as it is used by engine_group(s):",
 			eng_grp->idx);
 		for (i = 0; i < OTX_CPT_MAX_ENGINE_GROUPS; i++) {
 			if (eng_grp->g->grp[i].mirror.is_ena &&
 			    eng_grp->g->grp[i].mirror.idx == eng_grp->idx)
-				dev_err(dev, "engine_group%d", i);
+				pr_cont(" %d", i);
 		}
+		pr_cont("\n");
 		return -EINVAL;
 	}
 
@@ -1182,7 +1183,7 @@ static int validate_1_ucode_scenario(struct device *dev,
 		if (!otx_cpt_uc_supports_eng_type(&eng_grp->ucode[0],
 						  engs[i].type)) {
 			dev_err(dev,
-				"Microcode %s does not support %s engines",
+				"Microcode %s does not support %s engines\n",
 				eng_grp->ucode[0].filename,
 				get_eng_type_str(engs[i].type));
 			return -EINVAL;
@@ -1220,7 +1221,7 @@ static int create_engine_group(struct device *dev,
 	/* Validate if requested engine types are supported by this device */
 	for (i = 0; i < engs_cnt; i++)
 		if (!dev_supports_eng_type(eng_grps, engs[i].type)) {
-			dev_err(dev, "Device does not support %s engines",
+			dev_err(dev, "Device does not support %s engines\n",
 				get_eng_type_str(engs[i].type));
 			return -EPERM;
 		}
@@ -1228,7 +1229,7 @@ static int create_engine_group(struct device *dev,
 	/* Find engine group which is not used */
 	eng_grp = find_unused_eng_grp(eng_grps);
 	if (!eng_grp) {
-		dev_err(dev, "Error all engine groups are being used");
+		dev_err(dev, "Error all engine groups are being used\n");
 		return -ENOSPC;
 	}
 
@@ -1298,11 +1299,11 @@ static int create_engine_group(struct device *dev,
 	eng_grp->is_enabled = true;
 	if (eng_grp->mirror.is_ena)
 		dev_info(dev,
-			 "Engine_group%d: reuse microcode %s from group %d",
+			 "Engine_group%d: reuse microcode %s from group %d\n",
 			 eng_grp->idx, mirrored_eng_grp->ucode[0].ver_str,
 			 mirrored_eng_grp->idx);
 	else
-		dev_info(dev, "Engine_group%d: microcode loaded %s",
+		dev_info(dev, "Engine_group%d: microcode loaded %s\n",
 			 eng_grp->idx, eng_grp->ucode[0].ver_str);
 
 	return 0;
@@ -1412,14 +1413,14 @@ static ssize_t ucode_load_store(struct device *dev,
 	} else {
 		if (del_grp_idx < 0 ||
 		    del_grp_idx >= OTX_CPT_MAX_ENGINE_GROUPS) {
-			dev_err(dev, "Invalid engine group index %d",
+			dev_err(dev, "Invalid engine group index %d\n",
 				del_grp_idx);
 			ret = -EINVAL;
 			return ret;
 		}
 
 		if (!eng_grps->grp[del_grp_idx].is_enabled) {
-			dev_err(dev, "Error engine_group%d is not configured",
+			dev_err(dev, "Error engine_group%d is not configured\n",
 				del_grp_idx);
 			ret = -EINVAL;
 			return ret;
@@ -1568,7 +1569,7 @@ void otx_cpt_disable_all_cores(struct otx_cpt_device *cpt)
 		udelay(CSR_DELAY);
 		reg = readq(cpt->reg_base + OTX_CPT_PF_EXEC_BUSY);
 		if (timeout--) {
-			dev_warn(&cpt->pdev->dev, "Cores still busy");
+			dev_warn(&cpt->pdev->dev, "Cores still busy\n");
 			break;
 		}
 	}
@@ -1626,7 +1627,7 @@ int otx_cpt_init_eng_grps(struct pci_dev *pdev,
 			     eng_grps->avail.max_ae_cnt;
 	if (eng_grps->engs_num > OTX_CPT_MAX_ENGINES) {
 		dev_err(&pdev->dev,
-			"Number of engines %d > than max supported %d",
+			"Number of engines %d > than max supported %d\n",
 			eng_grps->engs_num, OTX_CPT_MAX_ENGINES);
 		ret = -EINVAL;
 		goto err;
diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
index 06202bcffb33..60e744f680d3 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptvf_algs.c
@@ -1660,7 +1660,7 @@ int otx_cpt_crypto_init(struct pci_dev *pdev, struct module *mod,
 	case OTX_CPT_SE_TYPES:
 		count = atomic_read(&se_devices.count);
 		if (count >= CPT_MAX_VF_NUM) {
-			dev_err(&pdev->dev, "No space to add a new device");
+			dev_err(&pdev->dev, "No space to add a new device\n");
 			ret = -ENOSPC;
 			goto err;
 		}
@@ -1687,7 +1687,7 @@ int otx_cpt_crypto_init(struct pci_dev *pdev, struct module *mod,
 	case OTX_CPT_AE_TYPES:
 		count = atomic_read(&ae_devices.count);
 		if (count >= CPT_MAX_VF_NUM) {
-			dev_err(&pdev->dev, "No space to a add new device");
+			dev_err(&pdev->dev, "No space to a add new device\n");
 			ret = -ENOSPC;
 			goto err;
 		}
@@ -1728,7 +1728,7 @@ void otx_cpt_crypto_exit(struct pci_dev *pdev, struct module *mod,
 		}
 
 	if (!dev_found) {
-		dev_err(&pdev->dev, "%s device not found", __func__);
+		dev_err(&pdev->dev, "%s device not found\n", __func__);
 		goto exit;
 	}
 
diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_main.c b/drivers/crypto/marvell/octeontx/otx_cptvf_main.c
index a91860b5dc77..ce3168327a39 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptvf_main.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptvf_main.c
@@ -584,7 +584,7 @@ static irqreturn_t cptvf_done_intr_handler(int __always_unused irq,
 		cptvf_write_vq_done_ack(cptvf, intr);
 		wqe = get_cptvf_vq_wqe(cptvf, 0);
 		if (unlikely(!wqe)) {
-			dev_err(&pdev->dev, "No work to schedule for VF (%d)",
+			dev_err(&pdev->dev, "No work to schedule for VF (%d)\n",
 				cptvf->vfid);
 			return IRQ_NONE;
 		}
@@ -602,7 +602,7 @@ static void cptvf_set_irq_affinity(struct otx_cptvf *cptvf, int vec)
 	if (!zalloc_cpumask_var(&cptvf->affinity_mask[vec],
 				GFP_KERNEL)) {
 		dev_err(&pdev->dev,
-			"Allocation failed for affinity_mask for VF %d",
+			"Allocation failed for affinity_mask for VF %d\n",
 			cptvf->vfid);
 		return;
 	}
@@ -691,7 +691,7 @@ static ssize_t vf_engine_group_store(struct device *dev,
 		return -EINVAL;
 
 	if (val >= OTX_CPT_MAX_ENGINE_GROUPS) {
-		dev_err(dev, "Engine group >= than max available groups %d",
+		dev_err(dev, "Engine group >= than max available groups %d\n",
 			OTX_CPT_MAX_ENGINE_GROUPS);
 		return -EINVAL;
 	}
@@ -837,7 +837,7 @@ static int otx_cptvf_probe(struct pci_dev *pdev,
 			  cptvf_misc_intr_handler, 0, "CPT VF misc intr",
 			  cptvf);
 	if (err) {
-		dev_err(dev, "Failed to request misc irq");
+		dev_err(dev, "Failed to request misc irq\n");
 		goto free_vectors;
 	}
 
@@ -854,7 +854,7 @@ static int otx_cptvf_probe(struct pci_dev *pdev,
 	cptvf->cqinfo.qchunksize = OTX_CPT_CMD_QCHUNK_SIZE;
 	err = cptvf_sw_init(cptvf, OTX_CPT_CMD_QLEN, OTX_CPT_NUM_QS_PER_VF);
 	if (err) {
-		dev_err(dev, "cptvf_sw_init() failed");
+		dev_err(dev, "cptvf_sw_init() failed\n");
 		goto free_misc_irq;
 	}
 	/* Convey VQ LEN to PF */
@@ -946,7 +946,7 @@ static void otx_cptvf_remove(struct pci_dev *pdev)
 
 	/* Convey DOWN to PF */
 	if (otx_cptvf_send_vf_down(cptvf)) {
-		dev_err(&pdev->dev, "PF not responding to DOWN msg");
+		dev_err(&pdev->dev, "PF not responding to DOWN msg\n");
 	} else {
 		sysfs_remove_group(&pdev->dev.kobj, &otx_cptvf_sysfs_group);
 		otx_cpt_crypto_exit(pdev, THIS_MODULE, cptvf->vftype);
diff --git a/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c b/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c
index df839b880354..239195cccf93 100644
--- a/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c
+++ b/drivers/crypto/marvell/octeontx/otx_cptvf_reqmgr.c
@@ -314,7 +314,7 @@ static int process_request(struct pci_dev *pdev, struct otx_cpt_req_info *req,
 							      GFP_ATOMIC;
 	ret = setup_sgio_list(pdev, &info, req, gfp);
 	if (unlikely(ret)) {
-		dev_err(&pdev->dev, "Setting up SG list failed");
+		dev_err(&pdev->dev, "Setting up SG list failed\n");
 		goto request_cleanup;
 	}
 	cpt_req->dlen = info->dlen;
@@ -410,17 +410,17 @@ int otx_cpt_do_request(struct pci_dev *pdev, struct otx_cpt_req_info *req,
 	struct otx_cptvf *cptvf = pci_get_drvdata(pdev);
 
 	if (!otx_cpt_device_ready(cptvf)) {
-		dev_err(&pdev->dev, "CPT Device is not ready");
+		dev_err(&pdev->dev, "CPT Device is not ready\n");
 		return -ENODEV;
 	}
 
 	if ((cptvf->vftype == OTX_CPT_SE_TYPES) && (!req->ctrl.s.se_req)) {
-		dev_err(&pdev->dev, "CPTVF-%d of SE TYPE got AE request",
+		dev_err(&pdev->dev, "CPTVF-%d of SE TYPE got AE request\n",
 			cptvf->vfid);
 		return -EINVAL;
 	} else if ((cptvf->vftype == OTX_CPT_AE_TYPES) &&
 		   (req->ctrl.s.se_req)) {
-		dev_err(&pdev->dev, "CPTVF-%d of AE TYPE got SE request",
+		dev_err(&pdev->dev, "CPTVF-%d of AE TYPE got SE request\n",
 			cptvf->vfid);
 		return -EINVAL;
 	}
@@ -461,7 +461,7 @@ static int cpt_process_ccode(struct pci_dev *pdev,
 		/* check for timeout */
 		if (time_after_eq(jiffies, cpt_info->time_in +
 				  OTX_CPT_COMMAND_TIMEOUT * HZ))
-			dev_warn(&pdev->dev, "Request timed out 0x%p", req);
+			dev_warn(&pdev->dev, "Request timed out 0x%p\n", req);
 		else if (cpt_info->extra_time < OTX_CPT_TIME_IN_RESET_COUNT) {
 			cpt_info->time_in = jiffies;
 			cpt_info->extra_time++;
diff --git a/drivers/crypto/mediatek/mtk-sha.c b/drivers/crypto/mediatek/mtk-sha.c
index bd6309e57ab8..da3f0b8814aa 100644
--- a/drivers/crypto/mediatek/mtk-sha.c
+++ b/drivers/crypto/mediatek/mtk-sha.c
@@ -805,12 +805,9 @@ static int mtk_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 	size_t ds = crypto_shash_digestsize(bctx->shash);
 	int err, i;
 
-	SHASH_DESC_ON_STACK(shash, bctx->shash);
-
-	shash->tfm = bctx->shash;
-
 	if (keylen > bs) {
-		err = crypto_shash_digest(shash, key, keylen, bctx->ipad);
+		err = crypto_shash_tfm_digest(bctx->shash, key, keylen,
+					      bctx->ipad);
 		if (err)
 			return err;
 		keylen = ds;
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index f5c468f2cc82..6a828bbecea4 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -462,7 +462,6 @@ static int n2_hmac_async_setkey(struct crypto_ahash *tfm, const u8 *key,
 	struct n2_hmac_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct crypto_shash *child_shash = ctx->child_shash;
 	struct crypto_ahash *fallback_tfm;
-	SHASH_DESC_ON_STACK(shash, child_shash);
 	int err, bs, ds;
 
 	fallback_tfm = ctx->base.fallback_tfm;
@@ -470,14 +469,12 @@ static int n2_hmac_async_setkey(struct crypto_ahash *tfm, const u8 *key,
 	if (err)
 		return err;
 
-	shash->tfm = child_shash;
-
 	bs = crypto_shash_blocksize(child_shash);
 	ds = crypto_shash_digestsize(child_shash);
 	BUG_ON(ds > N2_HASH_KEY_MAX);
 	if (keylen > bs) {
-		err = crypto_shash_digest(shash, key, keylen,
-					  ctx->hash_key);
+		err = crypto_shash_tfm_digest(child_shash, key, keylen,
+					      ctx->hash_key);
 		if (err)
 			return err;
 		keylen = ds;
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index e4072cd38585..063ad5d03f33 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -33,7 +33,6 @@
 #include <linux/of_irq.h>
 #include <linux/delay.h>
 #include <linux/crypto.h>
-#include <linux/cryptohash.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/algapi.h>
 #include <crypto/sha.h>
@@ -1245,16 +1244,6 @@ static int omap_sham_update(struct ahash_request *req)
 	return omap_sham_enqueue(req, OP_UPDATE);
 }
 
-static int omap_sham_shash_digest(struct crypto_shash *tfm, u32 flags,
-				  const u8 *data, unsigned int len, u8 *out)
-{
-	SHASH_DESC_ON_STACK(shash, tfm);
-
-	shash->tfm = tfm;
-
-	return crypto_shash_digest(shash, data, len, out);
-}
-
 static int omap_sham_final_shash(struct ahash_request *req)
 {
 	struct omap_sham_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
@@ -1270,9 +1259,8 @@ static int omap_sham_final_shash(struct ahash_request *req)
 	    !test_bit(FLAGS_AUTO_XOR, &ctx->dd->flags))
 		offset = get_block_size(ctx);
 
-	return omap_sham_shash_digest(tctx->fallback, req->base.flags,
-				      ctx->buffer + offset,
-				      ctx->bufcnt - offset, req->result);
+	return crypto_shash_tfm_digest(tctx->fallback, ctx->buffer + offset,
+				       ctx->bufcnt - offset, req->result);
 }
 
 static int omap_sham_final(struct ahash_request *req)
@@ -1351,9 +1339,8 @@ static int omap_sham_setkey(struct crypto_ahash *tfm, const u8 *key,
 		return err;
 
 	if (keylen > bs) {
-		err = omap_sham_shash_digest(bctx->shash,
-				crypto_shash_get_flags(bctx->shash),
-				key, keylen, bctx->ipad);
+		err = crypto_shash_tfm_digest(bctx->shash, key, keylen,
+					      bctx->ipad);
 		if (err)
 			return err;
 		keylen = ds;
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 2a16800d2579..341433fbcc4a 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -1521,37 +1521,6 @@ static int s5p_hash_update(struct ahash_request *req)
 }
 
 /**
- * s5p_hash_shash_digest() - calculate shash digest
- * @tfm:	crypto transformation
- * @flags:	tfm flags
- * @data:	input data
- * @len:	length of data
- * @out:	output buffer
- */
-static int s5p_hash_shash_digest(struct crypto_shash *tfm, u32 flags,
-				 const u8 *data, unsigned int len, u8 *out)
-{
-	SHASH_DESC_ON_STACK(shash, tfm);
-
-	shash->tfm = tfm;
-
-	return crypto_shash_digest(shash, data, len, out);
-}
-
-/**
- * s5p_hash_final_shash() - calculate shash digest
- * @req:	AHASH request
- */
-static int s5p_hash_final_shash(struct ahash_request *req)
-{
-	struct s5p_hash_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
-	struct s5p_hash_reqctx *ctx = ahash_request_ctx(req);
-
-	return s5p_hash_shash_digest(tctx->fallback, req->base.flags,
-				     ctx->buffer, ctx->bufcnt, req->result);
-}
-
-/**
  * s5p_hash_final() - close up hash and calculate digest
  * @req:	AHASH request
  *
@@ -1582,8 +1551,12 @@ static int s5p_hash_final(struct ahash_request *req)
 	if (ctx->error)
 		return -EINVAL; /* uncompleted hash is not needed */
 
-	if (!ctx->digcnt && ctx->bufcnt < BUFLEN)
-		return s5p_hash_final_shash(req);
+	if (!ctx->digcnt && ctx->bufcnt < BUFLEN) {
+		struct s5p_hash_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
+
+		return crypto_shash_tfm_digest(tctx->fallback, ctx->buffer,
+					       ctx->bufcnt, req->result);
+	}
 
 	return s5p_hash_enqueue(req, false); /* HASH_OP_FINAL */
 }
diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c
index 8e92e4ac79f1..3ba41148c2a4 100644
--- a/drivers/crypto/stm32/stm32-crc32.c
+++ b/drivers/crypto/stm32/stm32-crc32.c
@@ -28,18 +28,23 @@
 
 /* Registers values */
 #define CRC_CR_RESET            BIT(0)
-#define CRC_CR_REVERSE          (BIT(7) | BIT(6) | BIT(5))
-#define CRC_INIT_DEFAULT        0xFFFFFFFF
+#define CRC_CR_REV_IN_WORD      (BIT(6) | BIT(5))
+#define CRC_CR_REV_IN_BYTE      BIT(5)
+#define CRC_CR_REV_OUT          BIT(7)
+#define CRC32C_INIT_DEFAULT     0xFFFFFFFF
 
 #define CRC_AUTOSUSPEND_DELAY	50
 
+static unsigned int burst_size;
+module_param(burst_size, uint, 0644);
+MODULE_PARM_DESC(burst_size, "Select burst byte size (0 unlimited)");
+
 struct stm32_crc {
 	struct list_head list;
 	struct device    *dev;
 	void __iomem     *regs;
 	struct clk       *clk;
-	u8               pending_data[sizeof(u32)];
-	size_t           nb_pending_bytes;
+	spinlock_t       lock;
 };
 
 struct stm32_crc_list {
@@ -59,14 +64,13 @@ struct stm32_crc_ctx {
 
 struct stm32_crc_desc_ctx {
 	u32    partial; /* crc32c: partial in first 4 bytes of that struct */
-	struct stm32_crc *crc;
 };
 
 static int stm32_crc32_cra_init(struct crypto_tfm *tfm)
 {
 	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
 
-	mctx->key = CRC_INIT_DEFAULT;
+	mctx->key = 0;
 	mctx->poly = CRC32_POLY_LE;
 	return 0;
 }
@@ -75,7 +79,7 @@ static int stm32_crc32c_cra_init(struct crypto_tfm *tfm)
 {
 	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
 
-	mctx->key = CRC_INIT_DEFAULT;
+	mctx->key = CRC32C_INIT_DEFAULT;
 	mctx->poly = CRC32C_POLY_LE;
 	return 0;
 }
@@ -92,87 +96,135 @@ static int stm32_crc_setkey(struct crypto_shash *tfm, const u8 *key,
 	return 0;
 }
 
+static struct stm32_crc *stm32_crc_get_next_crc(void)
+{
+	struct stm32_crc *crc;
+
+	spin_lock_bh(&crc_list.lock);
+	crc = list_first_entry(&crc_list.dev_list, struct stm32_crc, list);
+	if (crc)
+		list_move_tail(&crc->list, &crc_list.dev_list);
+	spin_unlock_bh(&crc_list.lock);
+
+	return crc;
+}
+
 static int stm32_crc_init(struct shash_desc *desc)
 {
 	struct stm32_crc_desc_ctx *ctx = shash_desc_ctx(desc);
 	struct stm32_crc_ctx *mctx = crypto_shash_ctx(desc->tfm);
 	struct stm32_crc *crc;
+	unsigned long flags;
 
-	spin_lock_bh(&crc_list.lock);
-	list_for_each_entry(crc, &crc_list.dev_list, list) {
-		ctx->crc = crc;
-		break;
-	}
-	spin_unlock_bh(&crc_list.lock);
+	crc = stm32_crc_get_next_crc();
+	if (!crc)
+		return -ENODEV;
+
+	pm_runtime_get_sync(crc->dev);
 
-	pm_runtime_get_sync(ctx->crc->dev);
+	spin_lock_irqsave(&crc->lock, flags);
 
 	/* Reset, set key, poly and configure in bit reverse mode */
-	writel_relaxed(bitrev32(mctx->key), ctx->crc->regs + CRC_INIT);
-	writel_relaxed(bitrev32(mctx->poly), ctx->crc->regs + CRC_POL);
-	writel_relaxed(CRC_CR_RESET | CRC_CR_REVERSE, ctx->crc->regs + CRC_CR);
+	writel_relaxed(bitrev32(mctx->key), crc->regs + CRC_INIT);
+	writel_relaxed(bitrev32(mctx->poly), crc->regs + CRC_POL);
+	writel_relaxed(CRC_CR_RESET | CRC_CR_REV_IN_WORD | CRC_CR_REV_OUT,
+		       crc->regs + CRC_CR);
 
 	/* Store partial result */
-	ctx->partial = readl_relaxed(ctx->crc->regs + CRC_DR);
-	ctx->crc->nb_pending_bytes = 0;
+	ctx->partial = readl_relaxed(crc->regs + CRC_DR);
 
-	pm_runtime_mark_last_busy(ctx->crc->dev);
-	pm_runtime_put_autosuspend(ctx->crc->dev);
+	spin_unlock_irqrestore(&crc->lock, flags);
+
+	pm_runtime_mark_last_busy(crc->dev);
+	pm_runtime_put_autosuspend(crc->dev);
 
 	return 0;
 }
 
-static int stm32_crc_update(struct shash_desc *desc, const u8 *d8,
-			    unsigned int length)
+static int burst_update(struct shash_desc *desc, const u8 *d8,
+			size_t length)
 {
 	struct stm32_crc_desc_ctx *ctx = shash_desc_ctx(desc);
-	struct stm32_crc *crc = ctx->crc;
-	u32 *d32;
-	unsigned int i;
+	struct stm32_crc_ctx *mctx = crypto_shash_ctx(desc->tfm);
+	struct stm32_crc *crc;
+	unsigned long flags;
+
+	crc = stm32_crc_get_next_crc();
+	if (!crc)
+		return -ENODEV;
 
 	pm_runtime_get_sync(crc->dev);
 
-	if (unlikely(crc->nb_pending_bytes)) {
-		while (crc->nb_pending_bytes != sizeof(u32) && length) {
-			/* Fill in pending data */
-			crc->pending_data[crc->nb_pending_bytes++] = *(d8++);
+	spin_lock_irqsave(&crc->lock, flags);
+
+	/*
+	 * Restore previously calculated CRC for this context as init value
+	 * Restore polynomial configuration
+	 * Configure in register for word input data,
+	 * Configure out register in reversed bit mode data.
+	 */
+	writel_relaxed(bitrev32(ctx->partial), crc->regs + CRC_INIT);
+	writel_relaxed(bitrev32(mctx->poly), crc->regs + CRC_POL);
+	writel_relaxed(CRC_CR_RESET | CRC_CR_REV_IN_WORD | CRC_CR_REV_OUT,
+		       crc->regs + CRC_CR);
+
+	if (d8 != PTR_ALIGN(d8, sizeof(u32))) {
+		/* Configure for byte data */
+		writel_relaxed(CRC_CR_REV_IN_BYTE | CRC_CR_REV_OUT,
+			       crc->regs + CRC_CR);
+		while (d8 != PTR_ALIGN(d8, sizeof(u32)) && length) {
+			writeb_relaxed(*d8++, crc->regs + CRC_DR);
 			length--;
 		}
-
-		if (crc->nb_pending_bytes == sizeof(u32)) {
-			/* Process completed pending data */
-			writel_relaxed(*(u32 *)crc->pending_data,
-				       crc->regs + CRC_DR);
-			crc->nb_pending_bytes = 0;
-		}
+		/* Configure for word data */
+		writel_relaxed(CRC_CR_REV_IN_WORD | CRC_CR_REV_OUT,
+			       crc->regs + CRC_CR);
 	}
 
-	d32 = (u32 *)d8;
-	for (i = 0; i < length >> 2; i++)
-		/* Process 32 bits data */
-		writel_relaxed(*(d32++), crc->regs + CRC_DR);
+	for (; length >= sizeof(u32); d8 += sizeof(u32), length -= sizeof(u32))
+		writel_relaxed(*((u32 *)d8), crc->regs + CRC_DR);
+
+	if (length) {
+		/* Configure for byte data */
+		writel_relaxed(CRC_CR_REV_IN_BYTE | CRC_CR_REV_OUT,
+			       crc->regs + CRC_CR);
+		while (length--)
+			writeb_relaxed(*d8++, crc->regs + CRC_DR);
+	}
 
 	/* Store partial result */
 	ctx->partial = readl_relaxed(crc->regs + CRC_DR);
 
+	spin_unlock_irqrestore(&crc->lock, flags);
+
 	pm_runtime_mark_last_busy(crc->dev);
 	pm_runtime_put_autosuspend(crc->dev);
 
-	/* Check for pending data (non 32 bits) */
-	length &= 3;
-	if (likely(!length))
-		return 0;
+	return 0;
+}
 
-	if ((crc->nb_pending_bytes + length) >= sizeof(u32)) {
-		/* Shall not happen */
-		dev_err(crc->dev, "Pending data overflow\n");
-		return -EINVAL;
-	}
+static int stm32_crc_update(struct shash_desc *desc, const u8 *d8,
+			    unsigned int length)
+{
+	const unsigned int burst_sz = burst_size;
+	unsigned int rem_sz;
+	const u8 *cur;
+	size_t size;
+	int ret;
 
-	d8 = (const u8 *)d32;
-	for (i = 0; i < length; i++)
-		/* Store pending data */
-		crc->pending_data[crc->nb_pending_bytes++] = *(d8++);
+	if (!burst_sz)
+		return burst_update(desc, d8, length);
+
+	/* Digest first bytes not 32bit aligned at first pass in the loop */
+	size = min(length,
+		   burst_sz + (unsigned int)d8 - ALIGN_DOWN((unsigned int)d8,
+							    sizeof(u32)));
+	for (rem_sz = length, cur = d8; rem_sz;
+	     rem_sz -= size, cur += size, size = min(rem_sz, burst_sz)) {
+		ret = burst_update(desc, cur, size);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
@@ -202,6 +254,8 @@ static int stm32_crc_digest(struct shash_desc *desc, const u8 *data,
 	return stm32_crc_init(desc) ?: stm32_crc_finup(desc, data, length, out);
 }
 
+static unsigned int refcnt;
+static DEFINE_MUTEX(refcnt_lock);
 static struct shash_alg algs[] = {
 	/* CRC-32 */
 	{
@@ -284,20 +338,29 @@ static int stm32_crc_probe(struct platform_device *pdev)
 
 	pm_runtime_get_noresume(dev);
 	pm_runtime_set_active(dev);
+	pm_runtime_irq_safe(dev);
 	pm_runtime_enable(dev);
 
+	spin_lock_init(&crc->lock);
+
 	platform_set_drvdata(pdev, crc);
 
 	spin_lock(&crc_list.lock);
 	list_add(&crc->list, &crc_list.dev_list);
 	spin_unlock(&crc_list.lock);
 
-	ret = crypto_register_shashes(algs, ARRAY_SIZE(algs));
-	if (ret) {
-		dev_err(dev, "Failed to register\n");
-		clk_disable_unprepare(crc->clk);
-		return ret;
+	mutex_lock(&refcnt_lock);
+	if (!refcnt) {
+		ret = crypto_register_shashes(algs, ARRAY_SIZE(algs));
+		if (ret) {
+			mutex_unlock(&refcnt_lock);
+			dev_err(dev, "Failed to register\n");
+			clk_disable_unprepare(crc->clk);
+			return ret;
+		}
 	}
+	refcnt++;
+	mutex_unlock(&refcnt_lock);
 
 	dev_info(dev, "Initialized\n");
 
@@ -318,7 +381,10 @@ static int stm32_crc_remove(struct platform_device *pdev)
 	list_del(&crc->list);
 	spin_unlock(&crc_list.lock);
 
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+	mutex_lock(&refcnt_lock);
+	if (!--refcnt)
+		crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+	mutex_unlock(&refcnt_lock);
 
 	pm_runtime_disable(crc->dev);
 	pm_runtime_put_noidle(crc->dev);
@@ -328,34 +394,60 @@ static int stm32_crc_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int stm32_crc_runtime_suspend(struct device *dev)
+static int __maybe_unused stm32_crc_suspend(struct device *dev)
 {
 	struct stm32_crc *crc = dev_get_drvdata(dev);
+	int ret;
 
-	clk_disable_unprepare(crc->clk);
+	ret = pm_runtime_force_suspend(dev);
+	if (ret)
+		return ret;
+
+	clk_unprepare(crc->clk);
 
 	return 0;
 }
 
-static int stm32_crc_runtime_resume(struct device *dev)
+static int __maybe_unused stm32_crc_resume(struct device *dev)
 {
 	struct stm32_crc *crc = dev_get_drvdata(dev);
 	int ret;
 
-	ret = clk_prepare_enable(crc->clk);
+	ret = clk_prepare(crc->clk);
 	if (ret) {
-		dev_err(crc->dev, "Failed to prepare_enable clock\n");
+		dev_err(crc->dev, "Failed to prepare clock\n");
+		return ret;
+	}
+
+	return pm_runtime_force_resume(dev);
+}
+
+static int __maybe_unused stm32_crc_runtime_suspend(struct device *dev)
+{
+	struct stm32_crc *crc = dev_get_drvdata(dev);
+
+	clk_disable(crc->clk);
+
+	return 0;
+}
+
+static int __maybe_unused stm32_crc_runtime_resume(struct device *dev)
+{
+	struct stm32_crc *crc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_enable(crc->clk);
+	if (ret) {
+		dev_err(crc->dev, "Failed to enable clock\n");
 		return ret;
 	}
 
 	return 0;
 }
-#endif
 
 static const struct dev_pm_ops stm32_crc_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
-				pm_runtime_force_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(stm32_crc_suspend,
+				stm32_crc_resume)
 	SET_RUNTIME_PM_OPS(stm32_crc_runtime_suspend,
 			   stm32_crc_runtime_resume, NULL)
 };
diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index 167b80eec437..03c5e6683805 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -507,6 +507,7 @@ static int stm32_hash_hmac_dma_send(struct stm32_hash_dev *hdev)
 static int stm32_hash_dma_init(struct stm32_hash_dev *hdev)
 {
 	struct dma_slave_config dma_conf;
+	struct dma_chan *chan;
 	int err;
 
 	memset(&dma_conf, 0, sizeof(dma_conf));
@@ -518,11 +519,11 @@ static int stm32_hash_dma_init(struct stm32_hash_dev *hdev)
 	dma_conf.dst_maxburst = hdev->dma_maxburst;
 	dma_conf.device_fc = false;
 
-	hdev->dma_lch = dma_request_chan(hdev->dev, "in");
-	if (IS_ERR(hdev->dma_lch)) {
-		dev_err(hdev->dev, "Couldn't acquire a slave DMA channel.\n");
-		return PTR_ERR(hdev->dma_lch);
-	}
+	chan = dma_request_chan(hdev->dev, "in");
+	if (IS_ERR(chan))
+		return PTR_ERR(chan);
+
+	hdev->dma_lch = chan;
 
 	err = dmaengine_slave_config(hdev->dma_lch, &dma_conf);
 	if (err) {
@@ -1463,8 +1464,11 @@ static int stm32_hash_probe(struct platform_device *pdev)
 
 	hdev->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(hdev->clk)) {
-		dev_err(dev, "failed to get clock for hash (%lu)\n",
-			PTR_ERR(hdev->clk));
+		if (PTR_ERR(hdev->clk) != -EPROBE_DEFER) {
+			dev_err(dev, "failed to get clock for hash (%lu)\n",
+				PTR_ERR(hdev->clk));
+		}
+
 		return PTR_ERR(hdev->clk);
 	}
 
@@ -1482,7 +1486,12 @@ static int stm32_hash_probe(struct platform_device *pdev)
 	pm_runtime_enable(dev);
 
 	hdev->rst = devm_reset_control_get(&pdev->dev, NULL);
-	if (!IS_ERR(hdev->rst)) {
+	if (IS_ERR(hdev->rst)) {
+		if (PTR_ERR(hdev->rst) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto err_reset;
+		}
+	} else {
 		reset_control_assert(hdev->rst);
 		udelay(2);
 		reset_control_deassert(hdev->rst);
@@ -1493,8 +1502,15 @@ static int stm32_hash_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, hdev);
 
 	ret = stm32_hash_dma_init(hdev);
-	if (ret)
+	switch (ret) {
+	case 0:
+		break;
+	case -ENOENT:
 		dev_dbg(dev, "DMA mode not available\n");
+		break;
+	default:
+		goto err_dma;
+	}
 
 	spin_lock(&stm32_hash.lock);
 	list_add_tail(&hdev->list, &stm32_hash.dev_list);
@@ -1532,10 +1548,10 @@ err_engine:
 	spin_lock(&stm32_hash.lock);
 	list_del(&hdev->list);
 	spin_unlock(&stm32_hash.lock);
-
+err_dma:
 	if (hdev->dma_lch)
 		dma_release_channel(hdev->dma_lch);
-
+err_reset:
 	pm_runtime_disable(dev);
 	pm_runtime_put_noidle(dev);
 
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index 3d0a7e702c94..1e678bdf5aed 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -22,6 +22,7 @@ int dev_dax_kmem_probe(struct device *dev)
 	resource_size_t kmem_size;
 	resource_size_t kmem_end;
 	struct resource *new_res;
+	const char *new_res_name;
 	int numa_node;
 	int rc;
 
@@ -48,11 +49,16 @@ int dev_dax_kmem_probe(struct device *dev)
 	kmem_size &= ~(memory_block_size_bytes() - 1);
 	kmem_end = kmem_start + kmem_size;
 
-	/* Region is permanently reserved.  Hot-remove not yet implemented. */
-	new_res = request_mem_region(kmem_start, kmem_size, dev_name(dev));
+	new_res_name = kstrdup(dev_name(dev), GFP_KERNEL);
+	if (!new_res_name)
+		return -ENOMEM;
+
+	/* Region is permanently reserved if hotremove fails. */
+	new_res = request_mem_region(kmem_start, kmem_size, new_res_name);
 	if (!new_res) {
 		dev_warn(dev, "could not reserve region [%pa-%pa]\n",
 			 &kmem_start, &kmem_end);
+		kfree(new_res_name);
 		return -EBUSY;
 	}
 
@@ -63,12 +69,12 @@ int dev_dax_kmem_probe(struct device *dev)
 	 * unknown to us that will break add_memory() below.
 	 */
 	new_res->flags = IORESOURCE_SYSTEM_RAM;
-	new_res->name = dev_name(dev);
 
 	rc = add_memory(numa_node, new_res->start, resource_size(new_res));
 	if (rc) {
 		release_resource(new_res);
 		kfree(new_res);
+		kfree(new_res_name);
 		return rc;
 	}
 	dev_dax->dax_kmem_res = new_res;
@@ -83,6 +89,7 @@ static int dev_dax_kmem_remove(struct device *dev)
 	struct resource *res = dev_dax->dax_kmem_res;
 	resource_size_t kmem_start = res->start;
 	resource_size_t kmem_size = resource_size(res);
+	const char *res_name = res->name;
 	int rc;
 
 	/*
@@ -102,6 +109,7 @@ static int dev_dax_kmem_remove(struct device *dev)
 	/* Release and free dax resources */
 	release_resource(res);
 	kfree(res);
+	kfree(res_name);
 	dev_dax->dax_kmem_res = NULL;
 
 	return 0;
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index ccc9eda1bc28..07df88f2e305 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -388,7 +388,8 @@ static long dma_buf_ioctl(struct file *file,
 
 		return ret;
 
-	case DMA_BUF_SET_NAME:
+	case DMA_BUF_SET_NAME_A:
+	case DMA_BUF_SET_NAME_B:
 		return dma_buf_set_name(dmabuf, (const char __user *)arg);
 
 	default:
@@ -655,8 +656,8 @@ EXPORT_SYMBOL_GPL(dma_buf_put);
  * calls attach() of dma_buf_ops to allow device-specific attach functionality
  * @dmabuf:		[in]	buffer to attach device to.
  * @dev:		[in]	device to be attached.
- * @importer_ops	[in]	importer operations for the attachment
- * @importer_priv	[in]	importer private pointer for the attachment
+ * @importer_ops:	[in]	importer operations for the attachment
+ * @importer_priv:	[in]	importer private pointer for the attachment
  *
  * Returns struct dma_buf_attachment pointer for this attachment. Attachments
  * must be cleaned up by calling dma_buf_detach().
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 092483644315..023db6883d05 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -241,7 +241,8 @@ config FSL_RAID
 
 config HISI_DMA
 	tristate "HiSilicon DMA Engine support"
-	depends on ARM64 || (COMPILE_TEST && PCI_MSI)
+	depends on ARM64 || COMPILE_TEST
+	depends on PCI_MSI
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 4830ba658ce1..d31076d9ef25 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -232,10 +232,6 @@ static void chan_dev_release(struct device *dev)
 	struct dma_chan_dev *chan_dev;
 
 	chan_dev = container_of(dev, typeof(*chan_dev), device);
-	if (atomic_dec_and_test(chan_dev->idr_ref)) {
-		ida_free(&dma_ida, chan_dev->dev_id);
-		kfree(chan_dev->idr_ref);
-	}
 	kfree(chan_dev);
 }
 
@@ -1043,27 +1039,9 @@ static int get_dma_id(struct dma_device *device)
 }
 
 static int __dma_async_device_channel_register(struct dma_device *device,
-					       struct dma_chan *chan,
-					       int chan_id)
+					       struct dma_chan *chan)
 {
 	int rc = 0;
-	int chancnt = device->chancnt;
-	atomic_t *idr_ref;
-	struct dma_chan *tchan;
-
-	tchan = list_first_entry_or_null(&device->channels,
-					 struct dma_chan, device_node);
-	if (!tchan)
-		return -ENODEV;
-
-	if (tchan->dev) {
-		idr_ref = tchan->dev->idr_ref;
-	} else {
-		idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
-		if (!idr_ref)
-			return -ENOMEM;
-		atomic_set(idr_ref, 0);
-	}
 
 	chan->local = alloc_percpu(typeof(*chan->local));
 	if (!chan->local)
@@ -1079,29 +1057,36 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 	 * When the chan_id is a negative value, we are dynamically adding
 	 * the channel. Otherwise we are static enumerating.
 	 */
-	chan->chan_id = chan_id < 0 ? chancnt : chan_id;
+	mutex_lock(&device->chan_mutex);
+	chan->chan_id = ida_alloc(&device->chan_ida, GFP_KERNEL);
+	mutex_unlock(&device->chan_mutex);
+	if (chan->chan_id < 0) {
+		pr_err("%s: unable to alloc ida for chan: %d\n",
+		       __func__, chan->chan_id);
+		goto err_out;
+	}
+
 	chan->dev->device.class = &dma_devclass;
 	chan->dev->device.parent = device->dev;
 	chan->dev->chan = chan;
-	chan->dev->idr_ref = idr_ref;
 	chan->dev->dev_id = device->dev_id;
-	atomic_inc(idr_ref);
 	dev_set_name(&chan->dev->device, "dma%dchan%d",
 		     device->dev_id, chan->chan_id);
-
 	rc = device_register(&chan->dev->device);
 	if (rc)
-		goto err_out;
+		goto err_out_ida;
 	chan->client_count = 0;
-	device->chancnt = chan->chan_id + 1;
+	device->chancnt++;
 
 	return 0;
 
+ err_out_ida:
+	mutex_lock(&device->chan_mutex);
+	ida_free(&device->chan_ida, chan->chan_id);
+	mutex_unlock(&device->chan_mutex);
  err_out:
 	free_percpu(chan->local);
 	kfree(chan->dev);
-	if (atomic_dec_return(idr_ref) == 0)
-		kfree(idr_ref);
 	return rc;
 }
 
@@ -1110,7 +1095,7 @@ int dma_async_device_channel_register(struct dma_device *device,
 {
 	int rc;
 
-	rc = __dma_async_device_channel_register(device, chan, -1);
+	rc = __dma_async_device_channel_register(device, chan);
 	if (rc < 0)
 		return rc;
 
@@ -1130,6 +1115,9 @@ static void __dma_async_device_channel_unregister(struct dma_device *device,
 	device->chancnt--;
 	chan->dev->chan = NULL;
 	mutex_unlock(&dma_list_mutex);
+	mutex_lock(&device->chan_mutex);
+	ida_free(&device->chan_ida, chan->chan_id);
+	mutex_unlock(&device->chan_mutex);
 	device_unregister(&chan->dev->device);
 	free_percpu(chan->local);
 }
@@ -1152,7 +1140,7 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_unregister);
  */
 int dma_async_device_register(struct dma_device *device)
 {
-	int rc, i = 0;
+	int rc;
 	struct dma_chan* chan;
 
 	if (!device)
@@ -1257,9 +1245,12 @@ int dma_async_device_register(struct dma_device *device)
 	if (rc != 0)
 		return rc;
 
+	mutex_init(&device->chan_mutex);
+	ida_init(&device->chan_ida);
+
 	/* represent channels in sysfs. Probably want devs too */
 	list_for_each_entry(chan, &device->channels, device_node) {
-		rc = __dma_async_device_channel_register(device, chan, i++);
+		rc = __dma_async_device_channel_register(device, chan);
 		if (rc < 0)
 			goto err_out;
 	}
@@ -1334,6 +1325,7 @@ void dma_async_device_unregister(struct dma_device *device)
 	 */
 	dma_cap_set(DMA_PRIVATE, device->cap_mask);
 	dma_channel_rebalance();
+	ida_free(&dma_ida, device->dev_id);
 	dma_device_put(device);
 	mutex_unlock(&dma_list_mutex);
 }
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index a2cadfa2e6d7..0425984db118 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -240,7 +240,7 @@ static bool is_threaded_test_run(struct dmatest_info *info)
 		struct dmatest_thread *thread;
 
 		list_for_each_entry(thread, &dtc->threads, node) {
-			if (!thread->done)
+			if (!thread->done && !thread->pending)
 				return true;
 		}
 	}
@@ -662,8 +662,8 @@ static int dmatest_func(void *data)
 		flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
 	ktime = ktime_get();
-	while (!kthread_should_stop()
-	       && !(params->iterations && total_tests >= params->iterations)) {
+	while (!(kthread_should_stop() ||
+	       (params->iterations && total_tests >= params->iterations))) {
 		struct dma_async_tx_descriptor *tx = NULL;
 		struct dmaengine_unmap_data *um;
 		dma_addr_t *dsts;
@@ -1166,10 +1166,11 @@ static int dmatest_run_set(const char *val, const struct kernel_param *kp)
 		mutex_unlock(&info->lock);
 		return ret;
 	} else if (dmatest_run) {
-		if (is_threaded_test_pending(info))
-			start_threaded_tests(info);
-		else
-			pr_info("Could not start test, no channels configured\n");
+		if (!is_threaded_test_pending(info)) {
+			pr_info("No channels configured, continue with any\n");
+			add_threaded_test(info);
+		}
+		start_threaded_tests(info);
 	} else {
 		stop_threaded_test(info);
 	}
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index f6f49f0f6fae..8d79a8787104 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -62,6 +62,13 @@ int idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id)
 	perm.ignore = 0;
 	iowrite32(perm.bits, idxd->reg_base + offset);
 
+	/*
+	 * A readback from the device ensures that any previously generated
+	 * completion record writes are visible to software based on PCI
+	 * ordering rules.
+	 */
+	perm.bits = ioread32(idxd->reg_base + offset);
+
 	return 0;
 }
 
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index d6fcd2e60103..6510791b9921 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -173,6 +173,7 @@ static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry,
 	struct llist_node *head;
 	int queued = 0;
 
+	*processed = 0;
 	head = llist_del_all(&irq_entry->pending_llist);
 	if (!head)
 		return 0;
@@ -197,6 +198,7 @@ static int irq_process_work_list(struct idxd_irq_entry *irq_entry,
 	struct list_head *node, *next;
 	int queued = 0;
 
+	*processed = 0;
 	if (list_empty(&irq_entry->work_list))
 		return 0;
 
@@ -218,10 +220,9 @@ static int irq_process_work_list(struct idxd_irq_entry *irq_entry,
 	return queued;
 }
 
-irqreturn_t idxd_wq_thread(int irq, void *data)
+static int idxd_desc_process(struct idxd_irq_entry *irq_entry)
 {
-	struct idxd_irq_entry *irq_entry = data;
-	int rc, processed = 0, retry = 0;
+	int rc, processed, total = 0;
 
 	/*
 	 * There are two lists we are processing. The pending_llist is where
@@ -244,15 +245,26 @@ irqreturn_t idxd_wq_thread(int irq, void *data)
 	 */
 	do {
 		rc = irq_process_work_list(irq_entry, &processed);
-		if (rc != 0) {
-			retry++;
+		total += processed;
+		if (rc != 0)
 			continue;
-		}
 
 		rc = irq_process_pending_llist(irq_entry, &processed);
-	} while (rc != 0 && retry != 10);
+		total += processed;
+	} while (rc != 0);
+
+	return total;
+}
+
+irqreturn_t idxd_wq_thread(int irq, void *data)
+{
+	struct idxd_irq_entry *irq_entry = data;
+	int processed;
 
+	processed = idxd_desc_process(irq_entry);
 	idxd_unmask_msix_vector(irq_entry->idxd, irq_entry->id);
+	/* catch anything unprocessed after unmasking */
+	processed += idxd_desc_process(irq_entry);
 
 	if (processed == 0)
 		return IRQ_NONE;
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index 10117f271b12..d683232d7fea 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -363,6 +363,8 @@ static void mmp_tdma_free_descriptor(struct mmp_tdma_chan *tdmac)
 		gen_pool_free(gpool, (unsigned long)tdmac->desc_arr,
 				size);
 	tdmac->desc_arr = NULL;
+	if (tdmac->status == DMA_ERROR)
+		tdmac->status = DMA_COMPLETE;
 
 	return;
 }
@@ -443,7 +445,8 @@ static struct dma_async_tx_descriptor *mmp_tdma_prep_dma_cyclic(
 	if (!desc)
 		goto err_out;
 
-	mmp_tdma_config_write(chan, direction, &tdmac->slave_config);
+	if (mmp_tdma_config_write(chan, direction, &tdmac->slave_config))
+		goto err_out;
 
 	while (buf < buf_len) {
 		desc = &tdmac->desc_arr[i];
diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c
index c683051257fd..66ef70b00ec0 100644
--- a/drivers/dma/owl-dma.c
+++ b/drivers/dma/owl-dma.c
@@ -175,13 +175,11 @@ struct owl_dma_txd {
  * @id: physical index to this channel
  * @base: virtual memory base for the dma channel
  * @vchan: the virtual channel currently being served by this physical channel
- * @lock: a lock to use when altering an instance of this struct
  */
 struct owl_dma_pchan {
 	u32			id;
 	void __iomem		*base;
 	struct owl_dma_vchan	*vchan;
-	spinlock_t		lock;
 };
 
 /**
@@ -437,14 +435,14 @@ static struct owl_dma_pchan *owl_dma_get_pchan(struct owl_dma *od,
 	for (i = 0; i < od->nr_pchans; i++) {
 		pchan = &od->pchans[i];
 
-		spin_lock_irqsave(&pchan->lock, flags);
+		spin_lock_irqsave(&od->lock, flags);
 		if (!pchan->vchan) {
 			pchan->vchan = vchan;
-			spin_unlock_irqrestore(&pchan->lock, flags);
+			spin_unlock_irqrestore(&od->lock, flags);
 			break;
 		}
 
-		spin_unlock_irqrestore(&pchan->lock, flags);
+		spin_unlock_irqrestore(&od->lock, flags);
 	}
 
 	return pchan;
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 581e7a290d98..a3b0b4c56a19 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -865,6 +865,7 @@ static int pch_dma_probe(struct pci_dev *pdev,
 	}
 
 	pci_set_master(pdev);
+	pd->dma.dev = &pdev->dev;
 
 	err = request_irq(pdev->irq, pd_irq, IRQF_SHARED, DRV_NAME, pd);
 	if (err) {
@@ -880,7 +881,6 @@ static int pch_dma_probe(struct pci_dev *pdev,
 		goto err_free_irq;
 	}
 
-	pd->dma.dev = &pdev->dev;
 
 	INIT_LIST_HEAD(&pd->dma.channels);
 
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index f6a2f42ffc51..b9f0d9636620 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -816,6 +816,13 @@ static bool tegra_dma_eoc_interrupt_deasserted(struct tegra_dma_channel *tdc)
 static void tegra_dma_synchronize(struct dma_chan *dc)
 {
 	struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
+	int err;
+
+	err = pm_runtime_get_sync(tdc->tdma->dev);
+	if (err < 0) {
+		dev_err(tdc2dev(tdc), "Failed to synchronize DMA: %d\n", err);
+		return;
+	}
 
 	/*
 	 * CPU, which handles interrupt, could be busy in
@@ -825,6 +832,8 @@ static void tegra_dma_synchronize(struct dma_chan *dc)
 	wait_event(tdc->wq, tegra_dma_eoc_interrupt_deasserted(tdc));
 
 	tasklet_kill(&tdc->tasklet);
+
+	pm_runtime_put(tdc->tdma->dev);
 }
 
 static unsigned int tegra_dma_sg_bytes_xferred(struct tegra_dma_channel *tdc,
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index c4ce5dfb149b..db58d7e4f9fe 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -900,7 +900,7 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	ret = dma_async_device_register(&tdma->dma_dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "ADMA registration failed: %d\n", ret);
-		goto irq_dispose;
+		goto rpm_put;
 	}
 
 	ret = of_dma_controller_register(pdev->dev.of_node,
diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c
index d7b965049ccb..fb7c8150b0d1 100644
--- a/drivers/dma/ti/k3-psil.c
+++ b/drivers/dma/ti/k3-psil.c
@@ -27,6 +27,7 @@ struct psil_endpoint_config *psil_get_ep_config(u32 thread_id)
 			soc_ep_map = &j721e_ep_map;
 		} else {
 			pr_err("PSIL: No compatible machine found for map\n");
+			mutex_unlock(&ep_map_mutex);
 			return ERR_PTR(-ENOTSUPP);
 		}
 		pr_debug("%s: Using map for %s\n", __func__, soc_ep_map->name);
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index a9c0251adf1a..a90e154b0ae0 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -2156,7 +2156,8 @@ udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl,
 		d->residue += sg_dma_len(sgent);
 	}
 
-	cppi5_tr_csf_set(&tr_req[tr_idx - 1].flags, CPPI5_TR_CSF_EOP);
+	cppi5_tr_csf_set(&tr_req[tr_idx - 1].flags,
+			 CPPI5_TR_CSF_SUPR_EVT | CPPI5_TR_CSF_EOP);
 
 	return d;
 }
@@ -2733,7 +2734,8 @@ udma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		tr_req[1].dicnt3 = 1;
 	}
 
-	cppi5_tr_csf_set(&tr_req[num_tr - 1].flags, CPPI5_TR_CSF_EOP);
+	cppi5_tr_csf_set(&tr_req[num_tr - 1].flags,
+			 CPPI5_TR_CSF_SUPR_EVT | CPPI5_TR_CSF_EOP);
 
 	if (uc->config.metadata_size)
 		d->vd.tx.metadata_ops = &metadata_ops;
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index aecd5a35a296..5429497d3560 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -1230,16 +1230,16 @@ static enum dma_status xilinx_dma_tx_status(struct dma_chan *dchan,
 		return ret;
 
 	spin_lock_irqsave(&chan->lock, flags);
-
-	desc = list_last_entry(&chan->active_list,
-			       struct xilinx_dma_tx_descriptor, node);
-	/*
-	 * VDMA and simple mode do not support residue reporting, so the
-	 * residue field will always be 0.
-	 */
-	if (chan->has_sg && chan->xdev->dma_config->dmatype != XDMA_TYPE_VDMA)
-		residue = xilinx_dma_get_residue(chan, desc);
-
+	if (!list_empty(&chan->active_list)) {
+		desc = list_last_entry(&chan->active_list,
+				       struct xilinx_dma_tx_descriptor, node);
+		/*
+		 * VDMA and simple mode do not support residue reporting, so the
+		 * residue field will always be 0.
+		 */
+		if (chan->has_sg && chan->xdev->dma_config->dmatype != XDMA_TYPE_VDMA)
+			residue = xilinx_dma_get_residue(chan, desc);
+	}
 	spin_unlock_irqrestore(&chan->lock, flags);
 
 	dma_set_residue(txstate, residue);
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index d47749a35863..ff253696d183 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -434,6 +434,7 @@ static void zynqmp_dma_free_descriptor(struct zynqmp_dma_chan *chan,
 	struct zynqmp_dma_desc_sw *child, *next;
 
 	chan->desc_free_cnt++;
+	list_del(&sdesc->node);
 	list_add_tail(&sdesc->node, &chan->free_list);
 	list_for_each_entry_safe(child, next, &sdesc->tx_list, node) {
 		chan->desc_free_cnt++;
@@ -608,8 +609,6 @@ static void zynqmp_dma_chan_desc_cleanup(struct zynqmp_dma_chan *chan)
 		dma_async_tx_callback callback;
 		void *callback_param;
 
-		list_del(&desc->node);
-
 		callback = desc->async_tx.callback;
 		callback_param = desc->async_tx.callback_param;
 		if (callback) {
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index f91f3bc1e0b2..9cf7cc1f3f72 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -3403,7 +3403,7 @@ static const struct attribute_group *amd64_edac_attr_groups[] = {
 static int hw_info_get(struct amd64_pvt *pvt)
 {
 	u16 pci_id1, pci_id2;
-	int ret = -EINVAL;
+	int ret;
 
 	if (pvt->fam >= 0x17) {
 		pvt->umc = kcalloc(fam_type->max_mcs, sizeof(struct amd64_umc), GFP_KERNEL);
diff --git a/drivers/edac/amd8131_edac.c b/drivers/edac/amd8131_edac.c
index 93c82bc17493..169353710982 100644
--- a/drivers/edac/amd8131_edac.c
+++ b/drivers/edac/amd8131_edac.c
@@ -44,14 +44,6 @@ static void edac_pci_write_dword(struct pci_dev *dev, int reg, u32 val32)
 			" PCI Access Write Error at 0x%x\n", reg);
 }
 
-static char * const bridge_str[] = {
-	[NORTH_A] = "NORTH A",
-	[NORTH_B] = "NORTH B",
-	[SOUTH_A] = "SOUTH A",
-	[SOUTH_B] = "SOUTH B",
-	[NO_BRIDGE] = "NO BRIDGE",
-};
-
 /* Support up to two AMD8131 chipsets on a platform */
 static struct amd8131_dev_info amd8131_devices[] = {
 	{
diff --git a/drivers/edac/armada_xp_edac.c b/drivers/edac/armada_xp_edac.c
index a7502ebe9bdc..e3e757513d1b 100644
--- a/drivers/edac/armada_xp_edac.c
+++ b/drivers/edac/armada_xp_edac.c
@@ -78,7 +78,7 @@ struct axp_mc_drvdata {
 	char msg[128];
 };
 
-/* derived from "DRAM Address Multiplexing" in the ARAMDA XP Functional Spec */
+/* derived from "DRAM Address Multiplexing" in the ARMADA XP Functional Spec */
 static uint32_t axp_mc_calc_address(struct axp_mc_drvdata *drvdata,
 				    uint8_t cs, uint8_t bank, uint16_t row,
 				    uint16_t col)
@@ -160,12 +160,12 @@ static void axp_mc_check(struct mem_ctl_info *mci)
 		if (cnt_sbe)
 			cnt_sbe--;
 		else
-			dev_warn(mci->pdev, "inconsistent SBE count detected");
+			dev_warn(mci->pdev, "inconsistent SBE count detected\n");
 	} else {
 		if (cnt_dbe)
 			cnt_dbe--;
 		else
-			dev_warn(mci->pdev, "inconsistent DBE count detected");
+			dev_warn(mci->pdev, "inconsistent DBE count detected\n");
 	}
 
 	/* report earlier errors */
@@ -304,7 +304,7 @@ static int axp_mc_probe(struct platform_device *pdev)
 
 	config = readl(base + SDRAM_CONFIG_REG);
 	if (!(config & SDRAM_CONFIG_ECC_MASK)) {
-		dev_warn(&pdev->dev, "SDRAM ECC is not enabled");
+		dev_warn(&pdev->dev, "SDRAM ECC is not enabled\n");
 		return -EINVAL;
 	}
 
@@ -532,9 +532,9 @@ static int aurora_l2_probe(struct platform_device *pdev)
 
 	l2x0_aux_ctrl = readl(base + L2X0_AUX_CTRL);
 	if (!(l2x0_aux_ctrl & AURORA_ACR_PARITY_EN))
-		dev_warn(&pdev->dev, "tag parity is not enabled");
+		dev_warn(&pdev->dev, "tag parity is not enabled\n");
 	if (!(l2x0_aux_ctrl & AURORA_ACR_ECC_EN))
-		dev_warn(&pdev->dev, "data ECC is not enabled");
+		dev_warn(&pdev->dev, "data ECC is not enabled\n");
 
 	dci = edac_device_alloc_ctl_info(sizeof(*drvdata),
 					 "cpu", 1, "L", 1, 2, NULL, 0, 0);
@@ -618,7 +618,7 @@ static int __init armada_xp_edac_init(void)
 
 	res = platform_register_drivers(drivers, ARRAY_SIZE(drivers));
 	if (res)
-		pr_warn("Aramda XP EDAC drivers fail to register\n");
+		pr_warn("Armada XP EDAC drivers fail to register\n");
 
 	return 0;
 }
diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index df08de963d10..9b0044cd21cd 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -122,10 +122,22 @@ static int i10nm_get_all_munits(void)
 	return 0;
 }
 
+static struct res_config i10nm_cfg0 = {
+	.type			= I10NM,
+	.decs_did		= 0x3452,
+	.busno_cfg_offset	= 0xcc,
+};
+
+static struct res_config i10nm_cfg1 = {
+	.type			= I10NM,
+	.decs_did		= 0x3452,
+	.busno_cfg_offset	= 0xd0,
+};
+
 static const struct x86_cpu_id i10nm_cpuids[] = {
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	NULL),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		NULL),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&i10nm_cfg0),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&i10nm_cfg0),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&i10nm_cfg1),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, i10nm_cpuids);
@@ -161,7 +173,7 @@ static int i10nm_get_dimm_config(struct mem_ctl_info *mci)
 				 mtr, mcddrtcfg, imc->mc, i, j);
 
 			if (IS_DIMM_PRESENT(mtr))
-				ndimms += skx_get_dimm_info(mtr, 0, dimm,
+				ndimms += skx_get_dimm_info(mtr, 0, 0, dimm,
 							    imc, i, j);
 			else if (IS_NVDIMM_PRESENT(mcddrtcfg, j))
 				ndimms += skx_get_nvdimm_info(dimm, imc, i, j,
@@ -234,6 +246,7 @@ static int __init i10nm_init(void)
 {
 	u8 mc = 0, src_id = 0, node_id = 0;
 	const struct x86_cpu_id *id;
+	struct res_config *cfg;
 	const char *owner;
 	struct skx_dev *d;
 	int rc, i, off[3] = {0xd0, 0xc8, 0xcc};
@@ -249,11 +262,17 @@ static int __init i10nm_init(void)
 	if (!id)
 		return -ENODEV;
 
+	cfg = (struct res_config *)id->driver_data;
+
+	/* Newer steppings have different offset for ATOM_TREMONT_D/ICELAKE_X */
+	if (boot_cpu_data.x86_stepping >= 4)
+		cfg->busno_cfg_offset = 0xd0;
+
 	rc = skx_get_hi_lo(0x09a2, off, &tolm, &tohm);
 	if (rc)
 		return rc;
 
-	rc = skx_get_all_bus_mappings(0x3452, 0xcc, I10NM, &i10nm_edac_list);
+	rc = skx_get_all_bus_mappings(cfg, &i10nm_edac_list);
 	if (rc < 0)
 		goto fail;
 	if (rc == 0) {
diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c
index 46a3a3440f5e..b907a0f4ece6 100644
--- a/drivers/edac/skx_base.c
+++ b/drivers/edac/skx_base.c
@@ -157,33 +157,35 @@ fail:
 	return -ENODEV;
 }
 
+static struct res_config skx_cfg = {
+	.type			= SKX,
+	.decs_did		= 0x2016,
+	.busno_cfg_offset	= 0xcc,
+};
+
 static const struct x86_cpu_id skx_cpuids[] = {
-	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,	&skx_cfg),
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, skx_cpuids);
 
-#define SKX_GET_MTMTR(dev, reg) \
-	pci_read_config_dword((dev), 0x87c, &(reg))
-
-static bool skx_check_ecc(struct pci_dev *pdev)
+static bool skx_check_ecc(u32 mcmtr)
 {
-	u32 mtmtr;
-
-	SKX_GET_MTMTR(pdev, mtmtr);
-
-	return !!GET_BITFIELD(mtmtr, 2, 2);
+	return !!GET_BITFIELD(mcmtr, 2, 2);
 }
 
 static int skx_get_dimm_config(struct mem_ctl_info *mci)
 {
 	struct skx_pvt *pvt = mci->pvt_info;
+	u32 mtr, mcmtr, amap, mcddrtcfg;
 	struct skx_imc *imc = pvt->imc;
-	u32 mtr, amap, mcddrtcfg;
 	struct dimm_info *dimm;
 	int i, j;
 	int ndimms;
 
+	/* Only the mcmtr on the first channel is effective */
+	pci_read_config_dword(imc->chan[0].cdev, 0x87c, &mcmtr);
+
 	for (i = 0; i < SKX_NUM_CHANNELS; i++) {
 		ndimms = 0;
 		pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap);
@@ -193,14 +195,14 @@ static int skx_get_dimm_config(struct mem_ctl_info *mci)
 			pci_read_config_dword(imc->chan[i].cdev,
 					      0x80 + 4 * j, &mtr);
 			if (IS_DIMM_PRESENT(mtr)) {
-				ndimms += skx_get_dimm_info(mtr, amap, dimm, imc, i, j);
+				ndimms += skx_get_dimm_info(mtr, mcmtr, amap, dimm, imc, i, j);
 			} else if (IS_NVDIMM_PRESENT(mcddrtcfg, j)) {
 				ndimms += skx_get_nvdimm_info(dimm, imc, i, j,
 							      EDAC_MOD_STR);
 				nvdimm_count++;
 			}
 		}
-		if (ndimms && !skx_check_ecc(imc->chan[0].cdev)) {
+		if (ndimms && !skx_check_ecc(mcmtr)) {
 			skx_printk(KERN_ERR, "ECC is disabled on imc %d\n", imc->mc);
 			return -ENODEV;
 		}
@@ -641,6 +643,7 @@ static inline void teardown_skx_debug(void) {}
 static int __init skx_init(void)
 {
 	const struct x86_cpu_id *id;
+	struct res_config *cfg;
 	const struct munit *m;
 	const char *owner;
 	int rc = 0, i, off[3] = {0xd0, 0xd4, 0xd8};
@@ -657,11 +660,13 @@ static int __init skx_init(void)
 	if (!id)
 		return -ENODEV;
 
+	cfg = (struct res_config *)id->driver_data;
+
 	rc = skx_get_hi_lo(0x2034, off, &skx_tolm, &skx_tohm);
 	if (rc)
 		return rc;
 
-	rc = skx_get_all_bus_mappings(0x2016, 0xcc, SKX, &skx_edac_list);
+	rc = skx_get_all_bus_mappings(cfg, &skx_edac_list);
 	if (rc < 0)
 		goto fail;
 	if (rc == 0) {
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index 99bbaf629b8d..46be1a77bd1d 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -197,12 +197,11 @@ static int get_width(u32 mtr)
 }
 
 /*
- * We use the per-socket device @did to count how many sockets are present,
+ * We use the per-socket device @cfg->did to count how many sockets are present,
  * and to detemine which PCI buses are associated with each socket. Allocate
  * and build the full list of all the skx_dev structures that we need here.
  */
-int skx_get_all_bus_mappings(unsigned int did, int off, enum type type,
-			     struct list_head **list)
+int skx_get_all_bus_mappings(struct res_config *cfg, struct list_head **list)
 {
 	struct pci_dev *pdev, *prev;
 	struct skx_dev *d;
@@ -211,7 +210,7 @@ int skx_get_all_bus_mappings(unsigned int did, int off, enum type type,
 
 	prev = NULL;
 	for (;;) {
-		pdev = pci_get_device(PCI_VENDOR_ID_INTEL, did, prev);
+		pdev = pci_get_device(PCI_VENDOR_ID_INTEL, cfg->decs_did, prev);
 		if (!pdev)
 			break;
 		ndev++;
@@ -221,7 +220,7 @@ int skx_get_all_bus_mappings(unsigned int did, int off, enum type type,
 			return -ENOMEM;
 		}
 
-		if (pci_read_config_dword(pdev, off, &reg)) {
+		if (pci_read_config_dword(pdev, cfg->busno_cfg_offset, &reg)) {
 			kfree(d);
 			pci_dev_put(pdev);
 			skx_printk(KERN_ERR, "Failed to read bus idx\n");
@@ -230,7 +229,7 @@ int skx_get_all_bus_mappings(unsigned int did, int off, enum type type,
 
 		d->bus[0] = GET_BITFIELD(reg, 0, 7);
 		d->bus[1] = GET_BITFIELD(reg, 8, 15);
-		if (type == SKX) {
+		if (cfg->type == SKX) {
 			d->seg = pci_domain_nr(pdev->bus);
 			d->bus[2] = GET_BITFIELD(reg, 16, 23);
 			d->bus[3] = GET_BITFIELD(reg, 24, 31);
@@ -304,7 +303,7 @@ static int skx_get_dimm_attr(u32 reg, int lobit, int hibit, int add,
 #define numrow(reg)	skx_get_dimm_attr(reg, 2, 4, 12, 1, 6, "rows")
 #define numcol(reg)	skx_get_dimm_attr(reg, 0, 1, 10, 0, 2, "cols")
 
-int skx_get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm,
+int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm,
 		      struct skx_imc *imc, int chan, int dimmno)
 {
 	int  banks = 16, ranks, rows, cols, npages;
@@ -324,8 +323,8 @@ int skx_get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm,
 		 imc->mc, chan, dimmno, size, npages,
 		 banks, 1 << ranks, rows, cols);
 
-	imc->chan[chan].dimms[dimmno].close_pg = GET_BITFIELD(mtr, 0, 0);
-	imc->chan[chan].dimms[dimmno].bank_xor_enable = GET_BITFIELD(mtr, 9, 9);
+	imc->chan[chan].dimms[dimmno].close_pg = GET_BITFIELD(mcmtr, 0, 0);
+	imc->chan[chan].dimms[dimmno].bank_xor_enable = GET_BITFIELD(mcmtr, 9, 9);
 	imc->chan[chan].dimms[dimmno].fine_grain_bank = GET_BITFIELD(amap, 0, 0);
 	imc->chan[chan].dimms[dimmno].rowbits = rows;
 	imc->chan[chan].dimms[dimmno].colbits = cols;
diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h
index 60d1ea669afd..78f8c1de0b71 100644
--- a/drivers/edac/skx_common.h
+++ b/drivers/edac/skx_common.h
@@ -112,6 +112,14 @@ struct decoded_addr {
 	int	bank_group;
 };
 
+struct res_config {
+	enum type type;
+	/* Configuration agent device ID */
+	unsigned int decs_did;
+	/* Default bus number configuration register offset */
+	int busno_cfg_offset;
+};
+
 typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci);
 typedef bool (*skx_decode_f)(struct decoded_addr *res);
 typedef void (*skx_show_retry_log_f)(struct decoded_addr *res, char *msg, int len);
@@ -123,12 +131,11 @@ void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log);
 int skx_get_src_id(struct skx_dev *d, int off, u8 *id);
 int skx_get_node_id(struct skx_dev *d, u8 *id);
 
-int skx_get_all_bus_mappings(unsigned int did, int off, enum type,
-			     struct list_head **list);
+int skx_get_all_bus_mappings(struct res_config *cfg, struct list_head **list);
 
 int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm);
 
-int skx_get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm,
+int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm,
 		      struct skx_imc *imc, int chan, int dimmno);
 
 int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc,
diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c
index 34be60fe6892..4af9744cc6d0 100644
--- a/drivers/edac/thunderx_edac.c
+++ b/drivers/edac/thunderx_edac.c
@@ -1278,7 +1278,7 @@ OCX_DEBUGFS_ATTR(lne23_badcnt, OCX_LNE_BAD_CNT(23));
 
 OCX_DEBUGFS_ATTR(com_int, OCX_COM_INT_W1S);
 
-struct debugfs_entry *ocx_dfs_ents[] = {
+static struct debugfs_entry *ocx_dfs_ents[] = {
 	&debugfs_tlk0_ecc_ctl,
 	&debugfs_tlk1_ecc_ctl,
 	&debugfs_tlk2_ecc_ctl,
@@ -1919,19 +1919,19 @@ err_free:
 
 L2C_DEBUGFS_ATTR(tad_int, L2C_TAD_INT_W1S);
 
-struct debugfs_entry *l2c_tad_dfs_ents[] = {
+static struct debugfs_entry *l2c_tad_dfs_ents[] = {
 	&debugfs_tad_int,
 };
 
 L2C_DEBUGFS_ATTR(cbc_int, L2C_CBC_INT_W1S);
 
-struct debugfs_entry *l2c_cbc_dfs_ents[] = {
+static struct debugfs_entry *l2c_cbc_dfs_ents[] = {
 	&debugfs_cbc_int,
 };
 
 L2C_DEBUGFS_ATTR(mci_int, L2C_MCI_INT_W1S);
 
-struct debugfs_entry *l2c_mci_dfs_ents[] = {
+static struct debugfs_entry *l2c_mci_dfs_ents[] = {
 	&debugfs_mci_int,
 };
 
diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c
index e4a1032ba0b5..1d2c27a00a4a 100644
--- a/drivers/edac/xgene_edac.c
+++ b/drivers/edac/xgene_edac.c
@@ -1349,7 +1349,6 @@ static int xgene_edac_l3_remove(struct xgene_edac_dev_ctx *l3)
 #define WORD_ALIGNED_ERR_MASK		BIT(28)
 #define PAGE_ACCESS_ERR_MASK		BIT(27)
 #define WRITE_ACCESS_MASK		BIT(26)
-#define RBERRADDR_RD(src)		((src) & 0x03FFFFFF)
 
 static const char * const soc_mem_err_v1[] = {
 	"10GbE0",
@@ -1483,13 +1482,11 @@ static void xgene_edac_rb_report(struct edac_device_ctl_info *edac_dev)
 		return;
 	if (reg & STICKYERR_MASK) {
 		bool write;
-		u32 address;
 
 		dev_err(edac_dev->dev, "IOB bus access error(s)\n");
 		if (regmap_read(ctx->edac->rb_map, RBEIR, &reg))
 			return;
 		write = reg & WRITE_ACCESS_MASK ? 1 : 0;
-		address = RBERRADDR_RD(reg);
 		if (reg & AGENT_OFFLINE_ERR_MASK)
 			dev_err(edac_dev->dev,
 				"IOB bus %s access to offline agent error\n",
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 8007d4aa76dc..4843e94713a4 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -295,15 +295,13 @@ config TURRIS_MOX_RWTM
 	  other manufacturing data and also utilize the Entropy Bit Generator
 	  for hardware random number generation.
 
-config HAVE_ARM_SMCCC
-	bool
-
-source "drivers/firmware/psci/Kconfig"
 source "drivers/firmware/broadcom/Kconfig"
 source "drivers/firmware/google/Kconfig"
 source "drivers/firmware/efi/Kconfig"
 source "drivers/firmware/imx/Kconfig"
 source "drivers/firmware/meson/Kconfig"
+source "drivers/firmware/psci/Kconfig"
+source "drivers/firmware/smccc/Kconfig"
 source "drivers/firmware/tegra/Kconfig"
 source "drivers/firmware/xilinx/Kconfig"
 
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index e9fb838af4df..99510be9f5ed 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -23,12 +23,13 @@ obj-$(CONFIG_TRUSTED_FOUNDATIONS) += trusted_foundations.o
 obj-$(CONFIG_TURRIS_MOX_RWTM)	+= turris-mox-rwtm.o
 
 obj-$(CONFIG_ARM_SCMI_PROTOCOL)	+= arm_scmi/
-obj-y				+= psci/
 obj-y				+= broadcom/
 obj-y				+= meson/
 obj-$(CONFIG_GOOGLE_FIRMWARE)	+= google/
 obj-$(CONFIG_EFI)		+= efi/
 obj-$(CONFIG_UEFI_CPER)		+= efi/
 obj-y				+= imx/
+obj-y				+= psci/
+obj-y				+= smccc/
 obj-y				+= tegra/
 obj-y				+= xilinx/
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index 334c8be0c11f..e7e36aab2386 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -429,7 +429,6 @@ int sdei_event_enable(u32 event_num)
 
 	return err;
 }
-EXPORT_SYMBOL(sdei_event_enable);
 
 static int sdei_api_event_disable(u32 event_num)
 {
@@ -471,7 +470,6 @@ int sdei_event_disable(u32 event_num)
 
 	return err;
 }
-EXPORT_SYMBOL(sdei_event_disable);
 
 static int sdei_api_event_unregister(u32 event_num)
 {
@@ -533,7 +531,6 @@ int sdei_event_unregister(u32 event_num)
 
 	return err;
 }
-EXPORT_SYMBOL(sdei_event_unregister);
 
 /*
  * unregister events, but don't destroy them as they are re-registered by
@@ -643,7 +640,6 @@ int sdei_event_register(u32 event_num, sdei_event_callback *cb, void *arg)
 
 	return err;
 }
-EXPORT_SYMBOL(sdei_event_register);
 
 static int sdei_reregister_event_llocked(struct sdei_event *event)
 {
@@ -1079,26 +1075,9 @@ static struct platform_driver sdei_driver = {
 	.probe		= sdei_probe,
 };
 
-static bool __init sdei_present_dt(void)
-{
-	struct device_node *np, *fw_np;
-
-	fw_np = of_find_node_by_name(NULL, "firmware");
-	if (!fw_np)
-		return false;
-
-	np = of_find_matching_node(fw_np, sdei_of_match);
-	if (!np)
-		return false;
-	of_node_put(np);
-
-	return true;
-}
-
 static bool __init sdei_present_acpi(void)
 {
 	acpi_status status;
-	struct platform_device *pdev;
 	struct acpi_table_header *sdei_table_header;
 
 	if (acpi_disabled)
@@ -1113,20 +1092,26 @@ static bool __init sdei_present_acpi(void)
 	if (ACPI_FAILURE(status))
 		return false;
 
-	pdev = platform_device_register_simple(sdei_driver.driver.name, 0, NULL,
-					       0);
-	if (IS_ERR(pdev))
-		return false;
+	acpi_put_table(sdei_table_header);
 
 	return true;
 }
 
 static int __init sdei_init(void)
 {
-	if (sdei_present_dt() || sdei_present_acpi())
-		platform_driver_register(&sdei_driver);
+	int ret = platform_driver_register(&sdei_driver);
 
-	return 0;
+	if (!ret && sdei_present_acpi()) {
+		struct platform_device *pdev;
+
+		pdev = platform_device_register_simple(sdei_driver.driver.name,
+						       0, NULL, 0);
+		if (IS_ERR(pdev))
+			pr_info("Failed to register ACPI:SDEI platform device %ld\n",
+				PTR_ERR(pdev));
+	}
+
+	return ret;
 }
 
 /*
@@ -1143,6 +1128,14 @@ int sdei_event_handler(struct pt_regs *regs,
 	mm_segment_t orig_addr_limit;
 	u32 event_num = arg->event_num;
 
+	/*
+	 * Save restore 'fs'.
+	 * The architecture's entry code save/restores 'fs' when taking an
+	 * exception from the kernel. This ensures addr_limit isn't inherited
+	 * if you interrupted something that allowed the uaccess routines to
+	 * access kernel memory.
+	 * Do the same here because this doesn't come via the same entry code.
+	*/
 	orig_addr_limit = get_fs();
 	set_fs(USER_DS);
 
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 613828d3f106..6b38f9e5d203 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -106,12 +106,12 @@ config EFI_PARAMS_FROM_FDT
 config EFI_RUNTIME_WRAPPERS
 	bool
 
-config EFI_ARMSTUB
+config EFI_GENERIC_STUB
 	bool
 
 config EFI_ARMSTUB_DTB_LOADER
 	bool "Enable the DTB loader"
-	depends on EFI_ARMSTUB
+	depends on EFI_GENERIC_STUB
 	default y
 	help
 	  Select this config option to add support for the dtb= command
@@ -124,6 +124,17 @@ config EFI_ARMSTUB_DTB_LOADER
 	  functionality for bootloaders that do not have such support
 	  this option is necessary.
 
+config EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER
+	bool "Enable the command line initrd loader" if !X86
+	depends on EFI_STUB && (EFI_GENERIC_STUB || X86)
+	default y
+	help
+	  Select this config option to add support for the initrd= command
+	  line parameter, allowing an initrd that resides on the same volume
+	  as the kernel image to be loaded into memory.
+
+	  This method is deprecated.
+
 config EFI_BOOTLOADER_CONTROL
 	tristate "EFI Bootloader Control"
 	depends on EFI_VARS
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index 9e5e62f5f94d..c697e70ca7e7 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -54,8 +54,8 @@ static phys_addr_t __init efi_to_phys(unsigned long addr)
 static __initdata unsigned long screen_info_table = EFI_INVALID_TABLE_ADDR;
 
 static const efi_config_table_type_t arch_tables[] __initconst = {
-	{LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID, NULL, &screen_info_table},
-	{NULL_GUID, NULL, NULL}
+	{LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID, &screen_info_table},
+	{}
 };
 
 static void __init init_screen_info(void)
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index b1af0de2e100..f564e15fbc7e 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -101,7 +101,7 @@ void cper_print_bits(const char *pfx, unsigned int bits,
 		if (!len)
 			len = snprintf(buf, sizeof(buf), "%s%s", pfx, str);
 		else
-			len += snprintf(buf+len, sizeof(buf)-len, ", %s", str);
+			len += scnprintf(buf+len, sizeof(buf)-len, ", %s", str);
 	}
 	if (len)
 		printk("%s\n", buf);
@@ -407,6 +407,58 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 	}
 }
 
+static const char * const fw_err_rec_type_strs[] = {
+	"IPF SAL Error Record",
+	"SOC Firmware Error Record Type1 (Legacy CrashLog Support)",
+	"SOC Firmware Error Record Type2",
+};
+
+static void cper_print_fw_err(const char *pfx,
+			      struct acpi_hest_generic_data *gdata,
+			      const struct cper_sec_fw_err_rec_ref *fw_err)
+{
+	void *buf = acpi_hest_get_payload(gdata);
+	u32 offset, length = gdata->error_data_length;
+
+	printk("%s""Firmware Error Record Type: %s\n", pfx,
+	       fw_err->record_type < ARRAY_SIZE(fw_err_rec_type_strs) ?
+	       fw_err_rec_type_strs[fw_err->record_type] : "unknown");
+	printk("%s""Revision: %d\n", pfx, fw_err->revision);
+
+	/* Record Type based on UEFI 2.7 */
+	if (fw_err->revision == 0) {
+		printk("%s""Record Identifier: %08llx\n", pfx,
+		       fw_err->record_identifier);
+	} else if (fw_err->revision == 2) {
+		printk("%s""Record Identifier: %pUl\n", pfx,
+		       &fw_err->record_identifier_guid);
+	}
+
+	/*
+	 * The FW error record may contain trailing data beyond the
+	 * structure defined by the specification. As the fields
+	 * defined (and hence the offset of any trailing data) vary
+	 * with the revision, set the offset to account for this
+	 * variation.
+	 */
+	if (fw_err->revision == 0) {
+		/* record_identifier_guid not defined */
+		offset = offsetof(struct cper_sec_fw_err_rec_ref,
+				  record_identifier_guid);
+	} else if (fw_err->revision == 1) {
+		/* record_identifier not defined */
+		offset = offsetof(struct cper_sec_fw_err_rec_ref,
+				  record_identifier);
+	} else {
+		offset = sizeof(*fw_err);
+	}
+
+	buf += offset;
+	length -= offset;
+
+	print_hex_dump(pfx, "", DUMP_PREFIX_OFFSET, 16, 4, buf, length, true);
+}
+
 static void cper_print_tstamp(const char *pfx,
 				   struct acpi_hest_generic_data_v300 *gdata)
 {
@@ -494,6 +546,16 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		else
 			goto err_section_too_small;
 #endif
+	} else if (guid_equal(sec_type, &CPER_SEC_FW_ERR_REC_REF)) {
+		struct cper_sec_fw_err_rec_ref *fw_err = acpi_hest_get_payload(gdata);
+
+		printk("%ssection_type: Firmware Error Record Reference\n",
+		       newpfx);
+		/* The minimal FW Error Record contains 16 bytes */
+		if (gdata->error_data_length >= SZ_16)
+			cper_print_fw_err(newpfx, gdata, fw_err);
+		else
+			goto err_section_too_small;
 	} else {
 		const void *err = acpi_hest_get_payload(gdata);
 
diff --git a/drivers/firmware/efi/earlycon.c b/drivers/firmware/efi/earlycon.c
index 5d4f84781aa0..a52236e11e5f 100644
--- a/drivers/firmware/efi/earlycon.c
+++ b/drivers/firmware/efi/earlycon.c
@@ -114,14 +114,16 @@ static void efi_earlycon_write_char(u32 *dst, unsigned char c, unsigned int h)
 	const u32 color_black = 0x00000000;
 	const u32 color_white = 0x00ffffff;
 	const u8 *src;
-	u8 s8;
-	int m;
+	int m, n, bytes;
+	u8 x;
 
-	src = font->data + c * font->height;
-	s8 = *(src + h);
+	bytes = BITS_TO_BYTES(font->width);
+	src = font->data + c * font->height * bytes + h * bytes;
 
-	for (m = 0; m < 8; m++) {
-		if ((s8 >> (7 - m)) & 1)
+	for (m = 0; m < font->width; m++) {
+		n = m % 8;
+		x = *(src + m / 8);
+		if ((x >> (7 - n)) & 1)
 			*dst = color_white;
 		else
 			*dst = color_black;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 911a2bd0f6b7..9357d6b6e87c 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -130,11 +130,8 @@ static ssize_t systab_show(struct kobject *kobj,
 	if (efi.smbios != EFI_INVALID_TABLE_ADDR)
 		str += sprintf(str, "SMBIOS=0x%lx\n", efi.smbios);
 
-	if (IS_ENABLED(CONFIG_IA64) || IS_ENABLED(CONFIG_X86)) {
-		extern char *efi_systab_show_arch(char *str);
-
+	if (IS_ENABLED(CONFIG_IA64) || IS_ENABLED(CONFIG_X86))
 		str = efi_systab_show_arch(str);
-	}
 
 	return str - buf;
 }
@@ -502,21 +499,21 @@ void __init efi_mem_reserve(phys_addr_t addr, u64 size)
 }
 
 static const efi_config_table_type_t common_tables[] __initconst = {
-	{ACPI_20_TABLE_GUID, "ACPI 2.0", &efi.acpi20},
-	{ACPI_TABLE_GUID, "ACPI", &efi.acpi},
-	{SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios},
-	{SMBIOS3_TABLE_GUID, "SMBIOS 3.0", &efi.smbios3},
-	{EFI_SYSTEM_RESOURCE_TABLE_GUID, "ESRT", &efi.esrt},
-	{EFI_MEMORY_ATTRIBUTES_TABLE_GUID, "MEMATTR", &efi_mem_attr_table},
-	{LINUX_EFI_RANDOM_SEED_TABLE_GUID, "RNG", &efi_rng_seed},
-	{LINUX_EFI_TPM_EVENT_LOG_GUID, "TPMEventLog", &efi.tpm_log},
-	{LINUX_EFI_TPM_FINAL_LOG_GUID, "TPMFinalLog", &efi.tpm_final_log},
-	{LINUX_EFI_MEMRESERVE_TABLE_GUID, "MEMRESERVE", &mem_reserve},
-	{EFI_RT_PROPERTIES_TABLE_GUID, "RTPROP", &rt_prop},
+	{ACPI_20_TABLE_GUID,			&efi.acpi20,		"ACPI 2.0"	},
+	{ACPI_TABLE_GUID,			&efi.acpi,		"ACPI"		},
+	{SMBIOS_TABLE_GUID,			&efi.smbios,		"SMBIOS"	},
+	{SMBIOS3_TABLE_GUID,			&efi.smbios3,		"SMBIOS 3.0"	},
+	{EFI_SYSTEM_RESOURCE_TABLE_GUID,	&efi.esrt,		"ESRT"		},
+	{EFI_MEMORY_ATTRIBUTES_TABLE_GUID,	&efi_mem_attr_table,	"MEMATTR"	},
+	{LINUX_EFI_RANDOM_SEED_TABLE_GUID,	&efi_rng_seed,		"RNG"		},
+	{LINUX_EFI_TPM_EVENT_LOG_GUID,		&efi.tpm_log,		"TPMEventLog"	},
+	{LINUX_EFI_TPM_FINAL_LOG_GUID,		&efi.tpm_final_log,	"TPMFinalLog"	},
+	{LINUX_EFI_MEMRESERVE_TABLE_GUID,	&mem_reserve,		"MEMRESERVE"	},
+	{EFI_RT_PROPERTIES_TABLE_GUID,		&rt_prop,		"RTPROP"	},
 #ifdef CONFIG_EFI_RCI2_TABLE
-	{DELLEMC_EFI_RCI2_TABLE_GUID, NULL, &rci2_table_phys},
+	{DELLEMC_EFI_RCI2_TABLE_GUID,		&rci2_table_phys			},
 #endif
-	{NULL_GUID, NULL, NULL},
+	{},
 };
 
 static __init int match_config_table(const efi_guid_t *guid,
@@ -525,15 +522,13 @@ static __init int match_config_table(const efi_guid_t *guid,
 {
 	int i;
 
-	if (table_types) {
-		for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) {
-			if (!efi_guidcmp(*guid, table_types[i].guid)) {
-				*(table_types[i].ptr) = table;
-				if (table_types[i].name)
-					pr_cont(" %s=0x%lx ",
-						table_types[i].name, table);
-				return 1;
-			}
+	for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) {
+		if (!efi_guidcmp(*guid, table_types[i].guid)) {
+			*(table_types[i].ptr) = table;
+			if (table_types[i].name[0])
+				pr_cont("%s=0x%lx ",
+					table_types[i].name, table);
+			return 1;
 		}
 	}
 
@@ -570,7 +565,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables,
 			table = tbl32[i].table;
 		}
 
-		if (!match_config_table(guid, table, common_tables))
+		if (!match_config_table(guid, table, common_tables) && arch_tables)
 			match_config_table(guid, table, arch_tables);
 	}
 	pr_cont("\n");
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 78ad1ba8c987..26528a46d99e 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -522,8 +522,10 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 	ret = kobject_init_and_add(&new_var->kobj, &efivar_ktype,
 				   NULL, "%s", short_name);
 	kfree(short_name);
-	if (ret)
+	if (ret) {
+		kobject_put(&new_var->kobj);
 		return ret;
+	}
 
 	kobject_uevent(&new_var->kobj, KOBJ_ADD);
 	if (efivar_entry_add(new_var, &efivar_sysfs_list)) {
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 094eabdecfe6..cce4a7436052 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -7,7 +7,7 @@
 #
 cflags-$(CONFIG_X86_32)		:= -march=i386
 cflags-$(CONFIG_X86_64)		:= -mcmodel=small
-cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -O2 \
+cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ \
 				   -fPIC -fno-strict-aliasing -mno-red-zone \
 				   -mno-mmx -mno-sse -fshort-wchar \
 				   -Wno-pointer-sign \
@@ -23,15 +23,19 @@ cflags-$(CONFIG_ARM)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
 
-cflags-$(CONFIG_EFI_ARMSTUB)	+= -I$(srctree)/scripts/dtc/libfdt
+cflags-$(CONFIG_EFI_GENERIC_STUB) += -I$(srctree)/scripts/dtc/libfdt
 
-KBUILD_CFLAGS			:= $(cflags-y) -DDISABLE_BRANCH_PROFILING \
+KBUILD_CFLAGS			:= $(cflags-y) -Os -DDISABLE_BRANCH_PROFILING \
 				   -include $(srctree)/drivers/firmware/efi/libstub/hidden.h \
 				   -D__NO_FORTIFY \
 				   $(call cc-option,-ffreestanding) \
 				   $(call cc-option,-fno-stack-protector) \
+				   $(call cc-option,-fno-addrsig) \
 				   -D__DISABLE_EXPORTS
 
+# remove SCS flags from all objects in this directory
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
+
 GCOV_PROFILE			:= n
 KASAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
@@ -42,16 +46,17 @@ KCOV_INSTRUMENT			:= n
 
 lib-y				:= efi-stub-helper.o gop.o secureboot.o tpm.o \
 				   file.o mem.o random.o randomalloc.o pci.o \
-				   skip_spaces.o lib-cmdline.o lib-ctype.o
+				   skip_spaces.o lib-cmdline.o lib-ctype.o \
+				   alignedmem.o relocate.o vsprintf.o
 
 # include the stub's generic dependencies from lib/ when building for ARM/arm64
-arm-deps-y := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c
+efi-deps-y := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c
 
 $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-lib-$(CONFIG_EFI_ARMSTUB)	+= arm-stub.o fdt.o string.o \
-				   $(patsubst %.c,lib-%.o,$(arm-deps-y))
+lib-$(CONFIG_EFI_GENERIC_STUB)	+= efi-stub.o fdt.o string.o \
+				   $(patsubst %.c,lib-%.o,$(efi-deps-y))
 
 lib-$(CONFIG_ARM)		+= arm32-stub.o
 lib-$(CONFIG_ARM64)		+= arm64-stub.o
@@ -60,6 +65,25 @@ CFLAGS_arm32-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_arm64-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 #
+# For x86, bootloaders like systemd-boot or grub-efi do not zero-initialize the
+# .bss section, so the .bss section of the EFI stub needs to be included in the
+# .data section of the compressed kernel to ensure initialization. Rename the
+# .bss section here so it's easy to pick out in the linker script.
+#
+STUBCOPY_FLAGS-$(CONFIG_X86)	+= --rename-section .bss=.bss.efistub,load,alloc
+STUBCOPY_RELOC-$(CONFIG_X86_32)	:= R_386_32
+STUBCOPY_RELOC-$(CONFIG_X86_64)	:= R_X86_64_64
+
+#
+# ARM discards the .data section because it disallows r/w data in the
+# decompressor. So move our .data to .data.efistub and .bss to .bss.efistub,
+# which are preserved explicitly by the decompressor linker script.
+#
+STUBCOPY_FLAGS-$(CONFIG_ARM)	+= --rename-section .data=.data.efistub	\
+				   --rename-section .bss=.bss.efistub,load,alloc
+STUBCOPY_RELOC-$(CONFIG_ARM)	:= R_ARM_ABS
+
+#
 # arm64 puts the stub in the kernel proper, which will unnecessarily retain all
 # code indefinitely unless it is annotated as __init/__initdata/__initconst etc.
 # So let's apply the __init annotations at the section level, by prefixing
@@ -73,8 +97,8 @@ CFLAGS_arm64-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 # a verification pass to see if any absolute relocations exist in any of the
 # object files.
 #
-extra-$(CONFIG_EFI_ARMSTUB)	:= $(lib-y)
-lib-$(CONFIG_EFI_ARMSTUB)	:= $(patsubst %.o,%.stub.o,$(lib-y))
+extra-y				:= $(lib-y)
+lib-y				:= $(patsubst %.o,%.stub.o,$(lib-y))
 
 STUBCOPY_FLAGS-$(CONFIG_ARM64)	+= --prefix-alloc-sections=.init \
 				   --prefix-symbols=__efistub_
@@ -97,11 +121,3 @@ quiet_cmd_stubcopy = STUBCPY $@
 		/bin/false;						\
 	fi;								\
 	$(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@
-
-#
-# ARM discards the .data section because it disallows r/w data in the
-# decompressor. So move our .data to .data.efistub, which is preserved
-# explicitly by the decompressor linker script.
-#
-STUBCOPY_FLAGS-$(CONFIG_ARM)	+= --rename-section .data=.data.efistub
-STUBCOPY_RELOC-$(CONFIG_ARM)	:= R_ARM_ABS
diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c
new file mode 100644
index 000000000000..cc89c4d6196f
--- /dev/null
+++ b/drivers/firmware/efi/libstub/alignedmem.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/efi.h>
+#include <asm/efi.h>
+
+#include "efistub.h"
+
+/**
+ * efi_allocate_pages_aligned() - Allocate memory pages
+ * @size:	minimum number of bytes to allocate
+ * @addr:	On return the address of the first allocated page. The first
+ *		allocated page has alignment EFI_ALLOC_ALIGN which is an
+ *		architecture dependent multiple of the page size.
+ * @max:	the address that the last allocated memory page shall not
+ *		exceed
+ * @align:	minimum alignment of the base of the allocation
+ *
+ * Allocate pages as EFI_LOADER_DATA. The allocated pages are aligned according
+ * to @align, which should be >= EFI_ALLOC_ALIGN. The last allocated page will
+ * not exceed the address given by @max.
+ *
+ * Return:	status code
+ */
+efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr,
+					unsigned long max, unsigned long align)
+{
+	efi_physical_addr_t alloc_addr;
+	efi_status_t status;
+	int slack;
+
+	if (align < EFI_ALLOC_ALIGN)
+		align = EFI_ALLOC_ALIGN;
+
+	alloc_addr = ALIGN_DOWN(max + 1, align) - 1;
+	size = round_up(size, EFI_ALLOC_ALIGN);
+	slack = align / EFI_PAGE_SIZE - 1;
+
+	status = efi_bs_call(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS,
+			     EFI_LOADER_DATA, size / EFI_PAGE_SIZE + slack,
+			     &alloc_addr);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	*addr = ALIGN((unsigned long)alloc_addr, align);
+
+	if (slack > 0) {
+		int l = (alloc_addr % align) / EFI_PAGE_SIZE;
+
+		if (l) {
+			efi_bs_call(free_pages, alloc_addr, slack - l + 1);
+			slack = l - 1;
+		}
+		if (slack)
+			efi_bs_call(free_pages, *addr + size, slack);
+	}
+	return EFI_SUCCESS;
+}
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index 7826553af2ba..40243f524556 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -18,7 +18,7 @@ efi_status_t check_platform_features(void)
 	/* LPAE kernels need compatible hardware */
 	block = cpuid_feature_extract(CPUID_EXT_MMFR0, 0);
 	if (block < 5) {
-		pr_efi_err("This LPAE kernel is not supported by your CPU\n");
+		efi_err("This LPAE kernel is not supported by your CPU\n");
 		return EFI_UNSUPPORTED;
 	}
 	return EFI_SUCCESS;
@@ -120,7 +120,7 @@ static efi_status_t reserve_kernel_base(unsigned long dram_base,
 	 */
 	status = efi_get_memory_map(&map);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("reserve_kernel_base(): Unable to retrieve memory map.\n");
+		efi_err("reserve_kernel_base(): Unable to retrieve memory map.\n");
 		return status;
 	}
 
@@ -162,7 +162,7 @@ static efi_status_t reserve_kernel_base(unsigned long dram_base,
 					     (end - start) / EFI_PAGE_SIZE,
 					     &start);
 			if (status != EFI_SUCCESS) {
-				pr_efi_err("reserve_kernel_base(): alloc failed.\n");
+				efi_err("reserve_kernel_base(): alloc failed.\n");
 				goto out;
 			}
 			break;
@@ -199,14 +199,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 	unsigned long kernel_base;
 	efi_status_t status;
 
-	/*
-	 * Verify that the DRAM base address is compatible with the ARM
-	 * boot protocol, which determines the base of DRAM by masking
-	 * off the low 27 bits of the address at which the zImage is
-	 * loaded. These assumptions are made by the decompressor,
-	 * before any memory map is available.
-	 */
-	kernel_base = round_up(dram_base, SZ_128M);
+	/* use a 16 MiB aligned base for the decompressed kernel */
+	kernel_base = round_up(dram_base, SZ_16M) + TEXT_OFFSET;
 
 	/*
 	 * Note that some platforms (notably, the Raspberry Pi 2) put
@@ -215,41 +209,14 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 	 * base of the kernel image is only partially used at the moment.
 	 * (Up to 5 pages are used for the swapper page tables)
 	 */
-	kernel_base += TEXT_OFFSET - 5 * PAGE_SIZE;
-
-	status = reserve_kernel_base(kernel_base, reserve_addr, reserve_size);
-	if (status != EFI_SUCCESS) {
-		pr_efi_err("Unable to allocate memory for uncompressed kernel.\n");
-		return status;
-	}
-
-	/*
-	 * Relocate the zImage, so that it appears in the lowest 128 MB
-	 * memory window.
-	 */
-	*image_addr = (unsigned long)image->image_base;
-	*image_size = image->image_size;
-	status = efi_relocate_kernel(image_addr, *image_size, *image_size,
-				     kernel_base + MAX_UNCOMP_KERNEL_SIZE, 0, 0);
+	status = reserve_kernel_base(kernel_base - 5 * PAGE_SIZE, reserve_addr,
+				     reserve_size);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to relocate kernel.\n");
-		efi_free(*reserve_size, *reserve_addr);
-		*reserve_size = 0;
+		efi_err("Unable to allocate memory for uncompressed kernel.\n");
 		return status;
 	}
 
-	/*
-	 * Check to see if we were able to allocate memory low enough
-	 * in memory. The kernel determines the base of DRAM from the
-	 * address at which the zImage is loaded.
-	 */
-	if (*image_addr + *image_size > dram_base + ZIMAGE_OFFSET_LIMIT) {
-		pr_efi_err("Failed to relocate kernel, no low memory available.\n");
-		efi_free(*reserve_size, *reserve_addr);
-		*reserve_size = 0;
-		efi_free(*image_size, *image_addr);
-		*image_size = 0;
-		return EFI_LOAD_ERROR;
-	}
+	*image_addr = kernel_base;
+	*image_size = 0;
 	return EFI_SUCCESS;
 }
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index fc9f8ab533a7..7f6a57dec513 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -26,14 +26,23 @@ efi_status_t check_platform_features(void)
 	tg = (read_cpuid(ID_AA64MMFR0_EL1) >> ID_AA64MMFR0_TGRAN_SHIFT) & 0xf;
 	if (tg != ID_AA64MMFR0_TGRAN_SUPPORTED) {
 		if (IS_ENABLED(CONFIG_ARM64_64K_PAGES))
-			pr_efi_err("This 64 KB granular kernel is not supported by your CPU\n");
+			efi_err("This 64 KB granular kernel is not supported by your CPU\n");
 		else
-			pr_efi_err("This 16 KB granular kernel is not supported by your CPU\n");
+			efi_err("This 16 KB granular kernel is not supported by your CPU\n");
 		return EFI_UNSUPPORTED;
 	}
 	return EFI_SUCCESS;
 }
 
+/*
+ * Relocatable kernels can fix up the misalignment with respect to
+ * MIN_KIMG_ALIGN, so they only require a minimum alignment of EFI_KIMG_ALIGN
+ * (which accounts for the alignment of statically allocated objects such as
+ * the swapper stack.)
+ */
+static const u64 min_kimg_align = IS_ENABLED(CONFIG_RELOCATABLE) ? EFI_KIMG_ALIGN
+								 : MIN_KIMG_ALIGN;
+
 efi_status_t handle_kernel_image(unsigned long *image_addr,
 				 unsigned long *image_size,
 				 unsigned long *reserve_addr,
@@ -43,106 +52,63 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 {
 	efi_status_t status;
 	unsigned long kernel_size, kernel_memsize = 0;
-	unsigned long preferred_offset;
-	u64 phys_seed = 0;
+	u32 phys_seed = 0;
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
-		if (!nokaslr()) {
+		if (!efi_nokaslr) {
 			status = efi_get_random_bytes(sizeof(phys_seed),
 						      (u8 *)&phys_seed);
 			if (status == EFI_NOT_FOUND) {
-				pr_efi("EFI_RNG_PROTOCOL unavailable, no randomness supplied\n");
+				efi_info("EFI_RNG_PROTOCOL unavailable, no randomness supplied\n");
 			} else if (status != EFI_SUCCESS) {
-				pr_efi_err("efi_get_random_bytes() failed\n");
+				efi_err("efi_get_random_bytes() failed\n");
 				return status;
 			}
 		} else {
-			pr_efi("KASLR disabled on kernel command line\n");
+			efi_info("KASLR disabled on kernel command line\n");
 		}
 	}
 
-	/*
-	 * The preferred offset of the kernel Image is TEXT_OFFSET bytes beyond
-	 * a 2 MB aligned base, which itself may be lower than dram_base, as
-	 * long as the resulting offset equals or exceeds it.
-	 */
-	preferred_offset = round_down(dram_base, MIN_KIMG_ALIGN) + TEXT_OFFSET;
-	if (preferred_offset < dram_base)
-		preferred_offset += MIN_KIMG_ALIGN;
+	if (image->image_base != _text)
+		efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n");
 
 	kernel_size = _edata - _text;
 	kernel_memsize = kernel_size + (_end - _edata);
+	*reserve_size = kernel_memsize + TEXT_OFFSET % min_kimg_align;
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && phys_seed != 0) {
 		/*
-		 * Produce a displacement in the interval [0, MIN_KIMG_ALIGN)
-		 * that doesn't violate this kernel's de-facto alignment
-		 * constraints.
-		 */
-		u32 mask = (MIN_KIMG_ALIGN - 1) & ~(EFI_KIMG_ALIGN - 1);
-		u32 offset = (phys_seed >> 32) & mask;
-
-		/*
-		 * With CONFIG_RANDOMIZE_TEXT_OFFSET=y, TEXT_OFFSET may not
-		 * be a multiple of EFI_KIMG_ALIGN, and we must ensure that
-		 * we preserve the misalignment of 'offset' relative to
-		 * EFI_KIMG_ALIGN so that statically allocated objects whose
-		 * alignment exceeds PAGE_SIZE appear correctly aligned in
-		 * memory.
-		 */
-		offset |= TEXT_OFFSET % EFI_KIMG_ALIGN;
-
-		/*
 		 * If KASLR is enabled, and we have some randomness available,
 		 * locate the kernel at a randomized offset in physical memory.
 		 */
-		*reserve_size = kernel_memsize + offset;
-		status = efi_random_alloc(*reserve_size,
-					  MIN_KIMG_ALIGN, reserve_addr,
-					  (u32)phys_seed);
-
-		*image_addr = *reserve_addr + offset;
+		status = efi_random_alloc(*reserve_size, min_kimg_align,
+					  reserve_addr, phys_seed);
 	} else {
-		/*
-		 * Else, try a straight allocation at the preferred offset.
-		 * This will work around the issue where, if dram_base == 0x0,
-		 * efi_low_alloc() refuses to allocate at 0x0 (to prevent the
-		 * address of the allocation to be mistaken for a FAIL return
-		 * value or a NULL pointer). It will also ensure that, on
-		 * platforms where the [dram_base, dram_base + TEXT_OFFSET)
-		 * interval is partially occupied by the firmware (like on APM
-		 * Mustang), we can still place the kernel at the address
-		 * 'dram_base + TEXT_OFFSET'.
-		 */
-		*image_addr = (unsigned long)_text;
-		if (*image_addr == preferred_offset)
-			return EFI_SUCCESS;
-
-		*image_addr = *reserve_addr = preferred_offset;
-		*reserve_size = round_up(kernel_memsize, EFI_ALLOC_ALIGN);
-
-		status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS,
-				     EFI_LOADER_DATA,
-				     *reserve_size / EFI_PAGE_SIZE,
-				     (efi_physical_addr_t *)reserve_addr);
+		status = EFI_OUT_OF_RESOURCES;
 	}
 
 	if (status != EFI_SUCCESS) {
-		*reserve_size = kernel_memsize + TEXT_OFFSET;
-		status = efi_low_alloc(*reserve_size,
-				       MIN_KIMG_ALIGN, reserve_addr);
+		if (IS_ALIGNED((u64)_text - TEXT_OFFSET, min_kimg_align)) {
+			/*
+			 * Just execute from wherever we were loaded by the
+			 * UEFI PE/COFF loader if the alignment is suitable.
+			 */
+			*image_addr = (u64)_text;
+			*reserve_size = 0;
+			return EFI_SUCCESS;
+		}
+
+		status = efi_allocate_pages_aligned(*reserve_size, reserve_addr,
+						    ULONG_MAX, min_kimg_align);
 
 		if (status != EFI_SUCCESS) {
-			pr_efi_err("Failed to relocate kernel\n");
+			efi_err("Failed to relocate kernel\n");
 			*reserve_size = 0;
 			return status;
 		}
-		*image_addr = *reserve_addr + TEXT_OFFSET;
 	}
 
-	if (image->image_base != _text)
-		pr_efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n");
-
+	*image_addr = *reserve_addr + TEXT_OFFSET % min_kimg_align;
 	memcpy((void *)*image_addr, _text, kernel_size);
 
 	return EFI_SUCCESS;
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 9f34c7242939..89f075275300 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -7,60 +7,151 @@
  * Copyright 2011 Intel Corporation; author Matt Fleming
  */
 
+#include <stdarg.h>
+
+#include <linux/ctype.h>
 #include <linux/efi.h>
+#include <linux/kernel.h>
+#include <linux/printk.h> /* For CONSOLE_LOGLEVEL_* */
 #include <asm/efi.h>
+#include <asm/setup.h>
 
 #include "efistub.h"
 
-static bool __efistub_global efi_nochunk;
-static bool __efistub_global efi_nokaslr;
-static bool __efistub_global efi_noinitrd;
-static bool __efistub_global efi_quiet;
-static bool __efistub_global efi_novamap;
-static bool __efistub_global efi_nosoftreserve;
-static bool __efistub_global efi_disable_pci_dma =
-					IS_ENABLED(CONFIG_EFI_DISABLE_PCI_DMA);
+bool efi_nochunk;
+bool efi_nokaslr;
+bool efi_noinitrd;
+int efi_loglevel = CONSOLE_LOGLEVEL_DEFAULT;
+bool efi_novamap;
 
-bool __pure nochunk(void)
-{
-	return efi_nochunk;
-}
-bool __pure nokaslr(void)
-{
-	return efi_nokaslr;
-}
-bool __pure noinitrd(void)
+static bool efi_nosoftreserve;
+static bool efi_disable_pci_dma = IS_ENABLED(CONFIG_EFI_DISABLE_PCI_DMA);
+
+bool __pure __efi_soft_reserve_enabled(void)
 {
-	return efi_noinitrd;
+	return !efi_nosoftreserve;
 }
-bool __pure is_quiet(void)
+
+void efi_char16_puts(efi_char16_t *str)
 {
-	return efi_quiet;
+	efi_call_proto(efi_table_attr(efi_system_table, con_out),
+		       output_string, str);
 }
-bool __pure novamap(void)
+
+static
+u32 utf8_to_utf32(const u8 **s8)
 {
-	return efi_novamap;
+	u32 c32;
+	u8 c0, cx;
+	size_t clen, i;
+
+	c0 = cx = *(*s8)++;
+	/*
+	 * The position of the most-significant 0 bit gives us the length of
+	 * a multi-octet encoding.
+	 */
+	for (clen = 0; cx & 0x80; ++clen)
+		cx <<= 1;
+	/*
+	 * If the 0 bit is in position 8, this is a valid single-octet
+	 * encoding. If the 0 bit is in position 7 or positions 1-3, the
+	 * encoding is invalid.
+	 * In either case, we just return the first octet.
+	 */
+	if (clen < 2 || clen > 4)
+		return c0;
+	/* Get the bits from the first octet. */
+	c32 = cx >> clen--;
+	for (i = 0; i < clen; ++i) {
+		/* Trailing octets must have 10 in most significant bits. */
+		cx = (*s8)[i] ^ 0x80;
+		if (cx & 0xc0)
+			return c0;
+		c32 = (c32 << 6) | cx;
+	}
+	/*
+	 * Check for validity:
+	 * - The character must be in the Unicode range.
+	 * - It must not be a surrogate.
+	 * - It must be encoded using the correct number of octets.
+	 */
+	if (c32 > 0x10ffff ||
+	    (c32 & 0xf800) == 0xd800 ||
+	    clen != (c32 >= 0x80) + (c32 >= 0x800) + (c32 >= 0x10000))
+		return c0;
+	*s8 += clen;
+	return c32;
 }
-bool __pure __efi_soft_reserve_enabled(void)
+
+void efi_puts(const char *str)
 {
-	return !efi_nosoftreserve;
+	efi_char16_t buf[128];
+	size_t pos = 0, lim = ARRAY_SIZE(buf);
+	const u8 *s8 = (const u8 *)str;
+	u32 c32;
+
+	while (*s8) {
+		if (*s8 == '\n')
+			buf[pos++] = L'\r';
+		c32 = utf8_to_utf32(&s8);
+		if (c32 < 0x10000) {
+			/* Characters in plane 0 use a single word. */
+			buf[pos++] = c32;
+		} else {
+			/*
+			 * Characters in other planes encode into a surrogate
+			 * pair.
+			 */
+			buf[pos++] = (0xd800 - (0x10000 >> 10)) + (c32 >> 10);
+			buf[pos++] = 0xdc00 + (c32 & 0x3ff);
+		}
+		if (*s8 == '\0' || pos >= lim - 2) {
+			buf[pos] = L'\0';
+			efi_char16_puts(buf);
+			pos = 0;
+		}
+	}
 }
 
-void efi_printk(char *str)
+int efi_printk(const char *fmt, ...)
 {
-	char *s8;
+	char printf_buf[256];
+	va_list args;
+	int printed;
+	int loglevel = printk_get_level(fmt);
+
+	switch (loglevel) {
+	case '0' ... '9':
+		loglevel -= '0';
+		break;
+	default:
+		/*
+		 * Use loglevel -1 for cases where we just want to print to
+		 * the screen.
+		 */
+		loglevel = -1;
+		break;
+	}
 
-	for (s8 = str; *s8; s8++) {
-		efi_char16_t ch[2] = { 0 };
+	if (loglevel >= efi_loglevel)
+		return 0;
 
-		ch[0] = *s8;
-		if (*s8 == '\n') {
-			efi_char16_t nl[2] = { '\r', 0 };
-			efi_char16_printk(nl);
-		}
+	if (loglevel >= 0)
+		efi_puts("EFI stub: ");
+
+	fmt = printk_skip_level(fmt);
+
+	va_start(args, fmt);
+	printed = vsnprintf(printf_buf, sizeof(printf_buf), fmt, args);
+	va_end(args);
 
-		efi_char16_printk(ch);
+	efi_puts(printf_buf);
+	if (printed >= sizeof(printf_buf)) {
+		efi_puts("[Message truncated]\n");
+		return -1;
 	}
+
+	return printed;
 }
 
 /*
@@ -91,7 +182,7 @@ efi_status_t efi_parse_options(char const *cmdline)
 		if (!strcmp(param, "nokaslr")) {
 			efi_nokaslr = true;
 		} else if (!strcmp(param, "quiet")) {
-			efi_quiet = true;
+			efi_loglevel = CONSOLE_LOGLEVEL_QUIET;
 		} else if (!strcmp(param, "noinitrd")) {
 			efi_noinitrd = true;
 		} else if (!strcmp(param, "efi") && val) {
@@ -105,6 +196,11 @@ efi_status_t efi_parse_options(char const *cmdline)
 				efi_disable_pci_dma = true;
 			if (parse_option_str(val, "no_disable_early_pci_dma"))
 				efi_disable_pci_dma = false;
+			if (parse_option_str(val, "debug"))
+				efi_loglevel = CONSOLE_LOGLEVEL_DEBUG;
+		} else if (!strcmp(param, "video") &&
+			   val && strstarts(val, "efifb:")) {
+			efi_parse_option_graphics(val + strlen("efifb:"));
 		}
 	}
 	efi_bs_call(free_pool, buf);
@@ -112,97 +208,79 @@ efi_status_t efi_parse_options(char const *cmdline)
 }
 
 /*
- * Get the number of UTF-8 bytes corresponding to an UTF-16 character.
- * This overestimates for surrogates, but that is okay.
- */
-static int efi_utf8_bytes(u16 c)
-{
-	return 1 + (c >= 0x80) + (c >= 0x800);
-}
-
-/*
- * Convert an UTF-16 string, not necessarily null terminated, to UTF-8.
- */
-static u8 *efi_utf16_to_utf8(u8 *dst, const u16 *src, int n)
-{
-	unsigned int c;
-
-	while (n--) {
-		c = *src++;
-		if (n && c >= 0xd800 && c <= 0xdbff &&
-		    *src >= 0xdc00 && *src <= 0xdfff) {
-			c = 0x10000 + ((c & 0x3ff) << 10) + (*src & 0x3ff);
-			src++;
-			n--;
-		}
-		if (c >= 0xd800 && c <= 0xdfff)
-			c = 0xfffd; /* Unmatched surrogate */
-		if (c < 0x80) {
-			*dst++ = c;
-			continue;
-		}
-		if (c < 0x800) {
-			*dst++ = 0xc0 + (c >> 6);
-			goto t1;
-		}
-		if (c < 0x10000) {
-			*dst++ = 0xe0 + (c >> 12);
-			goto t2;
-		}
-		*dst++ = 0xf0 + (c >> 18);
-		*dst++ = 0x80 + ((c >> 12) & 0x3f);
-	t2:
-		*dst++ = 0x80 + ((c >> 6) & 0x3f);
-	t1:
-		*dst++ = 0x80 + (c & 0x3f);
-	}
-
-	return dst;
-}
-
-/*
  * Convert the unicode UEFI command line to ASCII to pass to kernel.
  * Size of memory allocated return in *cmd_line_len.
  * Returns NULL on error.
  */
-char *efi_convert_cmdline(efi_loaded_image_t *image,
-			  int *cmd_line_len, unsigned long max_addr)
+char *efi_convert_cmdline(efi_loaded_image_t *image, int *cmd_line_len)
 {
 	const u16 *s2;
-	u8 *s1 = NULL;
 	unsigned long cmdline_addr = 0;
-	int load_options_chars = efi_table_attr(image, load_options_size) / 2;
+	int options_chars = efi_table_attr(image, load_options_size) / 2;
 	const u16 *options = efi_table_attr(image, load_options);
-	int options_bytes = 0;  /* UTF-8 bytes */
-	int options_chars = 0;  /* UTF-16 chars */
+	int options_bytes = 0, safe_options_bytes = 0;  /* UTF-8 bytes */
+	bool in_quote = false;
 	efi_status_t status;
-	u16 zero = 0;
 
 	if (options) {
 		s2 = options;
-		while (*s2 && *s2 != '\n'
-		       && options_chars < load_options_chars) {
-			options_bytes += efi_utf8_bytes(*s2++);
-			options_chars++;
+		while (options_bytes < COMMAND_LINE_SIZE && options_chars--) {
+			u16 c = *s2++;
+
+			if (c < 0x80) {
+				if (c == L'\0' || c == L'\n')
+					break;
+				if (c == L'"')
+					in_quote = !in_quote;
+				else if (!in_quote && isspace((char)c))
+					safe_options_bytes = options_bytes;
+
+				options_bytes++;
+				continue;
+			}
+
+			/*
+			 * Get the number of UTF-8 bytes corresponding to a
+			 * UTF-16 character.
+			 * The first part handles everything in the BMP.
+			 */
+			options_bytes += 2 + (c >= 0x800);
+			/*
+			 * Add one more byte for valid surrogate pairs. Invalid
+			 * surrogates will be replaced with 0xfffd and take up
+			 * only 3 bytes.
+			 */
+			if ((c & 0xfc00) == 0xd800) {
+				/*
+				 * If the very last word is a high surrogate,
+				 * we must ignore it since we can't access the
+				 * low surrogate.
+				 */
+				if (!options_chars) {
+					options_bytes -= 3;
+				} else if ((*s2 & 0xfc00) == 0xdc00) {
+					options_bytes++;
+					options_chars--;
+					s2++;
+				}
+			}
+		}
+		if (options_bytes >= COMMAND_LINE_SIZE) {
+			options_bytes = safe_options_bytes;
+			efi_err("Command line is too long: truncated to %d bytes\n",
+				options_bytes);
 		}
-	}
-
-	if (!options_chars) {
-		/* No command line options, so return empty string*/
-		options = &zero;
 	}
 
 	options_bytes++;	/* NUL termination */
 
-	status = efi_allocate_pages(options_bytes, &cmdline_addr, max_addr);
+	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, options_bytes,
+			     (void **)&cmdline_addr);
 	if (status != EFI_SUCCESS)
 		return NULL;
 
-	s1 = (u8 *)cmdline_addr;
-	s2 = (const u16 *)options;
-
-	s1 = efi_utf16_to_utf8(s1, s2, options_chars);
-	*s1 = '\0';
+	snprintf((char *)cmdline_addr, options_bytes, "%.*ls",
+		 options_bytes - 1, options);
 
 	*cmd_line_len = options_bytes;
 	return (char *)cmdline_addr;
@@ -285,8 +363,8 @@ fail:
 
 void *get_efi_config_table(efi_guid_t guid)
 {
-	unsigned long tables = efi_table_attr(efi_system_table(), tables);
-	int nr_tables = efi_table_attr(efi_system_table(), nr_tables);
+	unsigned long tables = efi_table_attr(efi_system_table, tables);
+	int nr_tables = efi_table_attr(efi_system_table, nr_tables);
 	int i;
 
 	for (i = 0; i < nr_tables; i++) {
@@ -301,12 +379,6 @@ void *get_efi_config_table(efi_guid_t guid)
 	return NULL;
 }
 
-void efi_char16_printk(efi_char16_t *str)
-{
-	efi_call_proto(efi_table_attr(efi_system_table(), con_out),
-		       output_string, str);
-}
-
 /*
  * The LINUX_EFI_INITRD_MEDIA_GUID vendor media device path below provides a way
  * for the firmware or bootloader to expose the initrd data directly to the stub
@@ -348,6 +420,7 @@ static const struct {
  *		%EFI_OUT_OF_RESOURCES if memory allocation failed
  *		%EFI_LOAD_ERROR in all other cases
  */
+static
 efi_status_t efi_load_initrd_dev_path(unsigned long *load_addr,
 				      unsigned long *load_size,
 				      unsigned long max)
@@ -360,9 +433,6 @@ efi_status_t efi_load_initrd_dev_path(unsigned long *load_addr,
 	efi_handle_t handle;
 	efi_status_t status;
 
-	if (!load_addr || !load_size)
-		return EFI_INVALID_PARAMETER;
-
 	dp = (efi_device_path_protocol_t *)&initrd_dev_path;
 	status = efi_bs_call(locate_device_path, &lf2_proto_guid, &dp, &handle);
 	if (status != EFI_SUCCESS)
@@ -392,3 +462,80 @@ efi_status_t efi_load_initrd_dev_path(unsigned long *load_addr,
 	*load_size = initrd_size;
 	return EFI_SUCCESS;
 }
+
+static
+efi_status_t efi_load_initrd_cmdline(efi_loaded_image_t *image,
+				     unsigned long *load_addr,
+				     unsigned long *load_size,
+				     unsigned long soft_limit,
+				     unsigned long hard_limit)
+{
+	if (!IS_ENABLED(CONFIG_EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER) ||
+	    (IS_ENABLED(CONFIG_X86) && (!efi_is_native() || image == NULL))) {
+		*load_addr = *load_size = 0;
+		return EFI_SUCCESS;
+	}
+
+	return handle_cmdline_files(image, L"initrd=", sizeof(L"initrd=") - 2,
+				    soft_limit, hard_limit,
+				    load_addr, load_size);
+}
+
+efi_status_t efi_load_initrd(efi_loaded_image_t *image,
+			     unsigned long *load_addr,
+			     unsigned long *load_size,
+			     unsigned long soft_limit,
+			     unsigned long hard_limit)
+{
+	efi_status_t status;
+
+	if (!load_addr || !load_size)
+		return EFI_INVALID_PARAMETER;
+
+	status = efi_load_initrd_dev_path(load_addr, load_size, hard_limit);
+	if (status == EFI_SUCCESS) {
+		efi_info("Loaded initrd from LINUX_EFI_INITRD_MEDIA_GUID device path\n");
+	} else if (status == EFI_NOT_FOUND) {
+		status = efi_load_initrd_cmdline(image, load_addr, load_size,
+						 soft_limit, hard_limit);
+		if (status == EFI_SUCCESS && *load_size > 0)
+			efi_info("Loaded initrd from command line option\n");
+	}
+
+	return status;
+}
+
+efi_status_t efi_wait_for_key(unsigned long usec, efi_input_key_t *key)
+{
+	efi_event_t events[2], timer;
+	unsigned long index;
+	efi_simple_text_input_protocol_t *con_in;
+	efi_status_t status;
+
+	con_in = efi_table_attr(efi_system_table, con_in);
+	if (!con_in)
+		return EFI_UNSUPPORTED;
+	efi_set_event_at(events, 0, efi_table_attr(con_in, wait_for_key));
+
+	status = efi_bs_call(create_event, EFI_EVT_TIMER, 0, NULL, NULL, &timer);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	status = efi_bs_call(set_timer, timer, EfiTimerRelative,
+			     EFI_100NSEC_PER_USEC * usec);
+	if (status != EFI_SUCCESS)
+		return status;
+	efi_set_event_at(events, 1, timer);
+
+	status = efi_bs_call(wait_for_event, 2, events, &index);
+	if (status == EFI_SUCCESS) {
+		if (index == 0)
+			status = efi_call_proto(con_in, read_keystroke, key);
+		else
+			status = EFI_TIMEOUT;
+	}
+
+	efi_bs_call(close_event, timer);
+
+	return status;
+}
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/efi-stub.c
index 99a5cde7c2d8..e97370bdfdb0 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/efi-stub.c
@@ -36,14 +36,9 @@
 #endif
 
 static u64 virtmap_base = EFI_RT_VIRTUAL_BASE;
-static bool __efistub_global flat_va_mapping;
+static bool flat_va_mapping;
 
-static efi_system_table_t *__efistub_global sys_table;
-
-__pure efi_system_table_t *efi_system_table(void)
-{
-	return sys_table;
-}
+const efi_system_table_t *efi_system_table;
 
 static struct screen_info *setup_graphics(void)
 {
@@ -60,12 +55,16 @@ static struct screen_info *setup_graphics(void)
 		si = alloc_screen_info();
 		if (!si)
 			return NULL;
-		efi_setup_gop(si, &gop_proto, size);
+		status = efi_setup_gop(si, &gop_proto, size);
+		if (status != EFI_SUCCESS) {
+			free_screen_info(si);
+			return NULL;
+		}
 	}
 	return si;
 }
 
-void install_memreserve_table(void)
+static void install_memreserve_table(void)
 {
 	struct linux_efi_memreserve *rsv;
 	efi_guid_t memreserve_table_guid = LINUX_EFI_MEMRESERVE_TABLE_GUID;
@@ -74,7 +73,7 @@ void install_memreserve_table(void)
 	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, sizeof(*rsv),
 			     (void **)&rsv);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to allocate memreserve entry!\n");
+		efi_err("Failed to allocate memreserve entry!\n");
 		return;
 	}
 
@@ -85,7 +84,7 @@ void install_memreserve_table(void)
 	status = efi_bs_call(install_configuration_table,
 			     &memreserve_table_guid, rsv);
 	if (status != EFI_SUCCESS)
-		pr_efi_err("Failed to install memreserve config table!\n");
+		efi_err("Failed to install memreserve config table!\n");
 }
 
 static unsigned long get_dram_base(void)
@@ -145,7 +144,8 @@ asmlinkage void __noreturn efi_enter_kernel(unsigned long entrypoint,
  * for both archictectures, with the arch-specific code provided in the
  * handle_kernel_image() function.
  */
-efi_status_t efi_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg)
+efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
+				   efi_system_table_t *sys_table_arg)
 {
 	efi_loaded_image_t *image;
 	efi_status_t status;
@@ -167,10 +167,10 @@ efi_status_t efi_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg)
 	efi_properties_table_t *prop_tbl;
 	unsigned long max_addr;
 
-	sys_table = sys_table_arg;
+	efi_system_table = sys_table_arg;
 
 	/* Check if we were booted by the EFI firmware */
-	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
+	if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
 		status = EFI_INVALID_PARAMETER;
 		goto fail;
 	}
@@ -184,16 +184,16 @@ efi_status_t efi_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg)
 	 * information about the running image, such as size and the command
 	 * line.
 	 */
-	status = sys_table->boottime->handle_protocol(handle,
+	status = efi_system_table->boottime->handle_protocol(handle,
 					&loaded_image_proto, (void *)&image);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to get loaded image protocol\n");
+		efi_err("Failed to get loaded image protocol\n");
 		goto fail;
 	}
 
 	dram_base = get_dram_base();
 	if (dram_base == EFI_ERROR) {
-		pr_efi_err("Failed to find DRAM base\n");
+		efi_err("Failed to find DRAM base\n");
 		status = EFI_LOAD_ERROR;
 		goto fail;
 	}
@@ -203,22 +203,32 @@ efi_status_t efi_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg)
 	 * protocol. We are going to copy the command line into the
 	 * device tree, so this can be allocated anywhere.
 	 */
-	cmdline_ptr = efi_convert_cmdline(image, &cmdline_size, ULONG_MAX);
+	cmdline_ptr = efi_convert_cmdline(image, &cmdline_size);
 	if (!cmdline_ptr) {
-		pr_efi_err("getting command line via LOADED_IMAGE_PROTOCOL\n");
+		efi_err("getting command line via LOADED_IMAGE_PROTOCOL\n");
 		status = EFI_OUT_OF_RESOURCES;
 		goto fail;
 	}
 
 	if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
 	    IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
-	    cmdline_size == 0)
-		efi_parse_options(CONFIG_CMDLINE);
+	    cmdline_size == 0) {
+		status = efi_parse_options(CONFIG_CMDLINE);
+		if (status != EFI_SUCCESS) {
+			efi_err("Failed to parse options\n");
+			goto fail_free_cmdline;
+		}
+	}
 
-	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && cmdline_size > 0)
-		efi_parse_options(cmdline_ptr);
+	if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && cmdline_size > 0) {
+		status = efi_parse_options(cmdline_ptr);
+		if (status != EFI_SUCCESS) {
+			efi_err("Failed to parse options\n");
+			goto fail_free_cmdline;
+		}
+	}
 
-	pr_efi("Booting Linux Kernel...\n");
+	efi_info("Booting Linux Kernel...\n");
 
 	si = setup_graphics();
 
@@ -227,8 +237,8 @@ efi_status_t efi_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg)
 				     &reserve_size,
 				     dram_base, image);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to relocate kernel\n");
-		goto fail_free_cmdline;
+		efi_err("Failed to relocate kernel\n");
+		goto fail_free_screeninfo;
 	}
 
 	efi_retrieve_tpm2_eventlog();
@@ -246,42 +256,34 @@ efi_status_t efi_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg)
 	if (!IS_ENABLED(CONFIG_EFI_ARMSTUB_DTB_LOADER) ||
 	     secure_boot != efi_secureboot_mode_disabled) {
 		if (strstr(cmdline_ptr, "dtb="))
-			pr_efi("Ignoring DTB from command line.\n");
+			efi_err("Ignoring DTB from command line.\n");
 	} else {
 		status = efi_load_dtb(image, &fdt_addr, &fdt_size);
 
 		if (status != EFI_SUCCESS) {
-			pr_efi_err("Failed to load device tree!\n");
+			efi_err("Failed to load device tree!\n");
 			goto fail_free_image;
 		}
 	}
 
 	if (fdt_addr) {
-		pr_efi("Using DTB from command line\n");
+		efi_info("Using DTB from command line\n");
 	} else {
 		/* Look for a device tree configuration table entry. */
 		fdt_addr = (uintptr_t)get_fdt(&fdt_size);
 		if (fdt_addr)
-			pr_efi("Using DTB from configuration table\n");
+			efi_info("Using DTB from configuration table\n");
 	}
 
 	if (!fdt_addr)
-		pr_efi("Generating empty DTB\n");
+		efi_info("Generating empty DTB\n");
 
-	if (!noinitrd()) {
+	if (!efi_noinitrd) {
 		max_addr = efi_get_max_initrd_addr(dram_base, image_addr);
-		status = efi_load_initrd_dev_path(&initrd_addr, &initrd_size,
-						  max_addr);
-		if (status == EFI_SUCCESS) {
-			pr_efi("Loaded initrd from LINUX_EFI_INITRD_MEDIA_GUID device path\n");
-		} else if (status == EFI_NOT_FOUND) {
-			status = efi_load_initrd(image, &initrd_addr, &initrd_size,
-						 ULONG_MAX, max_addr);
-			if (status == EFI_SUCCESS && initrd_size > 0)
-				pr_efi("Loaded initrd from command line option\n");
-		}
+		status = efi_load_initrd(image, &initrd_addr, &initrd_size,
+					 ULONG_MAX, max_addr);
 		if (status != EFI_SUCCESS)
-			pr_efi_err("Failed to load initrd!\n");
+			efi_err("Failed to load initrd!\n");
 	}
 
 	efi_random_get_seed();
@@ -299,7 +301,7 @@ efi_status_t efi_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg)
 			   EFI_PROPERTIES_RUNTIME_MEMORY_PROTECTION_NON_EXECUTABLE_PE_DATA);
 
 	/* hibernation expects the runtime regions to stay in the same place */
-	if (!IS_ENABLED(CONFIG_HIBERNATION) && !nokaslr() && !flat_va_mapping) {
+	if (!IS_ENABLED(CONFIG_HIBERNATION) && !efi_nokaslr && !flat_va_mapping) {
 		/*
 		 * Randomize the base of the UEFI runtime services region.
 		 * Preserve the 2 MB alignment of the region by taking a
@@ -331,7 +333,7 @@ efi_status_t efi_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg)
 	/* not reached */
 
 fail_free_initrd:
-	pr_efi_err("Failed to update FDT and exit boot services\n");
+	efi_err("Failed to update FDT and exit boot services\n");
 
 	efi_free(initrd_size, initrd_addr);
 	efi_free(fdt_size, fdt_addr);
@@ -339,9 +341,10 @@ fail_free_initrd:
 fail_free_image:
 	efi_free(image_size, image_addr);
 	efi_free(reserve_size, reserve_addr);
-fail_free_cmdline:
+fail_free_screeninfo:
 	free_screen_info(si);
-	efi_free(cmdline_size, (unsigned long)cmdline_ptr);
+fail_free_cmdline:
+	efi_bs_call(free_pool, cmdline_ptr);
 fail:
 	return status;
 }
@@ -372,7 +375,7 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size,
 		size = in->num_pages * EFI_PAGE_SIZE;
 
 		in->virt_addr = in->phys_addr;
-		if (novamap()) {
+		if (efi_novamap) {
 			continue;
 		}
 
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index cc90a748bcf0..bcd8c0a785f0 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -3,6 +3,13 @@
 #ifndef _DRIVERS_FIRMWARE_EFI_EFISTUB_H
 #define _DRIVERS_FIRMWARE_EFI_EFISTUB_H
 
+#include <linux/compiler.h>
+#include <linux/efi.h>
+#include <linux/kernel.h>
+#include <linux/kern_levels.h>
+#include <linux/types.h>
+#include <asm/efi.h>
+
 /* error code which can't be mistaken for valid address */
 #define EFI_ERROR	(~0UL)
 
@@ -25,25 +32,33 @@
 #define EFI_ALLOC_ALIGN		EFI_PAGE_SIZE
 #endif
 
-#ifdef CONFIG_ARM
-#define __efistub_global	__section(.data)
-#else
-#define __efistub_global
-#endif
+extern bool efi_nochunk;
+extern bool efi_nokaslr;
+extern bool efi_noinitrd;
+extern int efi_loglevel;
+extern bool efi_novamap;
 
-extern bool __pure nochunk(void);
-extern bool __pure nokaslr(void);
-extern bool __pure noinitrd(void);
-extern bool __pure is_quiet(void);
-extern bool __pure novamap(void);
+extern const efi_system_table_t *efi_system_table;
 
-extern __pure efi_system_table_t  *efi_system_table(void);
+efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
+				   efi_system_table_t *sys_table_arg);
 
-#define pr_efi(msg)		do {			\
-	if (!is_quiet()) efi_printk("EFI stub: "msg);	\
-} while (0)
+#ifndef ARCH_HAS_EFISTUB_WRAPPERS
 
-#define pr_efi_err(msg) efi_printk("EFI stub: ERROR: "msg)
+#define efi_is_native()		(true)
+#define efi_bs_call(func, ...)	efi_system_table->boottime->func(__VA_ARGS__)
+#define efi_rt_call(func, ...)	efi_system_table->runtime->func(__VA_ARGS__)
+#define efi_table_attr(inst, attr)	(inst->attr)
+#define efi_call_proto(inst, func, ...) inst->func(inst, ##__VA_ARGS__)
+
+#endif
+
+#define efi_info(fmt, ...) \
+	efi_printk(KERN_INFO fmt, ##__VA_ARGS__)
+#define efi_err(fmt, ...) \
+	efi_printk(KERN_ERR "ERROR: " fmt, ##__VA_ARGS__)
+#define efi_debug(fmt, ...) \
+	efi_printk(KERN_DEBUG "DEBUG: " fmt, ##__VA_ARGS__)
 
 /* Helper macros for the usual case of using simple C variables: */
 #ifndef fdt_setprop_inplace_var
@@ -77,6 +92,13 @@ extern __pure efi_system_table_t  *efi_system_table(void);
 		((handle = efi_get_handle_at((array), i)) || true);	\
 	     i++)
 
+static inline
+void efi_set_u64_split(u64 data, u32 *lo, u32 *hi)
+{
+	*lo = lower_32_bits(data);
+	*hi = upper_32_bits(data);
+}
+
 /*
  * Allocation types for calls to boottime->allocate_pages.
  */
@@ -92,6 +114,29 @@ extern __pure efi_system_table_t  *efi_system_table(void);
 #define EFI_LOCATE_BY_REGISTER_NOTIFY		1
 #define EFI_LOCATE_BY_PROTOCOL			2
 
+/*
+ * boottime->stall takes the time period in microseconds
+ */
+#define EFI_USEC_PER_SEC		1000000
+
+/*
+ * boottime->set_timer takes the time in 100ns units
+ */
+#define EFI_100NSEC_PER_USEC	((u64)10)
+
+/*
+ * An efi_boot_memmap is used by efi_get_memory_map() to return the
+ * EFI memory map in a dynamically allocated buffer.
+ *
+ * The buffer allocated for the EFI memory map includes extra room for
+ * a minimum of EFI_MMAP_NR_SLACK_SLOTS additional EFI memory descriptors.
+ * This facilitates the reuse of the EFI memory map buffer when a second
+ * call to ExitBootServices() is needed because of intervening changes to
+ * the EFI memory map. Other related structures, e.g. x86 e820ext, need
+ * to factor in this headroom requirement as well.
+ */
+#define EFI_MMAP_NR_SLACK_SLOTS	8
+
 struct efi_boot_memmap {
 	efi_memory_desc_t	**map;
 	unsigned long		*map_size;
@@ -103,6 +148,39 @@ struct efi_boot_memmap {
 
 typedef struct efi_generic_dev_path efi_device_path_protocol_t;
 
+typedef void *efi_event_t;
+/* Note that notifications won't work in mixed mode */
+typedef void (__efiapi *efi_event_notify_t)(efi_event_t, void *);
+
+#define EFI_EVT_TIMER		0x80000000U
+#define EFI_EVT_RUNTIME		0x40000000U
+#define EFI_EVT_NOTIFY_WAIT	0x00000100U
+#define EFI_EVT_NOTIFY_SIGNAL	0x00000200U
+
+/*
+ * boottime->wait_for_event takes an array of events as input.
+ * Provide a helper to set it up correctly for mixed mode.
+ */
+static inline
+void efi_set_event_at(efi_event_t *events, size_t idx, efi_event_t event)
+{
+	if (efi_is_native())
+		events[idx] = event;
+	else
+		((u32 *)events)[idx] = (u32)(unsigned long)event;
+}
+
+#define EFI_TPL_APPLICATION	4
+#define EFI_TPL_CALLBACK	8
+#define EFI_TPL_NOTIFY		16
+#define EFI_TPL_HIGH_LEVEL	31
+
+typedef enum {
+	EfiTimerCancel,
+	EfiTimerPeriodic,
+	EfiTimerRelative
+} EFI_TIMER_DELAY;
+
 /*
  * EFI Boot Services table
  */
@@ -121,11 +199,16 @@ union efi_boot_services {
 		efi_status_t (__efiapi *allocate_pool)(int, unsigned long,
 						       void **);
 		efi_status_t (__efiapi *free_pool)(void *);
-		void *create_event;
-		void *set_timer;
-		void *wait_for_event;
+		efi_status_t (__efiapi *create_event)(u32, unsigned long,
+						      efi_event_notify_t, void *,
+						      efi_event_t *);
+		efi_status_t (__efiapi *set_timer)(efi_event_t,
+						  EFI_TIMER_DELAY, u64);
+		efi_status_t (__efiapi *wait_for_event)(unsigned long,
+							efi_event_t *,
+							unsigned long *);
 		void *signal_event;
-		void *close_event;
+		efi_status_t (__efiapi *close_event)(efi_event_t);
 		void *check_event;
 		void *install_protocol_interface;
 		void *reinstall_protocol_interface;
@@ -152,7 +235,7 @@ union efi_boot_services {
 		efi_status_t (__efiapi *exit_boot_services)(efi_handle_t,
 							    unsigned long);
 		void *get_next_monotonic_count;
-		void *stall;
+		efi_status_t (__efiapi *stall)(unsigned long);
 		void *set_watchdog_timer;
 		void *connect_controller;
 		efi_status_t (__efiapi *disconnect_controller)(efi_handle_t,
@@ -237,6 +320,27 @@ union efi_uga_draw_protocol {
 	} mixed_mode;
 };
 
+typedef struct {
+	u16 scan_code;
+	efi_char16_t unicode_char;
+} efi_input_key_t;
+
+union efi_simple_text_input_protocol {
+	struct {
+		void *reset;
+		efi_status_t (__efiapi *read_keystroke)(efi_simple_text_input_protocol_t *,
+							efi_input_key_t *);
+		efi_event_t wait_for_key;
+	};
+	struct {
+		u32 reset;
+		u32 read_keystroke;
+		u32 wait_for_key;
+	} mixed_mode;
+};
+
+efi_status_t efi_wait_for_key(unsigned long usec, efi_input_key_t *key);
+
 union efi_simple_text_output_protocol {
 	struct {
 		void *reset;
@@ -298,8 +402,10 @@ typedef union efi_graphics_output_protocol efi_graphics_output_protocol_t;
 
 union efi_graphics_output_protocol {
 	struct {
-		void *query_mode;
-		void *set_mode;
+		efi_status_t (__efiapi *query_mode)(efi_graphics_output_protocol_t *,
+						    u32, unsigned long *,
+						    efi_graphics_output_mode_info_t **);
+		efi_status_t (__efiapi *set_mode)  (efi_graphics_output_protocol_t *, u32);
 		void *blt;
 		efi_graphics_output_protocol_mode_t *mode;
 	};
@@ -587,8 +693,6 @@ efi_status_t efi_exit_boot_services(void *handle,
 				    void *priv,
 				    efi_exit_boot_map_processing priv_func);
 
-void efi_char16_printk(efi_char16_t *);
-
 efi_status_t allocate_new_fdt_and_exit_boot(void *handle,
 					    unsigned long *new_fdt_addr,
 					    unsigned long max_addr,
@@ -612,33 +716,24 @@ efi_status_t check_platform_features(void);
 
 void *get_efi_config_table(efi_guid_t guid);
 
-void efi_printk(char *str);
+/* NOTE: These functions do not print a trailing newline after the string */
+void efi_char16_puts(efi_char16_t *);
+void efi_puts(const char *str);
+
+__printf(1, 2) int efi_printk(char const *fmt, ...);
 
 void efi_free(unsigned long size, unsigned long addr);
 
-char *efi_convert_cmdline(efi_loaded_image_t *image, int *cmd_line_len,
-			  unsigned long max_addr);
+char *efi_convert_cmdline(efi_loaded_image_t *image, int *cmd_line_len);
 
 efi_status_t efi_get_memory_map(struct efi_boot_memmap *map);
 
-efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align,
-				 unsigned long *addr, unsigned long min);
-
-static inline
-efi_status_t efi_low_alloc(unsigned long size, unsigned long align,
-			   unsigned long *addr)
-{
-	/*
-	 * Don't allocate at 0x0. It will confuse code that
-	 * checks pointers against NULL. Skip the first 8
-	 * bytes so we start at a nice even number.
-	 */
-	return efi_low_alloc_above(size, align, addr, 0x8);
-}
-
 efi_status_t efi_allocate_pages(unsigned long size, unsigned long *addr,
 				unsigned long max);
 
+efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr,
+					unsigned long max, unsigned long align);
+
 efi_status_t efi_relocate_kernel(unsigned long *image_addr,
 				 unsigned long image_size,
 				 unsigned long alloc_size,
@@ -648,12 +743,27 @@ efi_status_t efi_relocate_kernel(unsigned long *image_addr,
 
 efi_status_t efi_parse_options(char const *cmdline);
 
+void efi_parse_option_graphics(char *option);
+
 efi_status_t efi_setup_gop(struct screen_info *si, efi_guid_t *proto,
 			   unsigned long size);
 
-efi_status_t efi_load_dtb(efi_loaded_image_t *image,
-			  unsigned long *load_addr,
-			  unsigned long *load_size);
+efi_status_t handle_cmdline_files(efi_loaded_image_t *image,
+				  const efi_char16_t *optstr,
+				  int optstr_size,
+				  unsigned long soft_limit,
+				  unsigned long hard_limit,
+				  unsigned long *load_addr,
+				  unsigned long *load_size);
+
+
+static inline efi_status_t efi_load_dtb(efi_loaded_image_t *image,
+					unsigned long *load_addr,
+					unsigned long *load_size)
+{
+	return handle_cmdline_files(image, L"dtb=", sizeof(L"dtb=") - 2,
+				    ULONG_MAX, ULONG_MAX, load_addr, load_size);
+}
 
 efi_status_t efi_load_initrd(efi_loaded_image_t *image,
 			     unsigned long *load_addr,
@@ -661,8 +771,4 @@ efi_status_t efi_load_initrd(efi_loaded_image_t *image,
 			     unsigned long soft_limit,
 			     unsigned long hard_limit);
 
-efi_status_t efi_load_initrd_dev_path(unsigned long *load_addr,
-				      unsigned long *load_size,
-				      unsigned long max);
-
 #endif
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index 46cffac7a5f1..11ecf3c4640e 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -39,7 +39,7 @@ static efi_status_t update_fdt(void *orig_fdt, unsigned long orig_fdt_size,
 	/* Do some checks on provided FDT, if it exists: */
 	if (orig_fdt) {
 		if (fdt_check_header(orig_fdt)) {
-			pr_efi_err("Device Tree header not valid!\n");
+			efi_err("Device Tree header not valid!\n");
 			return EFI_LOAD_ERROR;
 		}
 		/*
@@ -47,7 +47,7 @@ static efi_status_t update_fdt(void *orig_fdt, unsigned long orig_fdt_size,
 		 * configuration table:
 		 */
 		if (orig_fdt_size && fdt_totalsize(orig_fdt) > orig_fdt_size) {
-			pr_efi_err("Truncated device tree! foo!\n");
+			efi_err("Truncated device tree! foo!\n");
 			return EFI_LOAD_ERROR;
 		}
 	}
@@ -110,7 +110,7 @@ static efi_status_t update_fdt(void *orig_fdt, unsigned long orig_fdt_size,
 
 	/* Add FDT entries for EFI runtime services in chosen node. */
 	node = fdt_subnode_offset(fdt, 0, "chosen");
-	fdt_val64 = cpu_to_fdt64((u64)(unsigned long)efi_system_table());
+	fdt_val64 = cpu_to_fdt64((u64)(unsigned long)efi_system_table);
 
 	status = fdt_setprop_var(fdt, node, "linux,uefi-system-table", fdt_val64);
 	if (status)
@@ -270,16 +270,16 @@ efi_status_t allocate_new_fdt_and_exit_boot(void *handle,
 	 */
 	status = efi_get_memory_map(&map);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Unable to retrieve UEFI memory map.\n");
+		efi_err("Unable to retrieve UEFI memory map.\n");
 		return status;
 	}
 
-	pr_efi("Exiting boot services and installing virtual address map...\n");
+	efi_info("Exiting boot services and installing virtual address map...\n");
 
 	map.map = &memory_map;
 	status = efi_allocate_pages(MAX_FDT_SIZE, new_fdt_addr, max_addr);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Unable to allocate memory for new device tree.\n");
+		efi_err("Unable to allocate memory for new device tree.\n");
 		goto fail;
 	}
 
@@ -296,7 +296,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(void *handle,
 			    initrd_addr, initrd_size);
 
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Unable to construct new device tree.\n");
+		efi_err("Unable to construct new device tree.\n");
 		goto fail_free_new_fdt;
 	}
 
@@ -310,11 +310,11 @@ efi_status_t allocate_new_fdt_and_exit_boot(void *handle,
 	if (status == EFI_SUCCESS) {
 		efi_set_virtual_address_map_t *svam;
 
-		if (novamap())
+		if (efi_novamap)
 			return EFI_SUCCESS;
 
 		/* Install the new virtual address map */
-		svam = efi_system_table()->runtime->set_virtual_address_map;
+		svam = efi_system_table->runtime->set_virtual_address_map;
 		status = svam(runtime_entry_count * desc_size, desc_size,
 			      desc_ver, runtime_map);
 
@@ -342,13 +342,13 @@ efi_status_t allocate_new_fdt_and_exit_boot(void *handle,
 		return EFI_SUCCESS;
 	}
 
-	pr_efi_err("Exit boot services failed.\n");
+	efi_err("Exit boot services failed.\n");
 
 fail_free_new_fdt:
 	efi_free(MAX_FDT_SIZE, *new_fdt_addr);
 
 fail:
-	efi_system_table()->boottime->free_pool(runtime_map);
+	efi_system_table->boottime->free_pool(runtime_map);
 
 	return EFI_LOAD_ERROR;
 }
@@ -363,7 +363,7 @@ void *get_fdt(unsigned long *fdt_size)
 		return NULL;
 
 	if (fdt_check_header(fdt) != 0) {
-		pr_efi_err("Invalid header detected on UEFI supplied FDT, ignoring ...\n");
+		efi_err("Invalid header detected on UEFI supplied FDT, ignoring ...\n");
 		return NULL;
 	}
 	*fdt_size = fdt_totalsize(fdt);
diff --git a/drivers/firmware/efi/libstub/file.c b/drivers/firmware/efi/libstub/file.c
index d4c7e5f59d2c..2005e33b33d5 100644
--- a/drivers/firmware/efi/libstub/file.c
+++ b/drivers/firmware/efi/libstub/file.c
@@ -29,38 +29,37 @@
  */
 #define EFI_READ_CHUNK_SIZE	SZ_1M
 
+struct finfo {
+	efi_file_info_t info;
+	efi_char16_t	filename[MAX_FILENAME_SIZE];
+};
+
 static efi_status_t efi_open_file(efi_file_protocol_t *volume,
-				  efi_char16_t *filename_16,
+				  struct finfo *fi,
 				  efi_file_protocol_t **handle,
 				  unsigned long *file_size)
 {
-	struct {
-		efi_file_info_t info;
-		efi_char16_t	filename[MAX_FILENAME_SIZE];
-	} finfo;
 	efi_guid_t info_guid = EFI_FILE_INFO_ID;
 	efi_file_protocol_t *fh;
 	unsigned long info_sz;
 	efi_status_t status;
 
-	status = volume->open(volume, &fh, filename_16, EFI_FILE_MODE_READ, 0);
+	status = volume->open(volume, &fh, fi->filename, EFI_FILE_MODE_READ, 0);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to open file: ");
-		efi_char16_printk(filename_16);
-		efi_printk("\n");
+		efi_err("Failed to open file: %ls\n", fi->filename);
 		return status;
 	}
 
-	info_sz = sizeof(finfo);
-	status = fh->get_info(fh, &info_guid, &info_sz, &finfo);
+	info_sz = sizeof(struct finfo);
+	status = fh->get_info(fh, &info_guid, &info_sz, fi);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to get file info\n");
+		efi_err("Failed to get file info\n");
 		fh->close(fh);
 		return status;
 	}
 
 	*handle = fh;
-	*file_size = finfo.info.file_size;
+	*file_size = fi->info.file_size;
 	return EFI_SUCCESS;
 }
 
@@ -74,13 +73,13 @@ static efi_status_t efi_open_volume(efi_loaded_image_t *image,
 	status = efi_bs_call(handle_protocol, image->device_handle, &fs_proto,
 			     (void **)&io);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to handle fs_proto\n");
+		efi_err("Failed to handle fs_proto\n");
 		return status;
 	}
 
 	status = io->open_volume(io, fh);
 	if (status != EFI_SUCCESS)
-		pr_efi_err("Failed to open volume\n");
+		efi_err("Failed to open volume\n");
 
 	return status;
 }
@@ -120,13 +119,13 @@ static int find_file_option(const efi_char16_t *cmdline, int cmdline_len,
  * We only support loading a file from the same filesystem as
  * the kernel image.
  */
-static efi_status_t handle_cmdline_files(efi_loaded_image_t *image,
-					 const efi_char16_t *optstr,
-					 int optstr_size,
-					 unsigned long soft_limit,
-					 unsigned long hard_limit,
-					 unsigned long *load_addr,
-					 unsigned long *load_size)
+efi_status_t handle_cmdline_files(efi_loaded_image_t *image,
+				  const efi_char16_t *optstr,
+				  int optstr_size,
+				  unsigned long soft_limit,
+				  unsigned long hard_limit,
+				  unsigned long *load_addr,
+				  unsigned long *load_size)
 {
 	const efi_char16_t *cmdline = image->load_options;
 	int cmdline_len = image->load_options_size / 2;
@@ -141,18 +140,18 @@ static efi_status_t handle_cmdline_files(efi_loaded_image_t *image,
 	if (!load_addr || !load_size)
 		return EFI_INVALID_PARAMETER;
 
-	if (IS_ENABLED(CONFIG_X86) && !nochunk())
+	if (IS_ENABLED(CONFIG_X86) && !efi_nochunk)
 		efi_chunk_size = EFI_READ_CHUNK_SIZE;
 
 	alloc_addr = alloc_size = 0;
 	do {
-		efi_char16_t filename[MAX_FILENAME_SIZE];
+		struct finfo fi;
 		unsigned long size;
 		void *addr;
 
 		offset = find_file_option(cmdline, cmdline_len,
 					  optstr, optstr_size,
-					  filename, ARRAY_SIZE(filename));
+					  fi.filename, ARRAY_SIZE(fi.filename));
 
 		if (!offset)
 			break;
@@ -166,7 +165,7 @@ static efi_status_t handle_cmdline_files(efi_loaded_image_t *image,
 				return status;
 		}
 
-		status = efi_open_file(volume, filename, &file, &size);
+		status = efi_open_file(volume, &fi, &file, &size);
 		if (status != EFI_SUCCESS)
 			goto err_close_volume;
 
@@ -190,7 +189,7 @@ static efi_status_t handle_cmdline_files(efi_loaded_image_t *image,
 							    &alloc_addr,
 							    hard_limit);
 			if (status != EFI_SUCCESS) {
-				pr_efi_err("Failed to allocate memory for files\n");
+				efi_err("Failed to allocate memory for files\n");
 				goto err_close_file;
 			}
 
@@ -214,7 +213,7 @@ static efi_status_t handle_cmdline_files(efi_loaded_image_t *image,
 
 			status = file->read(file, &chunksize, addr);
 			if (status != EFI_SUCCESS) {
-				pr_efi_err("Failed to read file\n");
+				efi_err("Failed to read file\n");
 				goto err_close_file;
 			}
 			addr += chunksize;
@@ -238,21 +237,3 @@ err_close_volume:
 	efi_free(alloc_size, alloc_addr);
 	return status;
 }
-
-efi_status_t efi_load_dtb(efi_loaded_image_t *image,
-			  unsigned long *load_addr,
-			  unsigned long *load_size)
-{
-	return handle_cmdline_files(image, L"dtb=", sizeof(L"dtb=") - 2,
-				    ULONG_MAX, ULONG_MAX, load_addr, load_size);
-}
-
-efi_status_t efi_load_initrd(efi_loaded_image_t *image,
-			     unsigned long *load_addr,
-			     unsigned long *load_size,
-			     unsigned long soft_limit,
-			     unsigned long hard_limit)
-{
-	return handle_cmdline_files(image, L"initrd=", sizeof(L"initrd=") - 2,
-				    soft_limit, hard_limit, load_addr, load_size);
-}
diff --git a/drivers/firmware/efi/libstub/gop.c b/drivers/firmware/efi/libstub/gop.c
index 55e6b3f286fe..ea5da307d542 100644
--- a/drivers/firmware/efi/libstub/gop.c
+++ b/drivers/firmware/efi/libstub/gop.c
@@ -5,169 +5,546 @@
  *
  * ----------------------------------------------------------------------- */
 
+#include <linux/bitops.h>
+#include <linux/ctype.h>
 #include <linux/efi.h>
 #include <linux/screen_info.h>
+#include <linux/string.h>
 #include <asm/efi.h>
 #include <asm/setup.h>
 
 #include "efistub.h"
 
-static void find_bits(unsigned long mask, u8 *pos, u8 *size)
+enum efi_cmdline_option {
+	EFI_CMDLINE_NONE,
+	EFI_CMDLINE_MODE_NUM,
+	EFI_CMDLINE_RES,
+	EFI_CMDLINE_AUTO,
+	EFI_CMDLINE_LIST
+};
+
+static struct {
+	enum efi_cmdline_option option;
+	union {
+		u32 mode;
+		struct {
+			u32 width, height;
+			int format;
+			u8 depth;
+		} res;
+	};
+} cmdline = { .option = EFI_CMDLINE_NONE };
+
+static bool parse_modenum(char *option, char **next)
+{
+	u32 m;
+
+	if (!strstarts(option, "mode="))
+		return false;
+	option += strlen("mode=");
+	m = simple_strtoull(option, &option, 0);
+	if (*option && *option++ != ',')
+		return false;
+	cmdline.option = EFI_CMDLINE_MODE_NUM;
+	cmdline.mode   = m;
+
+	*next = option;
+	return true;
+}
+
+static bool parse_res(char *option, char **next)
+{
+	u32 w, h, d = 0;
+	int pf = -1;
+
+	if (!isdigit(*option))
+		return false;
+	w = simple_strtoull(option, &option, 10);
+	if (*option++ != 'x' || !isdigit(*option))
+		return false;
+	h = simple_strtoull(option, &option, 10);
+	if (*option == '-') {
+		option++;
+		if (strstarts(option, "rgb")) {
+			option += strlen("rgb");
+			pf = PIXEL_RGB_RESERVED_8BIT_PER_COLOR;
+		} else if (strstarts(option, "bgr")) {
+			option += strlen("bgr");
+			pf = PIXEL_BGR_RESERVED_8BIT_PER_COLOR;
+		} else if (isdigit(*option))
+			d = simple_strtoull(option, &option, 10);
+		else
+			return false;
+	}
+	if (*option && *option++ != ',')
+		return false;
+	cmdline.option     = EFI_CMDLINE_RES;
+	cmdline.res.width  = w;
+	cmdline.res.height = h;
+	cmdline.res.format = pf;
+	cmdline.res.depth  = d;
+
+	*next = option;
+	return true;
+}
+
+static bool parse_auto(char *option, char **next)
+{
+	if (!strstarts(option, "auto"))
+		return false;
+	option += strlen("auto");
+	if (*option && *option++ != ',')
+		return false;
+	cmdline.option = EFI_CMDLINE_AUTO;
+
+	*next = option;
+	return true;
+}
+
+static bool parse_list(char *option, char **next)
 {
-	u8 first, len;
+	if (!strstarts(option, "list"))
+		return false;
+	option += strlen("list");
+	if (*option && *option++ != ',')
+		return false;
+	cmdline.option = EFI_CMDLINE_LIST;
+
+	*next = option;
+	return true;
+}
+
+void efi_parse_option_graphics(char *option)
+{
+	while (*option) {
+		if (parse_modenum(option, &option))
+			continue;
+		if (parse_res(option, &option))
+			continue;
+		if (parse_auto(option, &option))
+			continue;
+		if (parse_list(option, &option))
+			continue;
+
+		while (*option && *option++ != ',')
+			;
+	}
+}
+
+static u32 choose_mode_modenum(efi_graphics_output_protocol_t *gop)
+{
+	efi_status_t status;
+
+	efi_graphics_output_protocol_mode_t *mode;
+	efi_graphics_output_mode_info_t *info;
+	unsigned long info_size;
+
+	u32 max_mode, cur_mode;
+	int pf;
+
+	mode = efi_table_attr(gop, mode);
+
+	cur_mode = efi_table_attr(mode, mode);
+	if (cmdline.mode == cur_mode)
+		return cur_mode;
+
+	max_mode = efi_table_attr(mode, max_mode);
+	if (cmdline.mode >= max_mode) {
+		efi_err("Requested mode is invalid\n");
+		return cur_mode;
+	}
+
+	status = efi_call_proto(gop, query_mode, cmdline.mode,
+				&info_size, &info);
+	if (status != EFI_SUCCESS) {
+		efi_err("Couldn't get mode information\n");
+		return cur_mode;
+	}
+
+	pf = info->pixel_format;
+
+	efi_bs_call(free_pool, info);
+
+	if (pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX) {
+		efi_err("Invalid PixelFormat\n");
+		return cur_mode;
+	}
+
+	return cmdline.mode;
+}
+
+static u8 pixel_bpp(int pixel_format, efi_pixel_bitmask_t pixel_info)
+{
+	if (pixel_format == PIXEL_BIT_MASK) {
+		u32 mask = pixel_info.red_mask | pixel_info.green_mask |
+			   pixel_info.blue_mask | pixel_info.reserved_mask;
+		if (!mask)
+			return 0;
+		return __fls(mask) - __ffs(mask) + 1;
+	} else
+		return 32;
+}
+
+static u32 choose_mode_res(efi_graphics_output_protocol_t *gop)
+{
+	efi_status_t status;
+
+	efi_graphics_output_protocol_mode_t *mode;
+	efi_graphics_output_mode_info_t *info;
+	unsigned long info_size;
+
+	u32 max_mode, cur_mode;
+	int pf;
+	efi_pixel_bitmask_t pi;
+	u32 m, w, h;
+
+	mode = efi_table_attr(gop, mode);
+
+	cur_mode = efi_table_attr(mode, mode);
+	info = efi_table_attr(mode, info);
+	pf = info->pixel_format;
+	pi = info->pixel_information;
+	w  = info->horizontal_resolution;
+	h  = info->vertical_resolution;
+
+	if (w == cmdline.res.width && h == cmdline.res.height &&
+	    (cmdline.res.format < 0 || cmdline.res.format == pf) &&
+	    (!cmdline.res.depth || cmdline.res.depth == pixel_bpp(pf, pi)))
+		return cur_mode;
+
+	max_mode = efi_table_attr(mode, max_mode);
+
+	for (m = 0; m < max_mode; m++) {
+		if (m == cur_mode)
+			continue;
+
+		status = efi_call_proto(gop, query_mode, m,
+					&info_size, &info);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		pf = info->pixel_format;
+		pi = info->pixel_information;
+		w  = info->horizontal_resolution;
+		h  = info->vertical_resolution;
+
+		efi_bs_call(free_pool, info);
+
+		if (pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX)
+			continue;
+		if (w == cmdline.res.width && h == cmdline.res.height &&
+		    (cmdline.res.format < 0 || cmdline.res.format == pf) &&
+		    (!cmdline.res.depth || cmdline.res.depth == pixel_bpp(pf, pi)))
+			return m;
+	}
+
+	efi_err("Couldn't find requested mode\n");
+
+	return cur_mode;
+}
+
+static u32 choose_mode_auto(efi_graphics_output_protocol_t *gop)
+{
+	efi_status_t status;
+
+	efi_graphics_output_protocol_mode_t *mode;
+	efi_graphics_output_mode_info_t *info;
+	unsigned long info_size;
+
+	u32 max_mode, cur_mode, best_mode, area;
+	u8 depth;
+	int pf;
+	efi_pixel_bitmask_t pi;
+	u32 m, w, h, a;
+	u8 d;
+
+	mode = efi_table_attr(gop, mode);
+
+	cur_mode = efi_table_attr(mode, mode);
+	max_mode = efi_table_attr(mode, max_mode);
 
-	first = 0;
-	len = 0;
+	info = efi_table_attr(mode, info);
 
-	if (mask) {
-		while (!(mask & 0x1)) {
-			mask = mask >> 1;
-			first++;
+	pf = info->pixel_format;
+	pi = info->pixel_information;
+	w  = info->horizontal_resolution;
+	h  = info->vertical_resolution;
+
+	best_mode = cur_mode;
+	area = w * h;
+	depth = pixel_bpp(pf, pi);
+
+	for (m = 0; m < max_mode; m++) {
+		if (m == cur_mode)
+			continue;
+
+		status = efi_call_proto(gop, query_mode, m,
+					&info_size, &info);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		pf = info->pixel_format;
+		pi = info->pixel_information;
+		w  = info->horizontal_resolution;
+		h  = info->vertical_resolution;
+
+		efi_bs_call(free_pool, info);
+
+		if (pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX)
+			continue;
+		a = w * h;
+		if (a < area)
+			continue;
+		d = pixel_bpp(pf, pi);
+		if (a > area || d > depth) {
+			best_mode = m;
+			area = a;
+			depth = d;
 		}
+	}
+
+	return best_mode;
+}
+
+static u32 choose_mode_list(efi_graphics_output_protocol_t *gop)
+{
+	efi_status_t status;
+
+	efi_graphics_output_protocol_mode_t *mode;
+	efi_graphics_output_mode_info_t *info;
+	unsigned long info_size;
+
+	u32 max_mode, cur_mode;
+	int pf;
+	efi_pixel_bitmask_t pi;
+	u32 m, w, h;
+	u8 d;
+	const char *dstr;
+	bool valid;
+	efi_input_key_t key;
 
-		while (mask & 0x1) {
-			mask = mask >> 1;
-			len++;
+	mode = efi_table_attr(gop, mode);
+
+	cur_mode = efi_table_attr(mode, mode);
+	max_mode = efi_table_attr(mode, max_mode);
+
+	efi_printk("Available graphics modes are 0-%u\n", max_mode-1);
+	efi_puts("  * = current mode\n"
+		 "  - = unusable mode\n");
+	for (m = 0; m < max_mode; m++) {
+		status = efi_call_proto(gop, query_mode, m,
+					&info_size, &info);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		pf = info->pixel_format;
+		pi = info->pixel_information;
+		w  = info->horizontal_resolution;
+		h  = info->vertical_resolution;
+
+		efi_bs_call(free_pool, info);
+
+		valid = !(pf == PIXEL_BLT_ONLY || pf >= PIXEL_FORMAT_MAX);
+		d = 0;
+		switch (pf) {
+		case PIXEL_RGB_RESERVED_8BIT_PER_COLOR:
+			dstr = "rgb";
+			break;
+		case PIXEL_BGR_RESERVED_8BIT_PER_COLOR:
+			dstr = "bgr";
+			break;
+		case PIXEL_BIT_MASK:
+			dstr = "";
+			d = pixel_bpp(pf, pi);
+			break;
+		case PIXEL_BLT_ONLY:
+			dstr = "blt";
+			break;
+		default:
+			dstr = "xxx";
+			break;
 		}
+
+		efi_printk("Mode %3u %c%c: Resolution %ux%u-%s%.0hhu\n",
+			   m,
+			   m == cur_mode ? '*' : ' ',
+			   !valid ? '-' : ' ',
+			   w, h, dstr, d);
+	}
+
+	efi_puts("\nPress any key to continue (or wait 10 seconds)\n");
+	status = efi_wait_for_key(10 * EFI_USEC_PER_SEC, &key);
+	if (status != EFI_SUCCESS && status != EFI_TIMEOUT) {
+		efi_err("Unable to read key, continuing in 10 seconds\n");
+		efi_bs_call(stall, 10 * EFI_USEC_PER_SEC);
+	}
+
+	return cur_mode;
+}
+
+static void set_mode(efi_graphics_output_protocol_t *gop)
+{
+	efi_graphics_output_protocol_mode_t *mode;
+	u32 cur_mode, new_mode;
+
+	switch (cmdline.option) {
+	case EFI_CMDLINE_MODE_NUM:
+		new_mode = choose_mode_modenum(gop);
+		break;
+	case EFI_CMDLINE_RES:
+		new_mode = choose_mode_res(gop);
+		break;
+	case EFI_CMDLINE_AUTO:
+		new_mode = choose_mode_auto(gop);
+		break;
+	case EFI_CMDLINE_LIST:
+		new_mode = choose_mode_list(gop);
+		break;
+	default:
+		return;
+	}
+
+	mode = efi_table_attr(gop, mode);
+	cur_mode = efi_table_attr(mode, mode);
+
+	if (new_mode == cur_mode)
+		return;
+
+	if (efi_call_proto(gop, set_mode, new_mode) != EFI_SUCCESS)
+		efi_err("Failed to set requested mode\n");
+}
+
+static void find_bits(u32 mask, u8 *pos, u8 *size)
+{
+	if (!mask) {
+		*pos = *size = 0;
+		return;
 	}
 
-	*pos = first;
-	*size = len;
+	/* UEFI spec guarantees that the set bits are contiguous */
+	*pos  = __ffs(mask);
+	*size = __fls(mask) - *pos + 1;
 }
 
 static void
 setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line,
 		 efi_pixel_bitmask_t pixel_info, int pixel_format)
 {
-	if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
-		si->lfb_depth = 32;
-		si->lfb_linelength = pixels_per_scan_line * 4;
-		si->red_size = 8;
-		si->red_pos = 0;
-		si->green_size = 8;
-		si->green_pos = 8;
-		si->blue_size = 8;
-		si->blue_pos = 16;
-		si->rsvd_size = 8;
-		si->rsvd_pos = 24;
-	} else if (pixel_format == PIXEL_BGR_RESERVED_8BIT_PER_COLOR) {
-		si->lfb_depth = 32;
-		si->lfb_linelength = pixels_per_scan_line * 4;
-		si->red_size = 8;
-		si->red_pos = 16;
-		si->green_size = 8;
-		si->green_pos = 8;
-		si->blue_size = 8;
-		si->blue_pos = 0;
-		si->rsvd_size = 8;
-		si->rsvd_pos = 24;
-	} else if (pixel_format == PIXEL_BIT_MASK) {
-		find_bits(pixel_info.red_mask, &si->red_pos, &si->red_size);
-		find_bits(pixel_info.green_mask, &si->green_pos,
-			  &si->green_size);
-		find_bits(pixel_info.blue_mask, &si->blue_pos, &si->blue_size);
-		find_bits(pixel_info.reserved_mask, &si->rsvd_pos,
-			  &si->rsvd_size);
+	if (pixel_format == PIXEL_BIT_MASK) {
+		find_bits(pixel_info.red_mask,
+			  &si->red_pos, &si->red_size);
+		find_bits(pixel_info.green_mask,
+			  &si->green_pos, &si->green_size);
+		find_bits(pixel_info.blue_mask,
+			  &si->blue_pos, &si->blue_size);
+		find_bits(pixel_info.reserved_mask,
+			  &si->rsvd_pos, &si->rsvd_size);
 		si->lfb_depth = si->red_size + si->green_size +
 			si->blue_size + si->rsvd_size;
 		si->lfb_linelength = (pixels_per_scan_line * si->lfb_depth) / 8;
 	} else {
-		si->lfb_depth = 4;
-		si->lfb_linelength = si->lfb_width / 2;
-		si->red_size = 0;
-		si->red_pos = 0;
-		si->green_size = 0;
-		si->green_pos = 0;
-		si->blue_size = 0;
-		si->blue_pos = 0;
-		si->rsvd_size = 0;
-		si->rsvd_pos = 0;
+		if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
+			si->red_pos   = 0;
+			si->blue_pos  = 16;
+		} else /* PIXEL_BGR_RESERVED_8BIT_PER_COLOR */ {
+			si->blue_pos  = 0;
+			si->red_pos   = 16;
+		}
+
+		si->green_pos = 8;
+		si->rsvd_pos  = 24;
+		si->red_size = si->green_size =
+			si->blue_size = si->rsvd_size = 8;
+
+		si->lfb_depth = 32;
+		si->lfb_linelength = pixels_per_scan_line * 4;
 	}
 }
 
-static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
-			      unsigned long size, void **handles)
+static efi_graphics_output_protocol_t *
+find_gop(efi_guid_t *proto, unsigned long size, void **handles)
 {
-	efi_graphics_output_protocol_t *gop, *first_gop;
-	u16 width, height;
-	u32 pixels_per_scan_line;
-	u32 ext_lfb_base;
-	efi_physical_addr_t fb_base;
-	efi_pixel_bitmask_t pixel_info;
-	int pixel_format;
-	efi_status_t status;
+	efi_graphics_output_protocol_t *first_gop;
 	efi_handle_t h;
 	int i;
 
 	first_gop = NULL;
-	gop = NULL;
 
 	for_each_efi_handle(h, handles, size, i) {
+		efi_status_t status;
+
+		efi_graphics_output_protocol_t *gop;
 		efi_graphics_output_protocol_mode_t *mode;
-		efi_graphics_output_mode_info_t *info = NULL;
+		efi_graphics_output_mode_info_t *info;
+
 		efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
-		bool conout_found = false;
 		void *dummy = NULL;
-		efi_physical_addr_t current_fb_base;
 
 		status = efi_bs_call(handle_protocol, h, proto, (void **)&gop);
 		if (status != EFI_SUCCESS)
 			continue;
 
+		mode = efi_table_attr(gop, mode);
+		info = efi_table_attr(mode, info);
+		if (info->pixel_format == PIXEL_BLT_ONLY ||
+		    info->pixel_format >= PIXEL_FORMAT_MAX)
+			continue;
+
+		/*
+		 * Systems that use the UEFI Console Splitter may
+		 * provide multiple GOP devices, not all of which are
+		 * backed by real hardware. The workaround is to search
+		 * for a GOP implementing the ConOut protocol, and if
+		 * one isn't found, to just fall back to the first GOP.
+		 *
+		 * Once we've found a GOP supporting ConOut,
+		 * don't bother looking any further.
+		 */
 		status = efi_bs_call(handle_protocol, h, &conout_proto, &dummy);
 		if (status == EFI_SUCCESS)
-			conout_found = true;
+			return gop;
 
-		mode = efi_table_attr(gop, mode);
-		info = efi_table_attr(mode, info);
-		current_fb_base = efi_table_attr(mode, frame_buffer_base);
-
-		if ((!first_gop || conout_found) &&
-		    info->pixel_format != PIXEL_BLT_ONLY) {
-			/*
-			 * Systems that use the UEFI Console Splitter may
-			 * provide multiple GOP devices, not all of which are
-			 * backed by real hardware. The workaround is to search
-			 * for a GOP implementing the ConOut protocol, and if
-			 * one isn't found, to just fall back to the first GOP.
-			 */
-			width = info->horizontal_resolution;
-			height = info->vertical_resolution;
-			pixel_format = info->pixel_format;
-			pixel_info = info->pixel_information;
-			pixels_per_scan_line = info->pixels_per_scan_line;
-			fb_base = current_fb_base;
-
-			/*
-			 * Once we've found a GOP supporting ConOut,
-			 * don't bother looking any further.
-			 */
+		if (!first_gop)
 			first_gop = gop;
-			if (conout_found)
-				break;
-		}
 	}
 
+	return first_gop;
+}
+
+static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
+			      unsigned long size, void **handles)
+{
+	efi_graphics_output_protocol_t *gop;
+	efi_graphics_output_protocol_mode_t *mode;
+	efi_graphics_output_mode_info_t *info;
+
+	gop = find_gop(proto, size, handles);
+
 	/* Did we find any GOPs? */
-	if (!first_gop)
+	if (!gop)
 		return EFI_NOT_FOUND;
 
+	/* Change mode if requested */
+	set_mode(gop);
+
 	/* EFI framebuffer */
+	mode = efi_table_attr(gop, mode);
+	info = efi_table_attr(mode, info);
+
 	si->orig_video_isVGA = VIDEO_TYPE_EFI;
 
-	si->lfb_width = width;
-	si->lfb_height = height;
-	si->lfb_base = fb_base;
+	si->lfb_width  = info->horizontal_resolution;
+	si->lfb_height = info->vertical_resolution;
 
-	ext_lfb_base = (u64)(unsigned long)fb_base >> 32;
-	if (ext_lfb_base) {
+	efi_set_u64_split(efi_table_attr(mode, frame_buffer_base),
+			  &si->lfb_base, &si->ext_lfb_base);
+	if (si->ext_lfb_base)
 		si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE;
-		si->ext_lfb_base = ext_lfb_base;
-	}
 
 	si->pages = 1;
 
-	setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format);
+	setup_pixel_info(si, info->pixels_per_scan_line,
+			     info->pixel_information, info->pixel_format);
 
 	si->lfb_size = si->lfb_linelength * si->lfb_height;
 
diff --git a/drivers/firmware/efi/libstub/mem.c b/drivers/firmware/efi/libstub/mem.c
index 869a79c8946f..feef8d4be113 100644
--- a/drivers/firmware/efi/libstub/mem.c
+++ b/drivers/firmware/efi/libstub/mem.c
@@ -5,8 +5,6 @@
 
 #include "efistub.h"
 
-#define EFI_MMAP_NR_SLACK_SLOTS	8
-
 static inline bool mmap_has_headroom(unsigned long buff_size,
 				     unsigned long map_size,
 				     unsigned long desc_size)
@@ -93,120 +91,23 @@ fail:
 efi_status_t efi_allocate_pages(unsigned long size, unsigned long *addr,
 				unsigned long max)
 {
-	efi_physical_addr_t alloc_addr = ALIGN_DOWN(max + 1, EFI_ALLOC_ALIGN) - 1;
-	int slack = EFI_ALLOC_ALIGN / EFI_PAGE_SIZE - 1;
+	efi_physical_addr_t alloc_addr;
 	efi_status_t status;
 
-	size = round_up(size, EFI_ALLOC_ALIGN);
+	if (EFI_ALLOC_ALIGN > EFI_PAGE_SIZE)
+		return efi_allocate_pages_aligned(size, addr, max,
+						  EFI_ALLOC_ALIGN);
+
+	alloc_addr = ALIGN_DOWN(max + 1, EFI_ALLOC_ALIGN) - 1;
 	status = efi_bs_call(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS,
-			     EFI_LOADER_DATA, size / EFI_PAGE_SIZE + slack,
+			     EFI_LOADER_DATA, DIV_ROUND_UP(size, EFI_PAGE_SIZE),
 			     &alloc_addr);
 	if (status != EFI_SUCCESS)
 		return status;
 
-	*addr = ALIGN((unsigned long)alloc_addr, EFI_ALLOC_ALIGN);
-
-	if (slack > 0) {
-		int l = (alloc_addr % EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE;
-
-		if (l) {
-			efi_bs_call(free_pages, alloc_addr, slack - l + 1);
-			slack = l - 1;
-		}
-		if (slack)
-			efi_bs_call(free_pages, *addr + size, slack);
-	}
+	*addr = alloc_addr;
 	return EFI_SUCCESS;
 }
-/**
- * efi_low_alloc_above() - allocate pages at or above given address
- * @size:	size of the memory area to allocate
- * @align:	minimum alignment of the allocated memory area. It should
- *		a power of two.
- * @addr:	on exit the address of the allocated memory
- * @min:	minimum address to used for the memory allocation
- *
- * Allocate at the lowest possible address that is not below @min as
- * EFI_LOADER_DATA. The allocated pages are aligned according to @align but at
- * least EFI_ALLOC_ALIGN. The first allocated page will not below the address
- * given by @min.
- *
- * Return:	status code
- */
-efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align,
-				 unsigned long *addr, unsigned long min)
-{
-	unsigned long map_size, desc_size, buff_size;
-	efi_memory_desc_t *map;
-	efi_status_t status;
-	unsigned long nr_pages;
-	int i;
-	struct efi_boot_memmap boot_map;
-
-	boot_map.map		= &map;
-	boot_map.map_size	= &map_size;
-	boot_map.desc_size	= &desc_size;
-	boot_map.desc_ver	= NULL;
-	boot_map.key_ptr	= NULL;
-	boot_map.buff_size	= &buff_size;
-
-	status = efi_get_memory_map(&boot_map);
-	if (status != EFI_SUCCESS)
-		goto fail;
-
-	/*
-	 * Enforce minimum alignment that EFI or Linux requires when
-	 * requesting a specific address.  We are doing page-based (or
-	 * larger) allocations, and both the address and size must meet
-	 * alignment constraints.
-	 */
-	if (align < EFI_ALLOC_ALIGN)
-		align = EFI_ALLOC_ALIGN;
-
-	size = round_up(size, EFI_ALLOC_ALIGN);
-	nr_pages = size / EFI_PAGE_SIZE;
-	for (i = 0; i < map_size / desc_size; i++) {
-		efi_memory_desc_t *desc;
-		unsigned long m = (unsigned long)map;
-		u64 start, end;
-
-		desc = efi_early_memdesc_ptr(m, desc_size, i);
-
-		if (desc->type != EFI_CONVENTIONAL_MEMORY)
-			continue;
-
-		if (efi_soft_reserve_enabled() &&
-		    (desc->attribute & EFI_MEMORY_SP))
-			continue;
-
-		if (desc->num_pages < nr_pages)
-			continue;
-
-		start = desc->phys_addr;
-		end = start + desc->num_pages * EFI_PAGE_SIZE;
-
-		if (start < min)
-			start = min;
-
-		start = round_up(start, align);
-		if ((start + size) > end)
-			continue;
-
-		status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS,
-				     EFI_LOADER_DATA, nr_pages, &start);
-		if (status == EFI_SUCCESS) {
-			*addr = start;
-			break;
-		}
-	}
-
-	if (i == map_size / desc_size)
-		status = EFI_NOT_FOUND;
-
-	efi_bs_call(free_pool, map);
-fail:
-	return status;
-}
 
 /**
  * efi_free() - free memory pages
@@ -229,81 +130,3 @@ void efi_free(unsigned long size, unsigned long addr)
 	nr_pages = round_up(size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE;
 	efi_bs_call(free_pages, addr, nr_pages);
 }
-
-/**
- * efi_relocate_kernel() - copy memory area
- * @image_addr:		pointer to address of memory area to copy
- * @image_size:		size of memory area to copy
- * @alloc_size:		minimum size of memory to allocate, must be greater or
- *			equal to image_size
- * @preferred_addr:	preferred target address
- * @alignment:		minimum alignment of the allocated memory area. It
- *			should be a power of two.
- * @min_addr:		minimum target address
- *
- * Copy a memory area to a newly allocated memory area aligned according
- * to @alignment but at least EFI_ALLOC_ALIGN. If the preferred address
- * is not available, the allocated address will not be below @min_addr.
- * On exit, @image_addr is updated to the target copy address that was used.
- *
- * This function is used to copy the Linux kernel verbatim. It does not apply
- * any relocation changes.
- *
- * Return:		status code
- */
-efi_status_t efi_relocate_kernel(unsigned long *image_addr,
-				 unsigned long image_size,
-				 unsigned long alloc_size,
-				 unsigned long preferred_addr,
-				 unsigned long alignment,
-				 unsigned long min_addr)
-{
-	unsigned long cur_image_addr;
-	unsigned long new_addr = 0;
-	efi_status_t status;
-	unsigned long nr_pages;
-	efi_physical_addr_t efi_addr = preferred_addr;
-
-	if (!image_addr || !image_size || !alloc_size)
-		return EFI_INVALID_PARAMETER;
-	if (alloc_size < image_size)
-		return EFI_INVALID_PARAMETER;
-
-	cur_image_addr = *image_addr;
-
-	/*
-	 * The EFI firmware loader could have placed the kernel image
-	 * anywhere in memory, but the kernel has restrictions on the
-	 * max physical address it can run at.  Some architectures
-	 * also have a prefered address, so first try to relocate
-	 * to the preferred address.  If that fails, allocate as low
-	 * as possible while respecting the required alignment.
-	 */
-	nr_pages = round_up(alloc_size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE;
-	status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS,
-			     EFI_LOADER_DATA, nr_pages, &efi_addr);
-	new_addr = efi_addr;
-	/*
-	 * If preferred address allocation failed allocate as low as
-	 * possible.
-	 */
-	if (status != EFI_SUCCESS) {
-		status = efi_low_alloc_above(alloc_size, alignment, &new_addr,
-					     min_addr);
-	}
-	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to allocate usable memory for kernel.\n");
-		return status;
-	}
-
-	/*
-	 * We know source/dest won't overlap since both memory ranges
-	 * have been allocated by UEFI, so we can safely use memcpy.
-	 */
-	memcpy((void *)new_addr, (void *)cur_image_addr, image_size);
-
-	/* Return the new address of the relocated image. */
-	*image_addr = new_addr;
-
-	return status;
-}
diff --git a/drivers/firmware/efi/libstub/pci.c b/drivers/firmware/efi/libstub/pci.c
index b025e59b94df..99fb25d2bcf5 100644
--- a/drivers/firmware/efi/libstub/pci.c
+++ b/drivers/firmware/efi/libstub/pci.c
@@ -28,21 +28,21 @@ void efi_pci_disable_bridge_busmaster(void)
 
 	if (status != EFI_BUFFER_TOO_SMALL) {
 		if (status != EFI_SUCCESS && status != EFI_NOT_FOUND)
-			pr_efi_err("Failed to locate PCI I/O handles'\n");
+			efi_err("Failed to locate PCI I/O handles'\n");
 		return;
 	}
 
 	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, pci_handle_size,
 			     (void **)&pci_handle);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to allocate memory for 'pci_handle'\n");
+		efi_err("Failed to allocate memory for 'pci_handle'\n");
 		return;
 	}
 
 	status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, &pci_proto,
 			     NULL, &pci_handle_size, pci_handle);
 	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to locate PCI I/O handles'\n");
+		efi_err("Failed to locate PCI I/O handles'\n");
 		goto free_handle;
 	}
 
@@ -69,7 +69,7 @@ void efi_pci_disable_bridge_busmaster(void)
 		 * access to the framebuffer. Drivers for true PCIe graphics
 		 * controllers that are behind a PCIe root port do not use
 		 * DMA to implement the GOP framebuffer anyway [although they
-		 * may use it in their implentation of Gop->Blt()], and so
+		 * may use it in their implementation of Gop->Blt()], and so
 		 * disabling DMA in the PCI bridge should not interfere with
 		 * normal operation of the device.
 		 */
@@ -106,7 +106,7 @@ void efi_pci_disable_bridge_busmaster(void)
 		status = efi_call_proto(pci, pci.write, EfiPciIoWidthUint16,
 					PCI_COMMAND, 1, &command);
 		if (status != EFI_SUCCESS)
-			pr_efi_err("Failed to disable PCI busmastering\n");
+			efi_err("Failed to disable PCI busmastering\n");
 	}
 
 free_handle:
diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c
index 4578f59e160c..a408df474d83 100644
--- a/drivers/firmware/efi/libstub/randomalloc.c
+++ b/drivers/firmware/efi/libstub/randomalloc.c
@@ -74,6 +74,8 @@ efi_status_t efi_random_alloc(unsigned long size,
 	if (align < EFI_ALLOC_ALIGN)
 		align = EFI_ALLOC_ALIGN;
 
+	size = round_up(size, EFI_ALLOC_ALIGN);
+
 	/* count the suitable slots in each memory map entry */
 	for (map_offset = 0; map_offset < map_size; map_offset += desc_size) {
 		efi_memory_desc_t *md = (void *)memory_map + map_offset;
@@ -85,7 +87,7 @@ efi_status_t efi_random_alloc(unsigned long size,
 	}
 
 	/* find a random number between 0 and total_slots */
-	target_slot = (total_slots * (u16)random_seed) >> 16;
+	target_slot = (total_slots * (u64)(random_seed & U32_MAX)) >> 32;
 
 	/*
 	 * target_slot is now a value in the range [0, total_slots), and so
@@ -109,7 +111,7 @@ efi_status_t efi_random_alloc(unsigned long size,
 		}
 
 		target = round_up(md->phys_addr, align) + target_slot * align;
-		pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+		pages = size / EFI_PAGE_SIZE;
 
 		status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS,
 				     EFI_LOADER_DATA, pages, &target);
diff --git a/drivers/firmware/efi/libstub/relocate.c b/drivers/firmware/efi/libstub/relocate.c
new file mode 100644
index 000000000000..9b1aaf8b123f
--- /dev/null
+++ b/drivers/firmware/efi/libstub/relocate.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/efi.h>
+#include <asm/efi.h>
+
+#include "efistub.h"
+
+/**
+ * efi_low_alloc_above() - allocate pages at or above given address
+ * @size:	size of the memory area to allocate
+ * @align:	minimum alignment of the allocated memory area. It should
+ *		a power of two.
+ * @addr:	on exit the address of the allocated memory
+ * @min:	minimum address to used for the memory allocation
+ *
+ * Allocate at the lowest possible address that is not below @min as
+ * EFI_LOADER_DATA. The allocated pages are aligned according to @align but at
+ * least EFI_ALLOC_ALIGN. The first allocated page will not below the address
+ * given by @min.
+ *
+ * Return:	status code
+ */
+static efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align,
+					unsigned long *addr, unsigned long min)
+{
+	unsigned long map_size, desc_size, buff_size;
+	efi_memory_desc_t *map;
+	efi_status_t status;
+	unsigned long nr_pages;
+	int i;
+	struct efi_boot_memmap boot_map;
+
+	boot_map.map		= &map;
+	boot_map.map_size	= &map_size;
+	boot_map.desc_size	= &desc_size;
+	boot_map.desc_ver	= NULL;
+	boot_map.key_ptr	= NULL;
+	boot_map.buff_size	= &buff_size;
+
+	status = efi_get_memory_map(&boot_map);
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	/*
+	 * Enforce minimum alignment that EFI or Linux requires when
+	 * requesting a specific address.  We are doing page-based (or
+	 * larger) allocations, and both the address and size must meet
+	 * alignment constraints.
+	 */
+	if (align < EFI_ALLOC_ALIGN)
+		align = EFI_ALLOC_ALIGN;
+
+	size = round_up(size, EFI_ALLOC_ALIGN);
+	nr_pages = size / EFI_PAGE_SIZE;
+	for (i = 0; i < map_size / desc_size; i++) {
+		efi_memory_desc_t *desc;
+		unsigned long m = (unsigned long)map;
+		u64 start, end;
+
+		desc = efi_early_memdesc_ptr(m, desc_size, i);
+
+		if (desc->type != EFI_CONVENTIONAL_MEMORY)
+			continue;
+
+		if (efi_soft_reserve_enabled() &&
+		    (desc->attribute & EFI_MEMORY_SP))
+			continue;
+
+		if (desc->num_pages < nr_pages)
+			continue;
+
+		start = desc->phys_addr;
+		end = start + desc->num_pages * EFI_PAGE_SIZE;
+
+		if (start < min)
+			start = min;
+
+		start = round_up(start, align);
+		if ((start + size) > end)
+			continue;
+
+		status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS,
+				     EFI_LOADER_DATA, nr_pages, &start);
+		if (status == EFI_SUCCESS) {
+			*addr = start;
+			break;
+		}
+	}
+
+	if (i == map_size / desc_size)
+		status = EFI_NOT_FOUND;
+
+	efi_bs_call(free_pool, map);
+fail:
+	return status;
+}
+
+/**
+ * efi_relocate_kernel() - copy memory area
+ * @image_addr:		pointer to address of memory area to copy
+ * @image_size:		size of memory area to copy
+ * @alloc_size:		minimum size of memory to allocate, must be greater or
+ *			equal to image_size
+ * @preferred_addr:	preferred target address
+ * @alignment:		minimum alignment of the allocated memory area. It
+ *			should be a power of two.
+ * @min_addr:		minimum target address
+ *
+ * Copy a memory area to a newly allocated memory area aligned according
+ * to @alignment but at least EFI_ALLOC_ALIGN. If the preferred address
+ * is not available, the allocated address will not be below @min_addr.
+ * On exit, @image_addr is updated to the target copy address that was used.
+ *
+ * This function is used to copy the Linux kernel verbatim. It does not apply
+ * any relocation changes.
+ *
+ * Return:		status code
+ */
+efi_status_t efi_relocate_kernel(unsigned long *image_addr,
+				 unsigned long image_size,
+				 unsigned long alloc_size,
+				 unsigned long preferred_addr,
+				 unsigned long alignment,
+				 unsigned long min_addr)
+{
+	unsigned long cur_image_addr;
+	unsigned long new_addr = 0;
+	efi_status_t status;
+	unsigned long nr_pages;
+	efi_physical_addr_t efi_addr = preferred_addr;
+
+	if (!image_addr || !image_size || !alloc_size)
+		return EFI_INVALID_PARAMETER;
+	if (alloc_size < image_size)
+		return EFI_INVALID_PARAMETER;
+
+	cur_image_addr = *image_addr;
+
+	/*
+	 * The EFI firmware loader could have placed the kernel image
+	 * anywhere in memory, but the kernel has restrictions on the
+	 * max physical address it can run at.  Some architectures
+	 * also have a preferred address, so first try to relocate
+	 * to the preferred address.  If that fails, allocate as low
+	 * as possible while respecting the required alignment.
+	 */
+	nr_pages = round_up(alloc_size, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE;
+	status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS,
+			     EFI_LOADER_DATA, nr_pages, &efi_addr);
+	new_addr = efi_addr;
+	/*
+	 * If preferred address allocation failed allocate as low as
+	 * possible.
+	 */
+	if (status != EFI_SUCCESS) {
+		status = efi_low_alloc_above(alloc_size, alignment, &new_addr,
+					     min_addr);
+	}
+	if (status != EFI_SUCCESS) {
+		efi_err("Failed to allocate usable memory for kernel.\n");
+		return status;
+	}
+
+	/*
+	 * We know source/dest won't overlap since both memory ranges
+	 * have been allocated by UEFI, so we can safely use memcpy.
+	 */
+	memcpy((void *)new_addr, (void *)cur_image_addr, image_size);
+
+	/* Return the new address of the relocated image. */
+	*image_addr = new_addr;
+
+	return status;
+}
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index a765378ad18c..5efc524b14be 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -67,10 +67,10 @@ enum efi_secureboot_mode efi_get_secureboot(void)
 		return efi_secureboot_mode_disabled;
 
 secure_boot_enabled:
-	pr_efi("UEFI Secure Boot is enabled.\n");
+	efi_info("UEFI Secure Boot is enabled.\n");
 	return efi_secureboot_mode_enabled;
 
 out_efi_err:
-	pr_efi_err("Could not determine UEFI Secure Boot status.\n");
+	efi_err("Could not determine UEFI Secure Boot status.\n");
 	return efi_secureboot_mode_unknown;
 }
diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c
index 1d59e103a2e3..7acbac16eae0 100644
--- a/drivers/firmware/efi/libstub/tpm.c
+++ b/drivers/firmware/efi/libstub/tpm.c
@@ -54,7 +54,7 @@ void efi_retrieve_tpm2_eventlog(void)
 	efi_status_t status;
 	efi_physical_addr_t log_location = 0, log_last_entry = 0;
 	struct linux_efi_tpm_eventlog *log_tbl = NULL;
-	struct efi_tcg2_final_events_table *final_events_table;
+	struct efi_tcg2_final_events_table *final_events_table = NULL;
 	unsigned long first_entry_addr, last_entry_addr;
 	size_t log_size, last_entry_size;
 	efi_bool_t truncated;
@@ -119,7 +119,7 @@ void efi_retrieve_tpm2_eventlog(void)
 			     sizeof(*log_tbl) + log_size, (void **)&log_tbl);
 
 	if (status != EFI_SUCCESS) {
-		efi_printk("Unable to allocate memory for event log\n");
+		efi_err("Unable to allocate memory for event log\n");
 		return;
 	}
 
@@ -127,7 +127,8 @@ void efi_retrieve_tpm2_eventlog(void)
 	 * Figure out whether any events have already been logged to the
 	 * final events structure, and if so how much space they take up
 	 */
-	final_events_table = get_efi_config_table(LINUX_EFI_TPM_FINAL_LOG_GUID);
+	if (version == EFI_TCG2_EVENT_LOG_FORMAT_TCG_2)
+		final_events_table = get_efi_config_table(LINUX_EFI_TPM_FINAL_LOG_GUID);
 	if (final_events_table && final_events_table->nr_events) {
 		struct tcg_pcr_event2_head *header;
 		int offset;
diff --git a/drivers/firmware/efi/libstub/vsprintf.c b/drivers/firmware/efi/libstub/vsprintf.c
new file mode 100644
index 000000000000..e65ef49a54cd
--- /dev/null
+++ b/drivers/firmware/efi/libstub/vsprintf.c
@@ -0,0 +1,564 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Oh, it's a waste of space, but oh-so-yummy for debugging.
+ */
+
+#include <stdarg.h>
+
+#include <linux/compiler.h>
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/limits.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+static
+int skip_atoi(const char **s)
+{
+	int i = 0;
+
+	while (isdigit(**s))
+		i = i * 10 + *((*s)++) - '0';
+	return i;
+}
+
+/*
+ * put_dec_full4 handles numbers in the range 0 <= r < 10000.
+ * The multiplier 0xccd is round(2^15/10), and the approximation
+ * r/10 == (r * 0xccd) >> 15 is exact for all r < 16389.
+ */
+static
+void put_dec_full4(char *end, unsigned int r)
+{
+	int i;
+
+	for (i = 0; i < 3; i++) {
+		unsigned int q = (r * 0xccd) >> 15;
+		*--end = '0' + (r - q * 10);
+		r = q;
+	}
+	*--end = '0' + r;
+}
+
+/* put_dec is copied from lib/vsprintf.c with small modifications */
+
+/*
+ * Call put_dec_full4 on x % 10000, return x / 10000.
+ * The approximation x/10000 == (x * 0x346DC5D7) >> 43
+ * holds for all x < 1,128,869,999.  The largest value this
+ * helper will ever be asked to convert is 1,125,520,955.
+ * (second call in the put_dec code, assuming n is all-ones).
+ */
+static
+unsigned int put_dec_helper4(char *end, unsigned int x)
+{
+	unsigned int q = (x * 0x346DC5D7ULL) >> 43;
+
+	put_dec_full4(end, x - q * 10000);
+	return q;
+}
+
+/* Based on code by Douglas W. Jones found at
+ * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour>
+ * (with permission from the author).
+ * Performs no 64-bit division and hence should be fast on 32-bit machines.
+ */
+static
+char *put_dec(char *end, unsigned long long n)
+{
+	unsigned int d3, d2, d1, q, h;
+	char *p = end;
+
+	d1  = ((unsigned int)n >> 16); /* implicit "& 0xffff" */
+	h   = (n >> 32);
+	d2  = (h      ) & 0xffff;
+	d3  = (h >> 16); /* implicit "& 0xffff" */
+
+	/* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0
+	     = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */
+	q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((unsigned int)n & 0xffff);
+	q = put_dec_helper4(p, q);
+	p -= 4;
+
+	q += 7671 * d3 + 9496 * d2 + 6 * d1;
+	q = put_dec_helper4(p, q);
+	p -= 4;
+
+	q += 4749 * d3 + 42 * d2;
+	q = put_dec_helper4(p, q);
+	p -= 4;
+
+	q += 281 * d3;
+	q = put_dec_helper4(p, q);
+	p -= 4;
+
+	put_dec_full4(p, q);
+	p -= 4;
+
+	/* strip off the extra 0's we printed */
+	while (p < end && *p == '0')
+		++p;
+
+	return p;
+}
+
+static
+char *number(char *end, unsigned long long num, int base, char locase)
+{
+	/*
+	 * locase = 0 or 0x20. ORing digits or letters with 'locase'
+	 * produces same digits or (maybe lowercased) letters
+	 */
+
+	/* we are called with base 8, 10 or 16, only, thus don't need "G..."  */
+	static const char digits[16] = "0123456789ABCDEF"; /* "GHIJKLMNOPQRSTUVWXYZ"; */
+
+	switch (base) {
+	case 10:
+		if (num != 0)
+			end = put_dec(end, num);
+		break;
+	case 8:
+		for (; num != 0; num >>= 3)
+			*--end = '0' + (num & 07);
+		break;
+	case 16:
+		for (; num != 0; num >>= 4)
+			*--end = digits[num & 0xf] | locase;
+		break;
+	default:
+		unreachable();
+	};
+
+	return end;
+}
+
+#define ZEROPAD	1		/* pad with zero */
+#define SIGN	2		/* unsigned/signed long */
+#define PLUS	4		/* show plus */
+#define SPACE	8		/* space if plus */
+#define LEFT	16		/* left justified */
+#define SMALL	32		/* Must be 32 == 0x20 */
+#define SPECIAL	64		/* 0x */
+#define WIDE	128		/* UTF-16 string */
+
+static
+int get_flags(const char **fmt)
+{
+	int flags = 0;
+
+	do {
+		switch (**fmt) {
+		case '-':
+			flags |= LEFT;
+			break;
+		case '+':
+			flags |= PLUS;
+			break;
+		case ' ':
+			flags |= SPACE;
+			break;
+		case '#':
+			flags |= SPECIAL;
+			break;
+		case '0':
+			flags |= ZEROPAD;
+			break;
+		default:
+			return flags;
+		}
+		++(*fmt);
+	} while (1);
+}
+
+static
+int get_int(const char **fmt, va_list *ap)
+{
+	if (isdigit(**fmt))
+		return skip_atoi(fmt);
+	if (**fmt == '*') {
+		++(*fmt);
+		/* it's the next argument */
+		return va_arg(*ap, int);
+	}
+	return 0;
+}
+
+static
+unsigned long long get_number(int sign, int qualifier, va_list *ap)
+{
+	if (sign) {
+		switch (qualifier) {
+		case 'L':
+			return va_arg(*ap, long long);
+		case 'l':
+			return va_arg(*ap, long);
+		case 'h':
+			return (short)va_arg(*ap, int);
+		case 'H':
+			return (signed char)va_arg(*ap, int);
+		default:
+			return va_arg(*ap, int);
+		};
+	} else {
+		switch (qualifier) {
+		case 'L':
+			return va_arg(*ap, unsigned long long);
+		case 'l':
+			return va_arg(*ap, unsigned long);
+		case 'h':
+			return (unsigned short)va_arg(*ap, int);
+		case 'H':
+			return (unsigned char)va_arg(*ap, int);
+		default:
+			return va_arg(*ap, unsigned int);
+		}
+	}
+}
+
+static
+char get_sign(long long *num, int flags)
+{
+	if (!(flags & SIGN))
+		return 0;
+	if (*num < 0) {
+		*num = -(*num);
+		return '-';
+	}
+	if (flags & PLUS)
+		return '+';
+	if (flags & SPACE)
+		return ' ';
+	return 0;
+}
+
+static
+size_t utf16s_utf8nlen(const u16 *s16, size_t maxlen)
+{
+	size_t len, clen;
+
+	for (len = 0; len < maxlen && *s16; len += clen) {
+		u16 c0 = *s16++;
+
+		/* First, get the length for a BMP character */
+		clen = 1 + (c0 >= 0x80) + (c0 >= 0x800);
+		if (len + clen > maxlen)
+			break;
+		/*
+		 * If this is a high surrogate, and we're already at maxlen, we
+		 * can't include the character if it's a valid surrogate pair.
+		 * Avoid accessing one extra word just to check if it's valid
+		 * or not.
+		 */
+		if ((c0 & 0xfc00) == 0xd800) {
+			if (len + clen == maxlen)
+				break;
+			if ((*s16 & 0xfc00) == 0xdc00) {
+				++s16;
+				++clen;
+			}
+		}
+	}
+
+	return len;
+}
+
+static
+u32 utf16_to_utf32(const u16 **s16)
+{
+	u16 c0, c1;
+
+	c0 = *(*s16)++;
+	/* not a surrogate */
+	if ((c0 & 0xf800) != 0xd800)
+		return c0;
+	/* invalid: low surrogate instead of high */
+	if (c0 & 0x0400)
+		return 0xfffd;
+	c1 = **s16;
+	/* invalid: missing low surrogate */
+	if ((c1 & 0xfc00) != 0xdc00)
+		return 0xfffd;
+	/* valid surrogate pair */
+	++(*s16);
+	return (0x10000 - (0xd800 << 10) - 0xdc00) + (c0 << 10) + c1;
+}
+
+#define PUTC(c) \
+do {				\
+	if (pos < size)		\
+		buf[pos] = (c);	\
+	++pos;			\
+} while (0);
+
+int vsnprintf(char *buf, size_t size, const char *fmt, va_list ap)
+{
+	/* The maximum space required is to print a 64-bit number in octal */
+	char tmp[(sizeof(unsigned long long) * 8 + 2) / 3];
+	char *tmp_end = &tmp[ARRAY_SIZE(tmp)];
+	long long num;
+	int base;
+	const char *s;
+	size_t len, pos;
+	char sign;
+
+	int flags;		/* flags to number() */
+
+	int field_width;	/* width of output field */
+	int precision;		/* min. # of digits for integers; max
+				   number of chars for from string */
+	int qualifier;		/* 'h', 'hh', 'l' or 'll' for integer fields */
+
+	va_list args;
+
+	/*
+	 * We want to pass our input va_list to helper functions by reference,
+	 * but there's an annoying edge case. If va_list was originally passed
+	 * to us by value, we could just pass &ap down to the helpers. This is
+	 * the case on, for example, X86_32.
+	 * However, on X86_64 (and possibly others), va_list is actually a
+	 * size-1 array containing a structure. Our function parameter ap has
+	 * decayed from T[1] to T*, and &ap has type T** rather than T(*)[1],
+	 * which is what will be expected by a function taking a va_list *
+	 * parameter.
+	 * One standard way to solve this mess is by creating a copy in a local
+	 * variable of type va_list and then passing a pointer to that local
+	 * copy instead, which is what we do here.
+	 */
+	va_copy(args, ap);
+
+	for (pos = 0; *fmt; ++fmt) {
+		if (*fmt != '%' || *++fmt == '%') {
+			PUTC(*fmt);
+			continue;
+		}
+
+		/* process flags */
+		flags = get_flags(&fmt);
+
+		/* get field width */
+		field_width = get_int(&fmt, &args);
+		if (field_width < 0) {
+			field_width = -field_width;
+			flags |= LEFT;
+		}
+
+		if (flags & LEFT)
+			flags &= ~ZEROPAD;
+
+		/* get the precision */
+		precision = -1;
+		if (*fmt == '.') {
+			++fmt;
+			precision = get_int(&fmt, &args);
+			if (precision >= 0)
+				flags &= ~ZEROPAD;
+		}
+
+		/* get the conversion qualifier */
+		qualifier = -1;
+		if (*fmt == 'h' || *fmt == 'l') {
+			qualifier = *fmt;
+			++fmt;
+			if (qualifier == *fmt) {
+				qualifier -= 'a'-'A';
+				++fmt;
+			}
+		}
+
+		sign = 0;
+
+		switch (*fmt) {
+		case 'c':
+			flags &= LEFT;
+			s = tmp;
+			if (qualifier == 'l') {
+				((u16 *)tmp)[0] = (u16)va_arg(args, unsigned int);
+				((u16 *)tmp)[1] = L'\0';
+				precision = INT_MAX;
+				goto wstring;
+			} else {
+				tmp[0] = (unsigned char)va_arg(args, int);
+				precision = len = 1;
+			}
+			goto output;
+
+		case 's':
+			flags &= LEFT;
+			if (precision < 0)
+				precision = INT_MAX;
+			s = va_arg(args, void *);
+			if (!s)
+				s = precision < 6 ? "" : "(null)";
+			else if (qualifier == 'l') {
+		wstring:
+				flags |= WIDE;
+				precision = len = utf16s_utf8nlen((const u16 *)s, precision);
+				goto output;
+			}
+			precision = len = strnlen(s, precision);
+			goto output;
+
+			/* integer number formats - set up the flags and "break" */
+		case 'o':
+			base = 8;
+			break;
+
+		case 'p':
+			if (precision < 0)
+				precision = 2 * sizeof(void *);
+			fallthrough;
+		case 'x':
+			flags |= SMALL;
+			fallthrough;
+		case 'X':
+			base = 16;
+			break;
+
+		case 'd':
+		case 'i':
+			flags |= SIGN;
+			fallthrough;
+		case 'u':
+			flags &= ~SPECIAL;
+			base = 10;
+			break;
+
+		default:
+			/*
+			 * Bail out if the conversion specifier is invalid.
+			 * There's probably a typo in the format string and the
+			 * remaining specifiers are unlikely to match up with
+			 * the arguments.
+			 */
+			goto fail;
+		}
+		if (*fmt == 'p') {
+			num = (unsigned long)va_arg(args, void *);
+		} else {
+			num = get_number(flags & SIGN, qualifier, &args);
+		}
+
+		sign = get_sign(&num, flags);
+		if (sign)
+			--field_width;
+
+		s = number(tmp_end, num, base, flags & SMALL);
+		len = tmp_end - s;
+		/* default precision is 1 */
+		if (precision < 0)
+			precision = 1;
+		/* precision is minimum number of digits to print */
+		if (precision < len)
+			precision = len;
+		if (flags & SPECIAL) {
+			/*
+			 * For octal, a leading 0 is printed only if necessary,
+			 * i.e. if it's not already there because of the
+			 * precision.
+			 */
+			if (base == 8 && precision == len)
+				++precision;
+			/*
+			 * For hexadecimal, the leading 0x is skipped if the
+			 * output is empty, i.e. both the number and the
+			 * precision are 0.
+			 */
+			if (base == 16 && precision > 0)
+				field_width -= 2;
+			else
+				flags &= ~SPECIAL;
+		}
+		/*
+		 * For zero padding, increase the precision to fill the field
+		 * width.
+		 */
+		if ((flags & ZEROPAD) && field_width > precision)
+			precision = field_width;
+
+output:
+		/* Calculate the padding necessary */
+		field_width -= precision;
+		/* Leading padding with ' ' */
+		if (!(flags & LEFT))
+			while (field_width-- > 0)
+				PUTC(' ');
+		/* sign */
+		if (sign)
+			PUTC(sign);
+		/* 0x/0X for hexadecimal */
+		if (flags & SPECIAL) {
+			PUTC('0');
+			PUTC( 'X' | (flags & SMALL));
+		}
+		/* Zero padding and excess precision */
+		while (precision-- > len)
+			PUTC('0');
+		/* Actual output */
+		if (flags & WIDE) {
+			const u16 *ws = (const u16 *)s;
+
+			while (len-- > 0) {
+				u32 c32 = utf16_to_utf32(&ws);
+				u8 *s8;
+				size_t clen;
+
+				if (c32 < 0x80) {
+					PUTC(c32);
+					continue;
+				}
+
+				/* Number of trailing octets */
+				clen = 1 + (c32 >= 0x800) + (c32 >= 0x10000);
+
+				len -= clen;
+				s8 = (u8 *)&buf[pos];
+
+				/* Avoid writing partial character */
+				PUTC('\0');
+				pos += clen;
+				if (pos >= size)
+					continue;
+
+				/* Set high bits of leading octet */
+				*s8 = (0xf00 >> 1) >> clen;
+				/* Write trailing octets in reverse order */
+				for (s8 += clen; clen; --clen, c32 >>= 6)
+					*s8-- = 0x80 | (c32 & 0x3f);
+				/* Set low bits of leading octet */
+				*s8 |= c32;
+			}
+		} else {
+			while (len-- > 0)
+				PUTC(*s++);
+		}
+		/* Trailing padding with ' ' */
+		while (field_width-- > 0)
+			PUTC(' ');
+	}
+fail:
+	va_end(args);
+
+	if (size)
+		buf[min(pos, size-1)] = '\0';
+
+	return pos;
+}
+
+int snprintf(char *buf, size_t size, const char *fmt, ...)
+{
+	va_list args;
+	int i;
+
+	va_start(args, fmt);
+	i = vsnprintf(buf, size, fmt, args);
+	va_end(args);
+	return i;
+}
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 8d3a707789de..5a48d996ed71 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -20,21 +20,9 @@
 /* Maximum physical address for 64-bit kernel with 4-level paging */
 #define MAXMEM_X86_64_4LEVEL (1ull << 46)
 
-static efi_system_table_t *sys_table;
-extern const bool efi_is64;
+const efi_system_table_t *efi_system_table;
 extern u32 image_offset;
-
-__pure efi_system_table_t *efi_system_table(void)
-{
-	return sys_table;
-}
-
-__attribute_const__ bool efi_is_64bit(void)
-{
-	if (IS_ENABLED(CONFIG_EFI_MIXED))
-		return efi_is64;
-	return IS_ENABLED(CONFIG_X86_64);
-}
+static efi_loaded_image_t *image = NULL;
 
 static efi_status_t
 preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
@@ -62,7 +50,7 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size,
 			     (void **)&rom);
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to allocate memory for 'rom'\n");
+		efi_err("Failed to allocate memory for 'rom'\n");
 		return status;
 	}
 
@@ -78,7 +66,7 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 				PCI_VENDOR_ID, 1, &rom->vendor);
 
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to read rom->vendor\n");
+		efi_err("Failed to read rom->vendor\n");
 		goto free_struct;
 	}
 
@@ -86,7 +74,7 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 				PCI_DEVICE_ID, 1, &rom->devid);
 
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to read rom->devid\n");
+		efi_err("Failed to read rom->devid\n");
 		goto free_struct;
 	}
 
@@ -131,7 +119,7 @@ static void setup_efi_pci(struct boot_params *params)
 				     (void **)&pci_handle);
 
 		if (status != EFI_SUCCESS) {
-			efi_printk("Failed to allocate memory for 'pci_handle'\n");
+			efi_err("Failed to allocate memory for 'pci_handle'\n");
 			return;
 		}
 
@@ -185,7 +173,7 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 		return;
 
 	if (efi_table_attr(p, version) != 0x10000) {
-		efi_printk("Unsupported properties proto version\n");
+		efi_err("Unsupported properties proto version\n");
 		return;
 	}
 
@@ -198,7 +186,7 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 				     size + sizeof(struct setup_data),
 				     (void **)&new);
 		if (status != EFI_SUCCESS) {
-			efi_printk("Failed to allocate memory for 'properties'\n");
+			efi_err("Failed to allocate memory for 'properties'\n");
 			return;
 		}
 
@@ -227,7 +215,7 @@ static const efi_char16_t apple[] = L"Apple";
 static void setup_quirks(struct boot_params *boot_params)
 {
 	efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long)
-		efi_table_attr(efi_system_table(), fw_vendor);
+		efi_table_attr(efi_system_table, fw_vendor);
 
 	if (!memcmp(fw_vendor, apple, sizeof(apple))) {
 		if (IS_ENABLED(CONFIG_APPLE_PROPERTIES))
@@ -368,7 +356,6 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 {
 	struct boot_params *boot_params;
 	struct setup_header *hdr;
-	efi_loaded_image_t *image;
 	void *image_base;
 	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
 	int options_size = 0;
@@ -377,30 +364,29 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 	unsigned long ramdisk_addr;
 	unsigned long ramdisk_size;
 
-	sys_table = sys_table_arg;
+	efi_system_table = sys_table_arg;
 
 	/* Check if we were booted by the EFI firmware */
-	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+	if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		efi_exit(handle, EFI_INVALID_PARAMETER);
 
 	status = efi_bs_call(handle_protocol, handle, &proto, (void **)&image);
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
+		efi_err("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
 		efi_exit(handle, status);
 	}
 
 	image_base = efi_table_attr(image, image_base);
 	image_offset = (void *)startup_32 - image_base;
 
-	hdr = &((struct boot_params *)image_base)->hdr;
-
-	status = efi_allocate_pages(0x4000, (unsigned long *)&boot_params, ULONG_MAX);
+	status = efi_allocate_pages(sizeof(struct boot_params),
+				    (unsigned long *)&boot_params, ULONG_MAX);
 	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to allocate lowmem for boot params\n");
+		efi_err("Failed to allocate lowmem for boot params\n");
 		efi_exit(handle, status);
 	}
 
-	memset(boot_params, 0x0, 0x4000);
+	memset(boot_params, 0x0, sizeof(struct boot_params));
 
 	hdr = &boot_params->hdr;
 
@@ -418,43 +404,21 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 	hdr->type_of_loader = 0x21;
 
 	/* Convert unicode cmdline to ascii */
-	cmdline_ptr = efi_convert_cmdline(image, &options_size, ULONG_MAX);
+	cmdline_ptr = efi_convert_cmdline(image, &options_size);
 	if (!cmdline_ptr)
 		goto fail;
 
-	hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
-	/* Fill in upper bits of command line address, NOP on 32 bit  */
-	boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32;
+	efi_set_u64_split((unsigned long)cmdline_ptr,
+			  &hdr->cmd_line_ptr, &boot_params->ext_cmd_line_ptr);
 
 	hdr->ramdisk_image = 0;
 	hdr->ramdisk_size = 0;
 
-	if (efi_is_native()) {
-		status = efi_parse_options(cmdline_ptr);
-		if (status != EFI_SUCCESS)
-			goto fail2;
-
-		if (!noinitrd()) {
-			status = efi_load_initrd(image, &ramdisk_addr,
-						 &ramdisk_size,
-						 hdr->initrd_addr_max,
-						 ULONG_MAX);
-			if (status != EFI_SUCCESS)
-				goto fail2;
-			hdr->ramdisk_image = ramdisk_addr & 0xffffffff;
-			hdr->ramdisk_size  = ramdisk_size & 0xffffffff;
-			boot_params->ext_ramdisk_image = (u64)ramdisk_addr >> 32;
-			boot_params->ext_ramdisk_size  = (u64)ramdisk_size >> 32;
-		}
-	}
-
-	efi_stub_entry(handle, sys_table, boot_params);
+	efi_stub_entry(handle, sys_table_arg, boot_params);
 	/* not reached */
 
-fail2:
-	efi_free(options_size, (unsigned long)cmdline_ptr);
 fail:
-	efi_free(0x4000, (unsigned long)boot_params);
+	efi_free(sizeof(struct boot_params), (unsigned long)boot_params);
 
 	efi_exit(handle, status);
 }
@@ -608,24 +572,18 @@ static efi_status_t allocate_e820(struct boot_params *params,
 				  struct setup_data **e820ext,
 				  u32 *e820ext_size)
 {
-	unsigned long map_size, desc_size, buff_size;
-	struct efi_boot_memmap boot_map;
-	efi_memory_desc_t *map;
+	unsigned long map_size, desc_size, map_key;
 	efi_status_t status;
-	__u32 nr_desc;
-
-	boot_map.map		= &map;
-	boot_map.map_size	= &map_size;
-	boot_map.desc_size	= &desc_size;
-	boot_map.desc_ver	= NULL;
-	boot_map.key_ptr	= NULL;
-	boot_map.buff_size	= &buff_size;
+	__u32 nr_desc, desc_version;
 
-	status = efi_get_memory_map(&boot_map);
-	if (status != EFI_SUCCESS)
-		return status;
+	/* Only need the size of the mem map and size of each mem descriptor */
+	map_size = 0;
+	status = efi_bs_call(get_memory_map, &map_size, NULL, &map_key,
+			     &desc_size, &desc_version);
+	if (status != EFI_BUFFER_TOO_SMALL)
+		return (status != EFI_SUCCESS) ? status : EFI_UNSUPPORTED;
 
-	nr_desc = buff_size / desc_size;
+	nr_desc = map_size / desc_size + EFI_MMAP_NR_SLACK_SLOTS;
 
 	if (nr_desc > ARRAY_SIZE(params->e820_table)) {
 		u32 nr_e820ext = nr_desc - ARRAY_SIZE(params->e820_table);
@@ -653,17 +611,14 @@ static efi_status_t exit_boot_func(struct efi_boot_memmap *map,
 				   : EFI32_LOADER_SIGNATURE;
 	memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
 
-	p->efi->efi_systab		= (unsigned long)efi_system_table();
+	efi_set_u64_split((unsigned long)efi_system_table,
+			  &p->efi->efi_systab, &p->efi->efi_systab_hi);
 	p->efi->efi_memdesc_size	= *map->desc_size;
 	p->efi->efi_memdesc_version	= *map->desc_ver;
-	p->efi->efi_memmap		= (unsigned long)*map->map;
+	efi_set_u64_split((unsigned long)*map->map,
+			  &p->efi->efi_memmap, &p->efi->efi_memmap_hi);
 	p->efi->efi_memmap_size		= *map->map_size;
 
-#ifdef CONFIG_X86_64
-	p->efi->efi_systab_hi		= (unsigned long)efi_system_table() >> 32;
-	p->efi->efi_memmap_hi		= (unsigned long)*map->map >> 32;
-#endif
-
 	return EFI_SUCCESS;
 }
 
@@ -719,12 +674,11 @@ unsigned long efi_main(efi_handle_t handle,
 	unsigned long buffer_start, buffer_end;
 	struct setup_header *hdr = &boot_params->hdr;
 	efi_status_t status;
-	unsigned long cmdline_paddr;
 
-	sys_table = sys_table_arg;
+	efi_system_table = sys_table_arg;
 
 	/* Check if we were booted by the EFI firmware */
-	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+	if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		efi_exit(handle, EFI_INVALID_PARAMETER);
 
 	/*
@@ -742,8 +696,15 @@ unsigned long efi_main(efi_handle_t handle,
 	 * now use KERNEL_IMAGE_SIZE, which will be 512MiB, the same as what
 	 * KASLR uses.
 	 *
-	 * Also relocate it if image_offset is zero, i.e. we weren't loaded by
-	 * LoadImage, but we are not aligned correctly.
+	 * Also relocate it if image_offset is zero, i.e. the kernel wasn't
+	 * loaded by LoadImage, but rather by a bootloader that called the
+	 * handover entry. The reason we must always relocate in this case is
+	 * to handle the case of systemd-boot booting a unified kernel image,
+	 * which is a PE executable that contains the bzImage and an initrd as
+	 * COFF sections. The initrd section is placed after the bzImage
+	 * without ensuring that there are at least init_size bytes available
+	 * for the bzImage, and thus the compressed kernel's startup code may
+	 * overwrite the initrd unless it is moved out of the way.
 	 */
 
 	buffer_start = ALIGN(bzimage_addr - image_offset,
@@ -753,15 +714,14 @@ unsigned long efi_main(efi_handle_t handle,
 	if ((buffer_start < LOAD_PHYSICAL_ADDR)				     ||
 	    (IS_ENABLED(CONFIG_X86_32) && buffer_end > KERNEL_IMAGE_SIZE)    ||
 	    (IS_ENABLED(CONFIG_X86_64) && buffer_end > MAXMEM_X86_64_4LEVEL) ||
-	    (image_offset == 0 && !IS_ALIGNED(bzimage_addr,
-					      hdr->kernel_alignment))) {
+	    (image_offset == 0)) {
 		status = efi_relocate_kernel(&bzimage_addr,
 					     hdr->init_size, hdr->init_size,
 					     hdr->pref_address,
 					     hdr->kernel_alignment,
 					     LOAD_PHYSICAL_ADDR);
 		if (status != EFI_SUCCESS) {
-			efi_printk("efi_relocate_kernel() failed!\n");
+			efi_err("efi_relocate_kernel() failed!\n");
 			goto fail;
 		}
 		/*
@@ -772,35 +732,48 @@ unsigned long efi_main(efi_handle_t handle,
 		image_offset = 0;
 	}
 
-	/*
-	 * efi_pe_entry() may have been called before efi_main(), in which
-	 * case this is the second time we parse the cmdline. This is ok,
-	 * parsing the cmdline multiple times does not have side-effects.
-	 */
-	cmdline_paddr = ((u64)hdr->cmd_line_ptr |
-			 ((u64)boot_params->ext_cmd_line_ptr << 32));
-	efi_parse_options((char *)cmdline_paddr);
+#ifdef CONFIG_CMDLINE_BOOL
+	status = efi_parse_options(CONFIG_CMDLINE);
+	if (status != EFI_SUCCESS) {
+		efi_err("Failed to parse options\n");
+		goto fail;
+	}
+#endif
+	if (!IS_ENABLED(CONFIG_CMDLINE_OVERRIDE)) {
+		unsigned long cmdline_paddr = ((u64)hdr->cmd_line_ptr |
+					       ((u64)boot_params->ext_cmd_line_ptr << 32));
+		status = efi_parse_options((char *)cmdline_paddr);
+		if (status != EFI_SUCCESS) {
+			efi_err("Failed to parse options\n");
+			goto fail;
+		}
+	}
 
 	/*
-	 * At this point, an initrd may already have been loaded, either by
-	 * the bootloader and passed via bootparams, or loaded from a initrd=
-	 * command line option by efi_pe_entry() above. In either case, we
-	 * permit an initrd loaded from the LINUX_EFI_INITRD_MEDIA_GUID device
-	 * path to supersede it.
+	 * At this point, an initrd may already have been loaded by the
+	 * bootloader and passed via bootparams. We permit an initrd loaded
+	 * from the LINUX_EFI_INITRD_MEDIA_GUID device path to supersede it.
+	 *
+	 * If the device path is not present, any command-line initrd=
+	 * arguments will be processed only if image is not NULL, which will be
+	 * the case only if we were loaded via the PE entry point.
 	 */
-	if (!noinitrd()) {
+	if (!efi_noinitrd) {
 		unsigned long addr, size;
 
-		status = efi_load_initrd_dev_path(&addr, &size, ULONG_MAX);
-		if (status == EFI_SUCCESS) {
-			hdr->ramdisk_image		= (u32)addr;
-			hdr->ramdisk_size 		= (u32)size;
-			boot_params->ext_ramdisk_image	= (u64)addr >> 32;
-			boot_params->ext_ramdisk_size 	= (u64)size >> 32;
-		} else if (status != EFI_NOT_FOUND) {
-			efi_printk("efi_load_initrd_dev_path() failed!\n");
+		status = efi_load_initrd(image, &addr, &size,
+					 hdr->initrd_addr_max, ULONG_MAX);
+
+		if (status != EFI_SUCCESS) {
+			efi_err("Failed to load initrd!\n");
 			goto fail;
 		}
+		if (size > 0) {
+			efi_set_u64_split(addr, &hdr->ramdisk_image,
+					  &boot_params->ext_ramdisk_image);
+			efi_set_u64_split(size, &hdr->ramdisk_size,
+					  &boot_params->ext_ramdisk_size);
+		}
 	}
 
 	/*
@@ -825,13 +798,13 @@ unsigned long efi_main(efi_handle_t handle,
 
 	status = exit_boot(boot_params, handle);
 	if (status != EFI_SUCCESS) {
-		efi_printk("exit_boot() failed!\n");
+		efi_err("exit_boot() failed!\n");
 		goto fail;
 	}
 
 	return bzimage_addr;
 fail:
-	efi_printk("efi_main() failed!\n");
+	efi_err("efi_main() failed!\n");
 
 	efi_exit(handle, status);
 }
diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
index 31f9f0e369b9..c1955d320fec 100644
--- a/drivers/firmware/efi/tpm.c
+++ b/drivers/firmware/efi/tpm.c
@@ -16,7 +16,7 @@
 int efi_tpm_final_log_size;
 EXPORT_SYMBOL(efi_tpm_final_log_size);
 
-static int tpm2_calc_event_log_size(void *data, int count, void *size_info)
+static int __init tpm2_calc_event_log_size(void *data, int count, void *size_info)
 {
 	struct tcg_pcr_event2_head *header;
 	int event_size, size = 0;
@@ -62,8 +62,11 @@ int __init efi_tpm_eventlog_init(void)
 	tbl_size = sizeof(*log_tbl) + log_tbl->size;
 	memblock_reserve(efi.tpm_log, tbl_size);
 
-	if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR)
+	if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR ||
+	    log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) {
+		pr_warn(FW_BUG "TPM Final Events table missing or invalid\n");
 		goto out;
+	}
 
 	final_tbl = early_memremap(efi.tpm_final_log, sizeof(*final_tbl));
 
diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig
index 116707a075f3..1d2e5b85d7ca 100644
--- a/drivers/firmware/imx/Kconfig
+++ b/drivers/firmware/imx/Kconfig
@@ -12,7 +12,7 @@ config IMX_DSP
 
 config IMX_SCU
 	bool "IMX SCU Protocol driver"
-	depends on IMX_MBOX || COMPILE_TEST
+	depends on IMX_MBOX
 	help
 	  The System Controller Firmware (SCFW) is a low-level system function
 	  which runs on a dedicated Cortex-M core to provide power, clock, and
@@ -24,6 +24,6 @@ config IMX_SCU
 
 config IMX_SCU_PD
 	bool "IMX SCU Power Domain driver"
-	depends on IMX_SCU || COMPILE_TEST
+	depends on IMX_SCU
 	help
 	  The System Controller Firmware (SCFW) based power domain driver.
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 2937d44b5df4..92013ecc2d9e 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -46,25 +46,14 @@
  * require cooperation with a Trusted OS driver.
  */
 static int resident_cpu = -1;
+struct psci_operations psci_ops;
+static enum arm_smccc_conduit psci_conduit = SMCCC_CONDUIT_NONE;
 
 bool psci_tos_resident_on(int cpu)
 {
 	return cpu == resident_cpu;
 }
 
-struct psci_operations psci_ops = {
-	.conduit = SMCCC_CONDUIT_NONE,
-	.smccc_version = SMCCC_VERSION_1_0,
-};
-
-enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void)
-{
-	if (psci_ops.smccc_version < SMCCC_VERSION_1_1)
-		return SMCCC_CONDUIT_NONE;
-
-	return psci_ops.conduit;
-}
-
 typedef unsigned long (psci_fn)(unsigned long, unsigned long,
 				unsigned long, unsigned long);
 static psci_fn *invoke_psci_fn;
@@ -242,7 +231,7 @@ static void set_conduit(enum arm_smccc_conduit conduit)
 		WARN(1, "Unexpected PSCI conduit %d\n", conduit);
 	}
 
-	psci_ops.conduit = conduit;
+	psci_conduit = conduit;
 }
 
 static int get_set_conduit_method(struct device_node *np)
@@ -411,8 +400,8 @@ static void __init psci_init_smccc(void)
 	if (feature != PSCI_RET_NOT_SUPPORTED) {
 		u32 ret;
 		ret = invoke_psci_fn(ARM_SMCCC_VERSION_FUNC_ID, 0, 0, 0);
-		if (ret == ARM_SMCCC_VERSION_1_1) {
-			psci_ops.smccc_version = SMCCC_VERSION_1_1;
+		if (ret >= ARM_SMCCC_VERSION_1_1) {
+			arm_smccc_version_init(ret, psci_conduit);
 			ver = ret;
 		}
 	}
diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c
index da26a584dca0..a3e85186f8e6 100644
--- a/drivers/firmware/raspberrypi.c
+++ b/drivers/firmware/raspberrypi.c
@@ -182,16 +182,10 @@ rpi_firmware_print_firmware_revision(struct rpi_firmware *fw)
 					RPI_FIRMWARE_GET_FIRMWARE_REVISION,
 					&packet, sizeof(packet));
 
-	if (ret == 0) {
-		struct tm tm;
-
-		time64_to_tm(packet, 0, &tm);
+	if (ret)
+		return;
 
-		dev_info(fw->cl.dev,
-			 "Attached to firmware from %04ld-%02d-%02d %02d:%02d\n",
-			 tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
-			 tm.tm_hour, tm.tm_min);
-	}
+	dev_info(fw->cl.dev, "Attached to firmware from %ptT\n", &packet);
 }
 
 static void
diff --git a/drivers/firmware/smccc/Kconfig b/drivers/firmware/smccc/Kconfig
new file mode 100644
index 000000000000..27b675d76235
--- /dev/null
+++ b/drivers/firmware/smccc/Kconfig
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config HAVE_ARM_SMCCC
+	bool
+	help
+	  Include support for the Secure Monitor Call (SMC) and Hypervisor
+	  Call (HVC) instructions on Armv7 and above architectures.
+
+config HAVE_ARM_SMCCC_DISCOVERY
+	bool
+	depends on ARM_PSCI_FW
+	default y
+	help
+	 SMCCC v1.0 lacked discoverability and hence PSCI v1.0 was updated
+	 to add SMCCC discovery mechanism though the PSCI firmware
+	 implementation of PSCI_FEATURES(SMCCC_VERSION) which returns
+	 success on firmware compliant to SMCCC v1.1 and above.
diff --git a/drivers/firmware/smccc/Makefile b/drivers/firmware/smccc/Makefile
new file mode 100644
index 000000000000..6f369fe3f0b9
--- /dev/null
+++ b/drivers/firmware/smccc/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+obj-$(CONFIG_HAVE_ARM_SMCCC_DISCOVERY)	+= smccc.o
diff --git a/drivers/firmware/smccc/smccc.c b/drivers/firmware/smccc/smccc.c
new file mode 100644
index 000000000000..4e80921ee212
--- /dev/null
+++ b/drivers/firmware/smccc/smccc.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Arm Limited
+ */
+
+#define pr_fmt(fmt) "smccc: " fmt
+
+#include <linux/init.h>
+#include <linux/arm-smccc.h>
+
+static u32 smccc_version = ARM_SMCCC_VERSION_1_0;
+static enum arm_smccc_conduit smccc_conduit = SMCCC_CONDUIT_NONE;
+
+void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit)
+{
+	smccc_version = version;
+	smccc_conduit = conduit;
+}
+
+enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void)
+{
+	if (smccc_version < ARM_SMCCC_VERSION_1_1)
+		return SMCCC_CONDUIT_NONE;
+
+	return smccc_conduit;
+}
+
+u32 arm_smccc_get_version(void)
+{
+	return smccc_version;
+}
diff --git a/drivers/firmware/xilinx/zynqmp-debug.c b/drivers/firmware/xilinx/zynqmp-debug.c
index c6d0724da4db..43bc6cfdab45 100644
--- a/drivers/firmware/xilinx/zynqmp-debug.c
+++ b/drivers/firmware/xilinx/zynqmp-debug.c
@@ -35,7 +35,7 @@ static struct pm_api_info pm_api_list[] = {
 	PM_API(PM_QUERY_DATA),
 };
 
-struct dentry *firmware_debugfs_root;
+static struct dentry *firmware_debugfs_root;
 
 /**
  * zynqmp_pm_argument_value() - Extract argument value from a PM-API request
diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c
index 89ca292236ad..538755062ab7 100644
--- a/drivers/fpga/dfl-pci.c
+++ b/drivers/fpga/dfl-pci.c
@@ -248,11 +248,13 @@ static int cci_pci_sriov_configure(struct pci_dev *pcidev, int num_vfs)
 			return ret;
 
 		ret = pci_enable_sriov(pcidev, num_vfs);
-		if (ret)
+		if (ret) {
 			dfl_fpga_cdev_config_ports_pf(cdev);
+			return ret;
+		}
 	}
 
-	return ret;
+	return num_vfs;
 }
 
 static void cci_pci_remove(struct pci_dev *pcidev)
diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c
index ee7765049607..07fa8d9ec675 100644
--- a/drivers/fpga/zynq-fpga.c
+++ b/drivers/fpga/zynq-fpga.c
@@ -583,7 +583,8 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 
 	priv->clk = devm_clk_get(dev, "ref_clk");
 	if (IS_ERR(priv->clk)) {
-		dev_err(dev, "input clock not found\n");
+		if (PTR_ERR(priv->clk) != -EPROBE_DEFER)
+			dev_err(dev, "input clock not found\n");
 		return PTR_ERR(priv->clk);
 	}
 
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index baee8c3f06ad..cf3687a7925f 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -625,7 +625,7 @@ static int bcm_kona_gpio_probe(struct platform_device *pdev)
 
 	kona_gpio->reg_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(kona_gpio->reg_base)) {
-		ret = -ENXIO;
+		ret = PTR_ERR(kona_gpio->reg_base);
 		goto err_irq_domain;
 	}
 
diff --git a/drivers/gpio/gpio-exar.c b/drivers/gpio/gpio-exar.c
index da1ef0b1c291..b1accfba017d 100644
--- a/drivers/gpio/gpio-exar.c
+++ b/drivers/gpio/gpio-exar.c
@@ -148,8 +148,10 @@ static int gpio_exar_probe(struct platform_device *pdev)
 	mutex_init(&exar_gpio->lock);
 
 	index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL);
-	if (index < 0)
-		goto err_destroy;
+	if (index < 0) {
+		ret = index;
+		goto err_mutex_destroy;
+	}
 
 	sprintf(exar_gpio->name, "exar_gpio%d", index);
 	exar_gpio->gpio_chip.label = exar_gpio->name;
@@ -176,6 +178,7 @@ static int gpio_exar_probe(struct platform_device *pdev)
 
 err_destroy:
 	ida_simple_remove(&ida_index, index);
+err_mutex_destroy:
 	mutex_destroy(&exar_gpio->lock);
 	return ret;
 }
diff --git a/drivers/gpio/gpio-mlxbf2.c b/drivers/gpio/gpio-mlxbf2.c
index 7b7085050219..da570e63589d 100644
--- a/drivers/gpio/gpio-mlxbf2.c
+++ b/drivers/gpio/gpio-mlxbf2.c
@@ -127,8 +127,8 @@ static int mlxbf2_gpio_lock_acquire(struct mlxbf2_gpio_context *gs)
 {
 	u32 arm_gpio_lock_val;
 
-	spin_lock(&gs->gc.bgpio_lock);
 	mutex_lock(yu_arm_gpio_lock_param.lock);
+	spin_lock(&gs->gc.bgpio_lock);
 
 	arm_gpio_lock_val = readl(yu_arm_gpio_lock_param.io);
 
@@ -136,8 +136,8 @@ static int mlxbf2_gpio_lock_acquire(struct mlxbf2_gpio_context *gs)
 	 * When lock active bit[31] is set, ModeX is write enabled
 	 */
 	if (YU_LOCK_ACTIVE_BIT(arm_gpio_lock_val)) {
-		mutex_unlock(yu_arm_gpio_lock_param.lock);
 		spin_unlock(&gs->gc.bgpio_lock);
+		mutex_unlock(yu_arm_gpio_lock_param.lock);
 		return -EINVAL;
 	}
 
@@ -152,8 +152,8 @@ static int mlxbf2_gpio_lock_acquire(struct mlxbf2_gpio_context *gs)
 static void mlxbf2_gpio_lock_release(struct mlxbf2_gpio_context *gs)
 {
 	writel(YU_ARM_GPIO_LOCK_RELEASE, yu_arm_gpio_lock_param.io);
-	mutex_unlock(yu_arm_gpio_lock_param.lock);
 	spin_unlock(&gs->gc.bgpio_lock);
+	mutex_unlock(yu_arm_gpio_lock_param.lock);
 }
 
 /*
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index 3c9f4fb3d5a2..bd65114eb170 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -782,6 +782,15 @@ static int mvebu_pwm_probe(struct platform_device *pdev,
 				     "marvell,armada-370-gpio"))
 		return 0;
 
+	/*
+	 * There are only two sets of PWM configuration registers for
+	 * all the GPIO lines on those SoCs which this driver reserves
+	 * for the first two GPIO chips. So if the resource is missing
+	 * we can't treat it as an error.
+	 */
+	if (!platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm"))
+		return 0;
+
 	if (IS_ERR(mvchip->clk))
 		return PTR_ERR(mvchip->clk);
 
@@ -804,12 +813,6 @@ static int mvebu_pwm_probe(struct platform_device *pdev,
 	mvchip->mvpwm = mvpwm;
 	mvpwm->mvchip = mvchip;
 
-	/*
-	 * There are only two sets of PWM configuration registers for
-	 * all the GPIO lines on those SoCs which this driver reserves
-	 * for the first two GPIO chips. So if the resource is missing
-	 * we can't treat it as an error.
-	 */
 	mvpwm->membase = devm_platform_ioremap_resource_byname(pdev, "pwm");
 	if (IS_ERR(mvpwm->membase))
 		return PTR_ERR(mvpwm->membase);
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 5638b4e5355f..4269ea9a817e 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -531,7 +531,7 @@ static int pca953x_gpio_set_config(struct gpio_chip *gc, unsigned int offset,
 {
 	struct pca953x_chip *chip = gpiochip_get_data(gc);
 
-	switch (config) {
+	switch (pinconf_to_config_param(config)) {
 	case PIN_CONFIG_BIAS_PULL_UP:
 	case PIN_CONFIG_BIAS_PULL_DOWN:
 		return pca953x_gpio_set_pull_up_down(chip, offset, config);
diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index 1361270ecf8c..0cb6600b8eee 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -660,8 +660,8 @@ static int pxa_gpio_probe(struct platform_device *pdev)
 	pchip->irq1 = irq1;
 
 	gpio_reg_base = devm_platform_ioremap_resource(pdev, 0);
-	if (!gpio_reg_base)
-		return -EINVAL;
+	if (IS_ERR(gpio_reg_base))
+		return PTR_ERR(gpio_reg_base);
 
 	clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(clk)) {
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index acb99eff9939..86568154cdb3 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -368,6 +368,7 @@ static void tegra_gpio_irq_shutdown(struct irq_data *d)
 	struct tegra_gpio_info *tgi = bank->tgi;
 	unsigned int gpio = d->hwirq;
 
+	tegra_gpio_irq_mask(d);
 	gpiochip_unlock_as_irq(&tgi->gc, gpio);
 }
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 40f2d7f69be2..c14f0784274a 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -729,6 +729,10 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 			if (ret)
 				goto out_free_descs;
 		}
+
+		atomic_notifier_call_chain(&desc->gdev->notifier,
+					   GPIOLINE_CHANGED_REQUESTED, desc);
+
 		dev_dbg(&gdev->dev, "registered chardev handle for line %d\n",
 			offset);
 	}
@@ -1083,6 +1087,9 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
 	if (ret)
 		goto out_free_desc;
 
+	atomic_notifier_call_chain(&desc->gdev->notifier,
+				   GPIOLINE_CHANGED_REQUESTED, desc);
+
 	le->irq = gpiod_to_irq(desc);
 	if (le->irq <= 0) {
 		ret = -ENODEV;
@@ -1158,8 +1165,19 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc,
 				  struct gpioline_info *info)
 {
 	struct gpio_chip *gc = desc->gdev->chip;
+	bool ok_for_pinctrl;
 	unsigned long flags;
 
+	/*
+	 * This function takes a mutex so we must check this before taking
+	 * the spinlock.
+	 *
+	 * FIXME: find a non-racy way to retrieve this information. Maybe a
+	 * lock common to both frameworks?
+	 */
+	ok_for_pinctrl =
+		pinctrl_gpio_can_use_line(gc->base + info->line_offset);
+
 	spin_lock_irqsave(&gpio_lock, flags);
 
 	if (desc->name) {
@@ -1186,7 +1204,7 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc,
 	    test_bit(FLAG_USED_AS_IRQ, &desc->flags) ||
 	    test_bit(FLAG_EXPORT, &desc->flags) ||
 	    test_bit(FLAG_SYSFS, &desc->flags) ||
-	    !pinctrl_gpio_can_use_line(gc->base + info->line_offset))
+	    !ok_for_pinctrl)
 		info->flags |= GPIOLINE_FLAG_KERNEL;
 	if (test_bit(FLAG_IS_OUT, &desc->flags))
 		info->flags |= GPIOLINE_FLAG_IS_OUT;
@@ -1227,6 +1245,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	void __user *ip = (void __user *)arg;
 	struct gpio_desc *desc;
 	__u32 offset;
+	int hwgpio;
 
 	/* We fail any subsequent ioctl():s when the chip is gone */
 	if (!gc)
@@ -1259,13 +1278,19 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (IS_ERR(desc))
 			return PTR_ERR(desc);
 
+		hwgpio = gpio_chip_hwgpio(desc);
+
+		if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL &&
+		    test_bit(hwgpio, priv->watched_lines))
+			return -EBUSY;
+
 		gpio_desc_to_lineinfo(desc, &lineinfo);
 
 		if (copy_to_user(ip, &lineinfo, sizeof(lineinfo)))
 			return -EFAULT;
 
 		if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL)
-			set_bit(gpio_chip_hwgpio(desc), priv->watched_lines);
+			set_bit(hwgpio, priv->watched_lines);
 
 		return 0;
 	} else if (cmd == GPIO_GET_LINEHANDLE_IOCTL) {
@@ -1280,7 +1305,12 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (IS_ERR(desc))
 			return PTR_ERR(desc);
 
-		clear_bit(gpio_chip_hwgpio(desc), priv->watched_lines);
+		hwgpio = gpio_chip_hwgpio(desc);
+
+		if (!test_bit(hwgpio, priv->watched_lines))
+			return -EBUSY;
+
+		clear_bit(hwgpio, priv->watched_lines);
 		return 0;
 	}
 	return -EINVAL;
@@ -2975,8 +3005,6 @@ static int gpiod_request_commit(struct gpio_desc *desc, const char *label)
 	}
 done:
 	spin_unlock_irqrestore(&gpio_lock, flags);
-	atomic_notifier_call_chain(&desc->gdev->notifier,
-				   GPIOLINE_CHANGED_REQUESTED, desc);
 	return ret;
 }
 
@@ -4192,7 +4220,9 @@ int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset)
 		}
 	}
 
-	if (test_bit(FLAG_IS_OUT, &desc->flags)) {
+	/* To be valid for IRQ the line needs to be input or open drain */
+	if (test_bit(FLAG_IS_OUT, &desc->flags) &&
+	    !test_bit(FLAG_OPEN_DRAIN, &desc->flags)) {
 		chip_err(gc,
 			 "%s: tried to flag a GPIO set as output for IRQ\n",
 			 __func__);
@@ -4255,7 +4285,12 @@ void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset)
 
 	if (!IS_ERR(desc) &&
 	    !WARN_ON(!test_bit(FLAG_USED_AS_IRQ, &desc->flags))) {
-		WARN_ON(test_bit(FLAG_IS_OUT, &desc->flags));
+		/*
+		 * We must not be output when using IRQ UNLESS we are
+		 * open drain.
+		 */
+		WARN_ON(test_bit(FLAG_IS_OUT, &desc->flags) &&
+			!test_bit(FLAG_OPEN_DRAIN, &desc->flags));
 		set_bit(FLAG_IRQ_IS_ENABLED, &desc->flags);
 	}
 }
@@ -4938,6 +4973,9 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
 		return ERR_PTR(ret);
 	}
 
+	atomic_notifier_call_chain(&desc->gdev->notifier,
+				   GPIOLINE_CHANGED_REQUESTED, desc);
+
 	return desc;
 }
 EXPORT_SYMBOL_GPL(gpiod_get_index);
@@ -5003,6 +5041,9 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode,
 		return ERR_PTR(ret);
 	}
 
+	atomic_notifier_call_chain(&desc->gdev->notifier,
+				   GPIOLINE_CHANGED_REQUESTED, desc);
+
 	return desc;
 }
 EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod);
@@ -5289,8 +5330,9 @@ static int __init gpiolib_dev_init(void)
 	gpiolib_initialized = true;
 	gpiochip_setup_devs();
 
-	if (IS_ENABLED(CONFIG_OF_DYNAMIC))
-		WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier));
+#if IS_ENABLED(CONFIG_OF_DYNAMIC) && IS_ENABLED(CONFIG_OF_GPIO)
+	WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier));
+#endif /* CONFIG_OF_DYNAMIC && CONFIG_OF_GPIO */
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 2992a49ad4a5..8ac1581a6b53 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -945,6 +945,7 @@ struct amdgpu_device {
 
 	/* s3/s4 mask */
 	bool                            in_suspend;
+	bool				in_hibernate;
 
 	/* record last mm index being written through WREG32*/
 	unsigned long last_mm_index;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 9dff792c9290..6a5b91d23fd9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1343,7 +1343,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	}
 
 	/* Free the BO*/
-	amdgpu_bo_unref(&mem->bo);
+	drm_gem_object_put_unlocked(&mem->bo->tbo.base);
 	mutex_destroy(&mem->lock);
 	kfree(mem);
 
@@ -1688,7 +1688,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
 		| KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE
 		| KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE;
 
-	(*mem)->bo = amdgpu_bo_ref(bo);
+	drm_gem_object_get(&bo->tbo.base);
+	(*mem)->bo = bo;
 	(*mem)->va = va;
 	(*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ?
 		AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 559dc24ef436..affde2de2a0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2008,8 +2008,24 @@ static void amdgpu_device_fill_reset_magic(struct amdgpu_device *adev)
  */
 static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev)
 {
-	return !!memcmp(adev->gart.ptr, adev->reset_magic,
-			AMDGPU_RESET_MAGIC_NUM);
+	if (memcmp(adev->gart.ptr, adev->reset_magic,
+			AMDGPU_RESET_MAGIC_NUM))
+		return true;
+
+	if (!adev->in_gpu_reset)
+		return false;
+
+	/*
+	 * For all ASICs with baco/mode1 reset, the VRAM is
+	 * always assumed to be lost.
+	 */
+	switch (amdgpu_asic_reset_method(adev)) {
+	case AMD_RESET_METHOD_BACO:
+	case AMD_RESET_METHOD_MODE1:
+		return true;
+	default:
+		return false;
+	}
 }
 
 /**
@@ -2340,6 +2356,8 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 {
 	int i, r;
 
+	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
+	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)
@@ -3354,15 +3372,12 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		}
 	}
 
-	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
-	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
-
-	amdgpu_amdkfd_suspend(adev, !fbcon);
-
 	amdgpu_ras_suspend(adev);
 
 	r = amdgpu_device_ip_suspend_phase1(adev);
 
+	amdgpu_amdkfd_suspend(adev, !fbcon);
+
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 8ea86ffdea0d..a735d79a717b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -85,9 +85,10 @@
  * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
  * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
  * - 3.36.0 - Allow reading more status registers on si/cik
+ * - 3.37.0 - L2 is invalidated before SDMA IBs, needed for correctness
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	36
+#define KMS_DRIVER_MINOR	37
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -1180,7 +1181,9 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	struct amdgpu_device *adev = drm_dev->dev_private;
 	int r;
 
+	adev->in_hibernate = true;
 	r = amdgpu_device_suspend(drm_dev, true);
+	adev->in_hibernate = false;
 	if (r)
 		return r;
 	return amdgpu_asic_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 9ae7b61f696a..25ddb482466a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -133,8 +133,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 	u32 cpp;
 	u64 flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 			       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS     |
-			       AMDGPU_GEM_CREATE_VRAM_CLEARED 	     |
-			       AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+			       AMDGPU_GEM_CREATE_VRAM_CLEARED;
 
 	info = drm_get_format_info(adev->ddev, mode_cmd);
 	cpp = info->cpp[0];
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 006f21ef7ddf..62635e58e45e 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1358,8 +1358,6 @@ static int cik_asic_reset(struct amdgpu_device *adev)
 	int r;
 
 	if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
-		if (!adev->in_suspend)
-			amdgpu_inc_vram_lost(adev);
 		r = amdgpu_dpm_baco_reset(adev);
 	} else {
 		r = cik_asic_pci_config_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index d78059fd2c72..0e0daf0021b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -279,7 +279,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2_nv12[] =
 
 #define DEFAULT_SH_MEM_CONFIG \
 	((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \
-	 (SH_MEM_ALIGNMENT_MODE_DWORD << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
+	 (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
 	 (SH_MEM_RETRY_MODE_ALL << SH_MEM_CONFIG__RETRY_MODE__SHIFT) | \
 	 (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT))
 
@@ -4273,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 		/* ===  CGCG /CGLS for GFX 3D Only === */
 		gfx_v10_0_update_3d_clock_gating(adev, enable);
 		/* ===  MGCG + MGLS === */
-		/* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */
+		gfx_v10_0_update_medium_grain_clock_gating(adev, enable);
 	}
 
 	if (adev->cg_flags &
@@ -4353,11 +4353,7 @@ static int gfx_v10_0_set_powergating_state(void *handle,
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
-		if (!enable) {
-			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		} else
-			amdgpu_gfx_off_ctrl(adev, true);
+		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
 		break;
@@ -4918,6 +4914,19 @@ static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
 							   ref, mask);
 }
 
+static void gfx_v10_0_ring_soft_recovery(struct amdgpu_ring *ring,
+					 unsigned vmid)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t value = 0;
+
+	value = REG_SET_FIELD(value, SQ_CMD, CMD, 0x03);
+	value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01);
+	value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1);
+	value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid);
+	WREG32_SOC15(GC, 0, mmSQ_CMD, value);
+}
+
 static void
 gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 				      uint32_t me, uint32_t pipe,
@@ -5309,6 +5318,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 	.emit_wreg = gfx_v10_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
+	.soft_recovery = gfx_v10_0_ring_soft_recovery,
 };
 
 static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e6b113ed2f40..d2d9dce68c2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1234,6 +1234,10 @@ struct amdgpu_gfxoff_quirk {
 static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = {
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=204689 */
 	{ 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 },
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=207171 */
+	{ 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 },
+	/* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */
+	{ 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 },
 	{ 0, 0, 0, 0, 0 },
 };
 
@@ -5023,10 +5027,9 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:
-		if (!enable) {
+		if (!enable)
 			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		}
+
 		if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) {
 			gfx_v9_0_enable_sck_slow_down_on_power_up(adev, true);
 			gfx_v9_0_enable_sck_slow_down_on_power_down(adev, true);
@@ -5050,12 +5053,7 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 			amdgpu_gfx_off_ctrl(adev, true);
 		break;
 	case CHIP_VEGA12:
-		if (!enable) {
-			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		} else {
-			amdgpu_gfx_off_ctrl(adev, true);
-		}
+		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h b/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h
index 074a9a09c0a7..a5b60c9a2418 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h
@@ -73,6 +73,22 @@
 #define SDMA_OP_AQL_COPY  0
 #define SDMA_OP_AQL_BARRIER_OR  0
 
+#define SDMA_GCR_RANGE_IS_PA		(1 << 18)
+#define SDMA_GCR_SEQ(x)			(((x) & 0x3) << 16)
+#define SDMA_GCR_GL2_WB			(1 << 15)
+#define SDMA_GCR_GL2_INV		(1 << 14)
+#define SDMA_GCR_GL2_DISCARD		(1 << 13)
+#define SDMA_GCR_GL2_RANGE(x)		(((x) & 0x3) << 11)
+#define SDMA_GCR_GL2_US			(1 << 10)
+#define SDMA_GCR_GL1_INV		(1 << 9)
+#define SDMA_GCR_GLV_INV		(1 << 8)
+#define SDMA_GCR_GLK_INV		(1 << 7)
+#define SDMA_GCR_GLK_WB			(1 << 6)
+#define SDMA_GCR_GLM_INV		(1 << 5)
+#define SDMA_GCR_GLM_WB			(1 << 4)
+#define SDMA_GCR_GL1_RANGE(x)		(((x) & 0x3) << 2)
+#define SDMA_GCR_GLI_INV(x)		(((x) & 0x3) << 0)
+
 /*define for op field*/
 #define SDMA_PKT_HEADER_op_offset 0
 #define SDMA_PKT_HEADER_op_mask   0x000000FF
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 033cbbca2072..52318b03c424 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -351,8 +351,6 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 	struct smu_context *smu = &adev->smu;
 
 	if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
-		if (!adev->in_suspend)
-			amdgpu_inc_vram_lost(adev);
 		ret = smu_baco_enter(smu);
 		if (ret)
 			return ret;
@@ -360,8 +358,6 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 		if (ret)
 			return ret;
 	} else {
-		if (!adev->in_suspend)
-			amdgpu_inc_vram_lost(adev);
 		ret = nv_asic_mode1_reset(adev);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index ebfd2cdf4e65..d2840c2f6286 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -382,6 +382,18 @@ static void sdma_v5_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 	uint64_t csa_mc_addr = amdgpu_sdma_get_csa_mc_addr(ring, vmid);
 
+	/* Invalidate L2, because if we don't do it, we might get stale cache
+	 * lines from previous IBs.
+	 */
+	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_GCR_REQ));
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, (SDMA_GCR_GL2_INV |
+				 SDMA_GCR_GL2_WB |
+				 SDMA_GCR_GLM_INV |
+				 SDMA_GCR_GLM_WB) << 16);
+	amdgpu_ring_write(ring, 0xffffff80);
+	amdgpu_ring_write(ring, 0xffff);
+
 	/* An IB packet must end on a 8 DW boundary--the next dword
 	 * must be on a 8-dword boundary. Our IB packet below is 6
 	 * dwords long, thus add x number of NOPs, such that, in
@@ -1595,7 +1607,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = {
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 * 2 +
 		10 + 10 + 10, /* sdma_v5_0_ring_emit_fence x3 for user fence, vm fence */
-	.emit_ib_size = 7 + 6, /* sdma_v5_0_ring_emit_ib */
+	.emit_ib_size = 5 + 7 + 6, /* sdma_v5_0_ring_emit_ib */
 	.emit_ib = sdma_v5_0_ring_emit_ib,
 	.emit_fence = sdma_v5_0_ring_emit_fence,
 	.emit_pipeline_sync = sdma_v5_0_ring_emit_pipeline_sync,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index a40499d51c93..d42a8d8a0dea 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -569,14 +569,10 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 
 	switch (soc15_asic_reset_method(adev)) {
 		case AMD_RESET_METHOD_BACO:
-			if (!adev->in_suspend)
-				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_baco_reset(adev);
 		case AMD_RESET_METHOD_MODE2:
 			return amdgpu_dpm_mode2_reset(adev);
 		default:
-			if (!adev->in_suspend)
-				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_mode1_reset(adev);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 78b35901643b..3ce10e05d0d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -765,8 +765,6 @@ static int vi_asic_reset(struct amdgpu_device *adev)
 	int r;
 
 	if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
-		if (!adev->in_suspend)
-			amdgpu_inc_vram_lost(adev);
 		r = amdgpu_dpm_baco_reset(adev);
 	} else {
 		r = vi_asic_pci_config_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 4a3049841086..c24cad3c64ed 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1050,7 +1050,7 @@ void kfd_dec_compute_active(struct kfd_dev *dev);
 /* Check with device cgroup if @kfd device is accessible */
 static inline int kfd_devcgroup_check_permission(struct kfd_dev *kfd)
 {
-#if defined(CONFIG_CGROUP_DEVICE)
+#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
 	struct drm_device *ddev = kfd->ddev;
 
 	return devcgroup_check_permission(DEVCG_DEV_CHAR, ddev->driver->major,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index f7c5cdc10a70..7fc15b82fe48 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -441,7 +441,7 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 
 /**
  * dm_crtc_high_irq() - Handles CRTC interrupt
- * @interrupt_params: ignored
+ * @interrupt_params: used for determining the CRTC instance
  *
  * Handles the CRTC/VSYNC interrupt by notfying DRM's VBLANK
  * event handler.
@@ -455,70 +455,6 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	unsigned long flags;
 
 	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
-
-	if (acrtc) {
-		acrtc_state = to_dm_crtc_state(acrtc->base.state);
-
-		DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n",
-			      acrtc->crtc_id,
-			      amdgpu_dm_vrr_active(acrtc_state));
-
-		/* Core vblank handling at start of front-porch is only possible
-		 * in non-vrr mode, as only there vblank timestamping will give
-		 * valid results while done in front-porch. Otherwise defer it
-		 * to dm_vupdate_high_irq after end of front-porch.
-		 */
-		if (!amdgpu_dm_vrr_active(acrtc_state))
-			drm_crtc_handle_vblank(&acrtc->base);
-
-		/* Following stuff must happen at start of vblank, for crc
-		 * computation and below-the-range btr support in vrr mode.
-		 */
-		amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
-
-		if (acrtc_state->stream && adev->family >= AMDGPU_FAMILY_AI &&
-		    acrtc_state->vrr_params.supported &&
-		    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
-			spin_lock_irqsave(&adev->ddev->event_lock, flags);
-			mod_freesync_handle_v_update(
-				adev->dm.freesync_module,
-				acrtc_state->stream,
-				&acrtc_state->vrr_params);
-
-			dc_stream_adjust_vmin_vmax(
-				adev->dm.dc,
-				acrtc_state->stream,
-				&acrtc_state->vrr_params.adjust);
-			spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
-		}
-	}
-}
-
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-/**
- * dm_dcn_crtc_high_irq() - Handles VStartup interrupt for DCN generation ASICs
- * @interrupt params - interrupt parameters
- *
- * Notify DRM's vblank event handler at VSTARTUP
- *
- * Unlike DCE hardware, we trigger the handler at VSTARTUP. at which:
- * * We are close enough to VUPDATE - the point of no return for hw
- * * We are in the fixed portion of variable front porch when vrr is enabled
- * * We are before VUPDATE, where double-buffered vrr registers are swapped
- *
- * It is therefore the correct place to signal vblank, send user flip events,
- * and update VRR.
- */
-static void dm_dcn_crtc_high_irq(void *interrupt_params)
-{
-	struct common_irq_params *irq_params = interrupt_params;
-	struct amdgpu_device *adev = irq_params->adev;
-	struct amdgpu_crtc *acrtc;
-	struct dm_crtc_state *acrtc_state;
-	unsigned long flags;
-
-	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
-
 	if (!acrtc)
 		return;
 
@@ -528,22 +464,35 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params)
 			 amdgpu_dm_vrr_active(acrtc_state),
 			 acrtc_state->active_planes);
 
+	/**
+	 * Core vblank handling at start of front-porch is only possible
+	 * in non-vrr mode, as only there vblank timestamping will give
+	 * valid results while done in front-porch. Otherwise defer it
+	 * to dm_vupdate_high_irq after end of front-porch.
+	 */
+	if (!amdgpu_dm_vrr_active(acrtc_state))
+		drm_crtc_handle_vblank(&acrtc->base);
+
+	/**
+	 * Following stuff must happen at start of vblank, for crc
+	 * computation and below-the-range btr support in vrr mode.
+	 */
 	amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
-	drm_crtc_handle_vblank(&acrtc->base);
+
+	/* BTR updates need to happen before VUPDATE on Vega and above. */
+	if (adev->family < AMDGPU_FAMILY_AI)
+		return;
 
 	spin_lock_irqsave(&adev->ddev->event_lock, flags);
 
-	if (acrtc_state->vrr_params.supported &&
+	if (acrtc_state->stream && acrtc_state->vrr_params.supported &&
 	    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
-		mod_freesync_handle_v_update(
-		adev->dm.freesync_module,
-		acrtc_state->stream,
-		&acrtc_state->vrr_params);
+		mod_freesync_handle_v_update(adev->dm.freesync_module,
+					     acrtc_state->stream,
+					     &acrtc_state->vrr_params);
 
-		dc_stream_adjust_vmin_vmax(
-			adev->dm.dc,
-			acrtc_state->stream,
-			&acrtc_state->vrr_params.adjust);
+		dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc_state->stream,
+					   &acrtc_state->vrr_params.adjust);
 	}
 
 	/*
@@ -556,7 +505,8 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params)
 	 * avoid race conditions between flip programming and completion,
 	 * which could cause too early flip completion events.
 	 */
-	if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED &&
+	if (adev->family >= AMDGPU_FAMILY_RV &&
+	    acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED &&
 	    acrtc_state->active_planes == 0) {
 		if (acrtc->event) {
 			drm_crtc_send_vblank_event(&acrtc->base, acrtc->event);
@@ -568,7 +518,6 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params)
 
 	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
 }
-#endif
 
 static int dm_set_clockgating_state(void *handle,
 		  enum amd_clockgating_state state)
@@ -2008,17 +1957,22 @@ void amdgpu_dm_update_connector_after_detect(
 		dc_sink_retain(aconnector->dc_sink);
 		if (sink->dc_edid.length == 0) {
 			aconnector->edid = NULL;
-			drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux);
+			if (aconnector->dc_link->aux_mode) {
+				drm_dp_cec_unset_edid(
+					&aconnector->dm_dp_aux.aux);
+			}
 		} else {
 			aconnector->edid =
-				(struct edid *) sink->dc_edid.raw_edid;
-
+				(struct edid *)sink->dc_edid.raw_edid;
 
 			drm_connector_update_edid_property(connector,
-					aconnector->edid);
-			drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
-					    aconnector->edid);
+							   aconnector->edid);
+
+			if (aconnector->dc_link->aux_mode)
+				drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
+						    aconnector->edid);
 		}
+
 		amdgpu_dm_update_freesync_caps(connector, aconnector->edid);
 		update_connector_ext_caps(aconnector);
 	} else {
@@ -2440,8 +2394,36 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 		c_irq_params->adev = adev;
 		c_irq_params->irq_src = int_params.irq_source;
 
+		amdgpu_dm_irq_register_interrupt(
+			adev, &int_params, dm_crtc_high_irq, c_irq_params);
+	}
+
+	/* Use VUPDATE_NO_LOCK interrupt on DCN, which seems to correspond to
+	 * the regular VUPDATE interrupt on DCE. We want DC_IRQ_SOURCE_VUPDATEx
+	 * to trigger at end of each vblank, regardless of state of the lock,
+	 * matching DCE behaviour.
+	 */
+	for (i = DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT;
+	     i <= DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT + adev->mode_info.num_crtc - 1;
+	     i++) {
+		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->vupdate_irq);
+
+		if (r) {
+			DRM_ERROR("Failed to add vupdate irq id!\n");
+			return r;
+		}
+
+		int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT;
+		int_params.irq_source =
+			dc_interrupt_to_irq_source(dc, i, 0);
+
+		c_irq_params = &adev->dm.vupdate_params[int_params.irq_source - DC_IRQ_SOURCE_VUPDATE1];
+
+		c_irq_params->adev = adev;
+		c_irq_params->irq_src = int_params.irq_source;
+
 		amdgpu_dm_irq_register_interrupt(adev, &int_params,
-				dm_dcn_crtc_high_irq, c_irq_params);
+				dm_vupdate_high_irq, c_irq_params);
 	}
 
 	/* Use GRPH_PFLIP interrupt */
@@ -3340,7 +3322,8 @@ fill_plane_dcc_attributes(struct amdgpu_device *adev,
 			  const union dc_tiling_info *tiling_info,
 			  const uint64_t info,
 			  struct dc_plane_dcc_param *dcc,
-			  struct dc_plane_address *address)
+			  struct dc_plane_address *address,
+			  bool force_disable_dcc)
 {
 	struct dc *dc = adev->dm.dc;
 	struct dc_dcc_surface_param input;
@@ -3352,6 +3335,9 @@ fill_plane_dcc_attributes(struct amdgpu_device *adev,
 	memset(&input, 0, sizeof(input));
 	memset(&output, 0, sizeof(output));
 
+	if (force_disable_dcc)
+		return 0;
+
 	if (!offset)
 		return 0;
 
@@ -3401,7 +3387,8 @@ fill_plane_buffer_attributes(struct amdgpu_device *adev,
 			     union dc_tiling_info *tiling_info,
 			     struct plane_size *plane_size,
 			     struct dc_plane_dcc_param *dcc,
-			     struct dc_plane_address *address)
+			     struct dc_plane_address *address,
+			     bool force_disable_dcc)
 {
 	const struct drm_framebuffer *fb = &afb->base;
 	int ret;
@@ -3507,7 +3494,8 @@ fill_plane_buffer_attributes(struct amdgpu_device *adev,
 
 		ret = fill_plane_dcc_attributes(adev, afb, format, rotation,
 						plane_size, tiling_info,
-						tiling_flags, dcc, address);
+						tiling_flags, dcc, address,
+						force_disable_dcc);
 		if (ret)
 			return ret;
 	}
@@ -3599,7 +3587,8 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev,
 			    const struct drm_plane_state *plane_state,
 			    const uint64_t tiling_flags,
 			    struct dc_plane_info *plane_info,
-			    struct dc_plane_address *address)
+			    struct dc_plane_address *address,
+			    bool force_disable_dcc)
 {
 	const struct drm_framebuffer *fb = plane_state->fb;
 	const struct amdgpu_framebuffer *afb =
@@ -3681,7 +3670,8 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev,
 					   plane_info->rotation, tiling_flags,
 					   &plane_info->tiling_info,
 					   &plane_info->plane_size,
-					   &plane_info->dcc, address);
+					   &plane_info->dcc, address,
+					   force_disable_dcc);
 	if (ret)
 		return ret;
 
@@ -3704,6 +3694,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	struct dc_plane_info plane_info;
 	uint64_t tiling_flags;
 	int ret;
+	bool force_disable_dcc = false;
 
 	ret = fill_dc_scaling_info(plane_state, &scaling_info);
 	if (ret)
@@ -3718,9 +3709,11 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev,
 	if (ret)
 		return ret;
 
+	force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend;
 	ret = fill_dc_plane_info_and_addr(adev, plane_state, tiling_flags,
 					  &plane_info,
-					  &dc_plane_state->address);
+					  &dc_plane_state->address,
+					  force_disable_dcc);
 	if (ret)
 		return ret;
 
@@ -4437,10 +4430,6 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
 	struct amdgpu_device *adev = crtc->dev->dev_private;
 	int rc;
 
-	/* Do not set vupdate for DCN hardware */
-	if (adev->family > AMDGPU_FAMILY_AI)
-		return 0;
-
 	irq_source = IRQ_TYPE_VUPDATE + acrtc->otg_inst;
 
 	rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY;
@@ -4664,6 +4653,7 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector)
 		i2c_del_adapter(&aconnector->i2c->base);
 		kfree(aconnector->i2c);
 	}
+	kfree(aconnector->dm_dp_aux.aux.name);
 
 	kfree(connector);
 }
@@ -4723,10 +4713,19 @@ amdgpu_dm_connector_atomic_duplicate_state(struct drm_connector *connector)
 static int
 amdgpu_dm_connector_late_register(struct drm_connector *connector)
 {
-#if defined(CONFIG_DEBUG_FS)
 	struct amdgpu_dm_connector *amdgpu_dm_connector =
 		to_amdgpu_dm_connector(connector);
+	int r;
 
+	if ((connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) ||
+	    (connector->connector_type == DRM_MODE_CONNECTOR_eDP)) {
+		amdgpu_dm_connector->dm_dp_aux.aux.dev = connector->kdev;
+		r = drm_dp_aux_register(&amdgpu_dm_connector->dm_dp_aux.aux);
+		if (r)
+			return r;
+	}
+
+#if defined(CONFIG_DEBUG_FS)
 	connector_debugfs_init(amdgpu_dm_connector);
 #endif
 
@@ -5332,6 +5331,7 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 	uint64_t tiling_flags;
 	uint32_t domain;
 	int r;
+	bool force_disable_dcc = false;
 
 	dm_plane_state_old = to_dm_plane_state(plane->state);
 	dm_plane_state_new = to_dm_plane_state(new_state);
@@ -5390,11 +5390,13 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 			dm_plane_state_old->dc_state != dm_plane_state_new->dc_state) {
 		struct dc_plane_state *plane_state = dm_plane_state_new->dc_state;
 
+		force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend;
 		fill_plane_buffer_attributes(
 			adev, afb, plane_state->format, plane_state->rotation,
 			tiling_flags, &plane_state->tiling_info,
 			&plane_state->plane_size, &plane_state->dcc,
-			&plane_state->address);
+			&plane_state->address,
+			force_disable_dcc);
 	}
 
 	return 0;
@@ -6092,7 +6094,7 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm,
 
 	if (connector_type == DRM_MODE_CONNECTOR_DisplayPort
 		|| connector_type == DRM_MODE_CONNECTOR_eDP)
-		amdgpu_dm_initialize_dp_connector(dm, aconnector);
+		amdgpu_dm_initialize_dp_connector(dm, aconnector, link->link_index);
 
 out_free:
 	if (res) {
@@ -6666,7 +6668,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		fill_dc_plane_info_and_addr(
 			dm->adev, new_plane_state, tiling_flags,
 			&bundle->plane_infos[planes_count],
-			&bundle->flip_addrs[planes_count].address);
+			&bundle->flip_addrs[planes_count].address,
+			false);
+
+		DRM_DEBUG_DRIVER("plane: id=%d dcc_en=%d\n",
+				 new_plane_state->plane->index,
+				 bundle->plane_infos[planes_count].dcc.enable);
 
 		bundle->surface_updates[planes_count].plane_info =
 			&bundle->plane_infos[planes_count];
@@ -7848,6 +7855,7 @@ static int dm_update_plane_state(struct dc *dc,
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct dm_crtc_state *dm_new_crtc_state, *dm_old_crtc_state;
 	struct dm_plane_state *dm_new_plane_state, *dm_old_plane_state;
+	struct amdgpu_crtc *new_acrtc;
 	bool needs_reset;
 	int ret = 0;
 
@@ -7857,9 +7865,23 @@ static int dm_update_plane_state(struct dc *dc,
 	dm_new_plane_state = to_dm_plane_state(new_plane_state);
 	dm_old_plane_state = to_dm_plane_state(old_plane_state);
 
-	/*TODO Implement atomic check for cursor plane */
-	if (plane->type == DRM_PLANE_TYPE_CURSOR)
+	/*TODO Implement better atomic check for cursor plane */
+	if (plane->type == DRM_PLANE_TYPE_CURSOR) {
+		if (!enable || !new_plane_crtc ||
+			drm_atomic_plane_disabling(plane->state, new_plane_state))
+			return 0;
+
+		new_acrtc = to_amdgpu_crtc(new_plane_crtc);
+
+		if ((new_plane_state->crtc_w > new_acrtc->max_cursor_width) ||
+			(new_plane_state->crtc_h > new_acrtc->max_cursor_height)) {
+			DRM_DEBUG_ATOMIC("Bad cursor size %d x %d\n",
+							 new_plane_state->crtc_w, new_plane_state->crtc_h);
+			return -EINVAL;
+		}
+
 		return 0;
+	}
 
 	needs_reset = should_reset_plane(state, plane, old_plane_state,
 					 new_plane_state);
@@ -8086,7 +8108,8 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm,
 				ret = fill_dc_plane_info_and_addr(
 					dm->adev, new_plane_state, tiling_flags,
 					plane_info,
-					&flip_addr->address);
+					&flip_addr->address,
+					false);
 				if (ret)
 					goto cleanup;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 78e1c11d4ae5..dcf84a61de37 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -398,15 +398,15 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	struct mod_hdcp_display *display = &hdcp_work[link_index].display;
 	struct mod_hdcp_link *link = &hdcp_work[link_index].link;
 
-	memset(display, 0, sizeof(*display));
-	memset(link, 0, sizeof(*link));
-
-	display->index = aconnector->base.index;
-
 	if (config->dpms_off) {
 		hdcp_remove_display(hdcp_work, link_index, aconnector);
 		return;
 	}
+
+	memset(display, 0, sizeof(*display));
+	memset(link, 0, sizeof(*link));
+
+	display->index = aconnector->base.index;
 	display->state = MOD_HDCP_DISPLAY_ACTIVE;
 
 	if (aconnector->dc_sink != NULL)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index fabbe78d5aef..d2917759b7ab 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -156,16 +156,16 @@ amdgpu_dm_mst_connector_late_register(struct drm_connector *connector)
 		to_amdgpu_dm_connector(connector);
 	int r;
 
-	amdgpu_dm_connector->dm_dp_aux.aux.dev = connector->kdev;
-	r = drm_dp_aux_register(&amdgpu_dm_connector->dm_dp_aux.aux);
-	if (r)
+	r = drm_dp_mst_connector_late_register(connector,
+					       amdgpu_dm_connector->port);
+	if (r < 0)
 		return r;
 
 #if defined(CONFIG_DEBUG_FS)
 	connector_debugfs_init(amdgpu_dm_connector);
 #endif
 
-	return r;
+	return 0;
 }
 
 static void
@@ -472,9 +472,12 @@ static const struct drm_dp_mst_topology_cbs dm_mst_cbs = {
 };
 
 void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
-				       struct amdgpu_dm_connector *aconnector)
+				       struct amdgpu_dm_connector *aconnector,
+				       int link_index)
 {
-	aconnector->dm_dp_aux.aux.name = "dmdc";
+	aconnector->dm_dp_aux.aux.name =
+		kasprintf(GFP_KERNEL, "AMDGPU DM aux hw bus %d",
+			  link_index);
 	aconnector->dm_dp_aux.aux.transfer = dm_dp_aux_transfer;
 	aconnector->dm_dp_aux.ddc_service = aconnector->dc_link->ddc;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index d6813ce67bbd..d2c56579a2cc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -32,7 +32,8 @@ struct amdgpu_dm_connector;
 int dm_mst_get_pbn_divider(struct dc_link *link);
 
 void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
-				       struct amdgpu_dm_connector *aconnector);
+				       struct amdgpu_dm_connector *aconnector,
+				       int link_index);
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 8489f1e56892..47431ca6986d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -834,11 +834,10 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context)
 {
 	int i;
-	int count = 0;
-	struct pipe_ctx *pipe;
 	PERF_TRACE();
 	for (i = 0; i < MAX_PIPES; i++) {
-		pipe = &context->res_ctx.pipe_ctx[i];
+		int count = 0;
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 
 		if (!pipe->plane_state)
 			continue;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 7cbb1efb4f68..caa090d0b6ac 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -220,6 +220,30 @@ static enum dpcd_training_patterns
 	return dpcd_tr_pattern;
 }
 
+static uint8_t dc_dp_initialize_scrambling_data_symbols(
+	struct dc_link *link,
+	enum dc_dp_training_pattern pattern)
+{
+	uint8_t disable_scrabled_data_symbols = 0;
+
+	switch (pattern) {
+	case DP_TRAINING_PATTERN_SEQUENCE_1:
+	case DP_TRAINING_PATTERN_SEQUENCE_2:
+	case DP_TRAINING_PATTERN_SEQUENCE_3:
+		disable_scrabled_data_symbols = 1;
+		break;
+	case DP_TRAINING_PATTERN_SEQUENCE_4:
+		disable_scrabled_data_symbols = 0;
+		break;
+	default:
+		ASSERT(0);
+		DC_LOG_HW_LINK_TRAINING("%s: Invalid HW Training pattern: %d\n",
+			__func__, pattern);
+		break;
+	}
+	return disable_scrabled_data_symbols;
+}
+
 static inline bool is_repeater(struct dc_link *link, uint32_t offset)
 {
 	return (!link->is_lttpr_mode_transparent && offset != 0);
@@ -252,6 +276,9 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 	dpcd_pattern.v1_4.TRAINING_PATTERN_SET =
 		dc_dp_training_pattern_to_dpcd_training_pattern(link, pattern);
 
+	dpcd_pattern.v1_4.SCRAMBLING_DISABLE =
+		dc_dp_initialize_scrambling_data_symbols(link, pattern);
+
 	dpcd_lt_buffer[DP_TRAINING_PATTERN_SET - DP_TRAINING_PATTERN_SET]
 		= dpcd_pattern.raw;
 
@@ -2911,6 +2938,12 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 		for (i = 0; i < MAX_PIPES; i++) {
 			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
 			if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link)
+				link->dc->hwss.blank_stream(pipe_ctx);
+		}
+
+		for (i = 0; i < MAX_PIPES; i++) {
+			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+			if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link)
 				break;
 		}
 
@@ -2927,6 +2960,12 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 		if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 			dc_link_reallocate_mst_payload(link);
 
+		for (i = 0; i < MAX_PIPES; i++) {
+			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+			if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link)
+				link->dc->hwss.unblank_stream(pipe_ctx, &previous_link_settings);
+		}
+
 		status = false;
 		if (out_link_loss)
 			*out_link_loss = true;
@@ -4227,6 +4266,21 @@ void dp_set_fec_enable(struct dc_link *link, bool enable)
 void dpcd_set_source_specific_data(struct dc_link *link)
 {
 	const uint32_t post_oui_delay = 30; // 30ms
+	uint8_t dspc = 0;
+	enum dc_status ret = DC_ERROR_UNEXPECTED;
+
+	ret = core_link_read_dpcd(link, DP_DOWN_STREAM_PORT_COUNT, &dspc,
+				  sizeof(dspc));
+
+	if (ret != DC_OK) {
+		DC_LOG_ERROR("Error in DP aux read transaction,"
+			     " not writing source specific data\n");
+		return;
+	}
+
+	/* Return if OUI unsupported */
+	if (!(dspc & DP_OUI_SUPPORT))
+		return;
 
 	if (!link->dc->vendor_signature.is_valid) {
 		struct dpcd_amd_signature amd_signature;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 6ddbb00ed37a..4f0e7203dba4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -231,34 +231,6 @@ struct dc_stream_status *dc_stream_get_status(
 	return dc_stream_get_status_from_state(dc->current_state, stream);
 }
 
-static void delay_cursor_until_vupdate(struct pipe_ctx *pipe_ctx, struct dc *dc)
-{
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-	unsigned int vupdate_line;
-	unsigned int lines_to_vupdate, us_to_vupdate, vpos, nvpos;
-	struct dc_stream_state *stream = pipe_ctx->stream;
-	unsigned int us_per_line;
-
-	if (stream->ctx->asic_id.chip_family == FAMILY_RV &&
-			ASICREV_IS_RAVEN(stream->ctx->asic_id.hw_internal_rev)) {
-
-		vupdate_line = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx);
-		if (!dc_stream_get_crtc_position(dc, &stream, 1, &vpos, &nvpos))
-			return;
-
-		if (vpos >= vupdate_line)
-			return;
-
-		us_per_line = stream->timing.h_total * 10000 / stream->timing.pix_clk_100hz;
-		lines_to_vupdate = vupdate_line - vpos;
-		us_to_vupdate = lines_to_vupdate * us_per_line;
-
-		/* 70 us is a conservative estimate of cursor update time*/
-		if (us_to_vupdate < 70)
-			udelay(us_to_vupdate);
-	}
-#endif
-}
 
 /**
  * dc_stream_set_cursor_attributes() - Update cursor attributes and set cursor surface address
@@ -298,9 +270,7 @@ bool dc_stream_set_cursor_attributes(
 
 		if (!pipe_to_program) {
 			pipe_to_program = pipe_ctx;
-
-			delay_cursor_until_vupdate(pipe_ctx, dc);
-			dc->hwss.pipe_control_lock(dc, pipe_to_program, true);
+			dc->hwss.cursor_lock(dc, pipe_to_program, true);
 		}
 
 		dc->hwss.set_cursor_attribute(pipe_ctx);
@@ -309,7 +279,7 @@ bool dc_stream_set_cursor_attributes(
 	}
 
 	if (pipe_to_program)
-		dc->hwss.pipe_control_lock(dc, pipe_to_program, false);
+		dc->hwss.cursor_lock(dc, pipe_to_program, false);
 
 	return true;
 }
@@ -349,16 +319,14 @@ bool dc_stream_set_cursor_position(
 
 		if (!pipe_to_program) {
 			pipe_to_program = pipe_ctx;
-
-			delay_cursor_until_vupdate(pipe_ctx, dc);
-			dc->hwss.pipe_control_lock(dc, pipe_to_program, true);
+			dc->hwss.cursor_lock(dc, pipe_to_program, true);
 		}
 
 		dc->hwss.set_cursor_position(pipe_ctx);
 	}
 
 	if (pipe_to_program)
-		dc->hwss.pipe_control_lock(dc, pipe_to_program, false);
+		dc->hwss.cursor_lock(dc, pipe_to_program, false);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index c279982947e1..10527593868c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -2757,6 +2757,7 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.disable_plane = dce110_power_down_fe,
 	.pipe_control_lock = dce_pipe_control_lock,
 	.interdependent_update_lock = NULL,
+	.cursor_lock = dce_pipe_control_lock,
 	.prepare_bandwidth = dce110_prepare_bandwidth,
 	.optimize_bandwidth = dce110_optimize_bandwidth,
 	.set_drr = set_drr,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index b0357546471b..416afb99529d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1625,6 +1625,85 @@ void dcn10_pipe_control_lock(
 		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
+/**
+ * delay_cursor_until_vupdate() - Delay cursor update if too close to VUPDATE.
+ *
+ * Software keepout workaround to prevent cursor update locking from stalling
+ * out cursor updates indefinitely or from old values from being retained in
+ * the case where the viewport changes in the same frame as the cursor.
+ *
+ * The idea is to calculate the remaining time from VPOS to VUPDATE. If it's
+ * too close to VUPDATE, then stall out until VUPDATE finishes.
+ *
+ * TODO: Optimize cursor programming to be once per frame before VUPDATE
+ *       to avoid the need for this workaround.
+ */
+static void delay_cursor_until_vupdate(struct dc *dc, struct pipe_ctx *pipe_ctx)
+{
+	struct dc_stream_state *stream = pipe_ctx->stream;
+	struct crtc_position position;
+	uint32_t vupdate_start, vupdate_end;
+	unsigned int lines_to_vupdate, us_to_vupdate, vpos;
+	unsigned int us_per_line, us_vupdate;
+
+	if (!dc->hwss.calc_vupdate_position || !dc->hwss.get_position)
+		return;
+
+	if (!pipe_ctx->stream_res.stream_enc || !pipe_ctx->stream_res.tg)
+		return;
+
+	dc->hwss.calc_vupdate_position(dc, pipe_ctx, &vupdate_start,
+				       &vupdate_end);
+
+	dc->hwss.get_position(&pipe_ctx, 1, &position);
+	vpos = position.vertical_count;
+
+	/* Avoid wraparound calculation issues */
+	vupdate_start += stream->timing.v_total;
+	vupdate_end += stream->timing.v_total;
+	vpos += stream->timing.v_total;
+
+	if (vpos <= vupdate_start) {
+		/* VPOS is in VACTIVE or back porch. */
+		lines_to_vupdate = vupdate_start - vpos;
+	} else if (vpos > vupdate_end) {
+		/* VPOS is in the front porch. */
+		return;
+	} else {
+		/* VPOS is in VUPDATE. */
+		lines_to_vupdate = 0;
+	}
+
+	/* Calculate time until VUPDATE in microseconds. */
+	us_per_line =
+		stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz;
+	us_to_vupdate = lines_to_vupdate * us_per_line;
+
+	/* 70 us is a conservative estimate of cursor update time*/
+	if (us_to_vupdate > 70)
+		return;
+
+	/* Stall out until the cursor update completes. */
+	if (vupdate_end < vupdate_start)
+		vupdate_end += stream->timing.v_total;
+	us_vupdate = (vupdate_end - vupdate_start + 1) * us_per_line;
+	udelay(us_to_vupdate + us_vupdate);
+}
+
+void dcn10_cursor_lock(struct dc *dc, struct pipe_ctx *pipe, bool lock)
+{
+	/* cursor lock is per MPCC tree, so only need to lock one pipe per stream */
+	if (!pipe || pipe->top_pipe)
+		return;
+
+	/* Prevent cursor lock from stalling out cursor updates. */
+	if (lock)
+		delay_cursor_until_vupdate(dc, pipe);
+
+	dc->res_pool->mpc->funcs->cursor_lock(dc->res_pool->mpc,
+			pipe->stream_res.opp->inst, lock);
+}
+
 static bool wait_for_reset_trigger_to_occur(
 	struct dc_context *dc_ctx,
 	struct timing_generator *tg)
@@ -3226,7 +3305,7 @@ int dcn10_get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx)
 	return vertical_line_start;
 }
 
-static void dcn10_calc_vupdate_position(
+void dcn10_calc_vupdate_position(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		uint32_t *start_line,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
index 16a50e05ffbf..42b6e016d71e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
@@ -34,6 +34,11 @@ struct dc;
 void dcn10_hw_sequencer_construct(struct dc *dc);
 
 int dcn10_get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx);
+void dcn10_calc_vupdate_position(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		uint32_t *start_line,
+		uint32_t *end_line);
 void dcn10_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
 enum dc_status dcn10_enable_stream_timing(
 		struct pipe_ctx *pipe_ctx,
@@ -49,6 +54,7 @@ void dcn10_pipe_control_lock(
 	struct dc *dc,
 	struct pipe_ctx *pipe,
 	bool lock);
+void dcn10_cursor_lock(struct dc *dc, struct pipe_ctx *pipe, bool lock);
 void dcn10_blank_pixel_data(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
index dd02d3983695..9e8e32629e47 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
@@ -50,6 +50,7 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.disable_audio_stream = dce110_disable_audio_stream,
 	.disable_plane = dcn10_disable_plane,
 	.pipe_control_lock = dcn10_pipe_control_lock,
+	.cursor_lock = dcn10_cursor_lock,
 	.interdependent_update_lock = dcn10_lock_all_pipes,
 	.prepare_bandwidth = dcn10_prepare_bandwidth,
 	.optimize_bandwidth = dcn10_optimize_bandwidth,
@@ -71,6 +72,7 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.set_clock = dcn10_set_clock,
 	.get_clock = dcn10_get_clock,
 	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
+	.calc_vupdate_position = dcn10_calc_vupdate_position,
 };
 
 static const struct hwseq_private_funcs dcn10_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 04f863499cfb..3fcd408e9103 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -223,6 +223,9 @@ struct mpcc *mpc1_insert_plane(
 	REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, dpp_id);
 	REG_SET(MPCC_OPP_ID[mpcc_id], 0, MPCC_OPP_ID, tree->opp_id);
 
+	/* Configure VUPDATE lock set for this MPCC to map to the OPP */
+	REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, tree->opp_id);
+
 	/* update mpc tree mux setting */
 	if (tree->opp_list == insert_above_mpcc) {
 		/* insert the toppest mpcc */
@@ -318,6 +321,7 @@ void mpc1_remove_mpcc(
 		REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
 		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
 		REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
+		REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf);
 
 		/* mark this mpcc as not in use */
 		mpc10->mpcc_in_use_mask &= ~(1 << mpcc_id);
@@ -328,6 +332,7 @@ void mpc1_remove_mpcc(
 		REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
 		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
 		REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
+		REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf);
 	}
 }
 
@@ -361,6 +366,7 @@ void mpc1_mpc_init(struct mpc *mpc)
 		REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
 		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
 		REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
+		REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf);
 
 		mpc1_init_mpcc(&(mpc->mpcc_array[mpcc_id]), mpcc_id);
 	}
@@ -381,6 +387,7 @@ void mpc1_mpc_init_single_inst(struct mpc *mpc, unsigned int mpcc_id)
 	REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
 	REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
 	REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
+	REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf);
 
 	mpc1_init_mpcc(&(mpc->mpcc_array[mpcc_id]), mpcc_id);
 
@@ -453,6 +460,13 @@ void mpc1_read_mpcc_state(
 			MPCC_BUSY, &s->busy);
 }
 
+void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock)
+{
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+
+	REG_SET(CUR[opp_id], 0, CUR_VUPDATE_LOCK_SET, lock ? 1 : 0);
+}
+
 static const struct mpc_funcs dcn10_mpc_funcs = {
 	.read_mpcc_state = mpc1_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
@@ -464,6 +478,7 @@ static const struct mpc_funcs dcn10_mpc_funcs = {
 	.assert_mpcc_idle_before_connect = mpc1_assert_mpcc_idle_before_connect,
 	.init_mpcc_list_from_hw = mpc1_init_mpcc_list_from_hw,
 	.update_blending = mpc1_update_blending,
+	.cursor_lock = mpc1_cursor_lock,
 	.set_denorm = NULL,
 	.set_denorm_clamp = NULL,
 	.set_output_csc = NULL,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
index 962a68e322ee..66a4719c22a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
@@ -39,11 +39,12 @@
 	SRII(MPCC_BG_G_Y, MPCC, inst),\
 	SRII(MPCC_BG_R_CR, MPCC, inst),\
 	SRII(MPCC_BG_B_CB, MPCC, inst),\
-	SRII(MPCC_BG_B_CB, MPCC, inst),\
-	SRII(MPCC_SM_CONTROL, MPCC, inst)
+	SRII(MPCC_SM_CONTROL, MPCC, inst),\
+	SRII(MPCC_UPDATE_LOCK_SEL, MPCC, inst)
 
 #define MPC_OUT_MUX_COMMON_REG_LIST_DCN1_0(inst) \
-	SRII(MUX, MPC_OUT, inst)
+	SRII(MUX, MPC_OUT, inst),\
+	VUPDATE_SRII(CUR, VUPDATE_LOCK_SET, inst)
 
 #define MPC_COMMON_REG_VARIABLE_LIST \
 	uint32_t MPCC_TOP_SEL[MAX_MPCC]; \
@@ -55,7 +56,9 @@
 	uint32_t MPCC_BG_R_CR[MAX_MPCC]; \
 	uint32_t MPCC_BG_B_CB[MAX_MPCC]; \
 	uint32_t MPCC_SM_CONTROL[MAX_MPCC]; \
-	uint32_t MUX[MAX_OPP];
+	uint32_t MUX[MAX_OPP]; \
+	uint32_t MPCC_UPDATE_LOCK_SEL[MAX_MPCC]; \
+	uint32_t CUR[MAX_OPP];
 
 #define MPC_COMMON_MASK_SH_LIST_DCN1_0(mask_sh)\
 	SF(MPCC0_MPCC_TOP_SEL, MPCC_TOP_SEL, mask_sh),\
@@ -78,7 +81,8 @@
 	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FIELD_ALT, mask_sh),\
 	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FORCE_NEXT_FRAME_POL, mask_sh),\
 	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FORCE_NEXT_TOP_POL, mask_sh),\
-	SF(MPC_OUT0_MUX, MPC_OUT_MUX, mask_sh)
+	SF(MPC_OUT0_MUX, MPC_OUT_MUX, mask_sh),\
+	SF(MPCC0_MPCC_UPDATE_LOCK_SEL, MPCC_UPDATE_LOCK_SEL, mask_sh)
 
 #define MPC_REG_FIELD_LIST(type) \
 	type MPCC_TOP_SEL;\
@@ -101,7 +105,9 @@
 	type MPCC_SM_FIELD_ALT;\
 	type MPCC_SM_FORCE_NEXT_FRAME_POL;\
 	type MPCC_SM_FORCE_NEXT_TOP_POL;\
-	type MPC_OUT_MUX;
+	type MPC_OUT_MUX;\
+	type MPCC_UPDATE_LOCK_SEL;\
+	type CUR_VUPDATE_LOCK_SET;
 
 struct dcn_mpc_registers {
 	MPC_COMMON_REG_VARIABLE_LIST
@@ -192,4 +198,6 @@ void mpc1_read_mpcc_state(
 		int mpcc_inst,
 		struct mpcc_state *s);
 
+void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 07265ca7d28c..ba849aa31e6e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -181,6 +181,14 @@ enum dcn10_clk_src_array_id {
 	.reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \
 					mm ## block ## id ## _ ## reg_name
 
+#define VUPDATE_SRII(reg_name, block, id)\
+	.reg_name[id] = BASE(mm ## reg_name ## 0 ## _ ## block ## id ## _BASE_IDX) + \
+					mm ## reg_name ## 0 ## _ ## block ## id
+
+/* set field/register/bitfield name */
+#define SFRB(field_name, reg_name, bitfield, post_fix)\
+	.field_name = reg_name ## __ ## bitfield ## post_fix
+
 /* NBIO */
 #define NBIO_BASE_INNER(seg) \
 	NBIF_BASE__INST0_SEG ## seg
@@ -419,11 +427,13 @@ static const struct dcn_mpc_registers mpc_regs = {
 };
 
 static const struct dcn_mpc_shift mpc_shift = {
-	MPC_COMMON_MASK_SH_LIST_DCN1_0(__SHIFT)
+	MPC_COMMON_MASK_SH_LIST_DCN1_0(__SHIFT),\
+	SFRB(CUR_VUPDATE_LOCK_SET, CUR0_VUPDATE_LOCK_SET0, CUR0_VUPDATE_LOCK_SET, __SHIFT)
 };
 
 static const struct dcn_mpc_mask mpc_mask = {
-	MPC_COMMON_MASK_SH_LIST_DCN1_0(_MASK),
+	MPC_COMMON_MASK_SH_LIST_DCN1_0(_MASK),\
+	SFRB(CUR_VUPDATE_LOCK_SET, CUR0_VUPDATE_LOCK_SET0, CUR0_VUPDATE_LOCK_SET, _MASK)
 };
 
 #define tg_regs(id)\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 22f421e82733..a023a4d59f41 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -2294,7 +2294,8 @@ void dcn20_fpga_init_hw(struct dc *dc)
 
 	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, 2);
 	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, 1);
-	REG_WRITE(REFCLK_CNTL, 0);
+	if (REG(REFCLK_CNTL))
+		REG_WRITE(REFCLK_CNTL, 0);
 	//
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
index 1e73357eda34..8334bbd6eabb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
@@ -52,6 +52,7 @@ static const struct hw_sequencer_funcs dcn20_funcs = {
 	.disable_plane = dcn20_disable_plane,
 	.pipe_control_lock = dcn20_pipe_control_lock,
 	.interdependent_update_lock = dcn10_lock_all_pipes,
+	.cursor_lock = dcn10_cursor_lock,
 	.prepare_bandwidth = dcn20_prepare_bandwidth,
 	.optimize_bandwidth = dcn20_optimize_bandwidth,
 	.update_bandwidth = dcn20_update_bandwidth,
@@ -82,6 +83,7 @@ static const struct hw_sequencer_funcs dcn20_funcs = {
 	.init_vm_ctx = dcn20_init_vm_ctx,
 	.set_flip_control_gsl = dcn20_set_flip_control_gsl,
 	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
+	.calc_vupdate_position = dcn10_calc_vupdate_position,
 };
 
 static const struct hwseq_private_funcs dcn20_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
index de9c857ab3e9..570dfd9a243f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
@@ -545,6 +545,7 @@ const struct mpc_funcs dcn20_mpc_funcs = {
 	.mpc_init = mpc1_mpc_init,
 	.mpc_init_single_inst = mpc1_mpc_init_single_inst,
 	.update_blending = mpc2_update_blending,
+	.cursor_lock = mpc1_cursor_lock,
 	.get_mpcc_for_dpp = mpc2_get_mpcc_for_dpp,
 	.wait_for_idle = mpc2_assert_idle_mpcc,
 	.assert_mpcc_idle_before_connect = mpc2_assert_mpcc_idle_before_connect,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h
index c78fd5123497..496658f420db 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h
@@ -179,7 +179,8 @@
 	SF(MPC_OUT0_DENORM_CLAMP_G_Y, MPC_OUT_DENORM_CLAMP_MAX_G_Y, mask_sh),\
 	SF(MPC_OUT0_DENORM_CLAMP_G_Y, MPC_OUT_DENORM_CLAMP_MIN_G_Y, mask_sh),\
 	SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MAX_B_CB, mask_sh),\
-	SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MIN_B_CB, mask_sh)
+	SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MIN_B_CB, mask_sh),\
+	SF(CUR_VUPDATE_LOCK_SET0, CUR_VUPDATE_LOCK_SET, mask_sh)
 
 /*
  *	DCN2 MPC_OCSC debug status register:
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 5cdbba0cd873..e4348e3b6389 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -508,6 +508,10 @@ enum dcn20_clk_src_array_id {
 	.block ## _ ## reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \
 					mm ## block ## id ## _ ## reg_name
 
+#define VUPDATE_SRII(reg_name, block, id)\
+	.reg_name[id] = BASE(mm ## reg_name ## _ ## block ## id ## _BASE_IDX) + \
+					mm ## reg_name ## _ ## block ## id
+
 /* NBIO */
 #define NBIO_BASE_INNER(seg) \
 	NBIO_BASE__INST0_SEG ## seg
@@ -3064,25 +3068,32 @@ validate_out:
 	return out;
 }
 
-
-bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
-		bool fast_validate)
+/*
+ * This must be noinline to ensure anything that deals with FP registers
+ * is contained within this call; previously our compiling with hard-float
+ * would result in fp instructions being emitted outside of the boundaries
+ * of the DC_FP_START/END macros, which makes sense as the compiler has no
+ * idea about what is wrapped and what is not
+ *
+ * This is largely just a workaround to avoid breakage introduced with 5.6,
+ * ideally all fp-using code should be moved into its own file, only that
+ * should be compiled with hard-float, and all code exported from there
+ * should be strictly wrapped with DC_FP_START/END
+ */
+static noinline bool dcn20_validate_bandwidth_fp(struct dc *dc,
+		struct dc_state *context, bool fast_validate)
 {
 	bool voltage_supported = false;
 	bool full_pstate_supported = false;
 	bool dummy_pstate_supported = false;
 	double p_state_latency_us;
 
-	DC_FP_START();
 	p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
 	context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support =
 		dc->debug.disable_dram_clock_change_vactive_support;
 
 	if (fast_validate) {
-		voltage_supported = dcn20_validate_bandwidth_internal(dc, context, true);
-
-		DC_FP_END();
-		return voltage_supported;
+		return dcn20_validate_bandwidth_internal(dc, context, true);
 	}
 
 	// Best case, we support full UCLK switch latency
@@ -3111,7 +3122,15 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
 
 restore_dml_state:
 	context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us;
+	return voltage_supported;
+}
 
+bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
+		bool fast_validate)
+{
+	bool voltage_supported = false;
+	DC_FP_START();
+	voltage_supported = dcn20_validate_bandwidth_fp(dc, context, fast_validate);
 	DC_FP_END();
 	return voltage_supported;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
index b9ff9767e08f..4dd634118df2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
@@ -53,6 +53,7 @@ static const struct hw_sequencer_funcs dcn21_funcs = {
 	.disable_plane = dcn20_disable_plane,
 	.pipe_control_lock = dcn20_pipe_control_lock,
 	.interdependent_update_lock = dcn10_lock_all_pipes,
+	.cursor_lock = dcn10_cursor_lock,
 	.prepare_bandwidth = dcn20_prepare_bandwidth,
 	.optimize_bandwidth = dcn20_optimize_bandwidth,
 	.update_bandwidth = dcn20_update_bandwidth,
@@ -85,6 +86,7 @@ static const struct hw_sequencer_funcs dcn21_funcs = {
 	.optimize_pwr_state = dcn21_optimize_pwr_state,
 	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
 	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
+	.calc_vupdate_position = dcn10_calc_vupdate_position,
 	.set_cursor_position = dcn10_set_cursor_position,
 	.set_cursor_attribute = dcn10_set_cursor_attribute,
 	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index b25484aa8222..a721bb401ef0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -284,7 +284,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = {
 	.dram_channel_width_bytes = 4,
 	.fabric_datapath_to_dcn_data_return_bytes = 32,
 	.dcn_downspread_percent = 0.5,
-	.downspread_percent = 0.5,
+	.downspread_percent = 0.38,
 	.dram_page_open_time_ns = 50.0,
 	.dram_rw_turnaround_time_ns = 17.5,
 	.dram_return_buffer_per_channel_bytes = 8192,
@@ -340,6 +340,10 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = {
 	.block ## _ ## reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \
 					mm ## block ## id ## _ ## reg_name
 
+#define VUPDATE_SRII(reg_name, block, id)\
+	.reg_name[id] = BASE(mm ## reg_name ## _ ## block ## id ## _BASE_IDX) + \
+					mm ## reg_name ## _ ## block ## id
+
 /* NBIO */
 #define NBIO_BASE_INNER(seg) \
 	NBIF0_BASE__INST0_SEG ## seg
@@ -1374,64 +1378,49 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 {
 	struct dcn21_resource_pool *pool = TO_DCN21_RES_POOL(dc->res_pool);
 	struct clk_limit_table *clk_table = &bw_params->clk_table;
-	unsigned int i, j, k;
-	int closest_clk_lvl;
+	struct _vcs_dpi_voltage_scaling_st clock_limits[DC__VOLTAGE_STATES];
+	unsigned int i, j, closest_clk_lvl;
 
 	// Default clock levels are used for diags, which may lead to overclocking.
-	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) && !IS_DIAG_DC(dc->ctx->dce_environment)) {
+	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
 		dcn2_1_ip.max_num_otg = pool->base.res_cap->num_timing_generator;
 		dcn2_1_ip.max_num_dpp = pool->base.pipe_count;
 		dcn2_1_soc.num_chans = bw_params->num_channels;
 
-		/* Vmin: leave lowest DCN clocks, override with dcfclk, fclk, memclk from fuse */
-		dcn2_1_soc.clock_limits[0].state = 0;
-		dcn2_1_soc.clock_limits[0].dcfclk_mhz = clk_table->entries[0].dcfclk_mhz;
-		dcn2_1_soc.clock_limits[0].fabricclk_mhz = clk_table->entries[0].fclk_mhz;
-		dcn2_1_soc.clock_limits[0].socclk_mhz = clk_table->entries[0].socclk_mhz;
-		dcn2_1_soc.clock_limits[0].dram_speed_mts = clk_table->entries[0].memclk_mhz * 2;
-
-		/*
-		 * Other levels: find closest DCN clocks that fit the given clock limit using dcfclk
-		 * as indicator
-		 */
-
-		closest_clk_lvl = -1;
-		/* index currently being filled */
-		k = 1;
-		for (i = 1; i < clk_table->num_entries; i++) {
-			/* loop backwards, skip duplicate state*/
-			for (j = dcn2_1_soc.num_states - 1; j >= k; j--) {
+		ASSERT(clk_table->num_entries);
+		for (i = 0; i < clk_table->num_entries; i++) {
+			/* loop backwards*/
+			for (closest_clk_lvl = 0, j = dcn2_1_soc.num_states - 1; j >= 0; j--) {
 				if ((unsigned int) dcn2_1_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) {
 					closest_clk_lvl = j;
 					break;
 				}
 			}
 
-			/* if found a lvl that fits, use the DCN clks from it, if not, go to next clk limit*/
-			if (closest_clk_lvl != -1) {
-				dcn2_1_soc.clock_limits[k].state = i;
-				dcn2_1_soc.clock_limits[k].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
-				dcn2_1_soc.clock_limits[k].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
-				dcn2_1_soc.clock_limits[k].socclk_mhz = clk_table->entries[i].socclk_mhz;
-				dcn2_1_soc.clock_limits[k].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2;
-
-				dcn2_1_soc.clock_limits[k].dispclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
-				dcn2_1_soc.clock_limits[k].dppclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
-				dcn2_1_soc.clock_limits[k].dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
-				dcn2_1_soc.clock_limits[k].dscclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
-				dcn2_1_soc.clock_limits[k].dtbclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
-				dcn2_1_soc.clock_limits[k].phyclk_d18_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
-				dcn2_1_soc.clock_limits[k].phyclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
-				k++;
-			}
+			clock_limits[i].state = i;
+			clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
+			clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
+			clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
+			clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2;
+
+			clock_limits[i].dispclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
+			clock_limits[i].dppclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
+			clock_limits[i].dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
+			clock_limits[i].dscclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
+			clock_limits[i].dtbclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
+			clock_limits[i].phyclk_d18_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
+			clock_limits[i].phyclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
+		}
+		for (i = 0; i < clk_table->num_entries; i++)
+			dcn2_1_soc.clock_limits[i] = clock_limits[i];
+		if (clk_table->num_entries) {
+			dcn2_1_soc.num_states = clk_table->num_entries;
+			/* duplicate last level */
+			dcn2_1_soc.clock_limits[dcn2_1_soc.num_states] = dcn2_1_soc.clock_limits[dcn2_1_soc.num_states - 1];
+			dcn2_1_soc.clock_limits[dcn2_1_soc.num_states].state = dcn2_1_soc.num_states;
 		}
-		dcn2_1_soc.num_states = k;
 	}
 
-	/* duplicate last level */
-	dcn2_1_soc.clock_limits[dcn2_1_soc.num_states] = dcn2_1_soc.clock_limits[dcn2_1_soc.num_states - 1];
-	dcn2_1_soc.clock_limits[dcn2_1_soc.num_states].state = dcn2_1_soc.num_states;
-
 	dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 7ee8b8460a9b..e34c3376efc1 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -63,10 +63,8 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
 endif
 CFLAGS_$(AMDDALPATH)/dc/dml/dml1_display_rq_dlg_calc.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_rq_dlg_helpers.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dml_common_defs.o := $(dml_ccflags)
 
 DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \
-	dml_common_defs.o
 
 ifdef CONFIG_DRM_AMD_DC_DCN
 DML += display_mode_vba.o dcn20/display_rq_dlg_calc_20.o dcn20/display_mode_vba_20.o
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h
index 8c86b63ddf07..1e557ddcb638 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.h
@@ -26,7 +26,6 @@
 #ifndef __DML20_DISPLAY_RQ_DLG_CALC_H__
 #define __DML20_DISPLAY_RQ_DLG_CALC_H__
 
-#include "../dml_common_defs.h"
 #include "../display_rq_dlg_helpers.h"
 
 struct display_mode_lib;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h
index 0378406bf7e7..0d53e871a9d1 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.h
@@ -26,7 +26,6 @@
 #ifndef __DML20V2_DISPLAY_RQ_DLG_CALC_H__
 #define __DML20V2_DISPLAY_RQ_DLG_CALC_H__
 
-#include "../dml_common_defs.h"
 #include "../display_rq_dlg_helpers.h"
 
 struct display_mode_lib;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
index a38baa73d484..b8ec08e3b7a3 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
@@ -1200,7 +1200,7 @@ static void dml_rq_dlg_get_dlg_params(
 	min_hratio_fact_l = 1.0;
 	min_hratio_fact_c = 1.0;
 
-	if (htaps_l <= 1)
+	if (hratio_l <= 1)
 		min_hratio_fact_l = 2.0;
 	else if (htaps_l <= 6) {
 		if ((hratio_l * 2.0) > 4.0)
@@ -1216,7 +1216,7 @@ static void dml_rq_dlg_get_dlg_params(
 
 	hscale_pixel_rate_l = min_hratio_fact_l * dppclk_freq_in_mhz;
 
-	if (htaps_c <= 1)
+	if (hratio_c <= 1)
 		min_hratio_fact_c = 2.0;
 	else if (htaps_c <= 6) {
 		if ((hratio_c * 2.0) > 4.0)
@@ -1522,8 +1522,8 @@ static void dml_rq_dlg_get_dlg_params(
 
 	disp_dlg_regs->refcyc_per_vm_group_vblank   = get_refcyc_per_vm_group_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
 	disp_dlg_regs->refcyc_per_vm_group_flip     = get_refcyc_per_vm_group_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
-	disp_dlg_regs->refcyc_per_vm_req_vblank     = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
-	disp_dlg_regs->refcyc_per_vm_req_flip       = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
+	disp_dlg_regs->refcyc_per_vm_req_vblank     = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10);
+	disp_dlg_regs->refcyc_per_vm_req_flip       = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10);
 
 	// Clamp to max for now
 	if (disp_dlg_regs->refcyc_per_vm_group_vblank >= (unsigned int)dml_pow(2, 23))
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.h b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.h
index 83e95f8cbff2..e8f7785e3fc6 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.h
@@ -26,7 +26,7 @@
 #ifndef __DML21_DISPLAY_RQ_DLG_CALC_H__
 #define __DML21_DISPLAY_RQ_DLG_CALC_H__
 
-#include "../dml_common_defs.h"
+#include "dm_services.h"
 #include "../display_rq_dlg_helpers.h"
 
 struct display_mode_lib;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
index cf2758ca5b02..c77c3d827e4a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
@@ -25,8 +25,10 @@
 #ifndef __DISPLAY_MODE_LIB_H__
 #define __DISPLAY_MODE_LIB_H__
 
-
-#include "dml_common_defs.h"
+#include "dm_services.h"
+#include "dc_features.h"
+#include "display_mode_structs.h"
+#include "display_mode_enums.h"
 #include "display_mode_vba.h"
 
 enum dml_project {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index 5d82fc5a7ed7..3a734171f083 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -27,8 +27,6 @@
 #ifndef __DML2_DISPLAY_MODE_VBA_H__
 #define __DML2_DISPLAY_MODE_VBA_H__
 
-#include "dml_common_defs.h"
-
 struct display_mode_lib;
 
 void ModeSupportAndSystemConfiguration(struct display_mode_lib *mode_lib);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h
index 1f24db830737..2555ef0358c2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.h
@@ -26,7 +26,6 @@
 #ifndef __DISPLAY_RQ_DLG_HELPERS_H__
 #define __DISPLAY_RQ_DLG_HELPERS_H__
 
-#include "dml_common_defs.h"
 #include "display_mode_lib.h"
 
 /* Function: Printer functions
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.h b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.h
index 304164986bd8..9c06913ad767 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.h
@@ -26,8 +26,6 @@
 #ifndef __DISPLAY_RQ_DLG_CALC_H__
 #define __DISPLAY_RQ_DLG_CALC_H__
 
-#include "dml_common_defs.h"
-
 struct display_mode_lib;
 
 #include "display_rq_dlg_helpers.h"
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
deleted file mode 100644
index 723af0b2dda0..000000000000
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Copyright 2017 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-
-#include "dml_common_defs.h"
-#include "dcn_calc_math.h"
-
-#include "dml_inline_defs.h"
-
-double dml_round(double a)
-{
-	double round_pt = 0.5;
-	double ceil = dml_ceil(a, 1);
-	double floor = dml_floor(a, 1);
-
-	if (a - floor >= round_pt)
-		return ceil;
-	else
-		return floor;
-}
-
-
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.h
deleted file mode 100644
index f78cbae9db88..000000000000
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright 2017 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-
-#ifndef __DC_COMMON_DEFS_H__
-#define __DC_COMMON_DEFS_H__
-
-#include "dm_services.h"
-#include "dc_features.h"
-#include "display_mode_structs.h"
-#include "display_mode_enums.h"
-
-
-double dml_round(double a);
-
-#endif /* __DC_COMMON_DEFS_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
index ded71ea82413..02e06c9b3230 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
@@ -26,7 +26,6 @@
 #ifndef __DML_INLINE_DEFS_H__
 #define __DML_INLINE_DEFS_H__
 
-#include "dml_common_defs.h"
 #include "dcn_calc_math.h"
 #include "dml_logger.h"
 
@@ -75,6 +74,18 @@ static inline double dml_floor(double a, double granularity)
 	return (double) dcn_bw_floor2(a, granularity);
 }
 
+static inline double dml_round(double a)
+{
+	double round_pt = 0.5;
+	double ceil = dml_ceil(a, 1);
+	double floor = dml_floor(a, 1);
+
+	if (a - floor >= round_pt)
+		return ceil;
+	else
+		return floor;
+}
+
 static inline int dml_log2(double x)
 {
 	return dml_round((double)dcn_bw_log(x, 2));
@@ -112,7 +123,7 @@ static inline double dml_log(double x, double base)
 
 static inline unsigned int dml_round_to_multiple(unsigned int num,
 						 unsigned int multiple,
-						 bool up)
+						 unsigned char up)
 {
 	unsigned int remainder;
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 094afc4c8173..50ee8aa7ec3b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -210,6 +210,22 @@ struct mpc_funcs {
 		struct mpcc_blnd_cfg *blnd_cfg,
 		int mpcc_id);
 
+	/*
+	 * Lock cursor updates for the specified OPP.
+	 * OPP defines the set of MPCC that are locked together for cursor.
+	 *
+	 * Parameters:
+	 * [in] 	mpc		- MPC context.
+	 * [in]     opp_id	- The OPP to lock cursor updates on
+	 * [in]		lock	- lock/unlock the OPP
+	 *
+	 * Return:  void
+	 */
+	void (*cursor_lock)(
+			struct mpc *mpc,
+			int opp_id,
+			bool lock);
+
 	struct mpcc* (*get_mpcc_for_dpp)(
 			struct mpc_tree *tree,
 			int dpp_id);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index d4c1fb242c63..08307f3796e3 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -86,11 +86,17 @@ struct hw_sequencer_funcs {
 			struct dc_state *context, bool lock);
 	void (*set_flip_control_gsl)(struct pipe_ctx *pipe_ctx,
 			bool flip_immediate);
+	void (*cursor_lock)(struct dc *dc, struct pipe_ctx *pipe, bool lock);
 
 	/* Timing Related */
 	void (*get_position)(struct pipe_ctx **pipe_ctx, int num_pipes,
 			struct crtc_position *position);
 	int (*get_vupdate_offset_from_vsync)(struct pipe_ctx *pipe_ctx);
+	void (*calc_vupdate_position)(
+			struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			uint32_t *start_line,
+			uint32_t *end_line);
 	void (*enable_per_frame_crtc_position_reset)(struct dc *dc,
 			int group_size, struct pipe_ctx *grouped_pipes[]);
 	void (*enable_timing_synchronization)(struct dc *dc,
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index c34eba19860a..6d7bca562eec 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -108,7 +108,7 @@
 #define ASSERT(expr) ASSERT_CRITICAL(expr)
 
 #else
-#define ASSERT(expr) WARN_ON(!(expr))
+#define ASSERT(expr) WARN_ON_ONCE(!(expr))
 #endif
 
 #define BREAK_TO_DEBUGGER() ASSERT(0)
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 2a12614a12c2..8e2acb4df860 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -319,12 +319,12 @@ static void pp_dpm_en_umd_pstate(struct pp_hwmgr  *hwmgr,
 		if (*level & profile_mode_mask) {
 			hwmgr->saved_dpm_level = hwmgr->dpm_level;
 			hwmgr->en_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
-						AMD_IP_BLOCK_TYPE_GFX,
-						AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_GFX,
 					AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
+						AMD_IP_BLOCK_TYPE_GFX,
+						AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/
@@ -1435,7 +1435,8 @@ static int pp_get_asic_baco_capability(void *handle, bool *cap)
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_asic_baco_capability)
+	if (!(hwmgr->not_vf && amdgpu_dpm) ||
+		!hwmgr->hwmgr_func->get_asic_baco_capability)
 		return 0;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1452,8 +1453,7 @@ static int pp_get_asic_baco_state(void *handle, int *state)
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (!(hwmgr->not_vf && amdgpu_dpm) ||
-		!hwmgr->hwmgr_func->get_asic_baco_state)
+	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_asic_baco_state)
 		return 0;
 
 	mutex_lock(&hwmgr->smu_lock);
@@ -1470,7 +1470,8 @@ static int pp_set_asic_baco_state(void *handle, int state)
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->set_asic_baco_state)
+	if (!(hwmgr->not_vf && amdgpu_dpm) ||
+		!hwmgr->hwmgr_func->set_asic_baco_state)
 		return 0;
 
 	mutex_lock(&hwmgr->smu_lock);
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index e8b27fab6aa1..e77046931e4c 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -1476,7 +1476,7 @@ static int smu_disable_dpm(struct smu_context *smu)
 	bool use_baco = !smu->is_apu &&
 		((adev->in_gpu_reset &&
 		  (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) ||
-		 (adev->in_runpm && amdgpu_asic_supports_baco(adev)));
+		 ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev)));
 
 	ret = smu_get_smc_version(smu, NULL, &smu_version);
 	if (ret) {
@@ -1744,12 +1744,12 @@ static int smu_enable_umd_pstate(void *handle,
 		if (*level & profile_mode_mask) {
 			smu_dpm_ctx->saved_dpm_level = smu_dpm_ctx->dpm_level;
 			smu_dpm_ctx->enable_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(smu->adev,
-							       AMD_IP_BLOCK_TYPE_GFX,
-							       AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(smu->adev,
 							       AMD_IP_BLOCK_TYPE_GFX,
 							       AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(smu->adev,
+							       AMD_IP_BLOCK_TYPE_GFX,
+							       AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
index 77c14671866c..719597c5d27d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c
@@ -984,6 +984,32 @@ static int init_thermal_controller(
 			struct pp_hwmgr *hwmgr,
 			const ATOM_PPLIB_POWERPLAYTABLE *powerplay_table)
 {
+	hwmgr->thermal_controller.ucType =
+			powerplay_table->sThermalController.ucType;
+	hwmgr->thermal_controller.ucI2cLine =
+			powerplay_table->sThermalController.ucI2cLine;
+	hwmgr->thermal_controller.ucI2cAddress =
+			powerplay_table->sThermalController.ucI2cAddress;
+
+	hwmgr->thermal_controller.fanInfo.bNoFan =
+		(0 != (powerplay_table->sThermalController.ucFanParameters &
+			ATOM_PP_FANPARAMETERS_NOFAN));
+
+	hwmgr->thermal_controller.fanInfo.ucTachometerPulsesPerRevolution =
+		powerplay_table->sThermalController.ucFanParameters &
+		ATOM_PP_FANPARAMETERS_TACHOMETER_PULSES_PER_REVOLUTION_MASK;
+
+	hwmgr->thermal_controller.fanInfo.ulMinRPM
+		= powerplay_table->sThermalController.ucFanMinRPM * 100UL;
+	hwmgr->thermal_controller.fanInfo.ulMaxRPM
+		= powerplay_table->sThermalController.ucFanMaxRPM * 100UL;
+
+	set_hw_cap(hwmgr,
+		   ATOM_PP_THERMALCONTROLLER_NONE != hwmgr->thermal_controller.ucType,
+		   PHM_PlatformCaps_ThermalController);
+
+	hwmgr->thermal_controller.use_hw_fan_control = 1;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 7740488999df..4795eb66b2b2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -3804,9 +3804,12 @@ static int smu7_trim_single_dpm_states(struct pp_hwmgr *hwmgr,
 {
 	uint32_t i;
 
+	/* force the trim if mclk_switching is disabled to prevent flicker */
+	bool force_trim = (low_limit == high_limit);
 	for (i = 0; i < dpm_table->count; i++) {
 	/*skip the trim if od is enabled*/
-		if (!hwmgr->od_enabled && (dpm_table->dpm_levels[i].value < low_limit
+		if ((!hwmgr->od_enabled || force_trim)
+			&& (dpm_table->dpm_levels[i].value < low_limit
 			|| dpm_table->dpm_levels[i].value > high_limit))
 			dpm_table->dpm_levels[i].enabled = false;
 		else
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index ff73a735b888..b0ed1b3fe79a 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -895,12 +895,17 @@ static int renoir_read_sensor(struct smu_context *smu,
 
 static bool renoir_is_dpm_running(struct smu_context *smu)
 {
+	struct amdgpu_device *adev = smu->adev;
+
 	/*
 	 * Util now, the pmfw hasn't exported the interface of SMU
 	 * feature mask to APU SKU so just force on all the feature
 	 * at early initial stage.
 	 */
-	return true;
+	if (adev->in_suspend)
+		return false;
+	else
+		return true;
 
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index 541c932a6005..655ba4fb05dc 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1718,6 +1718,12 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state)
 		if (ret)
 			goto out;
 
+		if (ras && ras->supported) {
+			ret = smu_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL);
+			if (ret)
+				goto out;
+		}
+
 		/* clear vbios scratch 6 and 7 for coming asic reinit */
 		WREG32(adev->bios_scratch_reg_offset + 6, 0);
 		WREG32(adev->bios_scratch_reg_offset + 7, 0);
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 197dca3fc84c..5232f81c16a5 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -311,7 +311,7 @@ static void __exit armada_drm_exit(void)
 }
 module_exit(armada_drm_exit);
 
-MODULE_AUTHOR("Russell King <rmk+kernel@arm.linux.org.uk>");
+MODULE_AUTHOR("Russell King <rmk+kernel@armlinux.org.uk>");
 MODULE_DESCRIPTION("Armada DRM Driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:armada-drm");
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
index 2bc6e4f85171..9af39ec958db 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
@@ -485,6 +485,9 @@ static int anx6345_get_modes(struct drm_connector *connector)
 
 	num_modes += drm_add_edid_modes(connector, anx6345->edid);
 
+	/* Driver currently supports only 6bpc */
+	connector->display_info.bpc = 6;
+
 unlock:
 	if (power_off)
 		anx6345_poweroff(anx6345);
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c
index dd56996fe9c7..d0db1acf11d7 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c
@@ -630,7 +630,7 @@ static struct platform_driver snd_dw_hdmi_driver = {
 
 module_platform_driver(snd_dw_hdmi_driver);
 
-MODULE_AUTHOR("Russell King <rmk+kernel@arm.linux.org.uk>");
+MODULE_AUTHOR("Russell King <rmk+kernel@armlinux.org.uk>");
 MODULE_DESCRIPTION("Synopsis Designware HDMI AHB ALSA interface");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 70c4b7afed12..35b62c5d18b4 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -3442,8 +3442,12 @@ static int drm_dp_send_dpcd_write(struct drm_dp_mst_topology_mgr *mgr,
 	drm_dp_queue_down_tx(mgr, txmsg);
 
 	ret = drm_dp_mst_wait_tx_reply(mstb, txmsg);
-	if (ret > 0 && txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK)
-		ret = -EIO;
+	if (ret > 0) {
+		if (txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK)
+			ret = -EIO;
+		else
+			ret = size;
+	}
 
 	kfree(txmsg);
 fail_put:
@@ -4295,6 +4299,7 @@ int drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state,
 	if (pos->vcpi) {
 		drm_dp_mst_put_port_malloc(port);
 		pos->vcpi = 0;
+		pos->pbn = 0;
 	}
 
 	return 0;
@@ -5494,7 +5499,7 @@ struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port)
 {
 	struct drm_dp_mst_port *immediate_upstream_port;
 	struct drm_dp_mst_port *fec_port;
-	struct drm_dp_desc desc = { 0 };
+	struct drm_dp_desc desc = { };
 	u8 endpoint_fec;
 	u8 endpoint_dsc;
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 116451101426..d96e3ce3e535 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -191,10 +191,11 @@ static const struct edid_quirk {
 	{ "HVR", 0xaa01, EDID_QUIRK_NON_DESKTOP },
 	{ "HVR", 0xaa02, EDID_QUIRK_NON_DESKTOP },
 
-	/* Oculus Rift DK1, DK2, and CV1 VR Headsets */
+	/* Oculus Rift DK1, DK2, CV1 and Rift S VR Headsets */
 	{ "OVR", 0x0001, EDID_QUIRK_NON_DESKTOP },
 	{ "OVR", 0x0003, EDID_QUIRK_NON_DESKTOP },
 	{ "OVR", 0x0004, EDID_QUIRK_NON_DESKTOP },
+	{ "OVR", 0x0012, EDID_QUIRK_NON_DESKTOP },
 
 	/* Windows Mixed Reality Headsets */
 	{ "ACR", 0x7fce, EDID_QUIRK_NON_DESKTOP },
@@ -5111,7 +5112,7 @@ static struct drm_display_mode *drm_mode_displayid_detailed(struct drm_device *d
 	struct drm_display_mode *mode;
 	unsigned pixel_clock = (timings->pixel_clock[0] |
 				(timings->pixel_clock[1] << 8) |
-				(timings->pixel_clock[2] << 16));
+				(timings->pixel_clock[2] << 16)) + 1;
 	unsigned hactive = (timings->hactive[0] | timings->hactive[1] << 8) + 1;
 	unsigned hblank = (timings->hblank[0] | timings->hblank[1] << 8) + 1;
 	unsigned hsync = (timings->hsync[0] | (timings->hsync[1] & 0x7f) << 8) + 1;
diff --git a/drivers/gpu/drm/drm_hdcp.c b/drivers/gpu/drm/drm_hdcp.c
index 7f386adcf872..910108ccaae1 100644
--- a/drivers/gpu/drm/drm_hdcp.c
+++ b/drivers/gpu/drm/drm_hdcp.c
@@ -241,8 +241,12 @@ static int drm_hdcp_request_srm(struct drm_device *drm_dev,
 
 	ret = request_firmware_direct(&fw, (const char *)fw_name,
 				      drm_dev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		*revoked_ksv_cnt = 0;
+		*revoked_ksv_list = NULL;
+		ret = 0;
 		goto exit;
+	}
 
 	if (fw->size && fw->data)
 		ret = drm_hdcp_srm_update(fw->data, fw->size, revoked_ksv_list,
@@ -287,6 +291,8 @@ int drm_hdcp_check_ksvs_revoked(struct drm_device *drm_dev, u8 *ksvs,
 
 	ret = drm_hdcp_request_srm(drm_dev, &revoked_ksv_list,
 				   &revoked_ksv_cnt);
+	if (ret)
+		return ret;
 
 	/* revoked_ksv_cnt will be zero when above function failed */
 	for (i = 0; i < revoked_ksv_cnt; i++)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index a8685b2e1803..7585d8f68fb9 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -736,7 +736,7 @@ static void __exit etnaviv_exit(void)
 module_exit(etnaviv_exit);
 
 MODULE_AUTHOR("Christian Gmeiner <christian.gmeiner@gmail.com>");
-MODULE_AUTHOR("Russell King <rmk+kernel@arm.linux.org.uk>");
+MODULE_AUTHOR("Russell King <rmk+kernel@armlinux.org.uk>");
 MODULE_AUTHOR("Lucas Stach <l.stach@pengutronix.de>");
 MODULE_DESCRIPTION("etnaviv DRM Driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index 3b0afa156d92..54def341c1db 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -238,8 +238,10 @@ static int submit_pin_objects(struct etnaviv_gem_submit *submit)
 		}
 
 		if ((submit->flags & ETNA_SUBMIT_SOFTPIN) &&
-		     submit->bos[i].va != mapping->iova)
+		     submit->bos[i].va != mapping->iova) {
+			etnaviv_gem_mapping_unreference(mapping);
 			return -EINVAL;
+		}
 
 		atomic_inc(&etnaviv_obj->gpu_active);
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
index e6795bafcbb9..75f9db8f7bec 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_perfmon.c
@@ -453,7 +453,7 @@ static const struct etnaviv_pm_domain *pm_domain(const struct etnaviv_gpu *gpu,
 		if (!(gpu->identity.features & meta->feature))
 			continue;
 
-		if (meta->nr_domains < (index - offset)) {
+		if (index - offset >= meta->nr_domains) {
 			offset += meta->nr_domains;
 			continue;
 		}
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 2c617c98db3a..52db7852827b 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3141,9 +3141,6 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
 				 crtc_state->lane_count, is_mst);
 
-	intel_dp->regs.dp_tp_ctl = DP_TP_CTL(port);
-	intel_dp->regs.dp_tp_status = DP_TP_STATUS(port);
-
 	intel_edp_panel_on(intel_dp);
 
 	intel_ddi_clk_select(encoder, crtc_state);
@@ -3848,12 +3845,18 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	u32 temp, flags = 0;
 
 	/* XXX: DSI transcoder paranoia */
 	if (drm_WARN_ON(&dev_priv->drm, transcoder_is_dsi(cpu_transcoder)))
 		return;
 
+	if (INTEL_GEN(dev_priv) >= 12) {
+		intel_dp->regs.dp_tp_ctl = TGL_DP_TP_CTL(cpu_transcoder);
+		intel_dp->regs.dp_tp_status = TGL_DP_TP_STATUS(cpu_transcoder);
+	}
+
 	intel_dsc_get_config(encoder, pipe_config);
 
 	temp = intel_de_read(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder));
@@ -4173,6 +4176,7 @@ static const struct drm_encoder_funcs intel_ddi_funcs = {
 static struct intel_connector *
 intel_ddi_init_dp_connector(struct intel_digital_port *intel_dig_port)
 {
+	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
 	struct intel_connector *connector;
 	enum port port = intel_dig_port->base.port;
 
@@ -4183,6 +4187,10 @@ intel_ddi_init_dp_connector(struct intel_digital_port *intel_dig_port)
 	intel_dig_port->dp.output_reg = DDI_BUF_CTL(port);
 	intel_dig_port->dp.prepare_link_retrain =
 		intel_ddi_prepare_link_retrain;
+	if (INTEL_GEN(dev_priv) < 12) {
+		intel_dig_port->dp.regs.dp_tp_ctl = DP_TP_CTL(port);
+		intel_dig_port->dp.regs.dp_tp_status = DP_TP_STATUS(port);
+	}
 
 	if (!intel_dp_init_connector(intel_dig_port, connector)) {
 		kfree(connector);
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 246e406bb385..84ecf8e58523 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -4140,7 +4140,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX D TBT1",
 		.domains = TGL_AUX_D_TBT1_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
+		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4151,7 +4151,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX E TBT2",
 		.domains = TGL_AUX_E_TBT2_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
+		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4162,7 +4162,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX F TBT3",
 		.domains = TGL_AUX_F_TBT3_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
+		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4173,7 +4173,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX G TBT4",
 		.domains = TGL_AUX_G_TBT4_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
+		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4184,7 +4184,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX H TBT5",
 		.domains = TGL_AUX_H_TBT5_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
+		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
@@ -4195,7 +4195,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	{
 		.name = "AUX I TBT6",
 		.domains = TGL_AUX_I_TBT6_IO_POWER_DOMAINS,
-		.ops = &hsw_power_well_ops,
+		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
 			.hsw.regs = &icl_aux_power_well_regs,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 804b1d966f66..a2fafd4499f2 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2517,9 +2517,6 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 				 intel_crtc_has_type(pipe_config,
 						     INTEL_OUTPUT_DP_MST));
 
-	intel_dp->regs.dp_tp_ctl = DP_TP_CTL(port);
-	intel_dp->regs.dp_tp_status = DP_TP_STATUS(port);
-
 	/*
 	 * There are four kinds of DP registers:
 	 *
@@ -7836,6 +7833,8 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 
 	intel_dig_port->dp.output_reg = output_reg;
 	intel_dig_port->max_lanes = 4;
+	intel_dig_port->dp.regs.dp_tp_ctl = DP_TP_CTL(port);
+	intel_dig_port->dp.regs.dp_tp_status = DP_TP_STATUS(port);
 
 	intel_encoder->type = INTEL_OUTPUT_DP;
 	intel_encoder->power_domain = intel_port_to_power_domain(port);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index 3e706bb850a8..dbfa6895795b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -342,6 +342,7 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector)
 	 */
 	if (dev_priv->vbt.backlight.type !=
 	    INTEL_BACKLIGHT_VESA_EDP_AUX_INTERFACE &&
+	    i915_modparams.enable_dpcd_backlight != 1 &&
 	    !drm_dp_has_quirk(&intel_dp->desc, intel_dp->edid_quirks,
 			      DP_QUIRK_FORCE_DPCD_BACKLIGHT)) {
 		DRM_DEV_INFO(dev->dev,
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 2e5d835a9eaa..c125ca9ab9b3 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -485,8 +485,7 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv,
 	if (!ret)
 		goto err_llb;
 	else if (ret > 1) {
-		DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
-
+		DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
 	}
 
 	fbc->threshold = ret;
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 39930232b253..821411b93dac 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1536,7 +1536,8 @@ bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port)
 	intel_de_write(i915, HDCP_RPRIME(i915, cpu_transcoder, port), ri.reg);
 
 	/* Wait for Ri prime match */
-	if (wait_for(intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port)) &
+	if (wait_for((intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port)) &
+		      (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC)) ==
 		     (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1)) {
 		DRM_ERROR("Ri' mismatch detected, link check failed (%x)\n",
 			  intel_de_read(i915, HDCP_STATUS(i915, cpu_transcoder, port)));
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index deda351719db..33d886141138 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -2817,19 +2817,25 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 	}
 }
 
-static bool gen12_plane_supports_mc_ccs(enum plane_id plane_id)
+static bool gen12_plane_supports_mc_ccs(struct drm_i915_private *dev_priv,
+					enum plane_id plane_id)
 {
+	/* Wa_14010477008:tgl[a0..c0] */
+	if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_C0))
+		return false;
+
 	return plane_id < PLANE_SPRITE4;
 }
 
 static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 					     u32 format, u64 modifier)
 {
+	struct drm_i915_private *dev_priv = to_i915(_plane->dev);
 	struct intel_plane *plane = to_intel_plane(_plane);
 
 	switch (modifier) {
 	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
-		if (!gen12_plane_supports_mc_ccs(plane->id))
+		if (!gen12_plane_supports_mc_ccs(dev_priv, plane->id))
 			return false;
 		/* fall through */
 	case DRM_FORMAT_MOD_LINEAR:
@@ -2998,9 +3004,10 @@ static const u32 *icl_get_plane_formats(struct drm_i915_private *dev_priv,
 	}
 }
 
-static const u64 *gen12_get_plane_modifiers(enum plane_id plane_id)
+static const u64 *gen12_get_plane_modifiers(struct drm_i915_private *dev_priv,
+					    enum plane_id plane_id)
 {
-	if (gen12_plane_supports_mc_ccs(plane_id))
+	if (gen12_plane_supports_mc_ccs(dev_priv, plane_id))
 		return gen12_plane_format_modifiers_mc_ccs;
 	else
 		return gen12_plane_format_modifiers_rc_ccs;
@@ -3070,7 +3077,7 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 
 	plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id);
 	if (INTEL_GEN(dev_priv) >= 12) {
-		modifiers = gen12_get_plane_modifiers(plane_id);
+		modifiers = gen12_get_plane_modifiers(dev_priv, plane_id);
 		plane_funcs = &gen12_plane_funcs;
 	} else {
 		if (plane->has_ccs)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 0cc40e77bbd2..4f96c8788a2e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -368,7 +368,6 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 
-	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
 	if (!atomic_read(&obj->bind_count))
 		return;
 
@@ -400,12 +399,8 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 void
 i915_gem_object_unpin_from_display_plane(struct i915_vma *vma)
 {
-	struct drm_i915_gem_object *obj = vma->obj;
-
-	assert_object_held(obj);
-
 	/* Bump the LRU to try and avoid premature eviction whilst flipping  */
-	i915_gem_object_bump_inactive_ggtt(obj);
+	i915_gem_object_bump_inactive_ggtt(vma->obj);
 
 	i915_vma_unpin(vma);
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index 37f77aee1212..0158e49bf9bb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -182,21 +182,35 @@ i915_gem_object_fence_prepare(struct drm_i915_gem_object *obj,
 			      int tiling_mode, unsigned int stride)
 {
 	struct i915_ggtt *ggtt = &to_i915(obj->base.dev)->ggtt;
-	struct i915_vma *vma;
+	struct i915_vma *vma, *vn;
+	LIST_HEAD(unbind);
 	int ret = 0;
 
 	if (tiling_mode == I915_TILING_NONE)
 		return 0;
 
 	mutex_lock(&ggtt->vm.mutex);
+
+	spin_lock(&obj->vma.lock);
 	for_each_ggtt_vma(vma, obj) {
+		GEM_BUG_ON(vma->vm != &ggtt->vm);
+
 		if (i915_vma_fence_prepare(vma, tiling_mode, stride))
 			continue;
 
+		list_move(&vma->vm_link, &unbind);
+	}
+	spin_unlock(&obj->vma.lock);
+
+	list_for_each_entry_safe(vma, vn, &unbind, vm_link) {
 		ret = __i915_vma_unbind(vma);
-		if (ret)
+		if (ret) {
+			/* Restore the remaining vma on an error */
+			list_splice(&unbind, &ggtt->vm.bound_list);
 			break;
+		}
 	}
+
 	mutex_unlock(&ggtt->vm.mutex);
 
 	return ret;
@@ -268,6 +282,7 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 	}
 	mutex_unlock(&obj->mm.lock);
 
+	spin_lock(&obj->vma.lock);
 	for_each_ggtt_vma(vma, obj) {
 		vma->fence_size =
 			i915_gem_fence_size(i915, vma->size, tiling, stride);
@@ -278,6 +293,7 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 		if (vma->fence)
 			vma->fence->dirty = true;
 	}
+	spin_unlock(&obj->vma.lock);
 
 	obj->tiling_and_stride = tiling | stride;
 	i915_gem_object_unlock(obj);
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 2d0fd50c5312..d4f94ca9ae0d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -1477,8 +1477,10 @@ static int igt_ppgtt_pin_update(void *arg)
 		unsigned int page_size = BIT(first);
 
 		obj = i915_gem_object_create_internal(dev_priv, page_size);
-		if (IS_ERR(obj))
-			return PTR_ERR(obj);
+		if (IS_ERR(obj)) {
+			err = PTR_ERR(obj);
+			goto out_vm;
+		}
 
 		vma = i915_vma_instance(obj, vm, NULL);
 		if (IS_ERR(vma)) {
@@ -1531,8 +1533,10 @@ static int igt_ppgtt_pin_update(void *arg)
 	}
 
 	obj = i915_gem_object_create_internal(dev_priv, PAGE_SIZE);
-	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto out_vm;
+	}
 
 	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 07cb83a0d017..ca0d4f4f3615 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -69,7 +69,13 @@ struct intel_context {
 #define CONTEXT_NOPREEMPT		7
 
 	u32 *lrc_reg_state;
-	u64 lrc_desc;
+	union {
+		struct {
+			u32 lrca;
+			u32 ccid;
+		};
+		u64 desc;
+	} lrc;
 	u32 tag; /* cookie passed to HW to track this context on submission */
 
 	/* Time on GPU as tracked by the hw. */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index b469de0dd9b6..a1aa0d3e8be1 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -333,13 +333,4 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
 	return intel_engine_has_preemption(engine);
 }
 
-static inline bool
-intel_engine_has_timeslices(const struct intel_engine_cs *engine)
-{
-	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
-		return false;
-
-	return intel_engine_has_semaphores(engine);
-}
-
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 3aa8a652c16d..883a9b7fe88d 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1295,6 +1295,12 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 
 	if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
 		drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID));
+	if (HAS_EXECLISTS(dev_priv)) {
+		drm_printf(m, "\tEL_STAT_HI: 0x%08x\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_HI));
+		drm_printf(m, "\tEL_STAT_LO: 0x%08x\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_LO));
+	}
 	drm_printf(m, "\tRING_START: 0x%08x\n",
 		   ENGINE_READ(engine, RING_START));
 	drm_printf(m, "\tRING_HEAD:  0x%08x\n",
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 80cdde712842..0be674ae1cf6 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -157,6 +157,20 @@ struct intel_engine_execlists {
 	struct i915_priolist default_priolist;
 
 	/**
+	 * @ccid: identifier for contexts submitted to this engine
+	 */
+	u32 ccid;
+
+	/**
+	 * @yield: CCID at the time of the last semaphore-wait interrupt.
+	 *
+	 * Instead of leaving a semaphore busy-spinning on an engine, we would
+	 * like to switch to another ready context, i.e. yielding the semaphore
+	 * timeslice.
+	 */
+	u32 yield;
+
+	/**
 	 * @error_interrupt: CS Master EIR
 	 *
 	 * The CS generates an interrupt when it detects an error. We capture
@@ -295,8 +309,7 @@ struct intel_engine_cs {
 	u32 context_size;
 	u32 mmio_base;
 
-	unsigned int context_tag;
-#define NUM_CONTEXT_TAG roundup_pow_of_two(2 * EXECLIST_MAX_PORTS)
+	unsigned long context_tag;
 
 	struct rb_node uabi_node;
 
@@ -483,10 +496,11 @@ struct intel_engine_cs {
 #define I915_ENGINE_SUPPORTS_STATS   BIT(1)
 #define I915_ENGINE_HAS_PREEMPTION   BIT(2)
 #define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
-#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
-#define I915_ENGINE_IS_VIRTUAL       BIT(5)
-#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6)
-#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
+#define I915_ENGINE_HAS_TIMESLICES   BIT(4)
+#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5)
+#define I915_ENGINE_IS_VIRTUAL       BIT(6)
+#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7)
+#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8)
 	unsigned int flags;
 
 	/*
@@ -585,6 +599,15 @@ intel_engine_has_semaphores(const struct intel_engine_cs *engine)
 }
 
 static inline bool
+intel_engine_has_timeslices(const struct intel_engine_cs *engine)
+{
+	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+		return false;
+
+	return engine->flags & I915_ENGINE_HAS_TIMESLICES;
+}
+
+static inline bool
 intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine)
 {
 	return engine->flags & I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index f0e7fd95165a..0cc7dd54f4f9 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -39,6 +39,15 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 		}
 	}
 
+	if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) {
+		WRITE_ONCE(engine->execlists.yield,
+			   ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI));
+		ENGINE_TRACE(engine, "semaphore yield: %08x\n",
+			     engine->execlists.yield);
+		if (del_timer(&engine->execlists.timer))
+			tasklet = true;
+	}
+
 	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
 		tasklet = true;
 
@@ -228,7 +237,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 	const u32 irqs =
 		GT_CS_MASTER_ERROR_INTERRUPT |
 		GT_RENDER_USER_INTERRUPT |
-		GT_CONTEXT_SWITCH_INTERRUPT;
+		GT_CONTEXT_SWITCH_INTERRUPT |
+		GT_WAIT_SEMAPHORE_INTERRUPT;
 	struct intel_uncore *uncore = gt->uncore;
 	const u32 dmask = irqs << 16 | irqs;
 	const u32 smask = irqs << 16;
@@ -366,7 +376,8 @@ void gen8_gt_irq_postinstall(struct intel_gt *gt)
 	const u32 irqs =
 		GT_CS_MASTER_ERROR_INTERRUPT |
 		GT_RENDER_USER_INTERRUPT |
-		GT_CONTEXT_SWITCH_INTERRUPT;
+		GT_CONTEXT_SWITCH_INTERRUPT |
+		GT_WAIT_SEMAPHORE_INTERRUPT;
 	const u32 gt_interrupts[] = {
 		irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT,
 		irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 683014e7bc51..2dfaddb8811e 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -456,10 +456,10 @@ assert_priority_queue(const struct i915_request *prev,
  * engine info, SW context ID and SW counter need to form a unique number
  * (Context ID) per lrc.
  */
-static u64
+static u32
 lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 {
-	u64 desc;
+	u32 desc;
 
 	desc = INTEL_LEGACY_32B_CONTEXT;
 	if (i915_vm_is_4lvl(ce->vm))
@@ -470,21 +470,7 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 	if (IS_GEN(engine->i915, 8))
 		desc |= GEN8_CTX_L3LLC_COHERENT;
 
-	desc |= i915_ggtt_offset(ce->state); /* bits 12-31 */
-	/*
-	 * The following 32bits are copied into the OA reports (dword 2).
-	 * Consider updating oa_get_render_ctx_id in i915_perf.c when changing
-	 * anything below.
-	 */
-	if (INTEL_GEN(engine->i915) >= 11) {
-		desc |= (u64)engine->instance << GEN11_ENGINE_INSTANCE_SHIFT;
-								/* bits 48-53 */
-
-		desc |= (u64)engine->class << GEN11_ENGINE_CLASS_SHIFT;
-								/* bits 61-63 */
-	}
-
-	return desc;
+	return i915_ggtt_offset(ce->state) | desc;
 }
 
 static inline unsigned int dword_in_page(void *addr)
@@ -1192,7 +1178,7 @@ static void reset_active(struct i915_request *rq,
 	__execlists_update_reg_state(ce, engine, head);
 
 	/* We've switched away, so this should be a no-op, but intent matters */
-	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
+	ce->lrc.desc |= CTX_DESC_FORCE_RESTORE;
 }
 
 static u32 intel_context_get_runtime(const struct intel_context *ce)
@@ -1251,18 +1237,23 @@ __execlists_schedule_in(struct i915_request *rq)
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		execlists_check_context(ce, engine);
 
-	ce->lrc_desc &= ~GENMASK_ULL(47, 37);
 	if (ce->tag) {
 		/* Use a fixed tag for OA and friends */
-		ce->lrc_desc |= (u64)ce->tag << 32;
+		GEM_BUG_ON(ce->tag <= BITS_PER_LONG);
+		ce->lrc.ccid = ce->tag;
 	} else {
 		/* We don't need a strict matching tag, just different values */
-		ce->lrc_desc |=
-			(u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
-			GEN11_SW_CTX_ID_SHIFT;
-		BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID);
+		unsigned int tag = ffs(engine->context_tag);
+
+		GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG);
+		clear_bit(tag - 1, &engine->context_tag);
+		ce->lrc.ccid = tag << (GEN11_SW_CTX_ID_SHIFT - 32);
+
+		BUILD_BUG_ON(BITS_PER_LONG > GEN12_MAX_CONTEXT_HW_ID);
 	}
 
+	ce->lrc.ccid |= engine->execlists.ccid;
+
 	__intel_gt_pm_get(engine->gt);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
@@ -1302,7 +1293,8 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 
 static inline void
 __execlists_schedule_out(struct i915_request *rq,
-			 struct intel_engine_cs * const engine)
+			 struct intel_engine_cs * const engine,
+			 unsigned int ccid)
 {
 	struct intel_context * const ce = rq->context;
 
@@ -1320,6 +1312,14 @@ __execlists_schedule_out(struct i915_request *rq,
 	    i915_request_completed(rq))
 		intel_engine_add_retire(engine, ce->timeline);
 
+	ccid >>= GEN11_SW_CTX_ID_SHIFT - 32;
+	ccid &= GEN12_MAX_CONTEXT_HW_ID;
+	if (ccid < BITS_PER_LONG) {
+		GEM_BUG_ON(ccid == 0);
+		GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag));
+		set_bit(ccid - 1, &engine->context_tag);
+	}
+
 	intel_context_update_runtime(ce);
 	intel_engine_context_out(engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
@@ -1345,15 +1345,17 @@ execlists_schedule_out(struct i915_request *rq)
 {
 	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *cur, *old;
+	u32 ccid;
 
 	trace_i915_request_out(rq);
 
+	ccid = rq->context->lrc.ccid;
 	old = READ_ONCE(ce->inflight);
 	do
 		cur = ptr_unmask_bits(old, 2) ? ptr_dec(old) : NULL;
 	while (!try_cmpxchg(&ce->inflight, &old, cur));
 	if (!cur)
-		__execlists_schedule_out(rq, old);
+		__execlists_schedule_out(rq, old, ccid);
 
 	i915_request_put(rq);
 }
@@ -1361,7 +1363,7 @@ execlists_schedule_out(struct i915_request *rq)
 static u64 execlists_update_context(struct i915_request *rq)
 {
 	struct intel_context *ce = rq->context;
-	u64 desc = ce->lrc_desc;
+	u64 desc = ce->lrc.desc;
 	u32 tail, prev;
 
 	/*
@@ -1400,7 +1402,7 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 */
 	wmb();
 
-	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
+	ce->lrc.desc &= ~CTX_DESC_FORCE_RESTORE;
 	return desc;
 }
 
@@ -1719,6 +1721,9 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl)
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
+			if (p->flags & I915_DEPENDENCY_WEAK)
+				continue;
+
 			/* Leave semaphores spinning on the other engines */
 			if (w->engine != rq->engine)
 				continue;
@@ -1754,7 +1759,8 @@ static void defer_active(struct intel_engine_cs *engine)
 }
 
 static bool
-need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
+need_timeslice(const struct intel_engine_cs *engine,
+	       const struct i915_request *rq)
 {
 	int hint;
 
@@ -1768,6 +1774,32 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
 	return hint >= effective_prio(rq);
 }
 
+static bool
+timeslice_yield(const struct intel_engine_execlists *el,
+		const struct i915_request *rq)
+{
+	/*
+	 * Once bitten, forever smitten!
+	 *
+	 * If the active context ever busy-waited on a semaphore,
+	 * it will be treated as a hog until the end of its timeslice (i.e.
+	 * until it is scheduled out and replaced by a new submission,
+	 * possibly even its own lite-restore). The HW only sends an interrupt
+	 * on the first miss, and we do know if that semaphore has been
+	 * signaled, or even if it is now stuck on another semaphore. Play
+	 * safe, yield if it might be stuck -- it will be given a fresh
+	 * timeslice in the near future.
+	 */
+	return rq->context->lrc.ccid == READ_ONCE(el->yield);
+}
+
+static bool
+timeslice_expired(const struct intel_engine_execlists *el,
+		  const struct i915_request *rq)
+{
+	return timer_expired(&el->timer) || timeslice_yield(el, rq);
+}
+
 static int
 switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq)
 {
@@ -1783,8 +1815,7 @@ timeslice(const struct intel_engine_cs *engine)
 	return READ_ONCE(engine->props.timeslice_duration_ms);
 }
 
-static unsigned long
-active_timeslice(const struct intel_engine_cs *engine)
+static unsigned long active_timeslice(const struct intel_engine_cs *engine)
 {
 	const struct intel_engine_execlists *execlists = &engine->execlists;
 	const struct i915_request *rq = *execlists->active;
@@ -1946,13 +1977,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
-			   timer_expired(&engine->execlists.timer)) {
+			   timeslice_expired(execlists, last)) {
 			ENGINE_TRACE(engine,
-				     "expired last=%llx:%lld, prio=%d, hint=%d\n",
+				     "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n",
 				     last->fence.context,
 				     last->fence.seqno,
 				     last->sched.attr.priority,
-				     execlists->queue_priority_hint);
+				     execlists->queue_priority_hint,
+				     yesno(timeslice_yield(execlists, last)));
 
 			ring_set_paused(engine, 1);
 			defer_active(engine);
@@ -2213,6 +2245,7 @@ done:
 		}
 		clear_ports(port + 1, last_port - port);
 
+		WRITE_ONCE(execlists->yield, -1);
 		execlists_submit_ports(engine);
 		set_preempt_timeout(engine, *active);
 	} else {
@@ -3043,7 +3076,7 @@ __execlists_context_pin(struct intel_context *ce,
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
 
-	ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
+	ce->lrc.lrca = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	__execlists_update_reg_state(ce, engine, ce->ring->tail);
 
@@ -3072,7 +3105,7 @@ static void execlists_context_reset(struct intel_context *ce)
 				 ce, ce->engine, ce->ring, true);
 	__execlists_update_reg_state(ce, ce->engine, ce->ring->tail);
 
-	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
+	ce->lrc.desc |= CTX_DESC_FORCE_RESTORE;
 }
 
 static const struct intel_context_ops execlists_context_ops = {
@@ -3541,7 +3574,7 @@ static void enable_execlists(struct intel_engine_cs *engine)
 
 	enable_error_interrupt(engine);
 
-	engine->context_tag = 0;
+	engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0);
 }
 
 static bool unexpected_starting_state(struct intel_engine_cs *engine)
@@ -3753,7 +3786,7 @@ out_replay:
 		     head, ce->ring->tail);
 	__execlists_reset_reg_state(ce, engine);
 	__execlists_update_reg_state(ce, engine, head);
-	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
+	ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
 
 unwind:
 	/* Push back any incomplete requests for replay after the reset. */
@@ -4369,8 +4402,11 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 	engine->flags |= I915_ENGINE_SUPPORTS_STATS;
 	if (!intel_vgpu_active(engine->i915)) {
 		engine->flags |= I915_ENGINE_HAS_SEMAPHORES;
-		if (HAS_LOGICAL_RING_PREEMPTION(engine->i915))
+		if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) {
 			engine->flags |= I915_ENGINE_HAS_PREEMPTION;
+			if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+				engine->flags |= I915_ENGINE_HAS_TIMESLICES;
+		}
 	}
 
 	if (INTEL_GEN(engine->i915) >= 12)
@@ -4449,6 +4485,7 @@ logical_ring_default_irqs(struct intel_engine_cs *engine)
 	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift;
 	engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift;
 	engine->irq_keep_mask |= GT_CS_MASTER_ERROR_INTERRUPT << shift;
+	engine->irq_keep_mask |= GT_WAIT_SEMAPHORE_INTERRUPT << shift;
 }
 
 static void rcs_submission_override(struct intel_engine_cs *engine)
@@ -4516,6 +4553,11 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	else
 		execlists->csb_size = GEN11_CSB_ENTRIES;
 
+	if (INTEL_GEN(engine->i915) >= 11) {
+		execlists->ccid |= engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32);
+		execlists->ccid |= engine->class << (GEN11_ENGINE_CLASS_SHIFT - 32);
+	}
+
 	reset_csb_pointers(engine);
 
 	/* Finally, take ownership and responsibility for cleanup! */
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index cfaf141bac4d..19542fd9e207 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -81,13 +81,14 @@ static void rps_enable_interrupts(struct intel_rps *rps)
 		events = (GEN6_PM_RP_UP_THRESHOLD |
 			  GEN6_PM_RP_DOWN_THRESHOLD |
 			  GEN6_PM_RP_DOWN_TIMEOUT);
-
 	WRITE_ONCE(rps->pm_events, events);
+
 	spin_lock_irq(&gt->irq_lock);
 	gen6_gt_pm_enable_irq(gt, rps->pm_events);
 	spin_unlock_irq(&gt->irq_lock);
 
-	set(gt->uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, rps->cur_freq));
+	intel_uncore_write(gt->uncore,
+			   GEN6_PMINTRMSK, rps_pm_mask(rps, rps->last_freq));
 }
 
 static void gen6_rps_reset_interrupts(struct intel_rps *rps)
@@ -120,7 +121,9 @@ static void rps_disable_interrupts(struct intel_rps *rps)
 	struct intel_gt *gt = rps_to_gt(rps);
 
 	WRITE_ONCE(rps->pm_events, 0);
-	set(gt->uncore, GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u));
+
+	intel_uncore_write(gt->uncore,
+			   GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u));
 
 	spin_lock_irq(&gt->irq_lock);
 	gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS);
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 91debbc97c9a..08b56d7ab4f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -521,6 +521,8 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 
 	rcu_read_lock();
 	cl = rcu_dereference(from->hwsp_cacheline);
+	if (i915_request_completed(from)) /* confirm cacheline is valid */
+		goto unlock;
 	if (unlikely(!i915_active_acquire_if_busy(&cl->active)))
 		goto unlock; /* seqno wrapped and completed! */
 	if (unlikely(i915_request_completed(from)))
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 6f06ba750a0a..f95ae15ce865 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -929,7 +929,7 @@ create_rewinder(struct intel_context *ce,
 			goto err;
 	}
 
-	cs = intel_ring_begin(rq, 10);
+	cs = intel_ring_begin(rq, 14);
 	if (IS_ERR(cs)) {
 		err = PTR_ERR(cs);
 		goto err;
@@ -941,8 +941,8 @@ create_rewinder(struct intel_context *ce,
 	*cs++ = MI_SEMAPHORE_WAIT |
 		MI_SEMAPHORE_GLOBAL_GTT |
 		MI_SEMAPHORE_POLL |
-		MI_SEMAPHORE_SAD_NEQ_SDD;
-	*cs++ = 0;
+		MI_SEMAPHORE_SAD_GTE_SDD;
+	*cs++ = idx;
 	*cs++ = offset;
 	*cs++ = 0;
 
@@ -951,6 +951,11 @@ create_rewinder(struct intel_context *ce,
 	*cs++ = offset + idx * sizeof(u32);
 	*cs++ = 0;
 
+	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+	*cs++ = offset;
+	*cs++ = 0;
+	*cs++ = idx + 1;
+
 	intel_ring_advance(rq, cs);
 
 	rq->sched.attr.priority = I915_PRIORITY_MASK;
@@ -984,7 +989,7 @@ static int live_timeslice_rewind(void *arg)
 
 	for_each_engine(engine, gt, id) {
 		enum { A1, A2, B1 };
-		enum { X = 1, Y, Z };
+		enum { X = 1, Z, Y };
 		struct i915_request *rq[3] = {};
 		struct intel_context *ce;
 		unsigned long heartbeat;
@@ -1017,13 +1022,13 @@ static int live_timeslice_rewind(void *arg)
 			goto err;
 		}
 
-		rq[0] = create_rewinder(ce, NULL, slot, 1);
+		rq[0] = create_rewinder(ce, NULL, slot, X);
 		if (IS_ERR(rq[0])) {
 			intel_context_put(ce);
 			goto err;
 		}
 
-		rq[1] = create_rewinder(ce, NULL, slot, 2);
+		rq[1] = create_rewinder(ce, NULL, slot, Y);
 		intel_context_put(ce);
 		if (IS_ERR(rq[1]))
 			goto err;
@@ -1041,7 +1046,7 @@ static int live_timeslice_rewind(void *arg)
 			goto err;
 		}
 
-		rq[2] = create_rewinder(ce, rq[0], slot, 3);
+		rq[2] = create_rewinder(ce, rq[0], slot, Z);
 		intel_context_put(ce);
 		if (IS_ERR(rq[2]))
 			goto err;
@@ -1055,15 +1060,12 @@ static int live_timeslice_rewind(void *arg)
 		GEM_BUG_ON(!timer_pending(&engine->execlists.timer));
 
 		/* ELSP[] = { { A:rq1, A:rq2 }, { B:rq1 } } */
-		GEM_BUG_ON(!i915_request_is_active(rq[A1]));
-		GEM_BUG_ON(!i915_request_is_active(rq[A2]));
-		GEM_BUG_ON(!i915_request_is_active(rq[B1]));
-
-		/* Wait for the timeslice to kick in */
-		del_timer(&engine->execlists.timer);
-		tasklet_hi_schedule(&engine->execlists.tasklet);
-		intel_engine_flush_submission(engine);
-
+		if (i915_request_is_active(rq[A2])) { /* semaphore yielded! */
+			/* Wait for the timeslice to kick in */
+			del_timer(&engine->execlists.timer);
+			tasklet_hi_schedule(&engine->execlists.tasklet);
+			intel_engine_flush_submission(engine);
+		}
 		/* -> ELSP[] = { { A:rq1 }, { B:rq1 } } */
 		GEM_BUG_ON(!i915_request_is_active(rq[A1]));
 		GEM_BUG_ON(!i915_request_is_active(rq[B1]));
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index fe7778c28d2d..aa6d56e25a10 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -217,7 +217,7 @@ static void guc_wq_item_append(struct intel_guc *guc,
 static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
-	u32 ctx_desc = lower_32_bits(rq->context->lrc_desc);
+	u32 ctx_desc = rq->context->lrc.ccid;
 	u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64);
 
 	guc_wq_item_append(guc, engine->guc_id, ctx_desc,
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index a83df2f84eb9..a1696e9ce4b6 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -208,14 +208,41 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG0) |
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG1) |
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG2);
-		vgpu_vreg_t(vgpu, LCPLL1_CTL) |=
-				LCPLL_PLL_ENABLE |
-				LCPLL_PLL_LOCK;
-		vgpu_vreg_t(vgpu, LCPLL2_CTL) |= LCPLL_PLL_ENABLE;
-
+		/*
+		 * Only 1 PIPE enabled in current vGPU display and PIPE_A is
+		 *  tied to TRANSCODER_A in HW, so it's safe to assume PIPE_A,
+		 *   TRANSCODER_A can be enabled. PORT_x depends on the input of
+		 *   setup_virtual_dp_monitor, we can bind DPLL0 to any PORT_x
+		 *   so we fixed to DPLL0 here.
+		 * Setup DPLL0: DP link clk 1620 MHz, non SSC, DP Mode
+		 */
+		vgpu_vreg_t(vgpu, DPLL_CTRL1) =
+			DPLL_CTRL1_OVERRIDE(DPLL_ID_SKL_DPLL0);
+		vgpu_vreg_t(vgpu, DPLL_CTRL1) |=
+			DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1620, DPLL_ID_SKL_DPLL0);
+		vgpu_vreg_t(vgpu, LCPLL1_CTL) =
+			LCPLL_PLL_ENABLE | LCPLL_PLL_LOCK;
+		vgpu_vreg_t(vgpu, DPLL_STATUS) = DPLL_LOCK(DPLL_ID_SKL_DPLL0);
+		/*
+		 * Golden M/N are calculated based on:
+		 *   24 bpp, 4 lanes, 154000 pixel clk (from virtual EDID),
+		 *   DP link clk 1620 MHz and non-constant_n.
+		 * TODO: calculate DP link symbol clk and stream clk m/n.
+		 */
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) = 63 << TU_SIZE_SHIFT;
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) |= 0x5b425e;
+		vgpu_vreg_t(vgpu, PIPE_DATA_N1(TRANSCODER_A)) = 0x800000;
+		vgpu_vreg_t(vgpu, PIPE_LINK_M1(TRANSCODER_A)) = 0x3cd6e;
+		vgpu_vreg_t(vgpu, PIPE_LINK_N1(TRANSCODER_A)) = 0x80000;
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_B);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_B);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_B);
 		vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -236,6 +263,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_C);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_C);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_C);
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -256,6 +289,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_D);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_D);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_D);
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 074c4efb58eb..eee530453aa6 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -131,6 +131,7 @@ struct kvmgt_vdev {
 	struct work_struct release_work;
 	atomic_t released;
 	struct vfio_device *vfio_device;
+	struct vfio_group *vfio_group;
 };
 
 static inline struct kvmgt_vdev *kvmgt_vdev(struct intel_vgpu *vgpu)
@@ -151,6 +152,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 		unsigned long size)
 {
 	struct drm_i915_private *i915 = vgpu->gvt->gt->i915;
+	struct kvmgt_vdev *vdev = kvmgt_vdev(vgpu);
 	int total_pages;
 	int npage;
 	int ret;
@@ -160,7 +162,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 	for (npage = 0; npage < total_pages; npage++) {
 		unsigned long cur_gfn = gfn + npage;
 
-		ret = vfio_unpin_pages(mdev_dev(kvmgt_vdev(vgpu)->mdev), &cur_gfn, 1);
+		ret = vfio_group_unpin_pages(vdev->vfio_group, &cur_gfn, 1);
 		drm_WARN_ON(&i915->drm, ret != 1);
 	}
 }
@@ -169,6 +171,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 		unsigned long size, struct page **page)
 {
+	struct kvmgt_vdev *vdev = kvmgt_vdev(vgpu);
 	unsigned long base_pfn = 0;
 	int total_pages;
 	int npage;
@@ -183,8 +186,8 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
 		unsigned long cur_gfn = gfn + npage;
 		unsigned long pfn;
 
-		ret = vfio_pin_pages(mdev_dev(kvmgt_vdev(vgpu)->mdev), &cur_gfn, 1,
-				     IOMMU_READ | IOMMU_WRITE, &pfn);
+		ret = vfio_group_pin_pages(vdev->vfio_group, &cur_gfn, 1,
+					   IOMMU_READ | IOMMU_WRITE, &pfn);
 		if (ret != 1) {
 			gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx, ret %d\n",
 				     cur_gfn, ret);
@@ -792,6 +795,7 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 	struct kvmgt_vdev *vdev = kvmgt_vdev(vgpu);
 	unsigned long events;
 	int ret;
+	struct vfio_group *vfio_group;
 
 	vdev->iommu_notifier.notifier_call = intel_vgpu_iommu_notifier;
 	vdev->group_notifier.notifier_call = intel_vgpu_group_notifier;
@@ -814,6 +818,14 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 		goto undo_iommu;
 	}
 
+	vfio_group = vfio_group_get_external_user_from_dev(mdev_dev(mdev));
+	if (IS_ERR_OR_NULL(vfio_group)) {
+		ret = !vfio_group ? -EFAULT : PTR_ERR(vfio_group);
+		gvt_vgpu_err("vfio_group_get_external_user_from_dev failed\n");
+		goto undo_register;
+	}
+	vdev->vfio_group = vfio_group;
+
 	/* Take a module reference as mdev core doesn't take
 	 * a reference for vendor driver.
 	 */
@@ -830,6 +842,10 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 	return ret;
 
 undo_group:
+	vfio_group_put_external_user(vdev->vfio_group);
+	vdev->vfio_group = NULL;
+
+undo_register:
 	vfio_unregister_notifier(mdev_dev(mdev), VFIO_GROUP_NOTIFY,
 					&vdev->group_notifier);
 
@@ -884,6 +900,7 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu)
 	kvmgt_guest_exit(info);
 
 	intel_vgpu_release_msi_eventfd_ctx(vgpu);
+	vfio_group_put_external_user(vdev->vfio_group);
 
 	vdev->kvm = NULL;
 	vgpu->handle = 0;
@@ -2035,33 +2052,14 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa,
 			void *buf, unsigned long len, bool write)
 {
 	struct kvmgt_guest_info *info;
-	struct kvm *kvm;
-	int idx, ret;
-	bool kthread = current->mm == NULL;
 
 	if (!handle_valid(handle))
 		return -ESRCH;
 
 	info = (struct kvmgt_guest_info *)handle;
-	kvm = info->kvm;
-
-	if (kthread) {
-		if (!mmget_not_zero(kvm->mm))
-			return -EFAULT;
-		use_mm(kvm->mm);
-	}
-
-	idx = srcu_read_lock(&kvm->srcu);
-	ret = write ? kvm_write_guest(kvm, gpa, buf, len) :
-		      kvm_read_guest(kvm, gpa, buf, len);
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	if (kthread) {
-		unuse_mm(kvm->mm);
-		mmput(kvm->mm);
-	}
 
-	return ret;
+	return vfio_dma_rw(kvmgt_vdev(info->vgpu)->vfio_group,
+			   gpa, buf, len, write);
 }
 
 static int kvmgt_read_gpa(unsigned long handle, unsigned long gpa,
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index cb11c3184085..e92ed96c9b23 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -290,7 +290,7 @@ static void
 shadow_context_descriptor_update(struct intel_context *ce,
 				 struct intel_vgpu_workload *workload)
 {
-	u64 desc = ce->lrc_desc;
+	u64 desc = ce->lrc.desc;
 
 	/*
 	 * Update bits 0-11 of the context descriptor which includes flags
@@ -300,7 +300,7 @@ shadow_context_descriptor_update(struct intel_context *ce,
 	desc |= (u64)workload->ctx_desc.addressing_mode <<
 		GEN8_CTX_ADDRESSING_MODE_SHIFT;
 
-	ce->lrc_desc = desc;
+	ce->lrc.desc = desc;
 }
 
 static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
@@ -379,7 +379,11 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 		for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) {
 			struct i915_page_directory * const pd =
 				i915_pd_entry(ppgtt->pd, i);
-
+			/* skip now as current i915 ppgtt alloc won't allocate
+			   top level pdp for non 4-level table, won't impact
+			   shadow ppgtt. */
+			if (!pd)
+				break;
 			px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i];
 		}
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1f5b9a584f71..62b901ffabf9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1507,6 +1507,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 	(IS_ICELAKE(p) && IS_REVID(p, since, until))
 
 #define TGL_REVID_A0		0x0
+#define TGL_REVID_B0		0x1
+#define TGL_REVID_C0		0x2
 
 #define IS_TGL_REVID(p, since, until) \
 	(IS_TIGERLAKE(p) && IS_REVID(p, since, until))
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 4518b9b35c3d..02ad1acd117c 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -128,6 +128,13 @@ search_again:
 	active = NULL;
 	INIT_LIST_HEAD(&eviction_list);
 	list_for_each_entry_safe(vma, next, &vm->bound_list, vm_link) {
+		if (vma == active) { /* now seen this vma twice */
+			if (flags & PIN_NONBLOCK)
+				break;
+
+			active = ERR_PTR(-EAGAIN);
+		}
+
 		/*
 		 * We keep this list in a rough least-recently scanned order
 		 * of active elements (inactive elements are cheap to reap).
@@ -143,21 +150,12 @@ search_again:
 		 * To notice when we complete one full cycle, we record the
 		 * first active element seen, before moving it to the tail.
 		 */
-		if (i915_vma_is_active(vma)) {
-			if (vma == active) {
-				if (flags & PIN_NONBLOCK)
-					break;
-
-				active = ERR_PTR(-EAGAIN);
-			}
-
-			if (active != ERR_PTR(-EAGAIN)) {
-				if (!active)
-					active = vma;
+		if (active != ERR_PTR(-EAGAIN) && i915_vma_is_active(vma)) {
+			if (!active)
+				active = vma;
 
-				list_move_tail(&vma->vm_link, &vm->bound_list);
-				continue;
-			}
+			list_move_tail(&vma->vm_link, &vm->bound_list);
+			continue;
 		}
 
 		if (mark_free(&scan, vma, flags, &eviction_list))
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 2a4cd0ba5464..5c8e51d2ba5b 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1207,8 +1207,6 @@ static void engine_record_registers(struct intel_engine_coredump *ee)
 static void record_request(const struct i915_request *request,
 			   struct i915_request_coredump *erq)
 {
-	const struct i915_gem_context *ctx;
-
 	erq->flags = request->fence.flags;
 	erq->context = request->fence.context;
 	erq->seqno = request->fence.seqno;
@@ -1219,9 +1217,13 @@ static void record_request(const struct i915_request *request,
 
 	erq->pid = 0;
 	rcu_read_lock();
-	ctx = rcu_dereference(request->context->gem_context);
-	if (ctx)
-		erq->pid = pid_nr(ctx->pid);
+	if (!intel_context_is_closed(request->context)) {
+		const struct i915_gem_context *ctx;
+
+		ctx = rcu_dereference(request->context->gem_context);
+		if (ctx)
+			erq->pid = pid_nr(ctx->pid);
+	}
 	rcu_read_unlock();
 }
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 9f0653cf0510..8a2b83807ffc 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3358,9 +3358,10 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 
-	u32 de_pipe_masked = GEN8_PIPE_CDCLK_CRC_DONE;
+	u32 de_pipe_masked = gen8_de_pipe_fault_mask(dev_priv) |
+		GEN8_PIPE_CDCLK_CRC_DONE;
 	u32 de_pipe_enables;
-	u32 de_port_masked = GEN8_AUX_CHANNEL_A;
+	u32 de_port_masked = gen8_de_port_aux_mask(dev_priv);
 	u32 de_port_enables;
 	u32 de_misc_masked = GEN8_DE_EDP_PSR;
 	enum pipe pipe;
@@ -3368,21 +3369,8 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	if (INTEL_GEN(dev_priv) <= 10)
 		de_misc_masked |= GEN8_DE_MISC_GSE;
 
-	if (INTEL_GEN(dev_priv) >= 9) {
-		de_pipe_masked |= GEN9_DE_PIPE_IRQ_FAULT_ERRORS;
-		de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
-				  GEN9_AUX_CHANNEL_D;
-		if (IS_GEN9_LP(dev_priv))
-			de_port_masked |= BXT_DE_PORT_GMBUS;
-	} else {
-		de_pipe_masked |= GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
-	}
-
-	if (INTEL_GEN(dev_priv) >= 11)
-		de_port_masked |= ICL_AUX_CHANNEL_E;
-
-	if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11)
-		de_port_masked |= CNL_AUX_CHANNEL_F;
+	if (IS_GEN9_LP(dev_priv))
+		de_port_masked |= BXT_DE_PORT_GMBUS;
 
 	de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
 					   GEN8_PIPE_FIFO_UNDERRUN;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 551be589d6f4..60da28d412d6 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1310,8 +1310,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 			 * dropped by GuC. They won't be part of the context
 			 * ID in the OA reports, so squash those lower bits.
 			 */
-			stream->specific_ctx_id =
-				lower_32_bits(ce->lrc_desc) >> 12;
+			stream->specific_ctx_id = ce->lrc.lrca >> 12;
 
 			/*
 			 * GuC uses the top bit to signal proxy submission, so
@@ -1328,11 +1327,10 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
 		/*
 		 * Pick an unused context id
-		 * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
+		 * 0 - BITS_PER_LONG are used by other contexts
 		 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
 		 */
 		stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-		BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG);
 		break;
 	}
 
@@ -2941,49 +2939,6 @@ void i915_oa_init_reg_state(const struct intel_context *ce,
 }
 
 /**
- * i915_perf_read_locked - &i915_perf_stream_ops->read with error normalisation
- * @stream: An i915 perf stream
- * @file: An i915 perf stream file
- * @buf: destination buffer given by userspace
- * @count: the number of bytes userspace wants to read
- * @ppos: (inout) file seek position (unused)
- *
- * Besides wrapping &i915_perf_stream_ops->read this provides a common place to
- * ensure that if we've successfully copied any data then reporting that takes
- * precedence over any internal error status, so the data isn't lost.
- *
- * For example ret will be -ENOSPC whenever there is more buffered data than
- * can be copied to userspace, but that's only interesting if we weren't able
- * to copy some data because it implies the userspace buffer is too small to
- * receive a single record (and we never split records).
- *
- * Another case with ret == -EFAULT is more of a grey area since it would seem
- * like bad form for userspace to ask us to overrun its buffer, but the user
- * knows best:
- *
- *   http://yarchive.net/comp/linux/partial_reads_writes.html
- *
- * Returns: The number of bytes copied or a negative error code on failure.
- */
-static ssize_t i915_perf_read_locked(struct i915_perf_stream *stream,
-				     struct file *file,
-				     char __user *buf,
-				     size_t count,
-				     loff_t *ppos)
-{
-	/* Note we keep the offset (aka bytes read) separate from any
-	 * error status so that the final check for whether we return
-	 * the bytes read with a higher precedence than any error (see
-	 * comment below) doesn't need to be handled/duplicated in
-	 * stream->ops->read() implementations.
-	 */
-	size_t offset = 0;
-	int ret = stream->ops->read(stream, buf, count, &offset);
-
-	return offset ?: (ret ?: -EAGAIN);
-}
-
-/**
  * i915_perf_read - handles read() FOP for i915 perf stream FDs
  * @file: An i915 perf stream file
  * @buf: destination buffer given by userspace
@@ -3008,7 +2963,8 @@ static ssize_t i915_perf_read(struct file *file,
 {
 	struct i915_perf_stream *stream = file->private_data;
 	struct i915_perf *perf = stream->perf;
-	ssize_t ret;
+	size_t offset = 0;
+	int ret;
 
 	/* To ensure it's handled consistently we simply treat all reads of a
 	 * disabled stream as an error. In particular it might otherwise lead
@@ -3031,13 +2987,12 @@ static ssize_t i915_perf_read(struct file *file,
 				return ret;
 
 			mutex_lock(&perf->lock);
-			ret = i915_perf_read_locked(stream, file,
-						    buf, count, ppos);
+			ret = stream->ops->read(stream, buf, count, &offset);
 			mutex_unlock(&perf->lock);
-		} while (ret == -EAGAIN);
+		} while (!offset && !ret);
 	} else {
 		mutex_lock(&perf->lock);
-		ret = i915_perf_read_locked(stream, file, buf, count, ppos);
+		ret = stream->ops->read(stream, buf, count, &offset);
 		mutex_unlock(&perf->lock);
 	}
 
@@ -3048,15 +3003,15 @@ static ssize_t i915_perf_read(struct file *file,
 	 * and read() returning -EAGAIN. Clearing the oa.pollin state here
 	 * effectively ensures we back off until the next hrtimer callback
 	 * before reporting another EPOLLIN event.
+	 * The exception to this is if ops->read() returned -ENOSPC which means
+	 * that more OA data is available than could fit in the user provided
+	 * buffer. In this case we want the next poll() call to not block.
 	 */
-	if (ret >= 0 || ret == -EAGAIN) {
-		/* Maybe make ->pollin per-stream state if we support multiple
-		 * concurrent streams in the future.
-		 */
+	if (ret != -ENOSPC)
 		stream->pollin = false;
-	}
 
-	return ret;
+	/* Possible values for ret are 0, -EFAULT, -ENOSPC, -EIO, ... */
+	return offset ?: (ret ?: -EAGAIN);
 }
 
 static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)
@@ -3433,10 +3388,10 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 	/* Similar to perf's kernel.perf_paranoid_cpu sysctl option
 	 * we check a dev.i915.perf_stream_paranoid sysctl option
 	 * to determine if it's ok to access system wide OA counters
-	 * without CAP_SYS_ADMIN privileges.
+	 * without CAP_PERFMON or CAP_SYS_ADMIN privileges.
 	 */
 	if (privileged_op &&
-	    i915_perf_stream_paranoid && !capable(CAP_SYS_ADMIN)) {
+	    i915_perf_stream_paranoid && !perfmon_capable()) {
 		DRM_DEBUG("Insufficient privileges to open i915 perf stream\n");
 		ret = -EACCES;
 		goto err_ctx;
@@ -3629,9 +3584,8 @@ static int read_properties_unlocked(struct i915_perf *perf,
 			} else
 				oa_freq_hz = 0;
 
-			if (oa_freq_hz > i915_oa_max_sample_rate &&
-			    !capable(CAP_SYS_ADMIN)) {
-				DRM_DEBUG("OA exponent would exceed the max sampling frequency (sysctl dev.i915.oa_max_sample_rate) %uHz without root privileges\n",
+			if (oa_freq_hz > i915_oa_max_sample_rate && !perfmon_capable()) {
+				DRM_DEBUG("OA exponent would exceed the max sampling frequency (sysctl dev.i915.oa_max_sample_rate) %uHz without CAP_PERFMON or CAP_SYS_ADMIN privileges\n",
 					  i915_oa_max_sample_rate);
 				return -EACCES;
 			}
@@ -4052,7 +4006,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	if (i915_perf_stream_paranoid && !capable(CAP_SYS_ADMIN)) {
+	if (i915_perf_stream_paranoid && !perfmon_capable()) {
 		DRM_DEBUG("Insufficient privileges to add i915 OA config\n");
 		return -EACCES;
 	}
@@ -4199,7 +4153,7 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 		return -ENOTSUPP;
 	}
 
-	if (i915_perf_stream_paranoid && !capable(CAP_SYS_ADMIN)) {
+	if (i915_perf_stream_paranoid && !perfmon_capable()) {
 		DRM_DEBUG("Insufficient privileges to remove i915 OA config\n");
 		return -EACCES;
 	}
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 59e64acc2c56..6e12000c4b6b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -34,8 +34,8 @@
  * Follow the style described here for new macros, and while changing existing
  * macros. Do **not** mass change existing definitions just to update the style.
  *
- * Layout
- * ~~~~~~
+ * File Layout
+ * ~~~~~~~~~~~
  *
  * Keep helper macros near the top. For example, _PIPE() and friends.
  *
@@ -3094,6 +3094,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
+#define GT_WAIT_SEMAPHORE_INTERRUPT		REG_BIT(11) /* bdw+ */
 #define GT_CONTEXT_SWITCH_INTERRUPT		(1 <<  8)
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index c0df71d7d0ff..e2b78db685ea 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1017,11 +1017,15 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 	GEM_BUG_ON(to == from);
 	GEM_BUG_ON(to->timeline == from->timeline);
 
-	if (i915_request_completed(from))
+	if (i915_request_completed(from)) {
+		i915_sw_fence_set_error_once(&to->submit, from->fence.error);
 		return 0;
+	}
 
 	if (to->engine->schedule) {
-		ret = i915_sched_node_add_dependency(&to->sched, &from->sched);
+		ret = i915_sched_node_add_dependency(&to->sched,
+						     &from->sched,
+						     I915_DEPENDENCY_EXTERNAL);
 		if (ret < 0)
 			return ret;
 	}
@@ -1183,7 +1187,9 @@ __i915_request_await_execution(struct i915_request *to,
 
 	/* Couple the dependency tree for PI on this exposed to->fence */
 	if (to->engine->schedule) {
-		err = i915_sched_node_add_dependency(&to->sched, &from->sched);
+		err = i915_sched_node_add_dependency(&to->sched,
+						     &from->sched,
+						     I915_DEPENDENCY_WEAK);
 		if (err < 0)
 			return err;
 	}
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 68b06a7ba667..f0a9e8958ca0 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -456,7 +456,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 }
 
 int i915_sched_node_add_dependency(struct i915_sched_node *node,
-				   struct i915_sched_node *signal)
+				   struct i915_sched_node *signal,
+				   unsigned long flags)
 {
 	struct i915_dependency *dep;
 
@@ -465,8 +466,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 		return -ENOMEM;
 
 	if (!__i915_sched_node_add_dependency(node, signal, dep,
-					      I915_DEPENDENCY_EXTERNAL |
-					      I915_DEPENDENCY_ALLOC))
+					      flags | I915_DEPENDENCY_ALLOC))
 		i915_dependency_free(dep);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index d1dc4efef77b..6f0bf00fc569 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -34,7 +34,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 				      unsigned long flags);
 
 int i915_sched_node_add_dependency(struct i915_sched_node *node,
-				   struct i915_sched_node *signal);
+				   struct i915_sched_node *signal,
+				   unsigned long flags);
 
 void i915_sched_node_fini(struct i915_sched_node *node);
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index d18e70550054..7186875088a0 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -78,6 +78,7 @@ struct i915_dependency {
 	unsigned long flags;
 #define I915_DEPENDENCY_ALLOC		BIT(0)
 #define I915_DEPENDENCY_EXTERNAL	BIT(1)
+#define I915_DEPENDENCY_WEAK		BIT(2)
 };
 
 #endif /* _I915_SCHEDULER_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 08699fa069aa..2cd7a7e87c0a 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -158,16 +158,18 @@ vma_create(struct drm_i915_gem_object *obj,
 
 	GEM_BUG_ON(!IS_ALIGNED(vma->size, I915_GTT_PAGE_SIZE));
 
+	spin_lock(&obj->vma.lock);
+
 	if (i915_is_ggtt(vm)) {
 		if (unlikely(overflows_type(vma->size, u32)))
-			goto err_vma;
+			goto err_unlock;
 
 		vma->fence_size = i915_gem_fence_size(vm->i915, vma->size,
 						      i915_gem_object_get_tiling(obj),
 						      i915_gem_object_get_stride(obj));
 		if (unlikely(vma->fence_size < vma->size || /* overflow */
 			     vma->fence_size > vm->total))
-			goto err_vma;
+			goto err_unlock;
 
 		GEM_BUG_ON(!IS_ALIGNED(vma->fence_size, I915_GTT_MIN_ALIGNMENT));
 
@@ -179,8 +181,6 @@ vma_create(struct drm_i915_gem_object *obj,
 		__set_bit(I915_VMA_GGTT_BIT, __i915_vma_flags(vma));
 	}
 
-	spin_lock(&obj->vma.lock);
-
 	rb = NULL;
 	p = &obj->vma.tree.rb_node;
 	while (*p) {
@@ -225,6 +225,8 @@ vma_create(struct drm_i915_gem_object *obj,
 
 	return vma;
 
+err_unlock:
+	spin_unlock(&obj->vma.lock);
 err_vma:
 	i915_vma_free(vma);
 	return ERR_PTR(-E2BIG);
@@ -1226,18 +1228,6 @@ int __i915_vma_unbind(struct i915_vma *vma)
 
 	lockdep_assert_held(&vma->vm->mutex);
 
-	/*
-	 * First wait upon any activity as retiring the request may
-	 * have side-effects such as unpinning or even unbinding this vma.
-	 *
-	 * XXX Actually waiting under the vm->mutex is a hinderance and
-	 * should be pipelined wherever possible. In cases where that is
-	 * unavoidable, we should lift the wait to before the mutex.
-	 */
-	ret = i915_vma_sync(vma);
-	if (ret)
-		return ret;
-
 	if (i915_vma_is_pinned(vma)) {
 		vma_print_allocator(vma, "is pinned");
 		return -EAGAIN;
@@ -1311,15 +1301,20 @@ int i915_vma_unbind(struct i915_vma *vma)
 	if (!drm_mm_node_allocated(&vma->node))
 		return 0;
 
-	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
-		/* XXX not always required: nop_clear_range */
-		wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
-
 	/* Optimistic wait before taking the mutex */
 	err = i915_vma_sync(vma);
 	if (err)
 		goto out_rpm;
 
+	if (i915_vma_is_pinned(vma)) {
+		vma_print_allocator(vma, "is pinned");
+		return -EAGAIN;
+	}
+
+	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
+		/* XXX not always required: nop_clear_range */
+		wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
+
 	err = mutex_lock_interruptible(&vm->mutex);
 	if (err)
 		goto out_rpm;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 8375054ba27d..a52986a9e7a6 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4992,7 +4992,7 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 	 * WaIncreaseLatencyIPCEnabled: kbl,cfl
 	 * Display WA #1141: kbl,cfl
 	 */
-	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) ||
+	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) &&
 	    dev_priv->ipc_enabled)
 		latency += 4;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index 58b5f40a07dd..af89c7fc8f59 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -173,7 +173,7 @@ static int igt_vma_create(void *arg)
 		}
 
 		nc = 0;
-		for_each_prime_number(num_ctx, 2 * NUM_CONTEXT_TAG) {
+		for_each_prime_number(num_ctx, 2 * BITS_PER_LONG) {
 			for (; nc < num_ctx; nc++) {
 				ctx = mock_context(i915, "mock");
 				if (!ctx)
diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c
index 9dfe7cb530e1..548cc25ea4ab 100644
--- a/drivers/gpu/drm/ingenic/ingenic-drm.c
+++ b/drivers/gpu/drm/ingenic/ingenic-drm.c
@@ -328,8 +328,8 @@ static int ingenic_drm_crtc_atomic_check(struct drm_crtc *crtc,
 	if (!drm_atomic_crtc_needs_modeset(state))
 		return 0;
 
-	if (state->mode.hdisplay > priv->soc_info->max_height ||
-	    state->mode.vdisplay > priv->soc_info->max_width)
+	if (state->mode.hdisplay > priv->soc_info->max_width ||
+	    state->mode.vdisplay > priv->soc_info->max_height)
 		return -EINVAL;
 
 	rate = clk_round_rate(priv->pix_clk,
@@ -474,7 +474,7 @@ static int ingenic_drm_encoder_atomic_check(struct drm_encoder *encoder,
 
 static irqreturn_t ingenic_drm_irq_handler(int irq, void *arg)
 {
-	struct ingenic_drm *priv = arg;
+	struct ingenic_drm *priv = drm_device_get_priv(arg);
 	unsigned int state;
 
 	regmap_read(priv->map, JZ_REG_LCD_STATE, &state);
@@ -843,6 +843,7 @@ static const struct of_device_id ingenic_drm_of_match[] = {
 	{ .compatible = "ingenic,jz4770-lcd", .data = &jz4770_soc_info },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, ingenic_drm_of_match);
 
 static struct platform_driver ingenic_drm_driver = {
 	.driver = {
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index b5f5eb7b4bb9..8c2e1b47e81a 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -412,9 +412,7 @@ static int __maybe_unused meson_drv_pm_resume(struct device *dev)
 	if (priv->afbcd.ops)
 		priv->afbcd.ops->init(priv);
 
-	drm_mode_config_helper_resume(priv->drm);
-
-	return 0;
+	return drm_mode_config_helper_resume(priv->drm);
 }
 
 static int compare_of(struct device *dev, void *data)
diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c
index e8c94915a4fc..64cb6ba4bc42 100644
--- a/drivers/gpu/drm/meson/meson_dw_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c
@@ -1034,10 +1034,8 @@ static int meson_dw_hdmi_bind(struct device *dev, struct device *master,
 		return PTR_ERR(dw_plat_data->regm);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "Failed to get hdmi top irq\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_threaded_irq(dev, irq, dw_hdmi_top_irq,
 					dw_hdmi_top_thread_irq, IRQF_SHARED,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c
index 232a9d7c51e5..e770c9497871 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c
@@ -25,6 +25,9 @@
 MODULE_FIRMWARE("nvidia/gp108/sec2/desc.bin");
 MODULE_FIRMWARE("nvidia/gp108/sec2/image.bin");
 MODULE_FIRMWARE("nvidia/gp108/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/gv100/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/gv100/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/gv100/sec2/sig.bin");
 
 static const struct nvkm_sec2_fwif
 gp108_sec2_fwif[] = {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c
index b6ebd95c9ba1..a8295653ceab 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c
@@ -56,6 +56,22 @@ tu102_sec2_nofw(struct nvkm_sec2 *sec2, int ver,
 	return 0;
 }
 
+MODULE_FIRMWARE("nvidia/tu102/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/tu102/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/tu102/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/tu104/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/tu104/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/tu104/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/tu106/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/tu106/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/tu106/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/tu116/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/tu116/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/tu116/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/tu117/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/tu117/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/tu117/sec2/sig.bin");
+
 static const struct nvkm_sec2_fwif
 tu102_sec2_fwif[] = {
 	{  0, gp102_sec2_load, &tu102_sec2, &gp102_sec2_acr_1 },
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index d1086b2a6892..05863b253d68 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -480,9 +480,10 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev,
 		return ret;
 
 	ret = qxl_release_reserve_list(release, true);
-	if (ret)
+	if (ret) {
+		qxl_release_free(qdev, release);
 		return ret;
-
+	}
 	cmd = (struct qxl_surface_cmd *)qxl_release_map(qdev, release);
 	cmd->type = QXL_SURFACE_CMD_CREATE;
 	cmd->flags = QXL_SURF_FLAG_KEEP_DATA;
@@ -499,8 +500,8 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev,
 	/* no need to add a release to the fence for this surface bo,
 	   since it is only released when we ask to destroy the surface
 	   and it would never signal otherwise */
-	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 
 	surf->hw_surf_alloc = true;
 	spin_lock(&qdev->surf_id_idr_lock);
@@ -542,9 +543,8 @@ int qxl_hw_surface_dealloc(struct qxl_device *qdev,
 	cmd->surface_id = id;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
-
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 09583a08e141..91f398d51cfa 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -510,8 +510,8 @@ static int qxl_primary_apply_cursor(struct drm_plane *plane)
 	cmd->u.set.visible = 1;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 
 	return ret;
 
@@ -652,8 +652,8 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane,
 	cmd->u.position.y = plane->state->crtc_y + fb->hot_y;
 
 	qxl_release_unmap(qdev, release, &cmd->release_info);
-	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 
 	if (old_cursor_bo != NULL)
 		qxl_bo_unpin(old_cursor_bo);
@@ -700,8 +700,8 @@ static void qxl_cursor_atomic_disable(struct drm_plane *plane,
 	cmd->type = QXL_CURSOR_HIDE;
 	qxl_release_unmap(qdev, release, &cmd->release_info);
 
-	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false);
 }
 
 static void qxl_update_dumb_head(struct qxl_device *qdev,
diff --git a/drivers/gpu/drm/qxl/qxl_draw.c b/drivers/gpu/drm/qxl/qxl_draw.c
index 5bebf1ea1c5d..3599db096973 100644
--- a/drivers/gpu/drm/qxl/qxl_draw.c
+++ b/drivers/gpu/drm/qxl/qxl_draw.c
@@ -209,9 +209,10 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev,
 		goto out_release_backoff;
 
 	rects = drawable_set_clipping(qdev, num_clips, clips_bo);
-	if (!rects)
+	if (!rects) {
+		ret = -EINVAL;
 		goto out_release_backoff;
-
+	}
 	drawable = (struct qxl_drawable *)qxl_release_map(qdev, release);
 
 	drawable->clip.type = SPICE_CLIP_TYPE_RECTS;
@@ -242,8 +243,8 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev,
 	}
 	qxl_bo_kunmap(clips_bo);
 
-	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
 	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false);
 
 out_release_backoff:
 	if (ret)
diff --git a/drivers/gpu/drm/qxl/qxl_image.c b/drivers/gpu/drm/qxl/qxl_image.c
index 43688ecdd8a0..60ab7151b84d 100644
--- a/drivers/gpu/drm/qxl/qxl_image.c
+++ b/drivers/gpu/drm/qxl/qxl_image.c
@@ -212,7 +212,8 @@ qxl_image_init_helper(struct qxl_device *qdev,
 		break;
 	default:
 		DRM_ERROR("unsupported image bit depth\n");
-		return -EINVAL; /* TODO: cleanup */
+		qxl_bo_kunmap_atomic_page(qdev, image_bo, ptr);
+		return -EINVAL;
 	}
 	image->u.bitmap.flags = QXL_BITMAP_TOP_DOWN;
 	image->u.bitmap.x = width;
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 8117a45b3610..72f3f1bbb40c 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -261,11 +261,8 @@ static int qxl_process_single_command(struct qxl_device *qdev,
 			apply_surf_reloc(qdev, &reloc_info[i]);
 	}
 
+	qxl_release_fence_buffer_objects(release);
 	ret = qxl_push_command_ring_release(qdev, release, cmd->type, true);
-	if (ret)
-		qxl_release_backoff_reserve_list(release);
-	else
-		qxl_release_fence_buffer_objects(release);
 
 out_free_bos:
 out_free_release:
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 8e731ed0d9d9..2f319102ae9f 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -676,7 +676,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 	 */
 	if ((sched->timeout != MAX_SCHEDULE_TIMEOUT &&
 	    !cancel_delayed_work(&sched->work_tdr)) ||
-	    __kthread_should_park(sched->thread))
+	    kthread_should_park())
 		return NULL;
 
 	spin_lock(&sched->job_list_lock);
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 059939789730..3eb89f1eb0e1 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -717,7 +717,7 @@ static void sun6i_dsi_encoder_enable(struct drm_encoder *encoder)
 	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder);
 	struct mipi_dsi_device *device = dsi->device;
-	union phy_configure_opts opts = { 0 };
+	union phy_configure_opts opts = { };
 	struct phy_configure_opts_mipi_dphy *cfg = &opts.mipi_dphy;
 	u16 delay;
 	int err;
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index bd268028fb3d..583cd6e0ae27 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -1039,6 +1039,7 @@ void tegra_drm_free(struct tegra_drm *tegra, size_t size, void *virt,
 
 static bool host1x_drm_wants_iommu(struct host1x_device *dev)
 {
+	struct host1x *host1x = dev_get_drvdata(dev->dev.parent);
 	struct iommu_domain *domain;
 
 	/*
@@ -1076,7 +1077,7 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev)
 	 * sufficient and whether or not the host1x is attached to an IOMMU
 	 * doesn't matter.
 	 */
-	if (!domain && dma_get_mask(dev->dev.parent) <= DMA_BIT_MASK(32))
+	if (!domain && host1x_get_dma_mask(host1x) <= DMA_BIT_MASK(32))
 		return true;
 
 	return domain != NULL;
diff --git a/drivers/gpu/drm/tidss/tidss_crtc.c b/drivers/gpu/drm/tidss/tidss_crtc.c
index d4ce9bab8c7e..3221a707e073 100644
--- a/drivers/gpu/drm/tidss/tidss_crtc.c
+++ b/drivers/gpu/drm/tidss/tidss_crtc.c
@@ -379,9 +379,17 @@ static struct drm_crtc_state *tidss_crtc_duplicate_state(struct drm_crtc *crtc)
 	return &state->base;
 }
 
+static void tidss_crtc_destroy(struct drm_crtc *crtc)
+{
+	struct tidss_crtc *tcrtc = to_tidss_crtc(crtc);
+
+	drm_crtc_cleanup(crtc);
+	kfree(tcrtc);
+}
+
 static const struct drm_crtc_funcs tidss_crtc_funcs = {
 	.reset = tidss_crtc_reset,
-	.destroy = drm_crtc_cleanup,
+	.destroy = tidss_crtc_destroy,
 	.set_config = drm_atomic_helper_set_config,
 	.page_flip = drm_atomic_helper_page_flip,
 	.atomic_duplicate_state = tidss_crtc_duplicate_state,
@@ -400,7 +408,7 @@ struct tidss_crtc *tidss_crtc_create(struct tidss_device *tidss,
 	bool has_ctm = tidss->feat->vp_feat.color.has_ctm;
 	int ret;
 
-	tcrtc = devm_kzalloc(tidss->dev, sizeof(*tcrtc), GFP_KERNEL);
+	tcrtc = kzalloc(sizeof(*tcrtc), GFP_KERNEL);
 	if (!tcrtc)
 		return ERR_PTR(-ENOMEM);
 
@@ -411,8 +419,10 @@ struct tidss_crtc *tidss_crtc_create(struct tidss_device *tidss,
 
 	ret = drm_crtc_init_with_planes(&tidss->ddev, crtc, primary,
 					NULL, &tidss_crtc_funcs, NULL);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(tcrtc);
 		return ERR_PTR(ret);
+	}
 
 	drm_crtc_helper_add(crtc, &tidss_crtc_helper_funcs);
 
diff --git a/drivers/gpu/drm/tidss/tidss_encoder.c b/drivers/gpu/drm/tidss/tidss_encoder.c
index 83785b0a66a9..30bf2a65949c 100644
--- a/drivers/gpu/drm/tidss/tidss_encoder.c
+++ b/drivers/gpu/drm/tidss/tidss_encoder.c
@@ -55,12 +55,18 @@ static int tidss_encoder_atomic_check(struct drm_encoder *encoder,
 	return 0;
 }
 
+static void tidss_encoder_destroy(struct drm_encoder *encoder)
+{
+	drm_encoder_cleanup(encoder);
+	kfree(encoder);
+}
+
 static const struct drm_encoder_helper_funcs encoder_helper_funcs = {
 	.atomic_check = tidss_encoder_atomic_check,
 };
 
 static const struct drm_encoder_funcs encoder_funcs = {
-	.destroy = drm_encoder_cleanup,
+	.destroy = tidss_encoder_destroy,
 };
 
 struct drm_encoder *tidss_encoder_create(struct tidss_device *tidss,
@@ -69,7 +75,7 @@ struct drm_encoder *tidss_encoder_create(struct tidss_device *tidss,
 	struct drm_encoder *enc;
 	int ret;
 
-	enc = devm_kzalloc(tidss->dev, sizeof(*enc), GFP_KERNEL);
+	enc = kzalloc(sizeof(*enc), GFP_KERNEL);
 	if (!enc)
 		return ERR_PTR(-ENOMEM);
 
@@ -77,8 +83,10 @@ struct drm_encoder *tidss_encoder_create(struct tidss_device *tidss,
 
 	ret = drm_encoder_init(&tidss->ddev, enc, &encoder_funcs,
 			       encoder_type, NULL);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(enc);
 		return ERR_PTR(ret);
+	}
 
 	drm_encoder_helper_add(enc, &encoder_helper_funcs);
 
diff --git a/drivers/gpu/drm/tidss/tidss_plane.c b/drivers/gpu/drm/tidss/tidss_plane.c
index ff99b2dd4a17..798488948fc5 100644
--- a/drivers/gpu/drm/tidss/tidss_plane.c
+++ b/drivers/gpu/drm/tidss/tidss_plane.c
@@ -141,6 +141,14 @@ static void tidss_plane_atomic_disable(struct drm_plane *plane,
 	dispc_plane_enable(tidss->dispc, tplane->hw_plane_id, false);
 }
 
+static void drm_plane_destroy(struct drm_plane *plane)
+{
+	struct tidss_plane *tplane = to_tidss_plane(plane);
+
+	drm_plane_cleanup(plane);
+	kfree(tplane);
+}
+
 static const struct drm_plane_helper_funcs tidss_plane_helper_funcs = {
 	.atomic_check = tidss_plane_atomic_check,
 	.atomic_update = tidss_plane_atomic_update,
@@ -151,7 +159,7 @@ static const struct drm_plane_funcs tidss_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
 	.reset = drm_atomic_helper_plane_reset,
-	.destroy = drm_plane_cleanup,
+	.destroy = drm_plane_destroy,
 	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
 };
@@ -175,7 +183,7 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss,
 			   BIT(DRM_MODE_BLEND_COVERAGE));
 	int ret;
 
-	tplane = devm_kzalloc(tidss->dev, sizeof(*tplane), GFP_KERNEL);
+	tplane = kzalloc(sizeof(*tplane), GFP_KERNEL);
 	if (!tplane)
 		return ERR_PTR(-ENOMEM);
 
@@ -190,7 +198,7 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss,
 				       formats, num_formats,
 				       NULL, type, NULL);
 	if (ret < 0)
-		return ERR_PTR(ret);
+		goto err;
 
 	drm_plane_helper_add(&tplane->plane, &tidss_plane_helper_funcs);
 
@@ -203,15 +211,19 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss,
 						default_encoding,
 						default_range);
 	if (ret)
-		return ERR_PTR(ret);
+		goto err;
 
 	ret = drm_plane_create_alpha_property(&tplane->plane);
 	if (ret)
-		return ERR_PTR(ret);
+		goto err;
 
 	ret = drm_plane_create_blend_mode_property(&tplane->plane, blend_modes);
 	if (ret)
-		return ERR_PTR(ret);
+		goto err;
 
 	return tplane;
+
+err:
+	kfree(tplane);
+	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index c1824bdf2418..7879ff58236f 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -221,6 +221,7 @@ struct virtio_gpu_fpriv {
 /* virtio_ioctl.c */
 #define DRM_VIRTIO_NUM_IOCTLS 10
 extern struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS];
+void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file);
 
 /* virtio_kms.c */
 int virtio_gpu_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c
index 0d6152c99a27..f0d5a8974677 100644
--- a/drivers/gpu/drm/virtio/virtgpu_gem.c
+++ b/drivers/gpu/drm/virtio/virtgpu_gem.c
@@ -39,6 +39,9 @@ int virtio_gpu_gem_create(struct drm_file *file,
 	int ret;
 	u32 handle;
 
+	if (vgdev->has_virgl_3d)
+		virtio_gpu_create_context(dev, file);
+
 	ret = virtio_gpu_object_create(vgdev, params, &obj, NULL);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 336cc9143205..512daff92038 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -27,14 +27,14 @@
 
 #include <linux/file.h>
 #include <linux/sync_file.h>
+#include <linux/uaccess.h>
 
 #include <drm/drm_file.h>
 #include <drm/virtgpu_drm.h>
 
 #include "virtgpu_drv.h"
 
-static void virtio_gpu_create_context(struct drm_device *dev,
-				      struct drm_file *file)
+void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file)
 {
 	struct virtio_gpu_device *vgdev = dev->dev_private;
 	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c
index 023a030ca7b9..0a5c8cf409fb 100644
--- a/drivers/gpu/drm/virtio/virtgpu_kms.c
+++ b/drivers/gpu/drm/virtio/virtgpu_kms.c
@@ -25,6 +25,7 @@
 
 #include <linux/virtio.h>
 #include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
 
 #include <drm/drm_file.h>
 
@@ -52,14 +53,6 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work)
 		      events_clear, &events_clear);
 }
 
-static void virtio_gpu_context_destroy(struct virtio_gpu_device *vgdev,
-				      uint32_t ctx_id)
-{
-	virtio_gpu_cmd_context_destroy(vgdev, ctx_id);
-	virtio_gpu_notify(vgdev);
-	ida_free(&vgdev->ctx_id_ida, ctx_id - 1);
-}
-
 static void virtio_gpu_init_vq(struct virtio_gpu_queue *vgvq,
 			       void (*work_func)(struct work_struct *work))
 {
@@ -274,14 +267,17 @@ int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file)
 void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct virtio_gpu_device *vgdev = dev->dev_private;
-	struct virtio_gpu_fpriv *vfpriv;
+	struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
 
 	if (!vgdev->has_virgl_3d)
 		return;
 
-	vfpriv = file->driver_priv;
+	if (vfpriv->context_created) {
+		virtio_gpu_cmd_context_destroy(vgdev, vfpriv->ctx_id);
+		virtio_gpu_notify(vgdev);
+	}
 
-	virtio_gpu_context_destroy(vgdev, vfpriv->ctx_id);
+	ida_free(&vgdev->ctx_id_ida, vfpriv->ctx_id - 1);
 	mutex_destroy(&vfpriv->context_lock);
 	kfree(vfpriv);
 	file->driver_priv = NULL;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 8cdcd6e5f9e1..3596f3923ea3 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -850,7 +850,7 @@ extern void vmw_bo_bo_free(struct ttm_buffer_object *bo);
 extern int vmw_bo_init(struct vmw_private *dev_priv,
 		       struct vmw_buffer_object *vmw_bo,
 		       size_t size, struct ttm_placement *placement,
-		       bool interuptable,
+		       bool interruptible,
 		       void (*bo_free)(struct ttm_buffer_object *bo));
 extern int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
 				     struct ttm_object_file *tfile);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 178a6cd1a06f..0f8d29397157 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -515,7 +515,7 @@ bool vmw_fence_obj_signaled(struct vmw_fence_obj *fence)
 	struct vmw_fence_manager *fman = fman_from_fence(fence);
 
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->base.flags))
-		return 1;
+		return true;
 
 	vmw_fences_update(fman);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 7ef51fa84b01..126f93c0b0b8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1651,7 +1651,7 @@ vmw_gb_surface_reference_internal(struct drm_device *dev,
 	struct vmw_surface_metadata *metadata;
 	struct ttm_base_object *base;
 	uint32_t backup_handle;
-	int ret = -EINVAL;
+	int ret;
 
 	ret = vmw_surface_handle_reference(dev_priv, file_priv, req->sid,
 					   req->handle_type, &base);
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 388bcc2889aa..d24344e91922 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -192,17 +192,55 @@ static void host1x_setup_sid_table(struct host1x *host)
 	}
 }
 
+static bool host1x_wants_iommu(struct host1x *host1x)
+{
+	/*
+	 * If we support addressing a maximum of 32 bits of physical memory
+	 * and if the host1x firewall is enabled, there's no need to enable
+	 * IOMMU support. This can happen for example on Tegra20, Tegra30
+	 * and Tegra114.
+	 *
+	 * Tegra124 and later can address up to 34 bits of physical memory and
+	 * many platforms come equipped with more than 2 GiB of system memory,
+	 * which requires crossing the 4 GiB boundary. But there's a catch: on
+	 * SoCs before Tegra186 (i.e. Tegra124 and Tegra210), the host1x can
+	 * only address up to 32 bits of memory in GATHER opcodes, which means
+	 * that command buffers need to either be in the first 2 GiB of system
+	 * memory (which could quickly lead to memory exhaustion), or command
+	 * buffers need to be treated differently from other buffers (which is
+	 * not possible with the current ABI).
+	 *
+	 * A third option is to use the IOMMU in these cases to make sure all
+	 * buffers will be mapped into a 32-bit IOVA space that host1x can
+	 * address. This allows all of the system memory to be used and works
+	 * within the limitations of the host1x on these SoCs.
+	 *
+	 * In summary, default to enable IOMMU on Tegra124 and later. For any
+	 * of the earlier SoCs, only use the IOMMU for additional safety when
+	 * the host1x firewall is disabled.
+	 */
+	if (host1x->info->dma_mask <= DMA_BIT_MASK(32)) {
+		if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL))
+			return false;
+	}
+
+	return true;
+}
+
 static struct iommu_domain *host1x_iommu_attach(struct host1x *host)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev);
 	int err;
 
 	/*
-	 * If the host1x firewall is enabled, there's no need to enable IOMMU
-	 * support. Similarly, if host1x is already attached to an IOMMU (via
-	 * the DMA API), don't try to attach again.
+	 * We may not always want to enable IOMMU support (for example if the
+	 * host1x firewall is already enabled and we don't support addressing
+	 * more than 32 bits of physical memory), so check for that first.
+	 *
+	 * Similarly, if host1x is already attached to an IOMMU (via the DMA
+	 * API), don't try to attach again.
 	 */
-	if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) || domain)
+	if (!host1x_wants_iommu(host) || domain)
 		return domain;
 
 	host->group = iommu_group_get(host->dev);
@@ -502,6 +540,19 @@ static void __exit tegra_host1x_exit(void)
 }
 module_exit(tegra_host1x_exit);
 
+/**
+ * host1x_get_dma_mask() - query the supported DMA mask for host1x
+ * @host1x: host1x instance
+ *
+ * Note that this returns the supported DMA mask for host1x, which can be
+ * different from the applicable DMA mask under certain circumstances.
+ */
+u64 host1x_get_dma_mask(struct host1x *host1x)
+{
+	return host1x->info->dma_mask;
+}
+EXPORT_SYMBOL(host1x_get_dma_mask);
+
 MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>");
 MODULE_AUTHOR("Terje Bergstrom <tbergstrom@nvidia.com>");
 MODULE_DESCRIPTION("Host1x driver for Tegra products");
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 7c89edbd6c5a..34f07371716d 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -1155,6 +1155,7 @@ config HID_ALPS
 config HID_MCP2221
 	tristate "Microchip MCP2221 HID USB-to-I2C/SMbus host support"
 	depends on USB_HID && I2C
+	depends on GPIOLIB
 	---help---
 	Provides I2C and SMBUS host adapter functionality over USB-HID
 	through MCP2221 device.
diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c
index fa704153cb00..b2ad319a74b9 100644
--- a/drivers/hid/hid-alps.c
+++ b/drivers/hid/hid-alps.c
@@ -802,6 +802,7 @@ static int alps_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		break;
 	case HID_DEVICE_ID_ALPS_U1_DUAL:
 	case HID_DEVICE_ID_ALPS_U1:
+	case HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY:
 		data->dev_type = U1;
 		break;
 	default:
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index b18b13147a6f..1c71a1aa76b2 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -79,10 +79,10 @@
 #define HID_DEVICE_ID_ALPS_U1_DUAL_PTP	0x121F
 #define HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP	0x1220
 #define HID_DEVICE_ID_ALPS_U1		0x1215
+#define HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY         0x121E
 #define HID_DEVICE_ID_ALPS_T4_BTNLESS	0x120C
 #define HID_DEVICE_ID_ALPS_1222		0x1222
 
-
 #define USB_VENDOR_ID_AMI		0x046b
 #define USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE	0xff10
 
@@ -385,6 +385,7 @@
 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_7349	0x7349
 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_73F7	0x73f7
 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001	0xa001
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002	0xc002
 
 #define USB_VENDOR_ID_ELAN		0x04f3
 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W	0x0401
@@ -759,6 +760,7 @@
 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2	0xc218
 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2_2	0xc219
 #define USB_DEVICE_ID_LOGITECH_G15_LCD		0xc222
+#define USB_DEVICE_ID_LOGITECH_G11		0xc225
 #define USB_DEVICE_ID_LOGITECH_G15_V2_LCD	0xc227
 #define USB_DEVICE_ID_LOGITECH_G510		0xc22d
 #define USB_DEVICE_ID_LOGITECH_G510_USB_AUDIO	0xc22e
@@ -1097,6 +1099,9 @@
 #define USB_DEVICE_ID_SYMBOL_SCANNER_2	0x1300
 #define USB_DEVICE_ID_SYMBOL_SCANNER_3	0x1200
 
+#define I2C_VENDOR_ID_SYNAPTICS     0x06cb
+#define I2C_PRODUCT_ID_SYNAPTICS_SYNA2393   0x7a13
+
 #define USB_VENDOR_ID_SYNAPTICS		0x06cb
 #define USB_DEVICE_ID_SYNAPTICS_TP	0x0001
 #define USB_DEVICE_ID_SYNAPTICS_INT_TP	0x0002
@@ -1111,6 +1116,7 @@
 #define USB_DEVICE_ID_SYNAPTICS_LTS2	0x1d10
 #define USB_DEVICE_ID_SYNAPTICS_HD	0x0ac3
 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD	0x1ac3
+#define USB_DEVICE_ID_SYNAPTICS_DELL_K12A	0x2819
 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012	0x2968
 #define USB_DEVICE_ID_SYNAPTICS_TP_V103	0x5710
 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5	0x81a7
diff --git a/drivers/hid/hid-lg-g15.c b/drivers/hid/hid-lg-g15.c
index ad4b5412a9f4..ef0cbcd7540d 100644
--- a/drivers/hid/hid-lg-g15.c
+++ b/drivers/hid/hid-lg-g15.c
@@ -872,6 +872,10 @@ error_hw_stop:
 }
 
 static const struct hid_device_id lg_g15_devices[] = {
+	/* The G11 is a G15 without the LCD, treat it as a G15 */
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
+		USB_DEVICE_ID_LOGITECH_G11),
+		.driver_data = LG_G15 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
 			 USB_DEVICE_ID_LOGITECH_G15_LCD),
 		.driver_data = LG_G15 },
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 362805ddf377..03c720b47306 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1922,6 +1922,9 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_EGALAX_SERIAL,
 		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
 			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001) },
+	{ .driver_data = MT_CLS_EGALAX,
+		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) },
 
 	/* Elitegroup panel */
 	{ .driver_data = MT_CLS_SERIAL,
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index ebec818344af..e4cb543de0cd 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -163,6 +163,7 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103), HID_QUIRK_NO_INIT_REPORTS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DELL_K12A), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TOPMAX, USB_DEVICE_ID_TOPMAX_COBRAPAD), HID_QUIRK_BADPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TOUCHPACK, USB_DEVICE_ID_TOUCHPACK_RTS), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TPV, USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN_8882), HID_QUIRK_NOGET },
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 009000c5d55c..294c84e136d7 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -177,6 +177,8 @@ static const struct i2c_hid_quirks {
 		 I2C_HID_QUIRK_BOGUS_IRQ },
 	{ USB_VENDOR_ID_ALPS_JP, HID_ANY_ID,
 		 I2C_HID_QUIRK_RESET_ON_RESUME },
+	{ I2C_VENDOR_ID_SYNAPTICS, I2C_PRODUCT_ID_SYNAPTICS_SYNA2393,
+		 I2C_HID_QUIRK_RESET_ON_RESUME },
 	{ USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720,
 		I2C_HID_QUIRK_BAD_INPUT_SIZE },
 	{ 0, 0 }
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index c7bc9db5b192..17a638f15082 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -682,16 +682,21 @@ static int usbhid_open(struct hid_device *hid)
 	struct usbhid_device *usbhid = hid->driver_data;
 	int res;
 
+	mutex_lock(&usbhid->mutex);
+
 	set_bit(HID_OPENED, &usbhid->iofl);
 
-	if (hid->quirks & HID_QUIRK_ALWAYS_POLL)
-		return 0;
+	if (hid->quirks & HID_QUIRK_ALWAYS_POLL) {
+		res = 0;
+		goto Done;
+	}
 
 	res = usb_autopm_get_interface(usbhid->intf);
 	/* the device must be awake to reliably request remote wakeup */
 	if (res < 0) {
 		clear_bit(HID_OPENED, &usbhid->iofl);
-		return -EIO;
+		res = -EIO;
+		goto Done;
 	}
 
 	usbhid->intf->needs_remote_wakeup = 1;
@@ -725,6 +730,9 @@ static int usbhid_open(struct hid_device *hid)
 		msleep(50);
 
 	clear_bit(HID_RESUME_RUNNING, &usbhid->iofl);
+
+ Done:
+	mutex_unlock(&usbhid->mutex);
 	return res;
 }
 
@@ -732,6 +740,8 @@ static void usbhid_close(struct hid_device *hid)
 {
 	struct usbhid_device *usbhid = hid->driver_data;
 
+	mutex_lock(&usbhid->mutex);
+
 	/*
 	 * Make sure we don't restart data acquisition due to
 	 * a resumption we no longer care about by avoiding racing
@@ -743,12 +753,13 @@ static void usbhid_close(struct hid_device *hid)
 		clear_bit(HID_IN_POLLING, &usbhid->iofl);
 	spin_unlock_irq(&usbhid->lock);
 
-	if (hid->quirks & HID_QUIRK_ALWAYS_POLL)
-		return;
+	if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) {
+		hid_cancel_delayed_stuff(usbhid);
+		usb_kill_urb(usbhid->urbin);
+		usbhid->intf->needs_remote_wakeup = 0;
+	}
 
-	hid_cancel_delayed_stuff(usbhid);
-	usb_kill_urb(usbhid->urbin);
-	usbhid->intf->needs_remote_wakeup = 0;
+	mutex_unlock(&usbhid->mutex);
 }
 
 /*
@@ -1057,6 +1068,8 @@ static int usbhid_start(struct hid_device *hid)
 	unsigned int n, insize = 0;
 	int ret;
 
+	mutex_lock(&usbhid->mutex);
+
 	clear_bit(HID_DISCONNECTED, &usbhid->iofl);
 
 	usbhid->bufsize = HID_MIN_BUFFER_SIZE;
@@ -1177,6 +1190,8 @@ static int usbhid_start(struct hid_device *hid)
 		usbhid_set_leds(hid);
 		device_set_wakeup_enable(&dev->dev, 1);
 	}
+
+	mutex_unlock(&usbhid->mutex);
 	return 0;
 
 fail:
@@ -1187,6 +1202,7 @@ fail:
 	usbhid->urbout = NULL;
 	usbhid->urbctrl = NULL;
 	hid_free_buffers(dev, hid);
+	mutex_unlock(&usbhid->mutex);
 	return ret;
 }
 
@@ -1202,6 +1218,8 @@ static void usbhid_stop(struct hid_device *hid)
 		usbhid->intf->needs_remote_wakeup = 0;
 	}
 
+	mutex_lock(&usbhid->mutex);
+
 	clear_bit(HID_STARTED, &usbhid->iofl);
 	spin_lock_irq(&usbhid->lock);	/* Sync with error and led handlers */
 	set_bit(HID_DISCONNECTED, &usbhid->iofl);
@@ -1222,6 +1240,8 @@ static void usbhid_stop(struct hid_device *hid)
 	usbhid->urbout = NULL;
 
 	hid_free_buffers(hid_to_usb_dev(hid), hid);
+
+	mutex_unlock(&usbhid->mutex);
 }
 
 static int usbhid_power(struct hid_device *hid, int lvl)
@@ -1382,6 +1402,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *
 	INIT_WORK(&usbhid->reset_work, hid_reset);
 	timer_setup(&usbhid->io_retry, hid_retry_timeout, 0);
 	spin_lock_init(&usbhid->lock);
+	mutex_init(&usbhid->mutex);
 
 	ret = hid_add_device(hid);
 	if (ret) {
diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h
index 8620408bd7af..75fe85d3d27a 100644
--- a/drivers/hid/usbhid/usbhid.h
+++ b/drivers/hid/usbhid/usbhid.h
@@ -80,6 +80,7 @@ struct usbhid_device {
 	dma_addr_t outbuf_dma;                                          /* Output buffer dma */
 	unsigned long last_out;							/* record of last output for timeouts */
 
+	struct mutex mutex;						/* start/stop/open/close */
 	spinlock_t lock;						/* fifo spinlock */
 	unsigned long iofl;                                             /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */
 	struct timer_list io_retry;                                     /* Retry timer */
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 5ded94b7bf68..cd71e7133944 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -319,9 +319,11 @@ static void wacom_feature_mapping(struct hid_device *hdev,
 			data[0] = field->report->id;
 			ret = wacom_get_report(hdev, HID_FEATURE_REPORT,
 					       data, n, WAC_CMD_RETRIES);
-			if (ret == n) {
+			if (ret == n && features->type == HID_GENERIC) {
 				ret = hid_report_raw_event(hdev,
 					HID_FEATURE_REPORT, data, n, 0);
+			} else if (ret == 2 && features->type != HID_GENERIC) {
+				features->touch_max = data[1];
 			} else {
 				features->touch_max = 16;
 				hid_warn(hdev, "wacom_feature_mapping: "
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index d99a9d407671..1c96809b51c9 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -1427,11 +1427,13 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom)
 {
 	struct input_dev *pad_input = wacom->pad_input;
 	unsigned char *data = wacom->data;
+	int nbuttons = wacom->features.numbered_buttons;
 
-	int buttons = data[282] | ((data[281] & 0x40) << 2);
+	int expresskeys = data[282];
+	int center = (data[281] & 0x40) >> 6;
 	int ring = data[285] & 0x7F;
 	bool ringstatus = data[285] & 0x80;
-	bool prox = buttons || ringstatus;
+	bool prox = expresskeys || center || ringstatus;
 
 	/* Fix touchring data: userspace expects 0 at left and increasing clockwise */
 	ring = 71 - ring;
@@ -1439,7 +1441,8 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom)
 	if (ring > 71)
 		ring -= 72;
 
-	wacom_report_numbered_buttons(pad_input, 9, buttons);
+	wacom_report_numbered_buttons(pad_input, nbuttons,
+                                      expresskeys | (center << (nbuttons - 1)));
 
 	input_report_abs(pad_input, ABS_WHEEL, ringstatus ? ring : 0);
 
@@ -2637,9 +2640,25 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev,
 			case HID_DG_TIPSWITCH:
 				hid_data->last_slot_field = equivalent_usage;
 				break;
+			case HID_DG_CONTACTCOUNT:
+				hid_data->cc_report = report->id;
+				hid_data->cc_index = i;
+				hid_data->cc_value_index = j;
+				break;
 			}
 		}
 	}
+
+	if (hid_data->cc_report != 0 &&
+	    hid_data->cc_index >= 0) {
+		struct hid_field *field = report->field[hid_data->cc_index];
+		int value = field->value[hid_data->cc_value_index];
+		if (value)
+			hid_data->num_expected = value;
+	}
+	else {
+		hid_data->num_expected = wacom_wac->features.touch_max;
+	}
 }
 
 static void wacom_wac_finger_report(struct hid_device *hdev,
@@ -2649,7 +2668,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev,
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
 	struct input_dev *input = wacom_wac->touch_input;
 	unsigned touch_max = wacom_wac->features.touch_max;
-	struct hid_data *hid_data = &wacom_wac->hid_data;
 
 	/* If more packets of data are expected, give us a chance to
 	 * process them rather than immediately syncing a partial
@@ -2663,7 +2681,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev,
 
 	input_sync(input);
 	wacom_wac->hid_data.num_received = 0;
-	hid_data->num_expected = 0;
 
 	/* keep touch state for pen event */
 	wacom_wac->shared->touch_down = wacom_wac_finger_count_touches(wacom_wac);
@@ -2738,73 +2755,12 @@ static void wacom_report_events(struct hid_device *hdev,
 	}
 }
 
-static void wacom_set_num_expected(struct hid_device *hdev,
-				   struct hid_report *report,
-				   int collection_index,
-				   struct hid_field *field,
-				   int field_index)
-{
-	struct wacom *wacom = hid_get_drvdata(hdev);
-	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct hid_data *hid_data = &wacom_wac->hid_data;
-	unsigned int original_collection_level =
-		hdev->collection[collection_index].level;
-	bool end_collection = false;
-	int i;
-
-	if (hid_data->num_expected)
-		return;
-
-	// find the contact count value for this segment
-	for (i = field_index; i < report->maxfield && !end_collection; i++) {
-		struct hid_field *field = report->field[i];
-		unsigned int field_level =
-			hdev->collection[field->usage[0].collection_index].level;
-		unsigned int j;
-
-		if (field_level != original_collection_level)
-			continue;
-
-		for (j = 0; j < field->maxusage; j++) {
-			struct hid_usage *usage = &field->usage[j];
-
-			if (usage->collection_index != collection_index) {
-				end_collection = true;
-				break;
-			}
-			if (wacom_equivalent_usage(usage->hid) == HID_DG_CONTACTCOUNT) {
-				hid_data->cc_report = report->id;
-				hid_data->cc_index = i;
-				hid_data->cc_value_index = j;
-
-				if (hid_data->cc_report != 0 &&
-				    hid_data->cc_index >= 0) {
-
-					struct hid_field *field =
-						report->field[hid_data->cc_index];
-					int value =
-						field->value[hid_data->cc_value_index];
-
-					if (value)
-						hid_data->num_expected = value;
-				}
-			}
-		}
-	}
-
-	if (hid_data->cc_report == 0 || hid_data->cc_index < 0)
-		hid_data->num_expected = wacom_wac->features.touch_max;
-}
-
 static int wacom_wac_collection(struct hid_device *hdev, struct hid_report *report,
 			 int collection_index, struct hid_field *field,
 			 int field_index)
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 
-	if (WACOM_FINGER_FIELD(field))
-		wacom_set_num_expected(hdev, report, collection_index, field,
-				       field_index);
 	wacom_report_events(hdev, report, collection_index, field_index);
 
 	/*
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 0370364169c4..501c43c5851d 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -839,6 +839,9 @@ void vmbus_initiate_unload(bool crash)
 {
 	struct vmbus_channel_message_header hdr;
 
+	if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED)
+		return;
+
 	/* Pre-Win2012R2 hosts don't support reconnect */
 	if (vmbus_proto_version < VERSION_WIN8_1)
 		return;
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 6098e0cbdb4b..533c8b82b344 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -184,11 +184,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 
 	shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR;
 	shared_sint.masked = false;
-	if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
-		shared_sint.auto_eoi = false;
-	else
-		shared_sint.auto_eoi = true;
-
+	shared_sint.auto_eoi = hv_recommend_using_aeoi();
 	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
 	/* Enable the global synic bit */
diff --git a/drivers/hv/hv_debugfs.c b/drivers/hv/hv_debugfs.c
index 8a2878573582..ccf752b6659a 100644
--- a/drivers/hv/hv_debugfs.c
+++ b/drivers/hv/hv_debugfs.c
@@ -11,7 +11,7 @@
 
 #include "hyperv_vmbus.h"
 
-struct dentry *hv_debug_root;
+static struct dentry *hv_debug_root;
 
 static int hv_debugfs_delay_get(void *data, u64 *val)
 {
diff --git a/drivers/hv/hv_trace.h b/drivers/hv/hv_trace.h
index e70783e33680..f9d14db980cb 100644
--- a/drivers/hv/hv_trace.h
+++ b/drivers/hv/hv_trace.h
@@ -286,8 +286,8 @@ TRACE_EVENT(vmbus_send_tl_connect_request,
 		    __field(int, ret)
 		    ),
 	    TP_fast_assign(
-		    memcpy(__entry->guest_id, &msg->guest_endpoint_id.b, 16);
-		    memcpy(__entry->host_id, &msg->host_service_id.b, 16);
+		    export_guid(__entry->guest_id, &msg->guest_endpoint_id);
+		    export_guid(__entry->host_id, &msg->host_service_id);
 		    __entry->ret = ret;
 		    ),
 	    TP_printk("sending guest_endpoint_id %pUl, host_service_id %pUl, "
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index f5fa3b3c9baf..70b30e223a57 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -292,7 +292,7 @@ struct vmbus_msginfo {
 	struct list_head msglist_entry;
 
 	/* The message itself */
-	unsigned char msg[0];
+	unsigned char msg[];
 };
 
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 029378c27421..e06c6b9555cf 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -31,6 +31,7 @@
 #include <linux/kdebug.h>
 #include <linux/efi.h>
 #include <linux/random.h>
+#include <linux/kernel.h>
 #include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
 #include "hyperv_vmbus.h"
@@ -48,14 +49,35 @@ static int hyperv_cpuhp_online;
 
 static void *hv_panic_page;
 
+/*
+ * Boolean to control whether to report panic messages over Hyper-V.
+ *
+ * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
+ */
+static int sysctl_record_panic_msg = 1;
+
+static int hyperv_report_reg(void)
+{
+	return !sysctl_record_panic_msg || !hv_panic_page;
+}
+
 static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
 			      void *args)
 {
 	struct pt_regs *regs;
 
-	regs = current_pt_regs();
+	vmbus_initiate_unload(true);
 
-	hyperv_report_panic(regs, val);
+	/*
+	 * Hyper-V should be notified only once about a panic.  If we will be
+	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
+	 * the notification here.
+	 */
+	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
+	    && hyperv_report_reg()) {
+		regs = current_pt_regs();
+		hyperv_report_panic(regs, val, false);
+	}
 	return NOTIFY_DONE;
 }
 
@@ -65,7 +87,13 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
 	struct die_args *die = (struct die_args *)args;
 	struct pt_regs *regs = die->regs;
 
-	hyperv_report_panic(regs, val);
+	/*
+	 * Hyper-V should be notified only once about a panic.  If we will be
+	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
+	 * the notification here.
+	 */
+	if (hyperv_report_reg())
+		hyperv_report_panic(regs, val, true);
 	return NOTIFY_DONE;
 }
 
@@ -950,6 +978,9 @@ static int vmbus_resume(struct device *child_device)
 
 	return drv->resume(dev);
 }
+#else
+#define vmbus_suspend NULL
+#define vmbus_resume NULL
 #endif /* CONFIG_PM_SLEEP */
 
 /*
@@ -969,11 +1000,22 @@ static void vmbus_device_release(struct device *device)
 }
 
 /*
- * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
- * SET_SYSTEM_SLEEP_PM_OPS: see the comment before vmbus_bus_pm.
+ * Note: we must use the "noirq" ops: see the comment before vmbus_bus_pm.
+ *
+ * suspend_noirq/resume_noirq are set to NULL to support Suspend-to-Idle: we
+ * shouldn't suspend the vmbus devices upon Suspend-to-Idle, otherwise there
+ * is no way to wake up a Generation-2 VM.
+ *
+ * The other 4 ops are for hibernation.
  */
+
 static const struct dev_pm_ops vmbus_pm = {
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_suspend, vmbus_resume)
+	.suspend_noirq	= NULL,
+	.resume_noirq	= NULL,
+	.freeze_noirq	= vmbus_suspend,
+	.thaw_noirq	= vmbus_resume,
+	.poweroff_noirq	= vmbus_suspend,
+	.restore_noirq	= vmbus_resume,
 };
 
 /* The one and only one */
@@ -1253,13 +1295,6 @@ static void vmbus_isr(void)
 }
 
 /*
- * Boolean to control whether to report panic messages over Hyper-V.
- *
- * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
- */
-static int sysctl_record_panic_msg = 1;
-
-/*
  * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg
  * buffer and call into Hyper-V to transfer the data.
  */
@@ -1382,19 +1417,29 @@ static int vmbus_bus_init(void)
 			hv_panic_page = (void *)hv_alloc_hyperv_zeroed_page();
 			if (hv_panic_page) {
 				ret = kmsg_dump_register(&hv_kmsg_dumper);
-				if (ret)
+				if (ret) {
 					pr_err("Hyper-V: kmsg dump register "
 						"error 0x%x\n", ret);
+					hv_free_hyperv_page(
+					    (unsigned long)hv_panic_page);
+					hv_panic_page = NULL;
+				}
 			} else
 				pr_err("Hyper-V: panic message page memory "
 					"allocation failed");
 		}
 
 		register_die_notifier(&hyperv_die_block);
-		atomic_notifier_chain_register(&panic_notifier_list,
-					       &hyperv_panic_block);
 	}
 
+	/*
+	 * Always register the panic notifier because we need to unload
+	 * the VMbus channel connection to prevent any VMbus
+	 * activity after the VM panics.
+	 */
+	atomic_notifier_chain_register(&panic_notifier_list,
+			       &hyperv_panic_block);
+
 	vmbus_request_offers();
 
 	return 0;
@@ -1407,7 +1452,6 @@ err_alloc:
 	hv_remove_vmbus_irq();
 
 	bus_unregister(&hv_bus);
-	hv_free_hyperv_page((unsigned long)hv_panic_page);
 	unregister_sysctl_table(hv_ctl_table_hdr);
 	hv_ctl_table_hdr = NULL;
 	return ret;
@@ -2204,8 +2248,6 @@ static int vmbus_bus_suspend(struct device *dev)
 
 	vmbus_initiate_unload(false);
 
-	vmbus_connection.conn_state = DISCONNECTED;
-
 	/* Reset the event for the next resume. */
 	reinit_completion(&vmbus_connection.ready_for_resume_event);
 
@@ -2253,6 +2295,9 @@ static int vmbus_bus_resume(struct device *dev)
 
 	return 0;
 }
+#else
+#define vmbus_bus_suspend NULL
+#define vmbus_bus_resume NULL
 #endif /* CONFIG_PM_SLEEP */
 
 static const struct acpi_device_id vmbus_acpi_device_ids[] = {
@@ -2263,16 +2308,24 @@ static const struct acpi_device_id vmbus_acpi_device_ids[] = {
 MODULE_DEVICE_TABLE(acpi, vmbus_acpi_device_ids);
 
 /*
- * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
- * SET_SYSTEM_SLEEP_PM_OPS, otherwise NIC SR-IOV can not work, because the
- * "pci_dev_pm_ops" uses the "noirq" callbacks: in the resume path, the
- * pci "noirq" restore callback runs before "non-noirq" callbacks (see
+ * Note: we must use the "no_irq" ops, otherwise hibernation can not work with
+ * PCI device assignment, because "pci_dev_pm_ops" uses the "noirq" ops: in
+ * the resume path, the pci "noirq" restore op runs before "non-noirq" op (see
  * resume_target_kernel() -> dpm_resume_start(), and hibernation_restore() ->
  * dpm_resume_end()). This means vmbus_bus_resume() and the pci-hyperv's
- * resume callback must also run via the "noirq" callbacks.
+ * resume callback must also run via the "noirq" ops.
+ *
+ * Set suspend_noirq/resume_noirq to NULL for Suspend-to-Idle: see the comment
+ * earlier in this file before vmbus_pm.
  */
+
 static const struct dev_pm_ops vmbus_bus_pm = {
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_bus_suspend, vmbus_bus_resume)
+	.suspend_noirq	= NULL,
+	.resume_noirq	= NULL,
+	.freeze_noirq	= vmbus_bus_suspend,
+	.thaw_noirq	= vmbus_bus_resume,
+	.poweroff_noirq	= vmbus_bus_suspend,
+	.restore_noirq	= vmbus_bus_resume
 };
 
 static struct acpi_driver vmbus_acpi_driver = {
@@ -2289,7 +2342,6 @@ static void hv_kexec_handler(void)
 {
 	hv_stimer_global_cleanup();
 	vmbus_initiate_unload(false);
-	vmbus_connection.conn_state = DISCONNECTED;
 	/* Make sure conn_state is set as hv_synic_cleanup checks for it */
 	mb();
 	cpuhp_remove_state(hyperv_cpuhp_online);
@@ -2306,7 +2358,6 @@ static void hv_crash_handler(struct pt_regs *regs)
 	 * doing the cleanup for current CPU only. This should be sufficient
 	 * for kdump.
 	 */
-	vmbus_connection.conn_state = DISCONNECTED;
 	cpu = smp_processor_id();
 	hv_stimer_cleanup(cpu);
 	hv_synic_disable_regs(cpu);
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 05a30832c6ba..288ae9f63588 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -324,6 +324,16 @@ config SENSORS_FAM15H_POWER
 	  This driver can also be built as a module. If so, the module
 	  will be called fam15h_power.
 
+config SENSORS_AMD_ENERGY
+	tristate "AMD RAPL MSR based Energy driver"
+	depends on X86
+	help
+	  If you say yes here you get support for core and package energy
+	  sensors, based on RAPL MSR for AMD family 17h and above CPUs.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called as amd_energy.
+
 config SENSORS_APPLESMC
 	tristate "Apple SMC (Motion sensor, light sensor, keyboard backlight)"
 	depends on INPUT && X86
@@ -404,6 +414,31 @@ config SENSORS_ATXP1
 	  This driver can also be built as a module. If so, the module
 	  will be called atxp1.
 
+config SENSORS_BT1_PVT
+	tristate "Baikal-T1 Process, Voltage, Temperature sensor driver"
+	depends on MIPS_BAIKAL_T1 || COMPILE_TEST
+	help
+	  If you say yes here you get support for Baikal-T1 PVT sensor
+	  embedded into the SoC.
+
+	  This driver can also be built as a module. If so, the module will be
+	  called bt1-pvt.
+
+config SENSORS_BT1_PVT_ALARMS
+	bool "Enable Baikal-T1 PVT sensor alarms"
+	depends on SENSORS_BT1_PVT
+	help
+	  Baikal-T1 PVT IP-block provides threshold registers for each
+	  supported sensor. But the corresponding interrupts might be
+	  generated by the thresholds comparator only in synchronization with
+	  a data conversion. Additionally there is only one sensor data can
+	  be converted at a time. All of these makes the interface impossible
+	  to be used for the hwmon alarms implementation without periodic
+	  switch between the PVT sensors. By default the data conversion is
+	  performed on demand from the user-space. If this config is enabled
+	  the data conversion will be periodically performed and the data will be
+	  saved in the internal driver cache.
+
 config SENSORS_DRIVETEMP
 	tristate "Hard disk drives with temperature sensors"
 	depends on SCSI && ATA
@@ -412,7 +447,7 @@ config SENSORS_DRIVETEMP
 	  hard disk drives.
 
 	  This driver can also be built as a module. If so, the module
-	  will be called satatemp.
+	  will be called drivetemp.
 
 config SENSORS_DS620
 	tristate "Dallas Semiconductor DS620"
@@ -523,6 +558,15 @@ config SENSORS_F75375S
 	  This driver can also be built as a module. If so, the module
 	  will be called f75375s.
 
+config SENSORS_GSC
+	tristate "Gateworks System Controller ADC"
+	depends on MFD_GATEWORKS_GSC
+	help
+	  Support for the Gateworks System Controller A/D converters.
+
+	  To compile this driver as a module, choose M here:
+	  the module will be called gsc-hwmon.
+
 config SENSORS_MC13783_ADC
         tristate "Freescale MC13783/MC13892 ADC"
         depends on MFD_MC13XXX
@@ -1198,10 +1242,11 @@ config SENSORS_LM90
 	help
 	  If you say yes here you get support for National Semiconductor LM90,
 	  LM86, LM89 and LM99, Analog Devices ADM1032, ADT7461, and ADT7461A,
-	  Maxim MAX6646, MAX6647, MAX6648, MAX6649, MAX6657, MAX6658, MAX6659,
-	  MAX6680, MAX6681, MAX6692, MAX6695, MAX6696, ON Semiconductor NCT1008,
-	  Winbond/Nuvoton W83L771W/G/AWG/ASG, Philips SA56004, GMT G781, and
-	  Texas Instruments TMP451 sensor chips.
+	  Maxim MAX6646, MAX6647, MAX6648, MAX6649, MAX6654, MAX6657, MAX6658,
+	  MAX6659, MAX6680, MAX6681, MAX6692, MAX6695, MAX6696,
+	  ON Semiconductor NCT1008, Winbond/Nuvoton W83L771W/G/AWG/ASG,
+	  Philips SA56004, GMT G781, and Texas Instruments TMP451
+	  sensor chips.
 
 	  This driver can also be built as a module. If so, the module
 	  will be called lm90.
@@ -1340,10 +1385,12 @@ config SENSORS_NCT7802
 
 config SENSORS_NCT7904
 	tristate "Nuvoton NCT7904"
-	depends on I2C
+	depends on I2C && WATCHDOG
+	select WATCHDOG_CORE
 	help
 	  If you say yes here you get support for the Nuvoton NCT7904
-	  hardware monitoring chip, including manual fan speed control.
+	  hardware monitoring chip, including manual fan speed control
+	  and support for the integrated watchdog.
 
 	  This driver can also be built as a module. If so, the module
 	  will be called nct7904.
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index b0b9c8e57176..3e32c21f5efe 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -45,6 +45,7 @@ obj-$(CONFIG_SENSORS_ADT7411)	+= adt7411.o
 obj-$(CONFIG_SENSORS_ADT7462)	+= adt7462.o
 obj-$(CONFIG_SENSORS_ADT7470)	+= adt7470.o
 obj-$(CONFIG_SENSORS_ADT7475)	+= adt7475.o
+obj-$(CONFIG_SENSORS_AMD_ENERGY) += amd_energy.o
 obj-$(CONFIG_SENSORS_APPLESMC)	+= applesmc.o
 obj-$(CONFIG_SENSORS_ARM_SCMI)	+= scmi-hwmon.o
 obj-$(CONFIG_SENSORS_ARM_SCPI)	+= scpi-hwmon.o
@@ -53,6 +54,7 @@ obj-$(CONFIG_SENSORS_ASC7621)	+= asc7621.o
 obj-$(CONFIG_SENSORS_ASPEED)	+= aspeed-pwm-tacho.o
 obj-$(CONFIG_SENSORS_ATXP1)	+= atxp1.o
 obj-$(CONFIG_SENSORS_AXI_FAN_CONTROL) += axi-fan-control.o
+obj-$(CONFIG_SENSORS_BT1_PVT)	+= bt1-pvt.o
 obj-$(CONFIG_SENSORS_CORETEMP)	+= coretemp.o
 obj-$(CONFIG_SENSORS_DA9052_ADC)+= da9052-hwmon.o
 obj-$(CONFIG_SENSORS_DA9055)+= da9055-hwmon.o
@@ -74,6 +76,7 @@ obj-$(CONFIG_SENSORS_G760A)	+= g760a.o
 obj-$(CONFIG_SENSORS_G762)	+= g762.o
 obj-$(CONFIG_SENSORS_GL518SM)	+= gl518sm.o
 obj-$(CONFIG_SENSORS_GL520SM)	+= gl520sm.o
+obj-$(CONFIG_SENSORS_GSC)	+= gsc-hwmon.o
 obj-$(CONFIG_SENSORS_GPIO_FAN)	+= gpio-fan.o
 obj-$(CONFIG_SENSORS_HIH6130)	+= hih6130.o
 obj-$(CONFIG_SENSORS_ULTRA45)	+= ultra45_env.o
diff --git a/drivers/hwmon/adt7411.c b/drivers/hwmon/adt7411.c
index c7010b91bc13..5a839cc2ed1c 100644
--- a/drivers/hwmon/adt7411.c
+++ b/drivers/hwmon/adt7411.c
@@ -716,7 +716,6 @@ static struct i2c_driver adt7411_driver = {
 
 module_i2c_driver(adt7411_driver);
 
-MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de> and "
-	"Wolfram Sang <w.sang@pengutronix.de>");
+MODULE_AUTHOR("Sascha Hauer, Wolfram Sang <kernel@pengutronix.de>");
 MODULE_DESCRIPTION("ADT7411 driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwmon/amd_energy.c b/drivers/hwmon/amd_energy.c
new file mode 100644
index 000000000000..e95b7426106e
--- /dev/null
+++ b/drivers/hwmon/amd_energy.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright (C) 2020 Advanced Micro Devices, Inc.
+ */
+#include <asm/cpu_device_id.h>
+
+#include <linux/bits.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/processor.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/topology.h>
+#include <linux/types.h>
+
+#define DRVNAME			"amd_energy"
+
+#define ENERGY_PWR_UNIT_MSR	0xC0010299
+#define ENERGY_CORE_MSR		0xC001029A
+#define ENERGY_PKG_MSR		0xC001029B
+
+#define AMD_ENERGY_UNIT_MASK	0x01F00
+#define AMD_ENERGY_MASK		0xFFFFFFFF
+
+struct sensor_accumulator {
+	u64 energy_ctr;
+	u64 prev_value;
+	char label[10];
+};
+
+struct amd_energy_data {
+	struct hwmon_channel_info energy_info;
+	const struct hwmon_channel_info *info[2];
+	struct hwmon_chip_info chip;
+	struct task_struct *wrap_accumulate;
+	/* Lock around the accumulator */
+	struct mutex lock;
+	/* An accumulator for each core and socket */
+	struct sensor_accumulator *accums;
+	/* Energy Status Units */
+	u64 energy_units;
+	int nr_cpus;
+	int nr_socks;
+	int core_id;
+};
+
+static int amd_energy_read_labels(struct device *dev,
+				  enum hwmon_sensor_types type,
+				  u32 attr, int channel,
+				  const char **str)
+{
+	struct amd_energy_data *data = dev_get_drvdata(dev);
+
+	*str = data->accums[channel].label;
+	return 0;
+}
+
+static void get_energy_units(struct amd_energy_data *data)
+{
+	u64 rapl_units;
+
+	rdmsrl_safe(ENERGY_PWR_UNIT_MSR, &rapl_units);
+	data->energy_units = (rapl_units & AMD_ENERGY_UNIT_MASK) >> 8;
+}
+
+static void accumulate_socket_delta(struct amd_energy_data *data,
+				    int sock, int cpu)
+{
+	struct sensor_accumulator *s_accum;
+	u64 input;
+
+	mutex_lock(&data->lock);
+	rdmsrl_safe_on_cpu(cpu, ENERGY_PKG_MSR, &input);
+	input &= AMD_ENERGY_MASK;
+
+	s_accum = &data->accums[data->nr_cpus + sock];
+	if (input >= s_accum->prev_value)
+		s_accum->energy_ctr +=
+			input - s_accum->prev_value;
+	else
+		s_accum->energy_ctr += UINT_MAX -
+			s_accum->prev_value + input;
+
+	s_accum->prev_value = input;
+	mutex_unlock(&data->lock);
+}
+
+static void accumulate_core_delta(struct amd_energy_data *data)
+{
+	struct sensor_accumulator *c_accum;
+	u64 input;
+	int cpu;
+
+	mutex_lock(&data->lock);
+	if (data->core_id >= data->nr_cpus)
+		data->core_id = 0;
+
+	cpu = data->core_id;
+
+	if (!cpu_online(cpu))
+		goto out;
+
+	rdmsrl_safe_on_cpu(cpu, ENERGY_CORE_MSR, &input);
+	input &= AMD_ENERGY_MASK;
+
+	c_accum = &data->accums[cpu];
+
+	if (input >= c_accum->prev_value)
+		c_accum->energy_ctr +=
+			input - c_accum->prev_value;
+	else
+		c_accum->energy_ctr += UINT_MAX -
+			c_accum->prev_value + input;
+
+	c_accum->prev_value = input;
+
+out:
+	data->core_id++;
+	mutex_unlock(&data->lock);
+}
+
+static void read_accumulate(struct amd_energy_data *data)
+{
+	int sock;
+
+	for (sock = 0; sock < data->nr_socks; sock++) {
+		int cpu;
+
+		cpu = cpumask_first_and(cpu_online_mask,
+					cpumask_of_node(sock));
+
+		accumulate_socket_delta(data, sock, cpu);
+	}
+
+	accumulate_core_delta(data);
+}
+
+static void amd_add_delta(struct amd_energy_data *data, int ch,
+			  int cpu, long *val, bool is_core)
+{
+	struct sensor_accumulator *s_accum, *c_accum;
+	u64 input;
+
+	mutex_lock(&data->lock);
+	if (!is_core) {
+		rdmsrl_safe_on_cpu(cpu, ENERGY_PKG_MSR, &input);
+		input &= AMD_ENERGY_MASK;
+
+		s_accum = &data->accums[ch];
+		if (input >= s_accum->prev_value)
+			input += s_accum->energy_ctr -
+				  s_accum->prev_value;
+		else
+			input += UINT_MAX - s_accum->prev_value +
+				  s_accum->energy_ctr;
+	} else {
+		rdmsrl_safe_on_cpu(cpu, ENERGY_CORE_MSR, &input);
+		input &= AMD_ENERGY_MASK;
+
+		c_accum = &data->accums[ch];
+		if (input >= c_accum->prev_value)
+			input += c_accum->energy_ctr -
+				 c_accum->prev_value;
+		else
+			input += UINT_MAX - c_accum->prev_value +
+				 c_accum->energy_ctr;
+	}
+
+	/* Energy consumed = (1/(2^ESU) * RAW * 1000000UL) μJoules */
+	*val = div64_ul(input * 1000000UL, BIT(data->energy_units));
+
+	mutex_unlock(&data->lock);
+}
+
+static int amd_energy_read(struct device *dev,
+			   enum hwmon_sensor_types type,
+			   u32 attr, int channel, long *val)
+{
+	struct amd_energy_data *data = dev_get_drvdata(dev);
+	int cpu;
+
+	if (channel >= data->nr_cpus) {
+		cpu = cpumask_first_and(cpu_online_mask,
+					cpumask_of_node
+					(channel - data->nr_cpus));
+		amd_add_delta(data, channel, cpu, val, false);
+	} else {
+		cpu = channel;
+		if (!cpu_online(cpu))
+			return -ENODEV;
+
+		amd_add_delta(data, channel, cpu, val, true);
+	}
+
+	return 0;
+}
+
+static umode_t amd_energy_is_visible(const void *_data,
+				     enum hwmon_sensor_types type,
+				     u32 attr, int channel)
+{
+	return 0444;
+}
+
+static int energy_accumulator(void *p)
+{
+	struct amd_energy_data *data = (struct amd_energy_data *)p;
+
+	while (!kthread_should_stop()) {
+		/*
+		 * Ignoring the conditions such as
+		 * cpu being offline or rdmsr failure
+		 */
+		read_accumulate(data);
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_stop())
+			break;
+
+		/*
+		 * On a 240W system, with default resolution the
+		 * Socket Energy status register may wrap around in
+		 * 2^32*15.3 e-6/240 = 273.8041 secs (~4.5 mins)
+		 *
+		 * let us accumulate for every 100secs
+		 */
+		schedule_timeout(msecs_to_jiffies(100000));
+	}
+	return 0;
+}
+
+static const struct hwmon_ops amd_energy_ops = {
+	.is_visible = amd_energy_is_visible,
+	.read = amd_energy_read,
+	.read_string = amd_energy_read_labels,
+};
+
+static int amd_create_sensor(struct device *dev,
+			     struct amd_energy_data *data,
+			     u8 type, u32 config)
+{
+	struct hwmon_channel_info *info = &data->energy_info;
+	struct sensor_accumulator *accums;
+	int i, num_siblings, cpus, sockets;
+	u32 *s_config;
+
+	/* Identify the number of siblings per core */
+	num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
+
+	sockets = num_possible_nodes();
+
+	/*
+	 * Energy counter register is accessed at core level.
+	 * Hence, filterout the siblings.
+	 */
+	cpus = num_present_cpus() / num_siblings;
+
+	s_config = devm_kcalloc(dev, cpus + sockets,
+				sizeof(u32), GFP_KERNEL);
+	if (!s_config)
+		return -ENOMEM;
+
+	accums = devm_kcalloc(dev, cpus + sockets,
+			      sizeof(struct sensor_accumulator),
+			      GFP_KERNEL);
+	if (!accums)
+		return -ENOMEM;
+
+	info->type = type;
+	info->config = s_config;
+
+	data->nr_cpus = cpus;
+	data->nr_socks = sockets;
+	data->accums = accums;
+
+	for (i = 0; i < cpus + sockets; i++) {
+		s_config[i] = config;
+		if (i < cpus)
+			scnprintf(accums[i].label, 10,
+				  "Ecore%03u", i);
+		else
+			scnprintf(accums[i].label, 10,
+				  "Esocket%u", (i - cpus));
+	}
+
+	return 0;
+}
+
+static int amd_energy_probe(struct platform_device *pdev)
+{
+	struct device *hwmon_dev;
+	struct amd_energy_data *data;
+	struct device *dev = &pdev->dev;
+
+	data = devm_kzalloc(dev,
+			    sizeof(struct amd_energy_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->chip.ops = &amd_energy_ops;
+	data->chip.info = data->info;
+
+	dev_set_drvdata(dev, data);
+	/* Populate per-core energy reporting */
+	data->info[0] = &data->energy_info;
+	amd_create_sensor(dev, data, hwmon_energy,
+			  HWMON_E_INPUT | HWMON_E_LABEL);
+
+	mutex_init(&data->lock);
+	get_energy_units(data);
+
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, DRVNAME,
+							 data,
+							 &data->chip,
+							 NULL);
+	if (IS_ERR(hwmon_dev))
+		return PTR_ERR(hwmon_dev);
+
+	data->wrap_accumulate = kthread_run(energy_accumulator, data,
+					    "%s", dev_name(hwmon_dev));
+	if (IS_ERR(data->wrap_accumulate))
+		return PTR_ERR(data->wrap_accumulate);
+
+	return PTR_ERR_OR_ZERO(data->wrap_accumulate);
+}
+
+static int amd_energy_remove(struct platform_device *pdev)
+{
+	struct amd_energy_data *data = dev_get_drvdata(&pdev->dev);
+
+	if (data && data->wrap_accumulate)
+		kthread_stop(data->wrap_accumulate);
+
+	return 0;
+}
+
+static const struct platform_device_id amd_energy_ids[] = {
+	{ .name = DRVNAME, },
+	{}
+};
+MODULE_DEVICE_TABLE(platform, amd_energy_ids);
+
+static struct platform_driver amd_energy_driver = {
+	.probe = amd_energy_probe,
+	.remove	= amd_energy_remove,
+	.id_table = amd_energy_ids,
+	.driver = {
+		.name = DRVNAME,
+	},
+};
+
+static struct platform_device *amd_energy_platdev;
+
+static const struct x86_cpu_id cpu_ids[] __initconst = {
+	X86_MATCH_VENDOR_FAM(AMD, 0x17, NULL),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, cpu_ids);
+
+static int __init amd_energy_init(void)
+{
+	int ret;
+
+	if (!x86_match_cpu(cpu_ids))
+		return -ENODEV;
+
+	ret = platform_driver_register(&amd_energy_driver);
+	if (ret)
+		return ret;
+
+	amd_energy_platdev = platform_device_alloc(DRVNAME, 0);
+	if (!amd_energy_platdev) {
+		platform_driver_unregister(&amd_energy_driver);
+		return -ENOMEM;
+	}
+
+	ret = platform_device_add(amd_energy_platdev);
+	if (ret) {
+		platform_device_put(amd_energy_platdev);
+		platform_driver_unregister(&amd_energy_driver);
+		return ret;
+	}
+
+	return ret;
+}
+
+static void __exit amd_energy_exit(void)
+{
+	platform_device_unregister(amd_energy_platdev);
+	platform_driver_unregister(&amd_energy_driver);
+}
+
+module_init(amd_energy_init);
+module_exit(amd_energy_exit);
+
+MODULE_DESCRIPTION("Driver for AMD Energy reporting from RAPL MSR via HWMON interface");
+MODULE_AUTHOR("Naveen Krishna Chatradhi <nchatrad@amd.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index ec93b8d673f5..316618409315 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -156,14 +156,19 @@ static struct workqueue_struct *applesmc_led_wq;
  */
 static int wait_read(void)
 {
+	unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC;
 	u8 status;
 	int us;
+
 	for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) {
-		udelay(us);
+		usleep_range(us, us * 16);
 		status = inb(APPLESMC_CMD_PORT);
 		/* read: wait for smc to settle */
 		if (status & 0x01)
 			return 0;
+		/* timeout: give up */
+		if (time_after(jiffies, end))
+			break;
 	}
 
 	pr_warn("wait_read() fail: 0x%02x\n", status);
@@ -178,10 +183,11 @@ static int send_byte(u8 cmd, u16 port)
 {
 	u8 status;
 	int us;
+	unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC;
 
 	outb(cmd, port);
 	for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) {
-		udelay(us);
+		usleep_range(us, us * 16);
 		status = inb(APPLESMC_CMD_PORT);
 		/* write: wait for smc to settle */
 		if (status & 0x02)
@@ -190,7 +196,7 @@ static int send_byte(u8 cmd, u16 port)
 		if (status & 0x04)
 			return 0;
 		/* timeout: give up */
-		if (us << 1 == APPLESMC_MAX_WAIT)
+		if (time_after(jiffies, end))
 			break;
 		/* busy: long wait and resend */
 		udelay(APPLESMC_RETRY_WAIT);
diff --git a/drivers/hwmon/bt1-pvt.c b/drivers/hwmon/bt1-pvt.c
new file mode 100644
index 000000000000..1a9772fb1f73
--- /dev/null
+++ b/drivers/hwmon/bt1-pvt.c
@@ -0,0 +1,1146 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC
+ *
+ * Authors:
+ *   Maxim Kaurkin <maxim.kaurkin@baikalelectronics.ru>
+ *   Serge Semin <Sergey.Semin@baikalelectronics.ru>
+ *
+ * Baikal-T1 Process, Voltage, Temperature sensor driver
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/hwmon.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/ktime.h>
+#include <linux/limits.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/seqlock.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+#include "bt1-pvt.h"
+
+/*
+ * For the sake of the code simplification we created the sensors info table
+ * with the sensor names, activation modes, threshold registers base address
+ * and the thresholds bit fields.
+ */
+static const struct pvt_sensor_info pvt_info[] = {
+	PVT_SENSOR_INFO(0, "CPU Core Temperature", hwmon_temp, TEMP, TTHRES),
+	PVT_SENSOR_INFO(0, "CPU Core Voltage", hwmon_in, VOLT, VTHRES),
+	PVT_SENSOR_INFO(1, "CPU Core Low-Vt", hwmon_in, LVT, LTHRES),
+	PVT_SENSOR_INFO(2, "CPU Core High-Vt", hwmon_in, HVT, HTHRES),
+	PVT_SENSOR_INFO(3, "CPU Core Standard-Vt", hwmon_in, SVT, STHRES),
+};
+
+/*
+ * The original translation formulae of the temperature (in degrees of Celsius)
+ * to PVT data and vice-versa are following:
+ * N = 1.8322e-8*(T^4) + 2.343e-5*(T^3) + 8.7018e-3*(T^2) + 3.9269*(T^1) +
+ *     1.7204e2,
+ * T = -1.6743e-11*(N^4) + 8.1542e-8*(N^3) + -1.8201e-4*(N^2) +
+ *     3.1020e-1*(N^1) - 4.838e1,
+ * where T = [-48.380, 147.438]C and N = [0, 1023].
+ * They must be accordingly altered to be suitable for the integer arithmetics.
+ * The technique is called 'factor redistribution', which just makes sure the
+ * multiplications and divisions are made so to have a result of the operations
+ * within the integer numbers limit. In addition we need to translate the
+ * formulae to accept millidegrees of Celsius. Here what they look like after
+ * the alterations:
+ * N = (18322e-20*(T^4) + 2343e-13*(T^3) + 87018e-9*(T^2) + 39269e-3*T +
+ *     17204e2) / 1e4,
+ * T = -16743e-12*(D^4) + 81542e-9*(D^3) - 182010e-6*(D^2) + 310200e-3*D -
+ *     48380,
+ * where T = [-48380, 147438] mC and N = [0, 1023].
+ */
+static const struct pvt_poly poly_temp_to_N = {
+	.total_divider = 10000,
+	.terms = {
+		{4, 18322, 10000, 10000},
+		{3, 2343, 10000, 10},
+		{2, 87018, 10000, 10},
+		{1, 39269, 1000, 1},
+		{0, 1720400, 1, 1}
+	}
+};
+
+static const struct pvt_poly poly_N_to_temp = {
+	.total_divider = 1,
+	.terms = {
+		{4, -16743, 1000, 1},
+		{3, 81542, 1000, 1},
+		{2, -182010, 1000, 1},
+		{1, 310200, 1000, 1},
+		{0, -48380, 1, 1}
+	}
+};
+
+/*
+ * Similar alterations are performed for the voltage conversion equations.
+ * The original formulae are:
+ * N = 1.8658e3*V - 1.1572e3,
+ * V = (N + 1.1572e3) / 1.8658e3,
+ * where V = [0.620, 1.168] V and N = [0, 1023].
+ * After the optimization they looks as follows:
+ * N = (18658e-3*V - 11572) / 10,
+ * V = N * 10^5 / 18658 + 11572 * 10^4 / 18658.
+ */
+static const struct pvt_poly poly_volt_to_N = {
+	.total_divider = 10,
+	.terms = {
+		{1, 18658, 1000, 1},
+		{0, -11572, 1, 1}
+	}
+};
+
+static const struct pvt_poly poly_N_to_volt = {
+	.total_divider = 10,
+	.terms = {
+		{1, 100000, 18658, 1},
+		{0, 115720000, 1, 18658}
+	}
+};
+
+/*
+ * Here is the polynomial calculation function, which performs the
+ * redistributed terms calculations. It's pretty straightforward. We walk
+ * over each degree term up to the free one, and perform the redistributed
+ * multiplication of the term coefficient, its divider (as for the rationale
+ * fraction representation), data power and the rational fraction divider
+ * leftover. Then all of this is collected in a total sum variable, which
+ * value is normalized by the total divider before being returned.
+ */
+static long pvt_calc_poly(const struct pvt_poly *poly, long data)
+{
+	const struct pvt_poly_term *term = poly->terms;
+	long tmp, ret = 0;
+	int deg;
+
+	do {
+		tmp = term->coef;
+		for (deg = 0; deg < term->deg; ++deg)
+			tmp = mult_frac(tmp, data, term->divider);
+		ret += tmp / term->divider_leftover;
+	} while ((term++)->deg);
+
+	return ret / poly->total_divider;
+}
+
+static inline u32 pvt_update(void __iomem *reg, u32 mask, u32 data)
+{
+	u32 old;
+
+	old = readl_relaxed(reg);
+	writel((old & ~mask) | (data & mask), reg);
+
+	return old & mask;
+}
+
+/*
+ * Baikal-T1 PVT mode can be updated only when the controller is disabled.
+ * So first we disable it, then set the new mode together with the controller
+ * getting back enabled. The same concerns the temperature trim and
+ * measurements timeout. If it is necessary the interface mutex is supposed
+ * to be locked at the time the operations are performed.
+ */
+static inline void pvt_set_mode(struct pvt_hwmon *pvt, u32 mode)
+{
+	u32 old;
+
+	mode = FIELD_PREP(PVT_CTRL_MODE_MASK, mode);
+
+	old = pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, 0);
+	pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_MODE_MASK | PVT_CTRL_EN,
+		   mode | old);
+}
+
+static inline u32 pvt_calc_trim(long temp)
+{
+	temp = clamp_val(temp, 0, PVT_TRIM_TEMP);
+
+	return DIV_ROUND_UP(temp, PVT_TRIM_STEP);
+}
+
+static inline void pvt_set_trim(struct pvt_hwmon *pvt, u32 trim)
+{
+	u32 old;
+
+	trim = FIELD_PREP(PVT_CTRL_TRIM_MASK, trim);
+
+	old = pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, 0);
+	pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_TRIM_MASK | PVT_CTRL_EN,
+		   trim | old);
+}
+
+static inline void pvt_set_tout(struct pvt_hwmon *pvt, u32 tout)
+{
+	u32 old;
+
+	old = pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, 0);
+	writel(tout, pvt->regs + PVT_TTIMEOUT);
+	pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, old);
+}
+
+/*
+ * This driver can optionally provide the hwmon alarms for each sensor the PVT
+ * controller supports. The alarms functionality is made compile-time
+ * configurable due to the hardware interface implementation peculiarity
+ * described further in this comment. So in case if alarms are unnecessary in
+ * your system design it's recommended to have them disabled to prevent the PVT
+ * IRQs being periodically raised to get the data cache/alarms status up to
+ * date.
+ *
+ * Baikal-T1 PVT embedded controller is based on the Analog Bits PVT sensor,
+ * but is equipped with a dedicated control wrapper. It exposes the PVT
+ * sub-block registers space via the APB3 bus. In addition the wrapper provides
+ * a common interrupt vector of the sensors conversion completion events and
+ * threshold value alarms. Alas the wrapper interface hasn't been fully thought
+ * through. There is only one sensor can be activated at a time, for which the
+ * thresholds comparator is enabled right after the data conversion is
+ * completed. Due to this if alarms need to be implemented for all available
+ * sensors we can't just set the thresholds and enable the interrupts. We need
+ * to enable the sensors one after another and let the controller to detect
+ * the alarms by itself at each conversion. This also makes pointless to handle
+ * the alarms interrupts, since in occasion they happen synchronously with
+ * data conversion completion. The best driver design would be to have the
+ * completion interrupts enabled only and keep the converted value in the
+ * driver data cache. This solution is implemented if hwmon alarms are enabled
+ * in this driver. In case if the alarms are disabled, the conversion is
+ * performed on demand at the time a sensors input file is read.
+ */
+
+#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS)
+
+#define pvt_hard_isr NULL
+
+static irqreturn_t pvt_soft_isr(int irq, void *data)
+{
+	const struct pvt_sensor_info *info;
+	struct pvt_hwmon *pvt = data;
+	struct pvt_cache *cache;
+	u32 val, thres_sts, old;
+
+	/*
+	 * DVALID bit will be cleared by reading the data. We need to save the
+	 * status before the next conversion happens. Threshold events will be
+	 * handled a bit later.
+	 */
+	thres_sts = readl(pvt->regs + PVT_RAW_INTR_STAT);
+
+	/*
+	 * Then lets recharge the PVT interface with the next sampling mode.
+	 * Lock the interface mutex to serialize trim, timeouts and alarm
+	 * thresholds settings.
+	 */
+	cache = &pvt->cache[pvt->sensor];
+	info = &pvt_info[pvt->sensor];
+	pvt->sensor = (pvt->sensor == PVT_SENSOR_LAST) ?
+		      PVT_SENSOR_FIRST : (pvt->sensor + 1);
+
+	/*
+	 * For some reason we have to mask the interrupt before changing the
+	 * mode, otherwise sometimes the temperature mode doesn't get
+	 * activated even though the actual mode in the ctrl register
+	 * corresponds to one. Then we read the data. By doing so we also
+	 * recharge the data conversion. After this the mode corresponding
+	 * to the next sensor in the row is set. Finally we enable the
+	 * interrupts back.
+	 */
+	mutex_lock(&pvt->iface_mtx);
+
+	old = pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_DVALID,
+			 PVT_INTR_DVALID);
+
+	val = readl(pvt->regs + PVT_DATA);
+
+	pvt_set_mode(pvt, pvt_info[pvt->sensor].mode);
+
+	pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_DVALID, old);
+
+	mutex_unlock(&pvt->iface_mtx);
+
+	/*
+	 * We can now update the data cache with data just retrieved from the
+	 * sensor. Lock write-seqlock to make sure the reader has a coherent
+	 * data.
+	 */
+	write_seqlock(&cache->data_seqlock);
+
+	cache->data = FIELD_GET(PVT_DATA_DATA_MASK, val);
+
+	write_sequnlock(&cache->data_seqlock);
+
+	/*
+	 * While PVT core is doing the next mode data conversion, we'll check
+	 * whether the alarms were triggered for the current sensor. Note that
+	 * according to the documentation only one threshold IRQ status can be
+	 * set at a time, that's why if-else statement is utilized.
+	 */
+	if ((thres_sts & info->thres_sts_lo) ^ cache->thres_sts_lo) {
+		WRITE_ONCE(cache->thres_sts_lo, thres_sts & info->thres_sts_lo);
+		hwmon_notify_event(pvt->hwmon, info->type, info->attr_min_alarm,
+				   info->channel);
+	} else if ((thres_sts & info->thres_sts_hi) ^ cache->thres_sts_hi) {
+		WRITE_ONCE(cache->thres_sts_hi, thres_sts & info->thres_sts_hi);
+		hwmon_notify_event(pvt->hwmon, info->type, info->attr_max_alarm,
+				   info->channel);
+	}
+
+	return IRQ_HANDLED;
+}
+
+inline umode_t pvt_limit_is_visible(enum pvt_sensor_type type)
+{
+	return 0644;
+}
+
+inline umode_t pvt_alarm_is_visible(enum pvt_sensor_type type)
+{
+	return 0444;
+}
+
+static int pvt_read_data(struct pvt_hwmon *pvt, enum pvt_sensor_type type,
+			 long *val)
+{
+	struct pvt_cache *cache = &pvt->cache[type];
+	unsigned int seq;
+	u32 data;
+
+	do {
+		seq = read_seqbegin(&cache->data_seqlock);
+		data = cache->data;
+	} while (read_seqretry(&cache->data_seqlock, seq));
+
+	if (type == PVT_TEMP)
+		*val = pvt_calc_poly(&poly_N_to_temp, data);
+	else
+		*val = pvt_calc_poly(&poly_N_to_volt, data);
+
+	return 0;
+}
+
+static int pvt_read_limit(struct pvt_hwmon *pvt, enum pvt_sensor_type type,
+			  bool is_low, long *val)
+{
+	u32 data;
+
+	/* No need in serialization, since it is just read from MMIO. */
+	data = readl(pvt->regs + pvt_info[type].thres_base);
+
+	if (is_low)
+		data = FIELD_GET(PVT_THRES_LO_MASK, data);
+	else
+		data = FIELD_GET(PVT_THRES_HI_MASK, data);
+
+	if (type == PVT_TEMP)
+		*val = pvt_calc_poly(&poly_N_to_temp, data);
+	else
+		*val = pvt_calc_poly(&poly_N_to_volt, data);
+
+	return 0;
+}
+
+static int pvt_write_limit(struct pvt_hwmon *pvt, enum pvt_sensor_type type,
+			   bool is_low, long val)
+{
+	u32 data, limit, mask;
+	int ret;
+
+	if (type == PVT_TEMP) {
+		val = clamp(val, PVT_TEMP_MIN, PVT_TEMP_MAX);
+		data = pvt_calc_poly(&poly_temp_to_N, val);
+	} else {
+		val = clamp(val, PVT_VOLT_MIN, PVT_VOLT_MAX);
+		data = pvt_calc_poly(&poly_volt_to_N, val);
+	}
+
+	/* Serialize limit update, since a part of the register is changed. */
+	ret = mutex_lock_interruptible(&pvt->iface_mtx);
+	if (ret)
+		return ret;
+
+	/* Make sure the upper and lower ranges don't intersect. */
+	limit = readl(pvt->regs + pvt_info[type].thres_base);
+	if (is_low) {
+		limit = FIELD_GET(PVT_THRES_HI_MASK, limit);
+		data = clamp_val(data, PVT_DATA_MIN, limit);
+		data = FIELD_PREP(PVT_THRES_LO_MASK, data);
+		mask = PVT_THRES_LO_MASK;
+	} else {
+		limit = FIELD_GET(PVT_THRES_LO_MASK, limit);
+		data = clamp_val(data, limit, PVT_DATA_MAX);
+		data = FIELD_PREP(PVT_THRES_HI_MASK, data);
+		mask = PVT_THRES_HI_MASK;
+	}
+
+	pvt_update(pvt->regs + pvt_info[type].thres_base, mask, data);
+
+	mutex_unlock(&pvt->iface_mtx);
+
+	return 0;
+}
+
+static int pvt_read_alarm(struct pvt_hwmon *pvt, enum pvt_sensor_type type,
+			  bool is_low, long *val)
+{
+	if (is_low)
+		*val = !!READ_ONCE(pvt->cache[type].thres_sts_lo);
+	else
+		*val = !!READ_ONCE(pvt->cache[type].thres_sts_hi);
+
+	return 0;
+}
+
+static const struct hwmon_channel_info *pvt_channel_info[] = {
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_TYPE | HWMON_T_LABEL |
+			   HWMON_T_MIN | HWMON_T_MIN_ALARM |
+			   HWMON_T_MAX | HWMON_T_MAX_ALARM |
+			   HWMON_T_OFFSET),
+	HWMON_CHANNEL_INFO(in,
+			   HWMON_I_INPUT | HWMON_I_LABEL |
+			   HWMON_I_MIN | HWMON_I_MIN_ALARM |
+			   HWMON_I_MAX | HWMON_I_MAX_ALARM,
+			   HWMON_I_INPUT | HWMON_I_LABEL |
+			   HWMON_I_MIN | HWMON_I_MIN_ALARM |
+			   HWMON_I_MAX | HWMON_I_MAX_ALARM,
+			   HWMON_I_INPUT | HWMON_I_LABEL |
+			   HWMON_I_MIN | HWMON_I_MIN_ALARM |
+			   HWMON_I_MAX | HWMON_I_MAX_ALARM,
+			   HWMON_I_INPUT | HWMON_I_LABEL |
+			   HWMON_I_MIN | HWMON_I_MIN_ALARM |
+			   HWMON_I_MAX | HWMON_I_MAX_ALARM),
+	NULL
+};
+
+#else /* !CONFIG_SENSORS_BT1_PVT_ALARMS */
+
+static irqreturn_t pvt_hard_isr(int irq, void *data)
+{
+	struct pvt_hwmon *pvt = data;
+	struct pvt_cache *cache;
+	u32 val;
+
+	/*
+	 * Mask the DVALID interrupt so after exiting from the handler a
+	 * repeated conversion wouldn't happen.
+	 */
+	pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_DVALID,
+		   PVT_INTR_DVALID);
+
+	/*
+	 * Nothing special for alarm-less driver. Just read the data, update
+	 * the cache and notify a waiter of this event.
+	 */
+	val = readl(pvt->regs + PVT_DATA);
+	if (!(val & PVT_DATA_VALID)) {
+		dev_err(pvt->dev, "Got IRQ when data isn't valid\n");
+		return IRQ_HANDLED;
+	}
+
+	cache = &pvt->cache[pvt->sensor];
+
+	WRITE_ONCE(cache->data, FIELD_GET(PVT_DATA_DATA_MASK, val));
+
+	complete(&cache->conversion);
+
+	return IRQ_HANDLED;
+}
+
+#define pvt_soft_isr NULL
+
+inline umode_t pvt_limit_is_visible(enum pvt_sensor_type type)
+{
+	return 0;
+}
+
+inline umode_t pvt_alarm_is_visible(enum pvt_sensor_type type)
+{
+	return 0;
+}
+
+static int pvt_read_data(struct pvt_hwmon *pvt, enum pvt_sensor_type type,
+			 long *val)
+{
+	struct pvt_cache *cache = &pvt->cache[type];
+	u32 data;
+	int ret;
+
+	/*
+	 * Lock PVT conversion interface until data cache is updated. The
+	 * data read procedure is following: set the requested PVT sensor
+	 * mode, enable IRQ and conversion, wait until conversion is finished,
+	 * then disable conversion and IRQ, and read the cached data.
+	 */
+	ret = mutex_lock_interruptible(&pvt->iface_mtx);
+	if (ret)
+		return ret;
+
+	pvt->sensor = type;
+	pvt_set_mode(pvt, pvt_info[type].mode);
+
+	/*
+	 * Unmask the DVALID interrupt and enable the sensors conversions.
+	 * Do the reverse procedure when conversion is done.
+	 */
+	pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_DVALID, 0);
+	pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, PVT_CTRL_EN);
+
+	wait_for_completion(&cache->conversion);
+
+	pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, 0);
+	pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_DVALID,
+		   PVT_INTR_DVALID);
+
+	data = READ_ONCE(cache->data);
+
+	mutex_unlock(&pvt->iface_mtx);
+
+	if (type == PVT_TEMP)
+		*val = pvt_calc_poly(&poly_N_to_temp, data);
+	else
+		*val = pvt_calc_poly(&poly_N_to_volt, data);
+
+	return 0;
+}
+
+static int pvt_read_limit(struct pvt_hwmon *pvt, enum pvt_sensor_type type,
+			  bool is_low, long *val)
+{
+	return -EOPNOTSUPP;
+}
+
+static int pvt_write_limit(struct pvt_hwmon *pvt, enum pvt_sensor_type type,
+			   bool is_low, long val)
+{
+	return -EOPNOTSUPP;
+}
+
+static int pvt_read_alarm(struct pvt_hwmon *pvt, enum pvt_sensor_type type,
+			  bool is_low, long *val)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct hwmon_channel_info *pvt_channel_info[] = {
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_TYPE | HWMON_T_LABEL |
+			   HWMON_T_OFFSET),
+	HWMON_CHANNEL_INFO(in,
+			   HWMON_I_INPUT | HWMON_I_LABEL,
+			   HWMON_I_INPUT | HWMON_I_LABEL,
+			   HWMON_I_INPUT | HWMON_I_LABEL,
+			   HWMON_I_INPUT | HWMON_I_LABEL),
+	NULL
+};
+
+#endif /* !CONFIG_SENSORS_BT1_PVT_ALARMS */
+
+static inline bool pvt_hwmon_channel_is_valid(enum hwmon_sensor_types type,
+					      int ch)
+{
+	switch (type) {
+	case hwmon_temp:
+		if (ch < 0 || ch >= PVT_TEMP_CHS)
+			return false;
+		break;
+	case hwmon_in:
+		if (ch < 0 || ch >= PVT_VOLT_CHS)
+			return false;
+		break;
+	default:
+		break;
+	}
+
+	/* The rest of the types are independent from the channel number. */
+	return true;
+}
+
+static umode_t pvt_hwmon_is_visible(const void *data,
+				    enum hwmon_sensor_types type,
+				    u32 attr, int ch)
+{
+	if (!pvt_hwmon_channel_is_valid(type, ch))
+		return 0;
+
+	switch (type) {
+	case hwmon_chip:
+		switch (attr) {
+		case hwmon_chip_update_interval:
+			return 0644;
+		}
+		break;
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_input:
+		case hwmon_temp_type:
+		case hwmon_temp_label:
+			return 0444;
+		case hwmon_temp_min:
+		case hwmon_temp_max:
+			return pvt_limit_is_visible(ch);
+		case hwmon_temp_min_alarm:
+		case hwmon_temp_max_alarm:
+			return pvt_alarm_is_visible(ch);
+		case hwmon_temp_offset:
+			return 0644;
+		}
+		break;
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_input:
+		case hwmon_in_label:
+			return 0444;
+		case hwmon_in_min:
+		case hwmon_in_max:
+			return pvt_limit_is_visible(PVT_VOLT + ch);
+		case hwmon_in_min_alarm:
+		case hwmon_in_max_alarm:
+			return pvt_alarm_is_visible(PVT_VOLT + ch);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int pvt_read_trim(struct pvt_hwmon *pvt, long *val)
+{
+	u32 data;
+
+	data = readl(pvt->regs + PVT_CTRL);
+	*val = FIELD_GET(PVT_CTRL_TRIM_MASK, data) * PVT_TRIM_STEP;
+
+	return 0;
+}
+
+static int pvt_write_trim(struct pvt_hwmon *pvt, long val)
+{
+	u32 trim;
+	int ret;
+
+	/*
+	 * Serialize trim update, since a part of the register is changed and
+	 * the controller is supposed to be disabled during this operation.
+	 */
+	ret = mutex_lock_interruptible(&pvt->iface_mtx);
+	if (ret)
+		return ret;
+
+	trim = pvt_calc_trim(val);
+	pvt_set_trim(pvt, trim);
+
+	mutex_unlock(&pvt->iface_mtx);
+
+	return 0;
+}
+
+static int pvt_read_timeout(struct pvt_hwmon *pvt, long *val)
+{
+	unsigned long rate;
+	ktime_t kt;
+	u32 data;
+
+	rate = clk_get_rate(pvt->clks[PVT_CLOCK_REF].clk);
+	if (!rate)
+		return -ENODEV;
+
+	/*
+	 * Don't bother with mutex here, since we just read data from MMIO.
+	 * We also have to scale the ticks timeout up to compensate the
+	 * ms-ns-data translations.
+	 */
+	data = readl(pvt->regs + PVT_TTIMEOUT) + 1;
+
+	/*
+	 * Calculate ref-clock based delay (Ttotal) between two consecutive
+	 * data samples of the same sensor. So we first must calculate the
+	 * delay introduced by the internal ref-clock timer (Tref * Fclk).
+	 * Then add the constant timeout cuased by each conversion latency
+	 * (Tmin). The basic formulae for each conversion is following:
+	 *   Ttotal = Tref * Fclk + Tmin
+	 * Note if alarms are enabled the sensors are polled one after
+	 * another, so in order to have the delay being applicable for each
+	 * sensor the requested value must be equally redistirbuted.
+	 */
+#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS)
+	kt = ktime_set(PVT_SENSORS_NUM * (u64)data, 0);
+	kt = ktime_divns(kt, rate);
+	kt = ktime_add_ns(kt, PVT_SENSORS_NUM * PVT_TOUT_MIN);
+#else
+	kt = ktime_set(data, 0);
+	kt = ktime_divns(kt, rate);
+	kt = ktime_add_ns(kt, PVT_TOUT_MIN);
+#endif
+
+	/* Return the result in msec as hwmon sysfs interface requires. */
+	*val = ktime_to_ms(kt);
+
+	return 0;
+}
+
+static int pvt_write_timeout(struct pvt_hwmon *pvt, long val)
+{
+	unsigned long rate;
+	ktime_t kt;
+	u32 data;
+	int ret;
+
+	rate = clk_get_rate(pvt->clks[PVT_CLOCK_REF].clk);
+	if (!rate)
+		return -ENODEV;
+
+	/*
+	 * If alarms are enabled, the requested timeout must be divided
+	 * between all available sensors to have the requested delay
+	 * applicable to each individual sensor.
+	 */
+	kt = ms_to_ktime(val);
+#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS)
+	kt = ktime_divns(kt, PVT_SENSORS_NUM);
+#endif
+
+	/*
+	 * Subtract a constant lag, which always persists due to the limited
+	 * PVT sampling rate. Make sure the timeout is not negative.
+	 */
+	kt = ktime_sub_ns(kt, PVT_TOUT_MIN);
+	if (ktime_to_ns(kt) < 0)
+		kt = ktime_set(0, 0);
+
+	/*
+	 * Finally recalculate the timeout in terms of the reference clock
+	 * period.
+	 */
+	data = ktime_divns(kt * rate, NSEC_PER_SEC);
+
+	/*
+	 * Update the measurements delay, but lock the interface first, since
+	 * we have to disable PVT in order to have the new delay actually
+	 * updated.
+	 */
+	ret = mutex_lock_interruptible(&pvt->iface_mtx);
+	if (ret)
+		return ret;
+
+	pvt_set_tout(pvt, data);
+
+	mutex_unlock(&pvt->iface_mtx);
+
+	return 0;
+}
+
+static int pvt_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			  u32 attr, int ch, long *val)
+{
+	struct pvt_hwmon *pvt = dev_get_drvdata(dev);
+
+	if (!pvt_hwmon_channel_is_valid(type, ch))
+		return -EINVAL;
+
+	switch (type) {
+	case hwmon_chip:
+		switch (attr) {
+		case hwmon_chip_update_interval:
+			return pvt_read_timeout(pvt, val);
+		}
+		break;
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_input:
+			return pvt_read_data(pvt, ch, val);
+		case hwmon_temp_type:
+			*val = 1;
+			return 0;
+		case hwmon_temp_min:
+			return pvt_read_limit(pvt, ch, true, val);
+		case hwmon_temp_max:
+			return pvt_read_limit(pvt, ch, false, val);
+		case hwmon_temp_min_alarm:
+			return pvt_read_alarm(pvt, ch, true, val);
+		case hwmon_temp_max_alarm:
+			return pvt_read_alarm(pvt, ch, false, val);
+		case hwmon_temp_offset:
+			return pvt_read_trim(pvt, val);
+		}
+		break;
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_input:
+			return pvt_read_data(pvt, PVT_VOLT + ch, val);
+		case hwmon_in_min:
+			return pvt_read_limit(pvt, PVT_VOLT + ch, true, val);
+		case hwmon_in_max:
+			return pvt_read_limit(pvt, PVT_VOLT + ch, false, val);
+		case hwmon_in_min_alarm:
+			return pvt_read_alarm(pvt, PVT_VOLT + ch, true, val);
+		case hwmon_in_max_alarm:
+			return pvt_read_alarm(pvt, PVT_VOLT + ch, false, val);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int pvt_hwmon_read_string(struct device *dev,
+				 enum hwmon_sensor_types type,
+				 u32 attr, int ch, const char **str)
+{
+	if (!pvt_hwmon_channel_is_valid(type, ch))
+		return -EINVAL;
+
+	switch (type) {
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_label:
+			*str = pvt_info[ch].label;
+			return 0;
+		}
+		break;
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_label:
+			*str = pvt_info[PVT_VOLT + ch].label;
+			return 0;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int pvt_hwmon_write(struct device *dev, enum hwmon_sensor_types type,
+			   u32 attr, int ch, long val)
+{
+	struct pvt_hwmon *pvt = dev_get_drvdata(dev);
+
+	if (!pvt_hwmon_channel_is_valid(type, ch))
+		return -EINVAL;
+
+	switch (type) {
+	case hwmon_chip:
+		switch (attr) {
+		case hwmon_chip_update_interval:
+			return pvt_write_timeout(pvt, val);
+		}
+		break;
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_min:
+			return pvt_write_limit(pvt, ch, true, val);
+		case hwmon_temp_max:
+			return pvt_write_limit(pvt, ch, false, val);
+		case hwmon_temp_offset:
+			return pvt_write_trim(pvt, val);
+		}
+		break;
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_min:
+			return pvt_write_limit(pvt, PVT_VOLT + ch, true, val);
+		case hwmon_in_max:
+			return pvt_write_limit(pvt, PVT_VOLT + ch, false, val);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static const struct hwmon_ops pvt_hwmon_ops = {
+	.is_visible = pvt_hwmon_is_visible,
+	.read = pvt_hwmon_read,
+	.read_string = pvt_hwmon_read_string,
+	.write = pvt_hwmon_write
+};
+
+static const struct hwmon_chip_info pvt_hwmon_info = {
+	.ops = &pvt_hwmon_ops,
+	.info = pvt_channel_info
+};
+
+static void pvt_clear_data(void *data)
+{
+	struct pvt_hwmon *pvt = data;
+#if !defined(CONFIG_SENSORS_BT1_PVT_ALARMS)
+	int idx;
+
+	for (idx = 0; idx < PVT_SENSORS_NUM; ++idx)
+		complete_all(&pvt->cache[idx].conversion);
+#endif
+
+	mutex_destroy(&pvt->iface_mtx);
+}
+
+static struct pvt_hwmon *pvt_create_data(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct pvt_hwmon *pvt;
+	int ret, idx;
+
+	pvt = devm_kzalloc(dev, sizeof(*pvt), GFP_KERNEL);
+	if (!pvt)
+		return ERR_PTR(-ENOMEM);
+
+	ret = devm_add_action(dev, pvt_clear_data, pvt);
+	if (ret) {
+		dev_err(dev, "Can't add PVT data clear action\n");
+		return ERR_PTR(ret);
+	}
+
+	pvt->dev = dev;
+	pvt->sensor = PVT_SENSOR_FIRST;
+	mutex_init(&pvt->iface_mtx);
+
+#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS)
+	for (idx = 0; idx < PVT_SENSORS_NUM; ++idx)
+		seqlock_init(&pvt->cache[idx].data_seqlock);
+#else
+	for (idx = 0; idx < PVT_SENSORS_NUM; ++idx)
+		init_completion(&pvt->cache[idx].conversion);
+#endif
+
+	return pvt;
+}
+
+static int pvt_request_regs(struct pvt_hwmon *pvt)
+{
+	struct platform_device *pdev = to_platform_device(pvt->dev);
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(pvt->dev, "Couldn't find PVT memresource\n");
+		return -EINVAL;
+	}
+
+	pvt->regs = devm_ioremap_resource(pvt->dev, res);
+	if (IS_ERR(pvt->regs)) {
+		dev_err(pvt->dev, "Couldn't map PVT registers\n");
+		return PTR_ERR(pvt->regs);
+	}
+
+	return 0;
+}
+
+static void pvt_disable_clks(void *data)
+{
+	struct pvt_hwmon *pvt = data;
+
+	clk_bulk_disable_unprepare(PVT_CLOCK_NUM, pvt->clks);
+}
+
+static int pvt_request_clks(struct pvt_hwmon *pvt)
+{
+	int ret;
+
+	pvt->clks[PVT_CLOCK_APB].id = "pclk";
+	pvt->clks[PVT_CLOCK_REF].id = "ref";
+
+	ret = devm_clk_bulk_get(pvt->dev, PVT_CLOCK_NUM, pvt->clks);
+	if (ret) {
+		dev_err(pvt->dev, "Couldn't get PVT clocks descriptors\n");
+		return ret;
+	}
+
+	ret = clk_bulk_prepare_enable(PVT_CLOCK_NUM, pvt->clks);
+	if (ret) {
+		dev_err(pvt->dev, "Couldn't enable the PVT clocks\n");
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(pvt->dev, pvt_disable_clks, pvt);
+	if (ret) {
+		dev_err(pvt->dev, "Can't add PVT clocks disable action\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void pvt_init_iface(struct pvt_hwmon *pvt)
+{
+	u32 trim, temp;
+
+	/*
+	 * Make sure all interrupts and controller are disabled so not to
+	 * accidentally have ISR executed before the driver data is fully
+	 * initialized. Clear the IRQ status as well.
+	 */
+	pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_ALL, PVT_INTR_ALL);
+	pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, 0);
+	readl(pvt->regs + PVT_CLR_INTR);
+	readl(pvt->regs + PVT_DATA);
+
+	/* Setup default sensor mode, timeout and temperature trim. */
+	pvt_set_mode(pvt, pvt_info[pvt->sensor].mode);
+	pvt_set_tout(pvt, PVT_TOUT_DEF);
+
+	trim = PVT_TRIM_DEF;
+	if (!of_property_read_u32(pvt->dev->of_node,
+	     "baikal,pvt-temp-offset-millicelsius", &temp))
+		trim = pvt_calc_trim(temp);
+
+	pvt_set_trim(pvt, trim);
+}
+
+static int pvt_request_irq(struct pvt_hwmon *pvt)
+{
+	struct platform_device *pdev = to_platform_device(pvt->dev);
+	int ret;
+
+	pvt->irq = platform_get_irq(pdev, 0);
+	if (pvt->irq < 0)
+		return pvt->irq;
+
+	ret = devm_request_threaded_irq(pvt->dev, pvt->irq,
+					pvt_hard_isr, pvt_soft_isr,
+#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS)
+					IRQF_SHARED | IRQF_TRIGGER_HIGH |
+					IRQF_ONESHOT,
+#else
+					IRQF_SHARED | IRQF_TRIGGER_HIGH,
+#endif
+					"pvt", pvt);
+	if (ret) {
+		dev_err(pvt->dev, "Couldn't request PVT IRQ\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int pvt_create_hwmon(struct pvt_hwmon *pvt)
+{
+	pvt->hwmon = devm_hwmon_device_register_with_info(pvt->dev, "pvt", pvt,
+		&pvt_hwmon_info, NULL);
+	if (IS_ERR(pvt->hwmon)) {
+		dev_err(pvt->dev, "Couldn't create hwmon device\n");
+		return PTR_ERR(pvt->hwmon);
+	}
+
+	return 0;
+}
+
+#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS)
+
+static void pvt_disable_iface(void *data)
+{
+	struct pvt_hwmon *pvt = data;
+
+	mutex_lock(&pvt->iface_mtx);
+	pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, 0);
+	pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_DVALID,
+		   PVT_INTR_DVALID);
+	mutex_unlock(&pvt->iface_mtx);
+}
+
+static int pvt_enable_iface(struct pvt_hwmon *pvt)
+{
+	int ret;
+
+	ret = devm_add_action(pvt->dev, pvt_disable_iface, pvt);
+	if (ret) {
+		dev_err(pvt->dev, "Can't add PVT disable interface action\n");
+		return ret;
+	}
+
+	/*
+	 * Enable sensors data conversion and IRQ. We need to lock the
+	 * interface mutex since hwmon has just been created and the
+	 * corresponding sysfs files are accessible from user-space,
+	 * which theoretically may cause races.
+	 */
+	mutex_lock(&pvt->iface_mtx);
+	pvt_update(pvt->regs + PVT_INTR_MASK, PVT_INTR_DVALID, 0);
+	pvt_update(pvt->regs + PVT_CTRL, PVT_CTRL_EN, PVT_CTRL_EN);
+	mutex_unlock(&pvt->iface_mtx);
+
+	return 0;
+}
+
+#else /* !CONFIG_SENSORS_BT1_PVT_ALARMS */
+
+static int pvt_enable_iface(struct pvt_hwmon *pvt)
+{
+	return 0;
+}
+
+#endif /* !CONFIG_SENSORS_BT1_PVT_ALARMS */
+
+static int pvt_probe(struct platform_device *pdev)
+{
+	struct pvt_hwmon *pvt;
+	int ret;
+
+	pvt = pvt_create_data(pdev);
+	if (IS_ERR(pvt))
+		return PTR_ERR(pvt);
+
+	ret = pvt_request_regs(pvt);
+	if (ret)
+		return ret;
+
+	ret = pvt_request_clks(pvt);
+	if (ret)
+		return ret;
+
+	pvt_init_iface(pvt);
+
+	ret = pvt_request_irq(pvt);
+	if (ret)
+		return ret;
+
+	ret = pvt_create_hwmon(pvt);
+	if (ret)
+		return ret;
+
+	ret = pvt_enable_iface(pvt);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct of_device_id pvt_of_match[] = {
+	{ .compatible = "baikal,bt1-pvt" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, pvt_of_match);
+
+static struct platform_driver pvt_driver = {
+	.probe = pvt_probe,
+	.driver = {
+		.name = "bt1-pvt",
+		.of_match_table = pvt_of_match
+	}
+};
+module_platform_driver(pvt_driver);
+
+MODULE_AUTHOR("Maxim Kaurkin <maxim.kaurkin@baikalelectronics.ru>");
+MODULE_DESCRIPTION("Baikal-T1 PVT driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwmon/bt1-pvt.h b/drivers/hwmon/bt1-pvt.h
new file mode 100644
index 000000000000..5eac73e94885
--- /dev/null
+++ b/drivers/hwmon/bt1-pvt.h
@@ -0,0 +1,244 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC
+ *
+ * Baikal-T1 Process, Voltage, Temperature sensor driver
+ */
+#ifndef __HWMON_BT1_PVT_H__
+#define __HWMON_BT1_PVT_H__
+
+#include <linux/completion.h>
+#include <linux/hwmon.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/seqlock.h>
+
+/* Baikal-T1 PVT registers and their bitfields */
+#define PVT_CTRL			0x00
+#define PVT_CTRL_EN			BIT(0)
+#define PVT_CTRL_MODE_FLD		1
+#define PVT_CTRL_MODE_MASK		GENMASK(3, PVT_CTRL_MODE_FLD)
+#define PVT_CTRL_MODE_TEMP		0x0
+#define PVT_CTRL_MODE_VOLT		0x1
+#define PVT_CTRL_MODE_LVT		0x2
+#define PVT_CTRL_MODE_HVT		0x4
+#define PVT_CTRL_MODE_SVT		0x6
+#define PVT_CTRL_TRIM_FLD		4
+#define PVT_CTRL_TRIM_MASK		GENMASK(8, PVT_CTRL_TRIM_FLD)
+#define PVT_DATA			0x04
+#define PVT_DATA_VALID			BIT(10)
+#define PVT_DATA_DATA_FLD		0
+#define PVT_DATA_DATA_MASK		GENMASK(9, PVT_DATA_DATA_FLD)
+#define PVT_TTHRES			0x08
+#define PVT_VTHRES			0x0C
+#define PVT_LTHRES			0x10
+#define PVT_HTHRES			0x14
+#define PVT_STHRES			0x18
+#define PVT_THRES_LO_FLD		0
+#define PVT_THRES_LO_MASK		GENMASK(9, PVT_THRES_LO_FLD)
+#define PVT_THRES_HI_FLD		10
+#define PVT_THRES_HI_MASK		GENMASK(19, PVT_THRES_HI_FLD)
+#define PVT_TTIMEOUT			0x1C
+#define PVT_INTR_STAT			0x20
+#define PVT_INTR_MASK			0x24
+#define PVT_RAW_INTR_STAT		0x28
+#define PVT_INTR_DVALID			BIT(0)
+#define PVT_INTR_TTHRES_LO		BIT(1)
+#define PVT_INTR_TTHRES_HI		BIT(2)
+#define PVT_INTR_VTHRES_LO		BIT(3)
+#define PVT_INTR_VTHRES_HI		BIT(4)
+#define PVT_INTR_LTHRES_LO		BIT(5)
+#define PVT_INTR_LTHRES_HI		BIT(6)
+#define PVT_INTR_HTHRES_LO		BIT(7)
+#define PVT_INTR_HTHRES_HI		BIT(8)
+#define PVT_INTR_STHRES_LO		BIT(9)
+#define PVT_INTR_STHRES_HI		BIT(10)
+#define PVT_INTR_ALL			GENMASK(10, 0)
+#define PVT_CLR_INTR			0x2C
+
+/*
+ * PVT sensors-related limits and default values
+ * @PVT_TEMP_MIN: Minimal temperature in millidegrees of Celsius.
+ * @PVT_TEMP_MAX: Maximal temperature in millidegrees of Celsius.
+ * @PVT_TEMP_CHS: Number of temperature hwmon channels.
+ * @PVT_VOLT_MIN: Minimal voltage in mV.
+ * @PVT_VOLT_MAX: Maximal voltage in mV.
+ * @PVT_VOLT_CHS: Number of voltage hwmon channels.
+ * @PVT_DATA_MIN: Minimal PVT raw data value.
+ * @PVT_DATA_MAX: Maximal PVT raw data value.
+ * @PVT_TRIM_MIN: Minimal temperature sensor trim value.
+ * @PVT_TRIM_MAX: Maximal temperature sensor trim value.
+ * @PVT_TRIM_DEF: Default temperature sensor trim value (set a proper value
+ *		  when one is determined for Baikal-T1 SoC).
+ * @PVT_TRIM_TEMP: Maximum temperature encoded by the trim factor.
+ * @PVT_TRIM_STEP: Temperature stride corresponding to the trim value.
+ * @PVT_TOUT_MIN: Minimal timeout between samples in nanoseconds.
+ * @PVT_TOUT_DEF: Default data measurements timeout. In case if alarms are
+ *		  activated the PVT IRQ is enabled to be raised after each
+ *		  conversion in order to have the thresholds checked and the
+ *		  converted value cached. Too frequent conversions may cause
+ *		  the system CPU overload. Lets set the 50ms delay between
+ *		  them by default to prevent this.
+ */
+#define PVT_TEMP_MIN		-48380L
+#define PVT_TEMP_MAX		147438L
+#define PVT_TEMP_CHS		1
+#define PVT_VOLT_MIN		620L
+#define PVT_VOLT_MAX		1168L
+#define PVT_VOLT_CHS		4
+#define PVT_DATA_MIN		0
+#define PVT_DATA_MAX		(PVT_DATA_DATA_MASK >> PVT_DATA_DATA_FLD)
+#define PVT_TRIM_MIN		0
+#define PVT_TRIM_MAX		(PVT_CTRL_TRIM_MASK >> PVT_CTRL_TRIM_FLD)
+#define PVT_TRIM_TEMP		7130
+#define PVT_TRIM_STEP		(PVT_TRIM_TEMP / PVT_TRIM_MAX)
+#define PVT_TRIM_DEF		0
+#define PVT_TOUT_MIN		(NSEC_PER_SEC / 3000)
+#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS)
+# define PVT_TOUT_DEF		60000
+#else
+# define PVT_TOUT_DEF		0
+#endif
+
+/*
+ * enum pvt_sensor_type - Baikal-T1 PVT sensor types (correspond to each PVT
+ *			  sampling mode)
+ * @PVT_SENSOR*: helpers to traverse the sensors in loops.
+ * @PVT_TEMP: PVT Temperature sensor.
+ * @PVT_VOLT: PVT Voltage sensor.
+ * @PVT_LVT: PVT Low-Voltage threshold sensor.
+ * @PVT_HVT: PVT High-Voltage threshold sensor.
+ * @PVT_SVT: PVT Standard-Voltage threshold sensor.
+ */
+enum pvt_sensor_type {
+	PVT_SENSOR_FIRST,
+	PVT_TEMP = PVT_SENSOR_FIRST,
+	PVT_VOLT,
+	PVT_LVT,
+	PVT_HVT,
+	PVT_SVT,
+	PVT_SENSOR_LAST = PVT_SVT,
+	PVT_SENSORS_NUM
+};
+
+/*
+ * enum pvt_clock_type - Baikal-T1 PVT clocks.
+ * @PVT_CLOCK_APB: APB clock.
+ * @PVT_CLOCK_REF: PVT reference clock.
+ */
+enum pvt_clock_type {
+	PVT_CLOCK_APB,
+	PVT_CLOCK_REF,
+	PVT_CLOCK_NUM
+};
+
+/*
+ * struct pvt_sensor_info - Baikal-T1 PVT sensor informational structure
+ * @channel: Sensor channel ID.
+ * @label: hwmon sensor label.
+ * @mode: PVT mode corresponding to the channel.
+ * @thres_base: upper and lower threshold values of the sensor.
+ * @thres_sts_lo: low threshold status bitfield.
+ * @thres_sts_hi: high threshold status bitfield.
+ * @type: Sensor type.
+ * @attr_min_alarm: Min alarm attribute ID.
+ * @attr_min_alarm: Max alarm attribute ID.
+ */
+struct pvt_sensor_info {
+	int channel;
+	const char *label;
+	u32 mode;
+	unsigned long thres_base;
+	u32 thres_sts_lo;
+	u32 thres_sts_hi;
+	enum hwmon_sensor_types type;
+	u32 attr_min_alarm;
+	u32 attr_max_alarm;
+};
+
+#define PVT_SENSOR_INFO(_ch, _label, _type, _mode, _thres)	\
+	{							\
+		.channel = _ch,					\
+		.label = _label,				\
+		.mode = PVT_CTRL_MODE_ ##_mode,			\
+		.thres_base = PVT_ ##_thres,			\
+		.thres_sts_lo = PVT_INTR_ ##_thres## _LO,	\
+		.thres_sts_hi = PVT_INTR_ ##_thres## _HI,	\
+		.type = _type,					\
+		.attr_min_alarm = _type## _min,			\
+		.attr_max_alarm = _type## _max,			\
+	}
+
+/*
+ * struct pvt_cache - PVT sensors data cache
+ * @data: data cache in raw format.
+ * @thres_sts_lo: low threshold status saved on the previous data conversion.
+ * @thres_sts_hi: high threshold status saved on the previous data conversion.
+ * @data_seqlock: cached data seq-lock.
+ * @conversion: data conversion completion.
+ */
+struct pvt_cache {
+	u32 data;
+#if defined(CONFIG_SENSORS_BT1_PVT_ALARMS)
+	seqlock_t data_seqlock;
+	u32 thres_sts_lo;
+	u32 thres_sts_hi;
+#else
+	struct completion conversion;
+#endif
+};
+
+/*
+ * struct pvt_hwmon - Baikal-T1 PVT private data
+ * @dev: device structure of the PVT platform device.
+ * @hwmon: hwmon device structure.
+ * @regs: pointer to the Baikal-T1 PVT registers region.
+ * @irq: PVT events IRQ number.
+ * @clks: Array of the PVT clocks descriptor (APB/ref clocks).
+ * @ref_clk: Pointer to the reference clocks descriptor.
+ * @iface_mtx: Generic interface mutex (used to lock the alarm registers
+ *	       when the alarms enabled, or the data conversion interface
+ *	       if alarms are disabled).
+ * @sensor: current PVT sensor the data conversion is being performed for.
+ * @cache: data cache descriptor.
+ */
+struct pvt_hwmon {
+	struct device *dev;
+	struct device *hwmon;
+
+	void __iomem *regs;
+	int irq;
+
+	struct clk_bulk_data clks[PVT_CLOCK_NUM];
+
+	struct mutex iface_mtx;
+	enum pvt_sensor_type sensor;
+	struct pvt_cache cache[PVT_SENSORS_NUM];
+};
+
+/*
+ * struct pvt_poly_term - a term descriptor of the PVT data translation
+ *			  polynomial
+ * @deg: degree of the term.
+ * @coef: multiplication factor of the term.
+ * @divider: distributed divider per each degree.
+ * @divider_leftover: divider leftover, which couldn't be redistributed.
+ */
+struct pvt_poly_term {
+	unsigned int deg;
+	long coef;
+	long divider;
+	long divider_leftover;
+};
+
+/*
+ * struct pvt_poly - PVT data translation polynomial descriptor
+ * @total_divider: total data divider.
+ * @terms: polynomial terms up to a free one.
+ */
+struct pvt_poly {
+	long total_divider;
+	struct pvt_poly_term terms[];
+};
+
+#endif /* __HWMON_BT1_PVT_H__ */
diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c
index 53b517dbe7e6..4af2fc309c28 100644
--- a/drivers/hwmon/da9052-hwmon.c
+++ b/drivers/hwmon/da9052-hwmon.c
@@ -244,9 +244,9 @@ static ssize_t da9052_tsi_show(struct device *dev,
 	int channel = to_sensor_dev_attr(devattr)->index;
 	int ret;
 
-	mutex_lock(&hwmon->hwmon_lock);
+	mutex_lock(&hwmon->da9052->auxadc_lock);
 	ret = __da9052_read_tsi(dev, channel);
-	mutex_unlock(&hwmon->hwmon_lock);
+	mutex_unlock(&hwmon->da9052->auxadc_lock);
 
 	if (ret < 0)
 		return ret;
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index ab719d372b0d..16be012a95ed 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -1073,13 +1073,6 @@ static const struct dmi_system_id i8k_dmi_table[] __initconst = {
 		},
 	},
 	{
-		.ident = "Dell XPS421",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "XPS L421X"),
-		},
-	},
-	{
 		.ident = "Dell Studio",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -1088,14 +1081,6 @@ static const struct dmi_system_id i8k_dmi_table[] __initconst = {
 		.driver_data = (void *)&i8k_config_data[DELL_STUDIO],
 	},
 	{
-		.ident = "Dell XPS 13",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "XPS13"),
-		},
-		.driver_data = (void *)&i8k_config_data[DELL_XPS],
-	},
-	{
 		.ident = "Dell XPS M140",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
@@ -1104,17 +1089,10 @@ static const struct dmi_system_id i8k_dmi_table[] __initconst = {
 		.driver_data = (void *)&i8k_config_data[DELL_XPS],
 	},
 	{
-		.ident = "Dell XPS 15 9560",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9560"),
-		},
-	},
-	{
-		.ident = "Dell XPS 15 9570",
+		.ident = "Dell XPS",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9570"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS"),
 		},
 	},
 	{ }
diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c
index 370d0c74eb01..0d4f3d97ffc6 100644
--- a/drivers/hwmon/drivetemp.c
+++ b/drivers/hwmon/drivetemp.c
@@ -264,12 +264,18 @@ static int drivetemp_get_scttemp(struct drivetemp_data *st, u32 attr, long *val)
 		return err;
 	switch (attr) {
 	case hwmon_temp_input:
+		if (!temp_is_valid(buf[SCT_STATUS_TEMP]))
+			return -ENODATA;
 		*val = temp_from_sct(buf[SCT_STATUS_TEMP]);
 		break;
 	case hwmon_temp_lowest:
+		if (!temp_is_valid(buf[SCT_STATUS_TEMP_LOWEST]))
+			return -ENODATA;
 		*val = temp_from_sct(buf[SCT_STATUS_TEMP_LOWEST]);
 		break;
 	case hwmon_temp_highest:
+		if (!temp_is_valid(buf[SCT_STATUS_TEMP_HIGHEST]))
+			return -ENODATA;
 		*val = temp_from_sct(buf[SCT_STATUS_TEMP_HIGHEST]);
 		break;
 	default:
@@ -340,7 +346,7 @@ static int drivetemp_identify_sata(struct drivetemp_data *st)
 	st->have_temp_highest = temp_is_valid(buf[SCT_STATUS_TEMP_HIGHEST]);
 
 	if (!have_sct_data_table)
-		goto skip_sct;
+		goto skip_sct_data;
 
 	/* Request and read temperature history table */
 	memset(buf, '\0', sizeof(st->smartdata));
diff --git a/drivers/hwmon/gsc-hwmon.c b/drivers/hwmon/gsc-hwmon.c
new file mode 100644
index 000000000000..2137bc65829d
--- /dev/null
+++ b/drivers/hwmon/gsc-hwmon.c
@@ -0,0 +1,390 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for Gateworks System Controller Hardware Monitor module
+ *
+ * Copyright (C) 2020 Gateworks Corporation
+ */
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/mfd/gsc.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include <linux/platform_data/gsc_hwmon.h>
+
+#define GSC_HWMON_MAX_TEMP_CH	16
+#define GSC_HWMON_MAX_IN_CH	16
+
+#define GSC_HWMON_RESOLUTION	12
+#define GSC_HWMON_VREF		2500
+
+struct gsc_hwmon_data {
+	struct gsc_dev *gsc;
+	struct gsc_hwmon_platform_data *pdata;
+	struct regmap *regmap;
+	const struct gsc_hwmon_channel *temp_ch[GSC_HWMON_MAX_TEMP_CH];
+	const struct gsc_hwmon_channel *in_ch[GSC_HWMON_MAX_IN_CH];
+	u32 temp_config[GSC_HWMON_MAX_TEMP_CH + 1];
+	u32 in_config[GSC_HWMON_MAX_IN_CH + 1];
+	struct hwmon_channel_info temp_info;
+	struct hwmon_channel_info in_info;
+	const struct hwmon_channel_info *info[3];
+	struct hwmon_chip_info chip;
+};
+
+static struct regmap_bus gsc_hwmon_regmap_bus = {
+	.reg_read = gsc_read,
+	.reg_write = gsc_write,
+};
+
+static const struct regmap_config gsc_hwmon_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.cache_type = REGCACHE_NONE,
+};
+
+static ssize_t pwm_auto_point_temp_show(struct device *dev,
+					struct device_attribute *devattr,
+					char *buf)
+{
+	struct gsc_hwmon_data *hwmon = dev_get_drvdata(dev);
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	u8 reg = hwmon->pdata->fan_base + (2 * attr->index);
+	u8 regs[2];
+	int ret;
+
+	ret = regmap_bulk_read(hwmon->regmap, reg, regs, 2);
+	if (ret)
+		return ret;
+
+	ret = regs[0] | regs[1] << 8;
+	return sprintf(buf, "%d\n", ret * 10);
+}
+
+static ssize_t pwm_auto_point_temp_store(struct device *dev,
+					 struct device_attribute *devattr,
+					 const char *buf, size_t count)
+{
+	struct gsc_hwmon_data *hwmon = dev_get_drvdata(dev);
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	u8 reg = hwmon->pdata->fan_base + (2 * attr->index);
+	u8 regs[2];
+	long temp;
+	int err;
+
+	if (kstrtol(buf, 10, &temp))
+		return -EINVAL;
+
+	temp = clamp_val(temp, 0, 10000);
+	temp = DIV_ROUND_CLOSEST(temp, 10);
+
+	regs[0] = temp & 0xff;
+	regs[1] = (temp >> 8) & 0xff;
+	err = regmap_bulk_write(hwmon->regmap, reg, regs, 2);
+	if (err)
+		return err;
+
+	return count;
+}
+
+static ssize_t pwm_auto_point_pwm_show(struct device *dev,
+				       struct device_attribute *devattr,
+				       char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+
+	return sprintf(buf, "%d\n", 255 * (50 + (attr->index * 10)) / 100);
+}
+
+static SENSOR_DEVICE_ATTR_RO(pwm1_auto_point1_pwm, pwm_auto_point_pwm, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm1_auto_point1_temp, pwm_auto_point_temp, 0);
+
+static SENSOR_DEVICE_ATTR_RO(pwm1_auto_point2_pwm, pwm_auto_point_pwm, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm1_auto_point2_temp, pwm_auto_point_temp, 1);
+
+static SENSOR_DEVICE_ATTR_RO(pwm1_auto_point3_pwm, pwm_auto_point_pwm, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm1_auto_point3_temp, pwm_auto_point_temp, 2);
+
+static SENSOR_DEVICE_ATTR_RO(pwm1_auto_point4_pwm, pwm_auto_point_pwm, 3);
+static SENSOR_DEVICE_ATTR_RW(pwm1_auto_point4_temp, pwm_auto_point_temp, 3);
+
+static SENSOR_DEVICE_ATTR_RO(pwm1_auto_point5_pwm, pwm_auto_point_pwm, 4);
+static SENSOR_DEVICE_ATTR_RW(pwm1_auto_point5_temp, pwm_auto_point_temp, 4);
+
+static SENSOR_DEVICE_ATTR_RO(pwm1_auto_point6_pwm, pwm_auto_point_pwm, 5);
+static SENSOR_DEVICE_ATTR_RW(pwm1_auto_point6_temp, pwm_auto_point_temp, 5);
+
+static struct attribute *gsc_hwmon_attributes[] = {
+	&sensor_dev_attr_pwm1_auto_point1_pwm.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point1_temp.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point2_pwm.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point2_temp.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point3_pwm.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point3_temp.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point4_pwm.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point4_temp.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point5_pwm.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point5_temp.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point6_pwm.dev_attr.attr,
+	&sensor_dev_attr_pwm1_auto_point6_temp.dev_attr.attr,
+	NULL
+};
+
+static const struct attribute_group gsc_hwmon_group = {
+	.attrs = gsc_hwmon_attributes,
+};
+__ATTRIBUTE_GROUPS(gsc_hwmon);
+
+static int
+gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+	       int channel, long *val)
+{
+	struct gsc_hwmon_data *hwmon = dev_get_drvdata(dev);
+	const struct gsc_hwmon_channel *ch;
+	int sz, ret;
+	long tmp;
+	u8 buf[3];
+
+	switch (type) {
+	case hwmon_in:
+		ch = hwmon->in_ch[channel];
+		break;
+	case hwmon_temp:
+		ch = hwmon->temp_ch[channel];
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	sz = (ch->mode == mode_voltage) ? 3 : 2;
+	ret = regmap_bulk_read(hwmon->regmap, ch->reg, buf, sz);
+	if (ret)
+		return ret;
+
+	tmp = 0;
+	while (sz-- > 0)
+		tmp |= (buf[sz] << (8 * sz));
+
+	switch (ch->mode) {
+	case mode_temperature:
+		if (tmp > 0x8000)
+			tmp -= 0xffff;
+		break;
+	case mode_voltage_raw:
+		tmp = clamp_val(tmp, 0, BIT(GSC_HWMON_RESOLUTION));
+		/* scale based on ref voltage and ADC resolution */
+		tmp *= GSC_HWMON_VREF;
+		tmp >>= GSC_HWMON_RESOLUTION;
+		/* scale based on optional voltage divider */
+		if (ch->vdiv[0] && ch->vdiv[1]) {
+			tmp *= (ch->vdiv[0] + ch->vdiv[1]);
+			tmp /= ch->vdiv[1];
+		}
+		/* adjust by uV offset */
+		tmp += ch->mvoffset;
+		break;
+	case mode_voltage:
+		/* no adjustment needed */
+		break;
+	}
+
+	*val = tmp;
+
+	return 0;
+}
+
+static int
+gsc_hwmon_read_string(struct device *dev, enum hwmon_sensor_types type,
+		      u32 attr, int channel, const char **buf)
+{
+	struct gsc_hwmon_data *hwmon = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_in:
+		*buf = hwmon->in_ch[channel]->name;
+		break;
+	case hwmon_temp:
+		*buf = hwmon->temp_ch[channel]->name;
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return 0;
+}
+
+static umode_t
+gsc_hwmon_is_visible(const void *_data, enum hwmon_sensor_types type, u32 attr,
+		     int ch)
+{
+	return 0444;
+}
+
+static const struct hwmon_ops gsc_hwmon_ops = {
+	.is_visible = gsc_hwmon_is_visible,
+	.read = gsc_hwmon_read,
+	.read_string = gsc_hwmon_read_string,
+};
+
+static struct gsc_hwmon_platform_data *
+gsc_hwmon_get_devtree_pdata(struct device *dev)
+{
+	struct gsc_hwmon_platform_data *pdata;
+	struct gsc_hwmon_channel *ch;
+	struct fwnode_handle *child;
+	struct device_node *fan;
+	int nchannels;
+
+	nchannels = device_get_child_node_count(dev);
+	if (nchannels == 0)
+		return ERR_PTR(-ENODEV);
+
+	pdata = devm_kzalloc(dev,
+			     sizeof(*pdata) + nchannels * sizeof(*ch),
+			     GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+	ch = (struct gsc_hwmon_channel *)(pdata + 1);
+	pdata->channels = ch;
+	pdata->nchannels = nchannels;
+
+	/* fan controller base address */
+	fan = of_find_compatible_node(dev->parent->of_node, NULL, "gw,gsc-fan");
+	if (fan && of_property_read_u32(fan, "reg", &pdata->fan_base)) {
+		dev_err(dev, "fan node without base\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* allocate structures for channels and count instances of each type */
+	device_for_each_child_node(dev, child) {
+		if (fwnode_property_read_string(child, "label", &ch->name)) {
+			dev_err(dev, "channel without label\n");
+			fwnode_handle_put(child);
+			return ERR_PTR(-EINVAL);
+		}
+		if (fwnode_property_read_u32(child, "reg", &ch->reg)) {
+			dev_err(dev, "channel without reg\n");
+			fwnode_handle_put(child);
+			return ERR_PTR(-EINVAL);
+		}
+		if (fwnode_property_read_u32(child, "gw,mode", &ch->mode)) {
+			dev_err(dev, "channel without mode\n");
+			fwnode_handle_put(child);
+			return ERR_PTR(-EINVAL);
+		}
+		if (ch->mode > mode_max) {
+			dev_err(dev, "invalid channel mode\n");
+			fwnode_handle_put(child);
+			return ERR_PTR(-EINVAL);
+		}
+
+		if (!fwnode_property_read_u32(child,
+					      "gw,voltage-offset-microvolt",
+					      &ch->mvoffset))
+			ch->mvoffset /= 1000;
+		fwnode_property_read_u32_array(child,
+					       "gw,voltage-divider-ohms",
+					       ch->vdiv, ARRAY_SIZE(ch->vdiv));
+		ch++;
+	}
+
+	return pdata;
+}
+
+static int gsc_hwmon_probe(struct platform_device *pdev)
+{
+	struct gsc_dev *gsc = dev_get_drvdata(pdev->dev.parent);
+	struct device *dev = &pdev->dev;
+	struct device *hwmon_dev;
+	struct gsc_hwmon_platform_data *pdata = dev_get_platdata(dev);
+	struct gsc_hwmon_data *hwmon;
+	const struct attribute_group **groups;
+	int i, i_in, i_temp;
+
+	if (!pdata) {
+		pdata = gsc_hwmon_get_devtree_pdata(dev);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+	}
+
+	hwmon = devm_kzalloc(dev, sizeof(*hwmon), GFP_KERNEL);
+	if (!hwmon)
+		return -ENOMEM;
+	hwmon->gsc = gsc;
+	hwmon->pdata = pdata;
+
+	hwmon->regmap = devm_regmap_init(dev, &gsc_hwmon_regmap_bus,
+					 gsc->i2c_hwmon,
+					 &gsc_hwmon_regmap_config);
+	if (IS_ERR(hwmon->regmap))
+		return PTR_ERR(hwmon->regmap);
+
+	for (i = 0, i_in = 0, i_temp = 0; i < hwmon->pdata->nchannels; i++) {
+		const struct gsc_hwmon_channel *ch = &pdata->channels[i];
+
+		switch (ch->mode) {
+		case mode_temperature:
+			if (i_temp == GSC_HWMON_MAX_TEMP_CH) {
+				dev_err(gsc->dev, "too many temp channels\n");
+				return -EINVAL;
+			}
+			hwmon->temp_ch[i_temp] = ch;
+			hwmon->temp_config[i_temp] = HWMON_T_INPUT |
+						     HWMON_T_LABEL;
+			i_temp++;
+			break;
+		case mode_voltage:
+		case mode_voltage_raw:
+			if (i_in == GSC_HWMON_MAX_IN_CH) {
+				dev_err(gsc->dev, "too many input channels\n");
+				return -EINVAL;
+			}
+			hwmon->in_ch[i_in] = ch;
+			hwmon->in_config[i_in] =
+				HWMON_I_INPUT | HWMON_I_LABEL;
+			i_in++;
+			break;
+		default:
+			dev_err(gsc->dev, "invalid mode: %d\n", ch->mode);
+			return -EINVAL;
+		}
+	}
+
+	/* setup config structures */
+	hwmon->chip.ops = &gsc_hwmon_ops;
+	hwmon->chip.info = hwmon->info;
+	hwmon->info[0] = &hwmon->temp_info;
+	hwmon->info[1] = &hwmon->in_info;
+	hwmon->temp_info.type = hwmon_temp;
+	hwmon->temp_info.config = hwmon->temp_config;
+	hwmon->in_info.type = hwmon_in;
+	hwmon->in_info.config = hwmon->in_config;
+
+	groups = pdata->fan_base ? gsc_hwmon_groups : NULL;
+	hwmon_dev = devm_hwmon_device_register_with_info(dev,
+							 KBUILD_MODNAME, hwmon,
+							 &hwmon->chip, groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct of_device_id gsc_hwmon_of_match[] = {
+	{ .compatible = "gw,gsc-adc", },
+	{}
+};
+
+static struct platform_driver gsc_hwmon_driver = {
+	.driver = {
+		.name = "gsc-hwmon",
+		.of_match_table = gsc_hwmon_of_match,
+	},
+	.probe = gsc_hwmon_probe,
+};
+
+module_platform_driver(gsc_hwmon_driver);
+
+MODULE_AUTHOR("Tim Harvey <tharvey@gateworks.com>");
+MODULE_DESCRIPTION("GSC hardware monitor driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 6a30fb453f7a..3f596a5328da 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -15,6 +15,7 @@
 #include <linux/gfp.h>
 #include <linux/hwmon.h>
 #include <linux/idr.h>
+#include <linux/list.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
@@ -31,7 +32,7 @@ struct hwmon_device {
 	const char *name;
 	struct device dev;
 	const struct hwmon_chip_info *chip;
-
+	struct list_head tzdata;
 	struct attribute_group group;
 	const struct attribute_group **groups;
 };
@@ -55,12 +56,12 @@ struct hwmon_device_attribute {
 
 /*
  * Thermal zone information
- * In addition to the reference to the hwmon device,
- * also provides the sensor index.
  */
 struct hwmon_thermal_data {
+	struct list_head node;		/* hwmon tzdata list entry */
 	struct device *dev;		/* Reference to hwmon device */
 	int index;			/* sensor index */
+	struct thermal_zone_device *tzd;/* thermal zone device */
 };
 
 static ssize_t
@@ -156,10 +157,17 @@ static const struct thermal_zone_of_device_ops hwmon_thermal_ops = {
 	.get_temp = hwmon_thermal_get_temp,
 };
 
+static void hwmon_thermal_remove_sensor(void *data)
+{
+	list_del(data);
+}
+
 static int hwmon_thermal_add_sensor(struct device *dev, int index)
 {
+	struct hwmon_device *hwdev = to_hwmon_device(dev);
 	struct hwmon_thermal_data *tdata;
 	struct thermal_zone_device *tzd;
+	int err;
 
 	tdata = devm_kzalloc(dev, sizeof(*tdata), GFP_KERNEL);
 	if (!tdata)
@@ -177,13 +185,68 @@ static int hwmon_thermal_add_sensor(struct device *dev, int index)
 	if (IS_ERR(tzd) && (PTR_ERR(tzd) != -ENODEV))
 		return PTR_ERR(tzd);
 
+	err = devm_add_action(dev, hwmon_thermal_remove_sensor, &tdata->node);
+	if (err)
+		return err;
+
+	tdata->tzd = tzd;
+	list_add(&tdata->node, &hwdev->tzdata);
+
 	return 0;
 }
+
+static int hwmon_thermal_register_sensors(struct device *dev)
+{
+	struct hwmon_device *hwdev = to_hwmon_device(dev);
+	const struct hwmon_chip_info *chip = hwdev->chip;
+	const struct hwmon_channel_info **info = chip->info;
+	void *drvdata = dev_get_drvdata(dev);
+	int i;
+
+	for (i = 1; info[i]; i++) {
+		int j;
+
+		if (info[i]->type != hwmon_temp)
+			continue;
+
+		for (j = 0; info[i]->config[j]; j++) {
+			int err;
+
+			if (!(info[i]->config[j] & HWMON_T_INPUT) ||
+			    !chip->ops->is_visible(drvdata, hwmon_temp,
+						   hwmon_temp_input, j))
+				continue;
+
+			err = hwmon_thermal_add_sensor(dev, j);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static void hwmon_thermal_notify(struct device *dev, int index)
+{
+	struct hwmon_device *hwdev = to_hwmon_device(dev);
+	struct hwmon_thermal_data *tzdata;
+
+	list_for_each_entry(tzdata, &hwdev->tzdata, node) {
+		if (tzdata->index == index) {
+			thermal_zone_device_update(tzdata->tzd,
+						   THERMAL_EVENT_UNSPECIFIED);
+		}
+	}
+}
+
 #else
-static int hwmon_thermal_add_sensor(struct device *dev, int index)
+static int hwmon_thermal_register_sensors(struct device *dev)
 {
 	return 0;
 }
+
+static void hwmon_thermal_notify(struct device *dev, int index) { }
+
 #endif /* IS_REACHABLE(CONFIG_THERMAL) && ... */
 
 static int hwmon_attr_base(enum hwmon_sensor_types type)
@@ -511,6 +574,35 @@ static const int __templates_size[] = {
 	[hwmon_intrusion] = ARRAY_SIZE(hwmon_intrusion_attr_templates),
 };
 
+int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type,
+		       u32 attr, int channel)
+{
+	char sattr[MAX_SYSFS_ATTR_NAME_LENGTH];
+	const char * const *templates;
+	const char *template;
+	int base;
+
+	if (type >= ARRAY_SIZE(__templates))
+		return -EINVAL;
+	if (attr >= __templates_size[type])
+		return -EINVAL;
+
+	templates = __templates[type];
+	template = templates[attr];
+
+	base = hwmon_attr_base(type);
+
+	scnprintf(sattr, MAX_SYSFS_ATTR_NAME_LENGTH, template, base + channel);
+	sysfs_notify(&dev->kobj, NULL, sattr);
+	kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+
+	if (type == hwmon_temp)
+		hwmon_thermal_notify(dev, channel);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hwmon_notify_event);
+
 static int hwmon_num_channel_attrs(const struct hwmon_channel_info *info)
 {
 	int i, n;
@@ -596,7 +688,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 {
 	struct hwmon_device *hwdev;
 	struct device *hdev;
-	int i, j, err, id;
+	int i, err, id;
 
 	/* Complain about invalid characters in hwmon name attribute */
 	if (name && (!strlen(name) || strpbrk(name, "-* \t\n")))
@@ -661,33 +753,19 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 	if (err)
 		goto free_hwmon;
 
+	INIT_LIST_HEAD(&hwdev->tzdata);
+
 	if (dev && dev->of_node && chip && chip->ops->read &&
 	    chip->info[0]->type == hwmon_chip &&
 	    (chip->info[0]->config[0] & HWMON_C_REGISTER_TZ)) {
-		const struct hwmon_channel_info **info = chip->info;
-
-		for (i = 1; info[i]; i++) {
-			if (info[i]->type != hwmon_temp)
-				continue;
-
-			for (j = 0; info[i]->config[j]; j++) {
-				if (!chip->ops->is_visible(drvdata, hwmon_temp,
-							   hwmon_temp_input, j))
-					continue;
-				if (info[i]->config[j] & HWMON_T_INPUT) {
-					err = hwmon_thermal_add_sensor(hdev, j);
-					if (err) {
-						device_unregister(hdev);
-						/*
-						 * Don't worry about hwdev;
-						 * hwmon_dev_release(), called
-						 * from device_unregister(),
-						 * will free it.
-						 */
-						goto ida_remove;
-					}
-				}
-			}
+		err = hwmon_thermal_register_sensors(hdev);
+		if (err) {
+			device_unregister(hdev);
+			/*
+			 * Don't worry about hwdev; hwmon_dev_release(), called
+			 * from device_unregister(), will free it.
+			 */
+			goto ida_remove;
 		}
 	}
 
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index e9e78c0b7212..55d474ec7c35 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -74,6 +74,17 @@
 #define INA226_READ_AVG(reg)		(((reg) & INA226_AVG_RD_MASK) >> 9)
 #define INA226_SHIFT_AVG(val)		((val) << 9)
 
+/* bit number of alert functions in Mask/Enable Register */
+#define INA226_SHUNT_OVER_VOLTAGE_BIT	15
+#define INA226_SHUNT_UNDER_VOLTAGE_BIT	14
+#define INA226_BUS_OVER_VOLTAGE_BIT	13
+#define INA226_BUS_UNDER_VOLTAGE_BIT	12
+#define INA226_POWER_OVER_LIMIT_BIT	11
+
+/* bit mask for alert config bits of Mask/Enable Register */
+#define INA226_ALERT_CONFIG_MASK	0xFC00
+#define INA226_ALERT_FUNCTION_FLAG	BIT(4)
+
 /* common attrs, ina226 attrs and NULL */
 #define INA2XX_MAX_ATTRIBUTE_GROUPS	3
 
@@ -303,6 +314,145 @@ static ssize_t ina2xx_value_show(struct device *dev,
 			ina2xx_get_value(data, attr->index, regval));
 }
 
+static int ina226_reg_to_alert(struct ina2xx_data *data, u8 bit, u16 regval)
+{
+	int reg;
+
+	switch (bit) {
+	case INA226_SHUNT_OVER_VOLTAGE_BIT:
+	case INA226_SHUNT_UNDER_VOLTAGE_BIT:
+		reg = INA2XX_SHUNT_VOLTAGE;
+		break;
+	case INA226_BUS_OVER_VOLTAGE_BIT:
+	case INA226_BUS_UNDER_VOLTAGE_BIT:
+		reg = INA2XX_BUS_VOLTAGE;
+		break;
+	case INA226_POWER_OVER_LIMIT_BIT:
+		reg = INA2XX_POWER;
+		break;
+	default:
+		/* programmer goofed */
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	return ina2xx_get_value(data, reg, regval);
+}
+
+/*
+ * Turns alert limit values into register values.
+ * Opposite of the formula in ina2xx_get_value().
+ */
+static s16 ina226_alert_to_reg(struct ina2xx_data *data, u8 bit, int val)
+{
+	switch (bit) {
+	case INA226_SHUNT_OVER_VOLTAGE_BIT:
+	case INA226_SHUNT_UNDER_VOLTAGE_BIT:
+		val *= data->config->shunt_div;
+		return clamp_val(val, SHRT_MIN, SHRT_MAX);
+	case INA226_BUS_OVER_VOLTAGE_BIT:
+	case INA226_BUS_UNDER_VOLTAGE_BIT:
+		val = (val * 1000) << data->config->bus_voltage_shift;
+		val = DIV_ROUND_CLOSEST(val, data->config->bus_voltage_lsb);
+		return clamp_val(val, 0, SHRT_MAX);
+	case INA226_POWER_OVER_LIMIT_BIT:
+		val = DIV_ROUND_CLOSEST(val, data->power_lsb_uW);
+		return clamp_val(val, 0, USHRT_MAX);
+	default:
+		/* programmer goofed */
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+}
+
+static ssize_t ina226_alert_show(struct device *dev,
+				 struct device_attribute *da, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+	struct ina2xx_data *data = dev_get_drvdata(dev);
+	int regval;
+	int val = 0;
+	int ret;
+
+	mutex_lock(&data->config_lock);
+	ret = regmap_read(data->regmap, INA226_MASK_ENABLE, &regval);
+	if (ret)
+		goto abort;
+
+	if (regval & BIT(attr->index)) {
+		ret = regmap_read(data->regmap, INA226_ALERT_LIMIT, &regval);
+		if (ret)
+			goto abort;
+		val = ina226_reg_to_alert(data, attr->index, regval);
+	}
+
+	ret = snprintf(buf, PAGE_SIZE, "%d\n", val);
+abort:
+	mutex_unlock(&data->config_lock);
+	return ret;
+}
+
+static ssize_t ina226_alert_store(struct device *dev,
+				  struct device_attribute *da,
+				  const char *buf, size_t count)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+	struct ina2xx_data *data = dev_get_drvdata(dev);
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Clear all alerts first to avoid accidentally triggering ALERT pin
+	 * due to register write sequence. Then, only enable the alert
+	 * if the value is non-zero.
+	 */
+	mutex_lock(&data->config_lock);
+	ret = regmap_update_bits(data->regmap, INA226_MASK_ENABLE,
+				 INA226_ALERT_CONFIG_MASK, 0);
+	if (ret < 0)
+		goto abort;
+
+	ret = regmap_write(data->regmap, INA226_ALERT_LIMIT,
+			   ina226_alert_to_reg(data, attr->index, val));
+	if (ret < 0)
+		goto abort;
+
+	if (val != 0) {
+		ret = regmap_update_bits(data->regmap, INA226_MASK_ENABLE,
+					 INA226_ALERT_CONFIG_MASK,
+					 BIT(attr->index));
+		if (ret < 0)
+			goto abort;
+	}
+
+	ret = count;
+abort:
+	mutex_unlock(&data->config_lock);
+	return ret;
+}
+
+static ssize_t ina226_alarm_show(struct device *dev,
+				 struct device_attribute *da, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+	struct ina2xx_data *data = dev_get_drvdata(dev);
+	int regval;
+	int alarm = 0;
+	int ret;
+
+	ret = regmap_read(data->regmap, INA226_MASK_ENABLE, &regval);
+	if (ret)
+		return ret;
+
+	alarm = (regval & BIT(attr->index)) &&
+		(regval & INA226_ALERT_FUNCTION_FLAG);
+	return snprintf(buf, PAGE_SIZE, "%d\n", alarm);
+}
+
 /*
  * In order to keep calibration register value fixed, the product
  * of current_lsb and shunt_resistor should also be fixed and equal
@@ -392,15 +542,38 @@ static ssize_t ina226_interval_show(struct device *dev,
 
 /* shunt voltage */
 static SENSOR_DEVICE_ATTR_RO(in0_input, ina2xx_value, INA2XX_SHUNT_VOLTAGE);
+/* shunt voltage over/under voltage alert setting and alarm */
+static SENSOR_DEVICE_ATTR_RW(in0_crit, ina226_alert,
+			     INA226_SHUNT_OVER_VOLTAGE_BIT);
+static SENSOR_DEVICE_ATTR_RW(in0_lcrit, ina226_alert,
+			     INA226_SHUNT_UNDER_VOLTAGE_BIT);
+static SENSOR_DEVICE_ATTR_RO(in0_crit_alarm, ina226_alarm,
+			     INA226_SHUNT_OVER_VOLTAGE_BIT);
+static SENSOR_DEVICE_ATTR_RO(in0_lcrit_alarm, ina226_alarm,
+			     INA226_SHUNT_UNDER_VOLTAGE_BIT);
 
 /* bus voltage */
 static SENSOR_DEVICE_ATTR_RO(in1_input, ina2xx_value, INA2XX_BUS_VOLTAGE);
+/* bus voltage over/under voltage alert setting and alarm */
+static SENSOR_DEVICE_ATTR_RW(in1_crit, ina226_alert,
+			     INA226_BUS_OVER_VOLTAGE_BIT);
+static SENSOR_DEVICE_ATTR_RW(in1_lcrit, ina226_alert,
+			     INA226_BUS_UNDER_VOLTAGE_BIT);
+static SENSOR_DEVICE_ATTR_RO(in1_crit_alarm, ina226_alarm,
+			     INA226_BUS_OVER_VOLTAGE_BIT);
+static SENSOR_DEVICE_ATTR_RO(in1_lcrit_alarm, ina226_alarm,
+			     INA226_BUS_UNDER_VOLTAGE_BIT);
 
 /* calculated current */
 static SENSOR_DEVICE_ATTR_RO(curr1_input, ina2xx_value, INA2XX_CURRENT);
 
 /* calculated power */
 static SENSOR_DEVICE_ATTR_RO(power1_input, ina2xx_value, INA2XX_POWER);
+/* over-limit power alert setting and alarm */
+static SENSOR_DEVICE_ATTR_RW(power1_crit, ina226_alert,
+			     INA226_POWER_OVER_LIMIT_BIT);
+static SENSOR_DEVICE_ATTR_RO(power1_crit_alarm, ina226_alarm,
+			     INA226_POWER_OVER_LIMIT_BIT);
 
 /* shunt resistance */
 static SENSOR_DEVICE_ATTR_RW(shunt_resistor, ina2xx_shunt, INA2XX_CALIBRATION);
@@ -423,6 +596,16 @@ static const struct attribute_group ina2xx_group = {
 };
 
 static struct attribute *ina226_attrs[] = {
+	&sensor_dev_attr_in0_crit.dev_attr.attr,
+	&sensor_dev_attr_in0_lcrit.dev_attr.attr,
+	&sensor_dev_attr_in0_crit_alarm.dev_attr.attr,
+	&sensor_dev_attr_in0_lcrit_alarm.dev_attr.attr,
+	&sensor_dev_attr_in1_crit.dev_attr.attr,
+	&sensor_dev_attr_in1_lcrit.dev_attr.attr,
+	&sensor_dev_attr_in1_crit_alarm.dev_attr.attr,
+	&sensor_dev_attr_in1_lcrit_alarm.dev_attr.attr,
+	&sensor_dev_attr_power1_crit.dev_attr.attr,
+	&sensor_dev_attr_power1_crit_alarm.dev_attr.attr,
 	&sensor_dev_attr_update_interval.dev_attr.attr,
 	NULL,
 };
diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c
index f2d81b0558e5..e3f1ebee7130 100644
--- a/drivers/hwmon/jc42.c
+++ b/drivers/hwmon/jc42.c
@@ -506,7 +506,7 @@ static int jc42_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	}
 	data->config = config;
 
-	hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name,
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, "jc42",
 							 data, &jc42_chip_info,
 							 NULL);
 	return PTR_ERR_OR_ZERO(hwmon_dev);
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 3f37d5d81fe4..9915578533bb 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -186,7 +186,7 @@ static long get_raw_temp(struct k10temp_data *data)
 	return temp;
 }
 
-const char *k10temp_temp_label[] = {
+static const char *k10temp_temp_label[] = {
 	"Tctl",
 	"Tdie",
 	"Tccd1",
@@ -199,12 +199,12 @@ const char *k10temp_temp_label[] = {
 	"Tccd8",
 };
 
-const char *k10temp_in_label[] = {
+static const char *k10temp_in_label[] = {
 	"Vcore",
 	"Vsoc",
 };
 
-const char *k10temp_curr_label[] = {
+static const char *k10temp_curr_label[] = {
 	"Icore",
 	"Isoc",
 };
diff --git a/drivers/hwmon/lm70.c b/drivers/hwmon/lm70.c
index 4122e59f0bb4..ae2b84263a44 100644
--- a/drivers/hwmon/lm70.c
+++ b/drivers/hwmon/lm70.c
@@ -25,7 +25,7 @@
 #include <linux/spi/spi.h>
 #include <linux/slab.h>
 #include <linux/of_device.h>
-
+#include <linux/acpi.h>
 
 #define DRVNAME		"lm70"
 
@@ -148,18 +148,50 @@ static const struct of_device_id lm70_of_ids[] = {
 MODULE_DEVICE_TABLE(of, lm70_of_ids);
 #endif
 
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id lm70_acpi_ids[] = {
+	{
+		.id = "LM000070",
+		.driver_data = LM70_CHIP_LM70,
+	},
+	{
+		.id = "TMP00121",
+		.driver_data = LM70_CHIP_TMP121,
+	},
+	{
+		.id = "LM000071",
+		.driver_data = LM70_CHIP_LM71,
+	},
+	{
+		.id = "LM000074",
+		.driver_data = LM70_CHIP_LM74,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, lm70_acpi_ids);
+#endif
+
 static int lm70_probe(struct spi_device *spi)
 {
-	const struct of_device_id *match;
+	const struct of_device_id *of_match;
 	struct device *hwmon_dev;
 	struct lm70 *p_lm70;
 	int chip;
 
-	match = of_match_device(lm70_of_ids, &spi->dev);
-	if (match)
-		chip = (int)(uintptr_t)match->data;
-	else
-		chip = spi_get_device_id(spi)->driver_data;
+	of_match = of_match_device(lm70_of_ids, &spi->dev);
+	if (of_match)
+		chip = (int)(uintptr_t)of_match->data;
+	else {
+#ifdef CONFIG_ACPI
+		const struct acpi_device_id *acpi_match;
+
+		acpi_match = acpi_match_device(lm70_acpi_ids, &spi->dev);
+		if (acpi_match)
+			chip = (int)(uintptr_t)acpi_match->driver_data;
+		else
+#endif
+			chip = spi_get_device_id(spi)->driver_data;
+	}
 
 	/* signaling is SPI_MODE_0 */
 	if (spi->mode & (SPI_CPOL | SPI_CPHA))
@@ -195,6 +227,7 @@ static struct spi_driver lm70_driver = {
 	.driver = {
 		.name	= "lm70",
 		.of_match_table	= of_match_ptr(lm70_of_ids),
+		.acpi_match_table = ACPI_PTR(lm70_acpi_ids),
 	},
 	.id_table = lm70_ids,
 	.probe	= lm70_probe,
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index 5e6392294c03..ba0be48aeadd 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -797,8 +797,10 @@ static int lm75_detect(struct i2c_client *new_client,
 
 	/* First check for LM75A */
 	if (i2c_smbus_read_byte_data(new_client, 7) == LM75A_ID) {
-		/* LM75A returns 0xff on unused registers so
-		   just to be sure we check for that too. */
+		/*
+		 * LM75A returns 0xff on unused registers so
+		 * just to be sure we check for that too.
+		 */
 		if (i2c_smbus_read_byte_data(new_client, 4) != 0xff
 		 || i2c_smbus_read_byte_data(new_client, 5) != 0xff
 		 || i2c_smbus_read_byte_data(new_client, 6) != 0xff)
@@ -849,6 +851,7 @@ static int lm75_suspend(struct device *dev)
 {
 	int status;
 	struct i2c_client *client = to_i2c_client(dev);
+
 	status = i2c_smbus_read_byte_data(client, LM75_REG_CONF);
 	if (status < 0) {
 		dev_dbg(&client->dev, "Can't read config? %d\n", status);
@@ -863,6 +866,7 @@ static int lm75_resume(struct device *dev)
 {
 	int status;
 	struct i2c_client *client = to_i2c_client(dev);
+
 	status = i2c_smbus_read_byte_data(client, LM75_REG_CONF);
 	if (status < 0) {
 		dev_dbg(&client->dev, "Can't read config? %d\n", status);
diff --git a/drivers/hwmon/lm75.h b/drivers/hwmon/lm75.h
index b614e6328566..a398171162a8 100644
--- a/drivers/hwmon/lm75.h
+++ b/drivers/hwmon/lm75.h
@@ -1,17 +1,15 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
-    lm75.h - Part of lm_sensors, Linux kernel modules for hardware
-	      monitoring
-    Copyright (c) 2003 Mark M. Hoffman <mhoffman@lightlink.com>
-
-*/
+ * lm75.h - Part of lm_sensors, Linux kernel modules for hardware monitoring
+ * Copyright (c) 2003 Mark M. Hoffman <mhoffman@lightlink.com>
+ */
 
 /*
-    This file contains common code for encoding/decoding LM75 type
-    temperature readings, which are emulated by many of the chips
-    we support.  As the user is unlikely to load more than one driver
-    which contains this code, we don't worry about the wasted space.
-*/
+ * This file contains common code for encoding/decoding LM75 type
+ * temperature readings, which are emulated by many of the chips
+ * we support.  As the user is unlikely to load more than one driver
+ * which contains this code, we don't worry about the wasted space.
+ */
 
 #include <linux/kernel.h>
 
@@ -20,18 +18,23 @@
 #define LM75_TEMP_MAX 125000
 #define LM75_SHUTDOWN 0x01
 
-/* TEMP: 0.001C/bit (-55C to +125C)
-   REG: (0.5C/bit, two's complement) << 7 */
+/*
+ * TEMP: 0.001C/bit (-55C to +125C)
+ * REG: (0.5C/bit, two's complement) << 7
+ */
 static inline u16 LM75_TEMP_TO_REG(long temp)
 {
 	int ntemp = clamp_val(temp, LM75_TEMP_MIN, LM75_TEMP_MAX);
+
 	ntemp += (ntemp < 0 ? -250 : 250);
 	return (u16)((ntemp / 500) << 7);
 }
 
 static inline int LM75_TEMP_FROM_REG(u16 reg)
 {
-	/* use integer division instead of equivalent right shift to
-	   guarantee arithmetic shift and preserve the sign */
+	/*
+	 * use integer division instead of equivalent right shift to
+	 * guarantee arithmetic shift and preserve the sign
+	 */
 	return ((s16)reg / 128) * 500;
 }
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 9b3c9f390ef8..7bdc664af55b 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -35,6 +35,14 @@
  * explicitly as max6659, or if its address is not 0x4c.
  * These chips lack the remote temperature offset feature.
  *
+ * This driver also supports the MAX6654 chip made by Maxim. This chip can
+ * be at 9 different addresses, similar to MAX6680/MAX6681. The MAX6654 is
+ * otherwise similar to MAX6657/MAX6658/MAX6659. Extended range is available
+ * by setting the configuration register accordingly, and is done during
+ * initialization. Extended precision is only available at conversion rates
+ * of 1 Hz and slower. Note that extended precision is not enabled by
+ * default, as this driver initializes all chips to 2 Hz by design.
+ *
  * This driver also supports the MAX6646, MAX6647, MAX6648, MAX6649 and
  * MAX6692 chips made by Maxim.  These are again similar to the LM86,
  * but they use unsigned temperature values and can report temperatures
@@ -94,8 +102,8 @@
  * have address 0x4d.
  * MAX6647 has address 0x4e.
  * MAX6659 can have address 0x4c, 0x4d or 0x4e.
- * MAX6680 and MAX6681 can have address 0x18, 0x19, 0x1a, 0x29, 0x2a, 0x2b,
- * 0x4c, 0x4d or 0x4e.
+ * MAX6654, MAX6680, and MAX6681 can have address 0x18, 0x19, 0x1a, 0x29,
+ * 0x2a, 0x2b, 0x4c, 0x4d or 0x4e.
  * SA56004 can have address 0x48 through 0x4F.
  */
 
@@ -104,7 +112,7 @@ static const unsigned short normal_i2c[] = {
 	0x4d, 0x4e, 0x4f, I2C_CLIENT_END };
 
 enum chips { lm90, adm1032, lm99, lm86, max6657, max6659, adt7461, max6680,
-	max6646, w83l771, max6696, sa56004, g781, tmp451 };
+	max6646, w83l771, max6696, sa56004, g781, tmp451, max6654 };
 
 /*
  * The LM90 registers
@@ -145,7 +153,7 @@ enum chips { lm90, adm1032, lm99, lm86, max6657, max6659, adt7461, max6680,
 #define LM90_REG_R_TCRIT_HYST		0x21
 #define LM90_REG_W_TCRIT_HYST		0x21
 
-/* MAX6646/6647/6649/6657/6658/6659/6695/6696 registers */
+/* MAX6646/6647/6649/6654/6657/6658/6659/6695/6696 registers */
 
 #define MAX6657_REG_R_LOCAL_TEMPL	0x11
 #define MAX6696_REG_R_STATUS2		0x12
@@ -209,6 +217,7 @@ static const struct i2c_device_id lm90_id[] = {
 	{ "max6646", max6646 },
 	{ "max6647", max6646 },
 	{ "max6649", max6646 },
+	{ "max6654", max6654 },
 	{ "max6657", max6657 },
 	{ "max6658", max6657 },
 	{ "max6659", max6659 },
@@ -270,6 +279,10 @@ static const struct of_device_id __maybe_unused lm90_of_match[] = {
 		.data = (void *)max6646
 	},
 	{
+		.compatible = "dallas,max6654",
+		.data = (void *)max6654
+	},
+	{
 		.compatible = "dallas,max6657",
 		.data = (void *)max6657
 	},
@@ -367,6 +380,11 @@ static const struct lm90_params lm90_params[] = {
 		.max_convrate = 6,
 		.reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL,
 	},
+	[max6654] = {
+		.alert_alarms = 0x7c,
+		.max_convrate = 7,
+		.reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL,
+	},
 	[max6657] = {
 		.flags = LM90_PAUSE_FOR_CONFIG,
 		.alert_alarms = 0x7c,
@@ -1557,6 +1575,16 @@ static int lm90_detect(struct i2c_client *client,
 		 && (config1 & 0x3f) == 0x00
 		 && convrate <= 0x07) {
 			name = "max6646";
+		} else
+		/*
+		 * The chip_id of the MAX6654 holds the revision of the chip.
+		 * The lowest 3 bits of the config1 register are unused and
+		 * should return zero when read.
+		 */
+		if (chip_id == 0x08
+		 && (config1 & 0x07) == 0x00
+		 && convrate <= 0x07) {
+			name = "max6654";
 		}
 	} else
 	if (address == 0x4C
@@ -1661,6 +1689,15 @@ static int lm90_init_client(struct i2c_client *client, struct lm90_data *data)
 		config |= 0x18;
 
 	/*
+	 * Put MAX6654 into extended range (0x20, extend minimum range from
+	 * 0 degrees to -64 degrees). Note that extended resolution is not
+	 * possible on the MAX6654 unless conversion rate is set to 1 Hz or
+	 * slower, which is intentionally not done by default.
+	 */
+	if (data->kind == max6654)
+		config |= 0x20;
+
+	/*
 	 * Select external channel 0 for max6695/96
 	 */
 	if (data->kind == max6696)
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index 7efa6bfef060..e7e1ddc1d631 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -2047,7 +2047,7 @@ store_temp_beep(struct device *dev, struct device_attribute *attr,
 static umode_t nct6775_in_is_visible(struct kobject *kobj,
 				     struct attribute *attr, int index)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct nct6775_data *data = dev_get_drvdata(dev);
 	int in = index / 5;	/* voltage index */
 
@@ -2253,7 +2253,7 @@ store_fan_pulses(struct device *dev, struct device_attribute *attr,
 static umode_t nct6775_fan_is_visible(struct kobject *kobj,
 				      struct attribute *attr, int index)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct nct6775_data *data = dev_get_drvdata(dev);
 	int fan = index / 6;	/* fan index */
 	int nr = index % 6;	/* attribute index */
@@ -2440,7 +2440,7 @@ store_temp_type(struct device *dev, struct device_attribute *attr,
 static umode_t nct6775_temp_is_visible(struct kobject *kobj,
 				       struct attribute *attr, int index)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct nct6775_data *data = dev_get_drvdata(dev);
 	int temp = index / 10;	/* temp index */
 	int nr = index % 10;	/* attribute index */
@@ -3257,7 +3257,7 @@ store_auto_temp(struct device *dev, struct device_attribute *attr,
 static umode_t nct6775_pwm_is_visible(struct kobject *kobj,
 				      struct attribute *attr, int index)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct nct6775_data *data = dev_get_drvdata(dev);
 	int pwm = index / 36;	/* pwm index */
 	int nr = index % 36;	/* attribute index */
@@ -3459,7 +3459,7 @@ static SENSOR_DEVICE_ATTR(beep_enable, S_IWUSR | S_IRUGO, show_beep,
 static umode_t nct6775_other_is_visible(struct kobject *kobj,
 					struct attribute *attr, int index)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct nct6775_data *data = dev_get_drvdata(dev);
 
 	if (index == 0 && !data->have_vid)
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index 2e97e56c72c7..570df8eb5272 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -679,7 +679,7 @@ static struct attribute *nct7802_temp_attrs[] = {
 static umode_t nct7802_temp_is_visible(struct kobject *kobj,
 				       struct attribute *attr, int index)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct nct7802_data *data = dev_get_drvdata(dev);
 	unsigned int reg;
 	int err;
@@ -778,7 +778,7 @@ static struct attribute *nct7802_in_attrs[] = {
 static umode_t nct7802_in_is_visible(struct kobject *kobj,
 				     struct attribute *attr, int index)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct nct7802_data *data = dev_get_drvdata(dev);
 	unsigned int reg;
 	int err;
@@ -853,7 +853,7 @@ static struct attribute *nct7802_fan_attrs[] = {
 static umode_t nct7802_fan_is_visible(struct kobject *kobj,
 				      struct attribute *attr, int index)
 {
-	struct device *dev = container_of(kobj, struct device, kobj);
+	struct device *dev = kobj_to_dev(kobj);
 	struct nct7802_data *data = dev_get_drvdata(dev);
 	int fan = index / 4;	/* 4 attributes per fan */
 	unsigned int reg;
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index 1f5743d68984..b0425694f702 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -8,6 +8,9 @@
  * Copyright (c) 2019 Advantech
  * Author: Amy.Shih <amy.shih@advantech.com.tw>
  *
+ * Copyright (c) 2020 Advantech
+ * Author: Yuechao Zhao <yuechao.zhao@advantech.com.cn>
+ *
  * Supports the following chips:
  *
  * Chip        #vin  #fan  #pwm  #temp  #dts  chip ID
@@ -20,6 +23,7 @@
 #include <linux/i2c.h>
 #include <linux/mutex.h>
 #include <linux/hwmon.h>
+#include <linux/watchdog.h>
 
 #define VENDOR_ID_REG		0x7A	/* Any bank */
 #define NUVOTON_ID		0x50
@@ -41,6 +45,7 @@
 #define FANCTL_MAX		4	/* Counted from 1 */
 #define TCPU_MAX		8	/* Counted from 1 */
 #define TEMP_MAX		4	/* Counted from 1 */
+#define SMI_STS_MAX		10	/* Counted from 1 */
 
 #define VT_ADC_CTRL0_REG	0x20	/* Bank 0 */
 #define VT_ADC_CTRL1_REG	0x21	/* Bank 0 */
@@ -87,18 +92,42 @@
 #define FANCTL1_FMR_REG		0x00	/* Bank 3; 1 reg per channel */
 #define FANCTL1_OUT_REG		0x10	/* Bank 3; 1 reg per channel */
 
+#define WDT_LOCK_REG		0xE0	/* W/O Lock Watchdog Register */
+#define WDT_EN_REG		0xE1	/* R/O Watchdog Enable Register */
+#define WDT_STS_REG		0xE2	/* R/O Watchdog Status Register */
+#define WDT_TIMER_REG		0xE3	/* R/W Watchdog Timer Register */
+#define WDT_SOFT_EN		0x55	/* Enable soft watchdog timer */
+#define WDT_SOFT_DIS		0xAA	/* Disable soft watchdog timer */
+
 #define VOLT_MONITOR_MODE	0x0
 #define THERMAL_DIODE_MODE	0x1
 #define THERMISTOR_MODE		0x3
 
 #define ENABLE_TSI	BIT(1)
 
+#define WATCHDOG_TIMEOUT	1	/* 1 minute default timeout */
+
+/*The timeout range is 1-255 minutes*/
+#define MIN_TIMEOUT		(1 * 60)
+#define MAX_TIMEOUT		(255 * 60)
+
+static int timeout;
+module_param(timeout, int, 0);
+MODULE_PARM_DESC(timeout, "Watchdog timeout in minutes. 1 <= timeout <= 255, default="
+			__MODULE_STRING(WATCHDOG_TIMEOUT) ".");
+
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
+			__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+
 static const unsigned short normal_i2c[] = {
 	0x2d, 0x2e, I2C_CLIENT_END
 };
 
 struct nct7904_data {
 	struct i2c_client *client;
+	struct watchdog_device wdt;
 	struct mutex bank_lock;
 	int bank_sel;
 	u32 fanin_mask;
@@ -361,6 +390,7 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret, temp;
 	unsigned int reg1, reg2, reg3;
+	s8 temps;
 
 	switch (attr) {
 	case hwmon_temp_input:
@@ -466,7 +496,8 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel,
 
 	if (ret < 0)
 		return ret;
-	*val = ret * 1000;
+	temps = ret;
+	*val = temps * 1000;
 	return 0;
 }
 
@@ -889,6 +920,95 @@ static const struct hwmon_chip_info nct7904_chip_info = {
 	.info = nct7904_info,
 };
 
+/*
+ * Watchdog Function
+ */
+static int nct7904_wdt_start(struct watchdog_device *wdt)
+{
+	struct nct7904_data *data = watchdog_get_drvdata(wdt);
+
+	/* Enable soft watchdog timer */
+	return nct7904_write_reg(data, BANK_0, WDT_LOCK_REG, WDT_SOFT_EN);
+}
+
+static int nct7904_wdt_stop(struct watchdog_device *wdt)
+{
+	struct nct7904_data *data = watchdog_get_drvdata(wdt);
+
+	return nct7904_write_reg(data, BANK_0, WDT_LOCK_REG, WDT_SOFT_DIS);
+}
+
+static int nct7904_wdt_set_timeout(struct watchdog_device *wdt,
+				   unsigned int timeout)
+{
+	struct nct7904_data *data = watchdog_get_drvdata(wdt);
+	/*
+	 * The NCT7904 is very special in watchdog function.
+	 * Its minimum unit is minutes. And wdt->timeout needs
+	 * to match the actual timeout selected. So, this needs
+	 * to be: wdt->timeout = timeout / 60 * 60.
+	 * For example, if the user configures a timeout of
+	 * 119 seconds, the actual timeout will be 60 seconds.
+	 * So, wdt->timeout must then be set to 60 seconds.
+	 */
+	wdt->timeout = timeout / 60 * 60;
+
+	return nct7904_write_reg(data, BANK_0, WDT_TIMER_REG,
+				 wdt->timeout / 60);
+}
+
+static int nct7904_wdt_ping(struct watchdog_device *wdt)
+{
+	/*
+	 * Note:
+	 * NCT7904 does not support refreshing WDT_TIMER_REG register when
+	 * the watchdog is active. Please disable watchdog before feeding
+	 * the watchdog and enable it again.
+	 */
+	struct nct7904_data *data = watchdog_get_drvdata(wdt);
+	int ret;
+
+	/* Disable soft watchdog timer */
+	ret = nct7904_write_reg(data, BANK_0, WDT_LOCK_REG, WDT_SOFT_DIS);
+	if (ret < 0)
+		return ret;
+
+	/* feed watchdog */
+	ret = nct7904_write_reg(data, BANK_0, WDT_TIMER_REG, wdt->timeout / 60);
+	if (ret < 0)
+		return ret;
+
+	/* Enable soft watchdog timer */
+	return nct7904_write_reg(data, BANK_0, WDT_LOCK_REG, WDT_SOFT_EN);
+}
+
+static unsigned int nct7904_wdt_get_timeleft(struct watchdog_device *wdt)
+{
+	struct nct7904_data *data = watchdog_get_drvdata(wdt);
+	int ret;
+
+	ret = nct7904_read_reg(data, BANK_0, WDT_TIMER_REG);
+	if (ret < 0)
+		return 0;
+
+	return ret * 60;
+}
+
+static const struct watchdog_info nct7904_wdt_info = {
+	.options	= WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING |
+				WDIOF_MAGICCLOSE,
+	.identity	= "nct7904 watchdog",
+};
+
+static const struct watchdog_ops nct7904_wdt_ops = {
+	.owner		= THIS_MODULE,
+	.start		= nct7904_wdt_start,
+	.stop		= nct7904_wdt_stop,
+	.ping		= nct7904_wdt_ping,
+	.set_timeout	= nct7904_wdt_set_timeout,
+	.get_timeleft	= nct7904_wdt_get_timeleft,
+};
+
 static int nct7904_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
@@ -1009,10 +1129,36 @@ static int nct7904_probe(struct i2c_client *client,
 		data->fan_mode[i] = ret;
 	}
 
+	/* Read all of SMI status register to clear alarms */
+	for (i = 0; i < SMI_STS_MAX; i++) {
+		ret = nct7904_read_reg(data, BANK_0, SMI_STS1_REG + i);
+		if (ret < 0)
+			return ret;
+	}
+
 	hwmon_dev =
 		devm_hwmon_device_register_with_info(dev, client->name, data,
 						     &nct7904_chip_info, NULL);
-	return PTR_ERR_OR_ZERO(hwmon_dev);
+	ret = PTR_ERR_OR_ZERO(hwmon_dev);
+	if (ret)
+		return ret;
+
+	/* Watchdog initialization */
+	data->wdt.ops = &nct7904_wdt_ops;
+	data->wdt.info = &nct7904_wdt_info;
+
+	data->wdt.timeout = WATCHDOG_TIMEOUT * 60; /* Set default timeout */
+	data->wdt.min_timeout = MIN_TIMEOUT;
+	data->wdt.max_timeout = MAX_TIMEOUT;
+	data->wdt.parent = &client->dev;
+
+	watchdog_init_timeout(&data->wdt, timeout * 60, &client->dev);
+	watchdog_set_nowayout(&data->wdt, nowayout);
+	watchdog_set_drvdata(&data->wdt, data);
+
+	watchdog_stop_on_unregister(&data->wdt);
+
+	return devm_watchdog_register_device(dev, &data->wdt);
 }
 
 static const struct i2c_device_id nct7904_id[] = {
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index de12a565006d..a337195b1c39 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -146,6 +146,15 @@ config SENSORS_MAX16064
 	  This driver can also be built as a module. If so, the module will
 	  be called max16064.
 
+config SENSORS_MAX16601
+	tristate "Maxim MAX16601"
+	help
+	  If you say yes here you get hardware monitoring support for Maxim
+	  MAX16601.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called max16601.
+
 config SENSORS_MAX20730
 	tristate "Maxim MAX20730, MAX20734, MAX20743"
 	help
diff --git a/drivers/hwmon/pmbus/Makefile b/drivers/hwmon/pmbus/Makefile
index 5feb45806123..c4b15db996ad 100644
--- a/drivers/hwmon/pmbus/Makefile
+++ b/drivers/hwmon/pmbus/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_SENSORS_LM25066)	+= lm25066.o
 obj-$(CONFIG_SENSORS_LTC2978)	+= ltc2978.o
 obj-$(CONFIG_SENSORS_LTC3815)	+= ltc3815.o
 obj-$(CONFIG_SENSORS_MAX16064)	+= max16064.o
+obj-$(CONFIG_SENSORS_MAX16601)	+= max16601.o
 obj-$(CONFIG_SENSORS_MAX20730)	+= max20730.o
 obj-$(CONFIG_SENSORS_MAX20751)	+= max20751.o
 obj-$(CONFIG_SENSORS_MAX31785)	+= max31785.o
diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c
index 4d2315208bb5..0c622711ef7e 100644
--- a/drivers/hwmon/pmbus/isl68137.c
+++ b/drivers/hwmon/pmbus/isl68137.c
@@ -21,8 +21,50 @@
 #define ISL68137_VOUT_AVS	0x30
 #define RAA_DMPVR2_READ_VMON	0xc8
 
-enum versions {
+enum chips {
 	isl68137,
+	isl68220,
+	isl68221,
+	isl68222,
+	isl68223,
+	isl68224,
+	isl68225,
+	isl68226,
+	isl68227,
+	isl68229,
+	isl68233,
+	isl68239,
+	isl69222,
+	isl69223,
+	isl69224,
+	isl69225,
+	isl69227,
+	isl69228,
+	isl69234,
+	isl69236,
+	isl69239,
+	isl69242,
+	isl69243,
+	isl69247,
+	isl69248,
+	isl69254,
+	isl69255,
+	isl69256,
+	isl69259,
+	isl69260,
+	isl69268,
+	isl69269,
+	isl69298,
+	raa228000,
+	raa228004,
+	raa228006,
+	raa228228,
+	raa229001,
+	raa229004,
+};
+
+enum variants {
+	raa_dmpvr1_2rail,
 	raa_dmpvr2_1rail,
 	raa_dmpvr2_2rail,
 	raa_dmpvr2_3rail,
@@ -186,7 +228,7 @@ static int isl68137_probe(struct i2c_client *client,
 	memcpy(info, &raa_dmpvr_info, sizeof(*info));
 
 	switch (id->driver_data) {
-	case isl68137:
+	case raa_dmpvr1_2rail:
 		info->pages = 2;
 		info->R[PSC_VOLTAGE_IN] = 3;
 		info->func[0] &= ~PMBUS_HAVE_VMON;
@@ -224,11 +266,47 @@ static int isl68137_probe(struct i2c_client *client,
 }
 
 static const struct i2c_device_id raa_dmpvr_id[] = {
-	{"isl68137", isl68137},
-	{"raa_dmpvr2_1rail", raa_dmpvr2_1rail},
-	{"raa_dmpvr2_2rail", raa_dmpvr2_2rail},
-	{"raa_dmpvr2_3rail", raa_dmpvr2_3rail},
-	{"raa_dmpvr2_hv", raa_dmpvr2_hv},
+	{"isl68137", raa_dmpvr1_2rail},
+	{"isl68220", raa_dmpvr2_2rail},
+	{"isl68221", raa_dmpvr2_3rail},
+	{"isl68222", raa_dmpvr2_2rail},
+	{"isl68223", raa_dmpvr2_2rail},
+	{"isl68224", raa_dmpvr2_3rail},
+	{"isl68225", raa_dmpvr2_2rail},
+	{"isl68226", raa_dmpvr2_3rail},
+	{"isl68227", raa_dmpvr2_1rail},
+	{"isl68229", raa_dmpvr2_3rail},
+	{"isl68233", raa_dmpvr2_2rail},
+	{"isl68239", raa_dmpvr2_3rail},
+
+	{"isl69222", raa_dmpvr2_2rail},
+	{"isl69223", raa_dmpvr2_3rail},
+	{"isl69224", raa_dmpvr2_2rail},
+	{"isl69225", raa_dmpvr2_2rail},
+	{"isl69227", raa_dmpvr2_3rail},
+	{"isl69228", raa_dmpvr2_3rail},
+	{"isl69234", raa_dmpvr2_2rail},
+	{"isl69236", raa_dmpvr2_2rail},
+	{"isl69239", raa_dmpvr2_3rail},
+	{"isl69242", raa_dmpvr2_2rail},
+	{"isl69243", raa_dmpvr2_1rail},
+	{"isl69247", raa_dmpvr2_2rail},
+	{"isl69248", raa_dmpvr2_2rail},
+	{"isl69254", raa_dmpvr2_2rail},
+	{"isl69255", raa_dmpvr2_2rail},
+	{"isl69256", raa_dmpvr2_2rail},
+	{"isl69259", raa_dmpvr2_2rail},
+	{"isl69260", raa_dmpvr2_2rail},
+	{"isl69268", raa_dmpvr2_2rail},
+	{"isl69269", raa_dmpvr2_3rail},
+	{"isl69298", raa_dmpvr2_2rail},
+
+	{"raa228000", raa_dmpvr2_hv},
+	{"raa228004", raa_dmpvr2_hv},
+	{"raa228006", raa_dmpvr2_hv},
+	{"raa228228", raa_dmpvr2_2rail},
+	{"raa229001", raa_dmpvr2_2rail},
+	{"raa229004", raa_dmpvr2_2rail},
 	{}
 };
 
diff --git a/drivers/hwmon/pmbus/max16601.c b/drivers/hwmon/pmbus/max16601.c
new file mode 100644
index 000000000000..51cdfaf9023c
--- /dev/null
+++ b/drivers/hwmon/pmbus/max16601.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hardware monitoring driver for Maxim MAX16601
+ *
+ * Implementation notes:
+ *
+ * Ths chip supports two rails, VCORE and VSA. Telemetry information for the
+ * two rails is reported in two subsequent I2C addresses. The driver
+ * instantiates a dummy I2C client at the second I2C address to report
+ * information for the VSA rail in a single instance of the driver.
+ * Telemetry for the VSA rail is reported to the PMBus core in PMBus page 2.
+ *
+ * The chip reports input current using two separate methods. The input current
+ * reported with the standard READ_IIN command is derived from the output
+ * current. The first method is reported to the PMBus core with PMBus page 0,
+ * the second method is reported with PMBus page 1.
+ *
+ * The chip supports reading per-phase temperatures and per-phase input/output
+ * currents for VCORE. Telemetry is reported in vendor specific registers.
+ * The driver translates the vendor specific register values to PMBus standard
+ * register values and reports per-phase information in PMBus page 0.
+ *
+ * Copyright 2019, 2020 Google LLC.
+ */
+
+#include <linux/bits.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "pmbus.h"
+
+#define REG_SETPT_DVID		0xd1
+#define  DAC_10MV_MODE		BIT(4)
+#define REG_IOUT_AVG_PK		0xee
+#define REG_IIN_SENSOR		0xf1
+#define REG_TOTAL_INPUT_POWER	0xf2
+#define REG_PHASE_ID		0xf3
+#define  CORE_RAIL_INDICATOR	BIT(7)
+#define REG_PHASE_REPORTING	0xf4
+
+struct max16601_data {
+	struct pmbus_driver_info info;
+	struct i2c_client *vsa;
+	int iout_avg_pkg;
+};
+
+#define to_max16601_data(x) container_of(x, struct max16601_data, info)
+
+static int max16601_read_byte(struct i2c_client *client, int page, int reg)
+{
+	const struct pmbus_driver_info *info = pmbus_get_driver_info(client);
+	struct max16601_data *data = to_max16601_data(info);
+
+	if (page > 0) {
+		if (page == 2)	/* VSA */
+			return i2c_smbus_read_byte_data(data->vsa, reg);
+		return -EOPNOTSUPP;
+	}
+	return -ENODATA;
+}
+
+static int max16601_read_word(struct i2c_client *client, int page, int phase,
+			      int reg)
+{
+	const struct pmbus_driver_info *info = pmbus_get_driver_info(client);
+	struct max16601_data *data = to_max16601_data(info);
+	u8 buf[I2C_SMBUS_BLOCK_MAX + 1];
+	int ret;
+
+	switch (page) {
+	case 0:		/* VCORE */
+		if (phase == 0xff)
+			return -ENODATA;
+		switch (reg) {
+		case PMBUS_READ_IIN:
+		case PMBUS_READ_IOUT:
+		case PMBUS_READ_TEMPERATURE_1:
+			ret = i2c_smbus_write_byte_data(client, REG_PHASE_ID,
+							phase);
+			if (ret)
+				return ret;
+			ret = i2c_smbus_read_block_data(client,
+							REG_PHASE_REPORTING,
+							buf);
+			if (ret < 0)
+				return ret;
+			if (ret < 6)
+				return -EIO;
+			switch (reg) {
+			case PMBUS_READ_TEMPERATURE_1:
+				return buf[1] << 8 | buf[0];
+			case PMBUS_READ_IOUT:
+				return buf[3] << 8 | buf[2];
+			case PMBUS_READ_IIN:
+				return buf[5] << 8 | buf[4];
+			default:
+				break;
+			}
+		}
+		return -EOPNOTSUPP;
+	case 1:		/* VCORE, read IIN/PIN from sensor element */
+		switch (reg) {
+		case PMBUS_READ_IIN:
+			return i2c_smbus_read_word_data(client, REG_IIN_SENSOR);
+		case PMBUS_READ_PIN:
+			return i2c_smbus_read_word_data(client,
+							REG_TOTAL_INPUT_POWER);
+		default:
+			break;
+		}
+		return -EOPNOTSUPP;
+	case 2:		/* VSA */
+		switch (reg) {
+		case PMBUS_VIRT_READ_IOUT_MAX:
+			ret = i2c_smbus_read_word_data(data->vsa,
+						       REG_IOUT_AVG_PK);
+			if (ret < 0)
+				return ret;
+			if (sign_extend32(ret, 10) >
+			    sign_extend32(data->iout_avg_pkg, 10))
+				data->iout_avg_pkg = ret;
+			return data->iout_avg_pkg;
+		case PMBUS_VIRT_RESET_IOUT_HISTORY:
+			return 0;
+		case PMBUS_IOUT_OC_FAULT_LIMIT:
+		case PMBUS_IOUT_OC_WARN_LIMIT:
+		case PMBUS_OT_FAULT_LIMIT:
+		case PMBUS_OT_WARN_LIMIT:
+		case PMBUS_READ_IIN:
+		case PMBUS_READ_IOUT:
+		case PMBUS_READ_TEMPERATURE_1:
+		case PMBUS_STATUS_WORD:
+			return i2c_smbus_read_word_data(data->vsa, reg);
+		default:
+			return -EOPNOTSUPP;
+		}
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int max16601_write_byte(struct i2c_client *client, int page, u8 reg)
+{
+	const struct pmbus_driver_info *info = pmbus_get_driver_info(client);
+	struct max16601_data *data = to_max16601_data(info);
+
+	if (page == 2) {
+		if (reg == PMBUS_CLEAR_FAULTS)
+			return i2c_smbus_write_byte(data->vsa, reg);
+		return -EOPNOTSUPP;
+	}
+	return -ENODATA;
+}
+
+static int max16601_write_word(struct i2c_client *client, int page, int reg,
+			       u16 value)
+{
+	const struct pmbus_driver_info *info = pmbus_get_driver_info(client);
+	struct max16601_data *data = to_max16601_data(info);
+
+	switch (page) {
+	case 0:		/* VCORE */
+		return -ENODATA;
+	case 1:		/* VCORE IIN/PIN from sensor element */
+	default:
+		return -EOPNOTSUPP;
+	case 2:		/* VSA */
+		switch (reg) {
+		case PMBUS_VIRT_RESET_IOUT_HISTORY:
+			data->iout_avg_pkg = 0xfc00;
+			return 0;
+		case PMBUS_IOUT_OC_FAULT_LIMIT:
+		case PMBUS_IOUT_OC_WARN_LIMIT:
+		case PMBUS_OT_FAULT_LIMIT:
+		case PMBUS_OT_WARN_LIMIT:
+			return i2c_smbus_write_word_data(data->vsa, reg, value);
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+}
+
+static int max16601_identify(struct i2c_client *client,
+			     struct pmbus_driver_info *info)
+{
+	int reg;
+
+	reg = i2c_smbus_read_byte_data(client, REG_SETPT_DVID);
+	if (reg < 0)
+		return reg;
+	if (reg & DAC_10MV_MODE)
+		info->vrm_version[0] = vr13;
+	else
+		info->vrm_version[0] = vr12;
+
+	return 0;
+}
+
+static struct pmbus_driver_info max16601_info = {
+	.pages = 3,
+	.format[PSC_VOLTAGE_IN] = linear,
+	.format[PSC_VOLTAGE_OUT] = vid,
+	.format[PSC_CURRENT_IN] = linear,
+	.format[PSC_CURRENT_OUT] = linear,
+	.format[PSC_TEMPERATURE] = linear,
+	.format[PSC_POWER] = linear,
+	.func[0] = PMBUS_HAVE_VIN | PMBUS_HAVE_IIN | PMBUS_HAVE_PIN |
+		PMBUS_HAVE_STATUS_INPUT |
+		PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT |
+		PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT |
+		PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP |
+		PMBUS_HAVE_POUT | PMBUS_PAGE_VIRTUAL | PMBUS_PHASE_VIRTUAL,
+	.func[1] = PMBUS_HAVE_IIN | PMBUS_HAVE_PIN | PMBUS_PAGE_VIRTUAL,
+	.func[2] = PMBUS_HAVE_IIN | PMBUS_HAVE_STATUS_INPUT |
+		PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT |
+		PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP | PMBUS_PAGE_VIRTUAL,
+	.phases[0] = 8,
+	.pfunc[0] = PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT | PMBUS_HAVE_TEMP,
+	.pfunc[1] = PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT,
+	.pfunc[2] = PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT | PMBUS_HAVE_TEMP,
+	.pfunc[3] = PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT,
+	.pfunc[4] = PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT | PMBUS_HAVE_TEMP,
+	.pfunc[5] = PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT,
+	.pfunc[6] = PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT | PMBUS_HAVE_TEMP,
+	.pfunc[7] = PMBUS_HAVE_IIN | PMBUS_HAVE_IOUT,
+	.identify = max16601_identify,
+	.read_byte_data = max16601_read_byte,
+	.read_word_data = max16601_read_word,
+	.write_byte = max16601_write_byte,
+	.write_word_data = max16601_write_word,
+};
+
+static void max16601_remove(void *_data)
+{
+	struct max16601_data *data = _data;
+
+	i2c_unregister_device(data->vsa);
+}
+
+static int max16601_probe(struct i2c_client *client,
+			  const struct i2c_device_id *id)
+{
+	struct device *dev = &client->dev;
+	u8 buf[I2C_SMBUS_BLOCK_MAX + 1];
+	struct max16601_data *data;
+	int ret;
+
+	if (!i2c_check_functionality(client->adapter,
+				     I2C_FUNC_SMBUS_READ_BYTE_DATA |
+				     I2C_FUNC_SMBUS_READ_BLOCK_DATA))
+		return -ENODEV;
+
+	ret = i2c_smbus_read_block_data(client, PMBUS_IC_DEVICE_ID, buf);
+	if (ret < 0)
+		return -ENODEV;
+
+	/* PMBUS_IC_DEVICE_ID is expected to return "MAX16601y.xx" */
+	if (ret < 11 || strncmp(buf, "MAX16601", 8)) {
+		buf[ret] = '\0';
+		dev_err(dev, "Unsupported chip '%s'\n", buf);
+		return -ENODEV;
+	}
+
+	ret = i2c_smbus_read_byte_data(client, REG_PHASE_ID);
+	if (ret < 0)
+		return ret;
+	if (!(ret & CORE_RAIL_INDICATOR)) {
+		dev_err(dev,
+			"Driver must be instantiated on CORE rail I2C address\n");
+		return -ENODEV;
+	}
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->iout_avg_pkg = 0xfc00;
+	data->vsa = i2c_new_dummy_device(client->adapter, client->addr + 1);
+	if (IS_ERR(data->vsa)) {
+		dev_err(dev, "Failed to register VSA client\n");
+		return PTR_ERR(data->vsa);
+	}
+	ret = devm_add_action_or_reset(dev, max16601_remove, data);
+	if (ret)
+		return ret;
+
+	data->info = max16601_info;
+
+	return pmbus_do_probe(client, id, &data->info);
+}
+
+static const struct i2c_device_id max16601_id[] = {
+	{"max16601", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, max16601_id);
+
+static struct i2c_driver max16601_driver = {
+	.driver = {
+		   .name = "max16601",
+		   },
+	.probe = max16601_probe,
+	.remove = pmbus_do_remove,
+	.id_table = max16601_id,
+};
+
+module_i2c_driver(max16601_driver);
+
+MODULE_AUTHOR("Guenter Roeck <linux@roeck-us.net>");
+MODULE_DESCRIPTION("PMBus driver for Maxim MAX16601");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index 8d321bf7d15b..a420877ba533 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -109,8 +109,8 @@ struct pmbus_data {
 	bool has_status_word;		/* device uses STATUS_WORD register */
 	int (*read_status)(struct i2c_client *client, int page);
 
-	u8 currpage;
-	u8 currphase;	/* current phase, 0xff for all */
+	s16 currpage;	/* current page, -1 for unknown/unset */
+	s16 currphase;	/* current phase, 0xff for all, -1 for unknown/unset */
 };
 
 struct pmbus_debugfs_entry {
@@ -2529,8 +2529,8 @@ int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id,
 	if (pdata)
 		data->flags = pdata->flags;
 	data->info = info;
-	data->currpage = 0xff;
-	data->currphase = 0xfe;
+	data->currpage = -1;
+	data->currphase = -1;
 
 	ret = pmbus_init_common(client, data, info);
 	if (ret < 0)
diff --git a/drivers/hwtracing/coresight/coresight-cti-platform.c b/drivers/hwtracing/coresight/coresight-cti-platform.c
index b44d83142b62..2fdaeec80ee5 100644
--- a/drivers/hwtracing/coresight/coresight-cti-platform.c
+++ b/drivers/hwtracing/coresight/coresight-cti-platform.c
@@ -120,7 +120,7 @@ static int cti_plat_create_v8_etm_connection(struct device *dev,
 
 	/* Can optionally have an etm node - return if not  */
 	cs_fwnode = fwnode_find_reference(root_fwnode, CTI_DT_CSDEV_ASSOC, 0);
-	if (IS_ERR_OR_NULL(cs_fwnode))
+	if (IS_ERR(cs_fwnode))
 		return 0;
 
 	/* allocate memory */
@@ -393,7 +393,7 @@ static int cti_plat_create_connection(struct device *dev,
 		/* associated device ? */
 		cs_fwnode = fwnode_find_reference(fwnode,
 						  CTI_DT_CSDEV_ASSOC, 0);
-		if (!IS_ERR_OR_NULL(cs_fwnode)) {
+		if (!IS_ERR(cs_fwnode)) {
 			assoc_name = cti_plat_get_csdev_or_node_name(cs_fwnode,
 								     &csdev);
 			fwnode_handle_put(cs_fwnode);
diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c
index dff4e178c732..7f10312d1b88 100644
--- a/drivers/i2c/algos/i2c-algo-pca.c
+++ b/drivers/i2c/algos/i2c-algo-pca.c
@@ -542,7 +542,7 @@ int i2c_pca_add_numbered_bus(struct i2c_adapter *adap)
 EXPORT_SYMBOL(i2c_pca_add_numbered_bus);
 
 MODULE_AUTHOR("Ian Campbell <icampbell@arcom.com>, "
-	"Wolfram Sang <w.sang@pengutronix.de>");
+	"Wolfram Sang <kernel@pengutronix.de>");
 MODULE_DESCRIPTION("I2C-Bus PCA9564/PCA9665 algorithm");
 MODULE_LICENSE("GPL");
 
diff --git a/drivers/i2c/busses/i2c-altera.c b/drivers/i2c/busses/i2c-altera.c
index 20ef63820c77..16ddc26c00e6 100644
--- a/drivers/i2c/busses/i2c-altera.c
+++ b/drivers/i2c/busses/i2c-altera.c
@@ -70,6 +70,7 @@
  * @isr_mask: cached copy of local ISR enables.
  * @isr_status: cached copy of local ISR status.
  * @lock: spinlock for IRQ synchronization.
+ * @isr_mutex: mutex for IRQ thread.
  */
 struct altr_i2c_dev {
 	void __iomem *base;
@@ -86,6 +87,7 @@ struct altr_i2c_dev {
 	u32 isr_mask;
 	u32 isr_status;
 	spinlock_t lock;	/* IRQ synchronization */
+	struct mutex isr_mutex;
 };
 
 static void
@@ -245,10 +247,11 @@ static irqreturn_t altr_i2c_isr(int irq, void *_dev)
 	struct altr_i2c_dev *idev = _dev;
 	u32 status = idev->isr_status;
 
+	mutex_lock(&idev->isr_mutex);
 	if (!idev->msg) {
 		dev_warn(idev->dev, "unexpected interrupt\n");
 		altr_i2c_int_clear(idev, ALTR_I2C_ALL_IRQ);
-		return IRQ_HANDLED;
+		goto out;
 	}
 	read = (idev->msg->flags & I2C_M_RD) != 0;
 
@@ -301,6 +304,8 @@ static irqreturn_t altr_i2c_isr(int irq, void *_dev)
 		complete(&idev->msg_complete);
 		dev_dbg(idev->dev, "Message Complete\n");
 	}
+out:
+	mutex_unlock(&idev->isr_mutex);
 
 	return IRQ_HANDLED;
 }
@@ -312,6 +317,7 @@ static int altr_i2c_xfer_msg(struct altr_i2c_dev *idev, struct i2c_msg *msg)
 	u32 value;
 	u8 addr = i2c_8bit_addr_from_msg(msg);
 
+	mutex_lock(&idev->isr_mutex);
 	idev->msg = msg;
 	idev->msg_len = msg->len;
 	idev->buf = msg->buf;
@@ -336,6 +342,7 @@ static int altr_i2c_xfer_msg(struct altr_i2c_dev *idev, struct i2c_msg *msg)
 		altr_i2c_int_enable(idev, imask, true);
 		altr_i2c_fill_tx_fifo(idev);
 	}
+	mutex_unlock(&idev->isr_mutex);
 
 	time_left = wait_for_completion_timeout(&idev->msg_complete,
 						ALTR_I2C_XFER_TIMEOUT);
@@ -384,7 +391,6 @@ static int altr_i2c_probe(struct platform_device *pdev)
 	struct altr_i2c_dev *idev = NULL;
 	struct resource *res;
 	int irq, ret;
-	u32 val;
 
 	idev = devm_kzalloc(&pdev->dev, sizeof(*idev), GFP_KERNEL);
 	if (!idev)
@@ -410,18 +416,19 @@ static int altr_i2c_probe(struct platform_device *pdev)
 	idev->dev = &pdev->dev;
 	init_completion(&idev->msg_complete);
 	spin_lock_init(&idev->lock);
+	mutex_init(&idev->isr_mutex);
 
-	val = device_property_read_u32(idev->dev, "fifo-size",
+	ret = device_property_read_u32(idev->dev, "fifo-size",
 				       &idev->fifo_size);
-	if (val) {
+	if (ret) {
 		dev_err(&pdev->dev, "FIFO size set to default of %d\n",
 			ALTR_I2C_DFLT_FIFO_SZ);
 		idev->fifo_size = ALTR_I2C_DFLT_FIFO_SZ;
 	}
 
-	val = device_property_read_u32(idev->dev, "clock-frequency",
+	ret = device_property_read_u32(idev->dev, "clock-frequency",
 				       &idev->bus_clk_rate);
-	if (val) {
+	if (ret) {
 		dev_err(&pdev->dev, "Default to 100kHz\n");
 		idev->bus_clk_rate = I2C_MAX_STANDARD_MODE_FREQ;	/* default clock rate */
 	}
diff --git a/drivers/i2c/busses/i2c-amd-mp2-pci.c b/drivers/i2c/busses/i2c-amd-mp2-pci.c
index 5e4800d72e00..cd3fd5ee5f65 100644
--- a/drivers/i2c/busses/i2c-amd-mp2-pci.c
+++ b/drivers/i2c/busses/i2c-amd-mp2-pci.c
@@ -349,12 +349,12 @@ static int amd_mp2_pci_probe(struct pci_dev *pci_dev,
 	if (!privdata)
 		return -ENOMEM;
 
+	privdata->pci_dev = pci_dev;
 	rc = amd_mp2_pci_init(privdata, pci_dev);
 	if (rc)
 		return rc;
 
 	mutex_init(&privdata->c2p_lock);
-	privdata->pci_dev = pci_dev;
 
 	pm_runtime_set_autosuspend_delay(&pci_dev->dev, 1000);
 	pm_runtime_use_autosuspend(&pci_dev->dev);
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index 07c1993274c5..f51702d86a90 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -603,6 +603,7 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id)
 	/* Ack all interrupts except for Rx done */
 	writel(irq_received & ~ASPEED_I2CD_INTR_RX_DONE,
 	       bus->base + ASPEED_I2C_INTR_STS_REG);
+	readl(bus->base + ASPEED_I2C_INTR_STS_REG);
 	irq_remaining = irq_received;
 
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
@@ -645,9 +646,11 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id)
 			irq_received, irq_handled);
 
 	/* Ack Rx done */
-	if (irq_received & ASPEED_I2CD_INTR_RX_DONE)
+	if (irq_received & ASPEED_I2CD_INTR_RX_DONE) {
 		writel(ASPEED_I2CD_INTR_RX_DONE,
 		       bus->base + ASPEED_I2C_INTR_STS_REG);
+		readl(bus->base + ASPEED_I2C_INTR_STS_REG);
+	}
 	spin_unlock(&bus->lock);
 	return irq_remaining ? IRQ_NONE : IRQ_HANDLED;
 }
diff --git a/drivers/i2c/busses/i2c-at91-master.c b/drivers/i2c/busses/i2c-at91-master.c
index 0aba51a7df32..37b96ac9dfae 100644
--- a/drivers/i2c/busses/i2c-at91-master.c
+++ b/drivers/i2c/busses/i2c-at91-master.c
@@ -845,6 +845,18 @@ static int at91_init_twi_recovery_info(struct platform_device *pdev,
 							 PINCTRL_STATE_DEFAULT);
 	dev->pinctrl_pins_gpio = pinctrl_lookup_state(dev->pinctrl,
 						      "gpio");
+	if (IS_ERR(dev->pinctrl_pins_default) ||
+	    IS_ERR(dev->pinctrl_pins_gpio)) {
+		dev_info(&pdev->dev, "pinctrl states incomplete for recovery\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * pins will be taken as GPIO, so we might as well inform pinctrl about
+	 * this and move the state to GPIO
+	 */
+	pinctrl_select_state(dev->pinctrl, dev->pinctrl_pins_gpio);
+
 	rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN);
 	if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
@@ -855,9 +867,7 @@ static int at91_init_twi_recovery_info(struct platform_device *pdev,
 		return -EPROBE_DEFER;
 
 	if (IS_ERR(rinfo->sda_gpiod) ||
-	    IS_ERR(rinfo->scl_gpiod) ||
-	    IS_ERR(dev->pinctrl_pins_default) ||
-	    IS_ERR(dev->pinctrl_pins_gpio)) {
+	    IS_ERR(rinfo->scl_gpiod)) {
 		dev_info(&pdev->dev, "recovery information incomplete\n");
 		if (!IS_ERR(rinfo->sda_gpiod)) {
 			gpiod_put(rinfo->sda_gpiod);
@@ -867,9 +877,13 @@ static int at91_init_twi_recovery_info(struct platform_device *pdev,
 			gpiod_put(rinfo->scl_gpiod);
 			rinfo->scl_gpiod = NULL;
 		}
+		pinctrl_select_state(dev->pinctrl, dev->pinctrl_pins_default);
 		return -EINVAL;
 	}
 
+	/* change the state of the pins back to their default state */
+	pinctrl_select_state(dev->pinctrl, dev->pinctrl_pins_default);
+
 	dev_info(&pdev->dev, "using scl, sda for recovery\n");
 
 	rinfo->prepare_recovery = at91_prepare_twi_recovery;
diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c
index 44be0926b566..d091a12596ad 100644
--- a/drivers/i2c/busses/i2c-bcm-iproc.c
+++ b/drivers/i2c/busses/i2c-bcm-iproc.c
@@ -360,6 +360,9 @@ static bool bcm_iproc_i2c_slave_isr(struct bcm_iproc_i2c_dev *iproc_i2c,
 			value = (u8)((val >> S_RX_DATA_SHIFT) & S_RX_DATA_MASK);
 			i2c_slave_event(iproc_i2c->slave,
 					I2C_SLAVE_WRITE_RECEIVED, &value);
+			if (rx_status == I2C_SLAVE_RX_END)
+				i2c_slave_event(iproc_i2c->slave,
+						I2C_SLAVE_STOP, &value);
 		}
 	} else if (status & BIT(IS_S_TX_UNDERRUN_SHIFT)) {
 		/* Master read other than start */
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index c98befe2a92e..5536673060cc 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -354,10 +354,16 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
 	adap->dev.of_node = pdev->dev.of_node;
 	adap->nr = -1;
 
-	dev_pm_set_driver_flags(&pdev->dev,
-				DPM_FLAG_SMART_PREPARE |
-				DPM_FLAG_SMART_SUSPEND |
-				DPM_FLAG_LEAVE_SUSPENDED);
+	if (dev->flags & ACCESS_NO_IRQ_SUSPEND) {
+		dev_pm_set_driver_flags(&pdev->dev,
+					DPM_FLAG_SMART_PREPARE |
+					DPM_FLAG_LEAVE_SUSPENDED);
+	} else {
+		dev_pm_set_driver_flags(&pdev->dev,
+					DPM_FLAG_SMART_PREPARE |
+					DPM_FLAG_SMART_SUSPEND |
+					DPM_FLAG_LEAVE_SUSPENDED);
+	}
 
 	/* The code below assumes runtime PM to be disabled. */
 	WARN_ON(pm_runtime_enabled(&pdev->dev));
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 5cc0b0ec5570..1f1442dfcad7 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -7,7 +7,7 @@
  *   Mux support by Rodolfo Giometti <giometti@enneenne.com> and
  *   Michael Lawnick <michael.lawnick.ext@nsn.com>
  *
- * Copyright (C) 2013-2017 Wolfram Sang <wsa@the-dreams.de>
+ * Copyright (C) 2013-2017 Wolfram Sang <wsa@kernel.org>
  */
 
 #define pr_fmt(fmt) "i2c-core: " fmt
@@ -338,8 +338,10 @@ static int i2c_device_probe(struct device *dev)
 		} else if (ACPI_COMPANION(dev)) {
 			irq = i2c_acpi_get_irq(client);
 		}
-		if (irq == -EPROBE_DEFER)
-			return irq;
+		if (irq == -EPROBE_DEFER) {
+			status = irq;
+			goto put_sync_adapter;
+		}
 
 		if (irq < 0)
 			irq = 0;
@@ -353,15 +355,19 @@ static int i2c_device_probe(struct device *dev)
 	 */
 	if (!driver->id_table &&
 	    !i2c_acpi_match_device(dev->driver->acpi_match_table, client) &&
-	    !i2c_of_match_device(dev->driver->of_match_table, client))
-		return -ENODEV;
+	    !i2c_of_match_device(dev->driver->of_match_table, client)) {
+		status = -ENODEV;
+		goto put_sync_adapter;
+	}
 
 	if (client->flags & I2C_CLIENT_WAKE) {
 		int wakeirq;
 
 		wakeirq = of_irq_get_byname(dev->of_node, "wakeup");
-		if (wakeirq == -EPROBE_DEFER)
-			return wakeirq;
+		if (wakeirq == -EPROBE_DEFER) {
+			status = wakeirq;
+			goto put_sync_adapter;
+		}
 
 		device_init_wakeup(&client->dev, true);
 
@@ -408,6 +414,10 @@ err_detach_pm_domain:
 err_clear_wakeup_irq:
 	dev_pm_clear_wake_irq(&client->dev);
 	device_init_wakeup(&client->dev, false);
+put_sync_adapter:
+	if (client->flags & I2C_CLIENT_HOST_NOTIFY)
+		pm_runtime_put_sync(&client->adapter->dev);
+
 	return status;
 }
 
@@ -2273,19 +2283,6 @@ i2c_new_scanned_device(struct i2c_adapter *adap,
 }
 EXPORT_SYMBOL_GPL(i2c_new_scanned_device);
 
-struct i2c_client *
-i2c_new_probed_device(struct i2c_adapter *adap,
-		      struct i2c_board_info *info,
-		      unsigned short const *addr_list,
-		      int (*probe)(struct i2c_adapter *adap, unsigned short addr))
-{
-	struct i2c_client *client;
-
-	client = i2c_new_scanned_device(adap, info, addr_list, probe);
-	return IS_ERR(client) ? NULL : client;
-}
-EXPORT_SYMBOL_GPL(i2c_new_probed_device);
-
 struct i2c_adapter *i2c_get_adapter(int nr)
 {
 	struct i2c_adapter *adapter;
diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c
index 6787c1f71483..3ed74aa4b44b 100644
--- a/drivers/i2c/i2c-core-of.c
+++ b/drivers/i2c/i2c-core-of.c
@@ -5,7 +5,7 @@
  * Copyright (C) 2008 Jochen Friedrich <jochen@scram.de>
  * based on a previous patch from Jon Smirl <jonsmirl@gmail.com>
  *
- * Copyright (C) 2013, 2018 Wolfram Sang <wsa@the-dreams.de>
+ * Copyright (C) 2013, 2018 Wolfram Sang <wsa@kernel.org>
  */
 
 #include <dt-bindings/i2c/i2c.h>
diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c
index 0e16490eb3a1..5365199a31f4 100644
--- a/drivers/i2c/muxes/i2c-demux-pinctrl.c
+++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c
@@ -272,6 +272,7 @@ static int i2c_demux_pinctrl_probe(struct platform_device *pdev)
 err_rollback_available:
 	device_remove_file(&pdev->dev, &dev_attr_available_masters);
 err_rollback:
+	i2c_demux_deactivate_master(priv);
 	for (j = 0; j < i; j++) {
 		of_node_put(priv->chan[j].parent_np);
 		of_changeset_destroy(&priv->chan[j].chgset);
diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index d79cd6d54b3a..97f2e29265da 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -1008,7 +1008,6 @@ static int i3c_master_getmrl_locked(struct i3c_master_controller *master,
 				    struct i3c_device_info *info)
 {
 	struct i3c_ccc_cmd_dest dest;
-	unsigned int expected_len;
 	struct i3c_ccc_mrl *mrl;
 	struct i3c_ccc_cmd cmd;
 	int ret;
@@ -1024,22 +1023,23 @@ static int i3c_master_getmrl_locked(struct i3c_master_controller *master,
 	if (!(info->bcr & I3C_BCR_IBI_PAYLOAD))
 		dest.payload.len -= 1;
 
-	expected_len = dest.payload.len;
 	i3c_ccc_cmd_init(&cmd, true, I3C_CCC_GETMRL, &dest, 1);
 	ret = i3c_master_send_ccc_cmd_locked(master, &cmd);
 	if (ret)
 		goto out;
 
-	if (dest.payload.len != expected_len) {
+	switch (dest.payload.len) {
+	case 3:
+		info->max_ibi_len = mrl->ibi_len;
+		fallthrough;
+	case 2:
+		info->max_read_len = be16_to_cpu(mrl->read_len);
+		break;
+	default:
 		ret = -EIO;
 		goto out;
 	}
 
-	info->max_read_len = be16_to_cpu(mrl->read_len);
-
-	if (info->bcr & I3C_BCR_IBI_PAYLOAD)
-		info->max_ibi_len = mrl->ibi_len;
-
 out:
 	i3c_ccc_cmd_dest_cleanup(&dest);
 
diff --git a/drivers/iio/accel/sca3000.c b/drivers/iio/accel/sca3000.c
index 66d768d971e1..6e429072e44a 100644
--- a/drivers/iio/accel/sca3000.c
+++ b/drivers/iio/accel/sca3000.c
@@ -980,7 +980,7 @@ static int sca3000_read_data(struct sca3000_state *st,
 	st->tx[0] = SCA3000_READ_REG(reg_address_high);
 	ret = spi_sync_transfer(st->us, xfer, ARRAY_SIZE(xfer));
 	if (ret) {
-		dev_err(get_device(&st->us->dev), "problem reading register");
+		dev_err(&st->us->dev, "problem reading register\n");
 		return ret;
 	}
 
diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c
index 02981f3d1794..08ba1a8f05eb 100644
--- a/drivers/iio/adc/ad7192.c
+++ b/drivers/iio/adc/ad7192.c
@@ -125,10 +125,10 @@
 #define AD7193_CH_AINCOM	0x600 /* AINCOM - AINCOM */
 
 /* ID Register Bit Designations (AD7192_REG_ID) */
-#define ID_AD7190		0x4
-#define ID_AD7192		0x0
-#define ID_AD7193		0x2
-#define ID_AD7195		0x6
+#define CHIPID_AD7190		0x4
+#define CHIPID_AD7192		0x0
+#define CHIPID_AD7193		0x2
+#define CHIPID_AD7195		0x6
 #define AD7192_ID_MASK		0x0F
 
 /* GPOCON Register Bit Designations (AD7192_REG_GPOCON) */
@@ -161,7 +161,20 @@ enum {
 	AD7192_SYSCALIB_FULL_SCALE,
 };
 
+enum {
+	ID_AD7190,
+	ID_AD7192,
+	ID_AD7193,
+	ID_AD7195,
+};
+
+struct ad7192_chip_info {
+	unsigned int			chip_id;
+	const char			*name;
+};
+
 struct ad7192_state {
+	const struct ad7192_chip_info	*chip_info;
 	struct regulator		*avdd;
 	struct regulator		*dvdd;
 	struct clk			*mclk;
@@ -172,7 +185,6 @@ struct ad7192_state {
 	u32				conf;
 	u32				scale_avail[8][2];
 	u8				gpocon;
-	u8				devid;
 	u8				clock_sel;
 	struct mutex			lock;	/* protect sensor state */
 	u8				syscalib_mode[8];
@@ -348,7 +360,7 @@ static int ad7192_setup(struct ad7192_state *st, struct device_node *np)
 
 	id &= AD7192_ID_MASK;
 
-	if (id != st->devid)
+	if (id != st->chip_info->chip_id)
 		dev_warn(&st->sd.spi->dev, "device ID query failed (0x%X)\n",
 			 id);
 
@@ -363,7 +375,7 @@ static int ad7192_setup(struct ad7192_state *st, struct device_node *np)
 		st->mode |= AD7192_MODE_REJ60;
 
 	refin2_en = of_property_read_bool(np, "adi,refin2-pins-enable");
-	if (refin2_en && st->devid != ID_AD7195)
+	if (refin2_en && st->chip_info->chip_id != CHIPID_AD7195)
 		st->conf |= AD7192_CONF_REFSEL;
 
 	st->conf &= ~AD7192_CONF_CHOP;
@@ -859,12 +871,31 @@ static const struct iio_chan_spec ad7193_channels[] = {
 	IIO_CHAN_SOFT_TIMESTAMP(14),
 };
 
+static const struct ad7192_chip_info ad7192_chip_info_tbl[] = {
+	[ID_AD7190] = {
+		.chip_id = CHIPID_AD7190,
+		.name = "ad7190",
+	},
+	[ID_AD7192] = {
+		.chip_id = CHIPID_AD7192,
+		.name = "ad7192",
+	},
+	[ID_AD7193] = {
+		.chip_id = CHIPID_AD7193,
+		.name = "ad7193",
+	},
+	[ID_AD7195] = {
+		.chip_id = CHIPID_AD7195,
+		.name = "ad7195",
+	},
+};
+
 static int ad7192_channels_config(struct iio_dev *indio_dev)
 {
 	struct ad7192_state *st = iio_priv(indio_dev);
 
-	switch (st->devid) {
-	case ID_AD7193:
+	switch (st->chip_info->chip_id) {
+	case CHIPID_AD7193:
 		indio_dev->channels = ad7193_channels;
 		indio_dev->num_channels = ARRAY_SIZE(ad7193_channels);
 		break;
@@ -878,10 +909,10 @@ static int ad7192_channels_config(struct iio_dev *indio_dev)
 }
 
 static const struct of_device_id ad7192_of_match[] = {
-	{ .compatible = "adi,ad7190", .data = (void *)ID_AD7190 },
-	{ .compatible = "adi,ad7192", .data = (void *)ID_AD7192 },
-	{ .compatible = "adi,ad7193", .data = (void *)ID_AD7193 },
-	{ .compatible = "adi,ad7195", .data = (void *)ID_AD7195 },
+	{ .compatible = "adi,ad7190", .data = &ad7192_chip_info_tbl[ID_AD7190] },
+	{ .compatible = "adi,ad7192", .data = &ad7192_chip_info_tbl[ID_AD7192] },
+	{ .compatible = "adi,ad7193", .data = &ad7192_chip_info_tbl[ID_AD7193] },
+	{ .compatible = "adi,ad7195", .data = &ad7192_chip_info_tbl[ID_AD7195] },
 	{}
 };
 MODULE_DEVICE_TABLE(of, ad7192_of_match);
@@ -938,16 +969,16 @@ static int ad7192_probe(struct spi_device *spi)
 	}
 
 	spi_set_drvdata(spi, indio_dev);
-	st->devid = (unsigned long)of_device_get_match_data(&spi->dev);
+	st->chip_info = of_device_get_match_data(&spi->dev);
 	indio_dev->dev.parent = &spi->dev;
-	indio_dev->name = spi_get_device_id(spi)->name;
+	indio_dev->name = st->chip_info->name;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 
 	ret = ad7192_channels_config(indio_dev);
 	if (ret < 0)
 		goto error_disable_dvdd;
 
-	if (st->devid == ID_AD7195)
+	if (st->chip_info->chip_id == CHIPID_AD7195)
 		indio_dev->info = &ad7195_info;
 	else
 		indio_dev->info = &ad7192_info;
diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c
index b747db97f78a..e5691e330323 100644
--- a/drivers/iio/adc/ad7793.c
+++ b/drivers/iio/adc/ad7793.c
@@ -542,7 +542,7 @@ static const struct iio_info ad7797_info = {
 	.read_raw = &ad7793_read_raw,
 	.write_raw = &ad7793_write_raw,
 	.write_raw_get_fmt = &ad7793_write_raw_get_fmt,
-	.attrs = &ad7793_attribute_group,
+	.attrs = &ad7797_attribute_group,
 	.validate_trigger = ad_sd_validate_trigger,
 };
 
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index 80c3f963527b..dfc3a306c667 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -1418,8 +1418,30 @@ static unsigned int stm32_adc_dma_residue(struct stm32_adc *adc)
 static void stm32_adc_dma_buffer_done(void *data)
 {
 	struct iio_dev *indio_dev = data;
+	struct stm32_adc *adc = iio_priv(indio_dev);
+	int residue = stm32_adc_dma_residue(adc);
+
+	/*
+	 * In DMA mode the trigger services of IIO are not used
+	 * (e.g. no call to iio_trigger_poll).
+	 * Calling irq handler associated to the hardware trigger is not
+	 * relevant as the conversions have already been done. Data
+	 * transfers are performed directly in DMA callback instead.
+	 * This implementation avoids to call trigger irq handler that
+	 * may sleep, in an atomic context (DMA irq handler context).
+	 */
+	dev_dbg(&indio_dev->dev, "%s bufi=%d\n", __func__, adc->bufi);
+
+	while (residue >= indio_dev->scan_bytes) {
+		u16 *buffer = (u16 *)&adc->rx_buf[adc->bufi];
 
-	iio_trigger_poll_chained(indio_dev->trig);
+		iio_push_to_buffers(indio_dev, buffer);
+
+		residue -= indio_dev->scan_bytes;
+		adc->bufi += indio_dev->scan_bytes;
+		if (adc->bufi >= adc->rx_buf_sz)
+			adc->bufi = 0;
+	}
 }
 
 static int stm32_adc_dma_start(struct iio_dev *indio_dev)
@@ -1790,18 +1812,18 @@ static int stm32_adc_chan_of_init(struct iio_dev *indio_dev)
 	return 0;
 }
 
-static int stm32_adc_dma_request(struct iio_dev *indio_dev)
+static int stm32_adc_dma_request(struct device *dev, struct iio_dev *indio_dev)
 {
 	struct stm32_adc *adc = iio_priv(indio_dev);
 	struct dma_slave_config config;
 	int ret;
 
-	adc->dma_chan = dma_request_chan(&indio_dev->dev, "rx");
+	adc->dma_chan = dma_request_chan(dev, "rx");
 	if (IS_ERR(adc->dma_chan)) {
 		ret = PTR_ERR(adc->dma_chan);
 		if (ret != -ENODEV) {
 			if (ret != -EPROBE_DEFER)
-				dev_err(&indio_dev->dev,
+				dev_err(dev,
 					"DMA channel request failed with %d\n",
 					ret);
 			return ret;
@@ -1845,6 +1867,7 @@ static int stm32_adc_probe(struct platform_device *pdev)
 {
 	struct iio_dev *indio_dev;
 	struct device *dev = &pdev->dev;
+	irqreturn_t (*handler)(int irq, void *p) = NULL;
 	struct stm32_adc *adc;
 	int ret;
 
@@ -1907,13 +1930,15 @@ static int stm32_adc_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
-	ret = stm32_adc_dma_request(indio_dev);
+	ret = stm32_adc_dma_request(dev, indio_dev);
 	if (ret < 0)
 		return ret;
 
+	if (!adc->dma_chan)
+		handler = &stm32_adc_trigger_handler;
+
 	ret = iio_triggered_buffer_setup(indio_dev,
-					 &iio_pollfunc_store_time,
-					 &stm32_adc_trigger_handler,
+					 &iio_pollfunc_store_time, handler,
 					 &stm32_adc_buffer_setup_ops);
 	if (ret) {
 		dev_err(&pdev->dev, "buffer setup failed\n");
diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c
index 76a60d93fe23..506bf519f64c 100644
--- a/drivers/iio/adc/stm32-dfsdm-adc.c
+++ b/drivers/iio/adc/stm32-dfsdm-adc.c
@@ -62,7 +62,7 @@ enum sd_converter_type {
 
 struct stm32_dfsdm_dev_data {
 	int type;
-	int (*init)(struct iio_dev *indio_dev);
+	int (*init)(struct device *dev, struct iio_dev *indio_dev);
 	unsigned int num_channels;
 	const struct regmap_config *regmap_cfg;
 };
@@ -1365,11 +1365,12 @@ static void stm32_dfsdm_dma_release(struct iio_dev *indio_dev)
 	}
 }
 
-static int stm32_dfsdm_dma_request(struct iio_dev *indio_dev)
+static int stm32_dfsdm_dma_request(struct device *dev,
+				   struct iio_dev *indio_dev)
 {
 	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
 
-	adc->dma_chan = dma_request_chan(&indio_dev->dev, "rx");
+	adc->dma_chan = dma_request_chan(dev, "rx");
 	if (IS_ERR(adc->dma_chan)) {
 		int ret = PTR_ERR(adc->dma_chan);
 
@@ -1425,7 +1426,7 @@ static int stm32_dfsdm_adc_chan_init_one(struct iio_dev *indio_dev,
 					  &adc->dfsdm->ch_list[ch->channel]);
 }
 
-static int stm32_dfsdm_audio_init(struct iio_dev *indio_dev)
+static int stm32_dfsdm_audio_init(struct device *dev, struct iio_dev *indio_dev)
 {
 	struct iio_chan_spec *ch;
 	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
@@ -1452,10 +1453,10 @@ static int stm32_dfsdm_audio_init(struct iio_dev *indio_dev)
 	indio_dev->num_channels = 1;
 	indio_dev->channels = ch;
 
-	return stm32_dfsdm_dma_request(indio_dev);
+	return stm32_dfsdm_dma_request(dev, indio_dev);
 }
 
-static int stm32_dfsdm_adc_init(struct iio_dev *indio_dev)
+static int stm32_dfsdm_adc_init(struct device *dev, struct iio_dev *indio_dev)
 {
 	struct iio_chan_spec *ch;
 	struct stm32_dfsdm_adc *adc = iio_priv(indio_dev);
@@ -1499,17 +1500,17 @@ static int stm32_dfsdm_adc_init(struct iio_dev *indio_dev)
 	init_completion(&adc->completion);
 
 	/* Optionally request DMA */
-	ret = stm32_dfsdm_dma_request(indio_dev);
+	ret = stm32_dfsdm_dma_request(dev, indio_dev);
 	if (ret) {
 		if (ret != -ENODEV) {
 			if (ret != -EPROBE_DEFER)
-				dev_err(&indio_dev->dev,
+				dev_err(dev,
 					"DMA channel request failed with %d\n",
 					ret);
 			return ret;
 		}
 
-		dev_dbg(&indio_dev->dev, "No DMA support\n");
+		dev_dbg(dev, "No DMA support\n");
 		return 0;
 	}
 
@@ -1622,7 +1623,7 @@ static int stm32_dfsdm_adc_probe(struct platform_device *pdev)
 		adc->dfsdm->fl_list[adc->fl_id].sync_mode = val;
 
 	adc->dev_data = dev_data;
-	ret = dev_data->init(iio);
+	ret = dev_data->init(dev, iio);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/iio/adc/ti-ads8344.c b/drivers/iio/adc/ti-ads8344.c
index 9a460807d46d..8a8792010c20 100644
--- a/drivers/iio/adc/ti-ads8344.c
+++ b/drivers/iio/adc/ti-ads8344.c
@@ -29,19 +29,20 @@ struct ads8344 {
 	struct mutex lock;
 
 	u8 tx_buf ____cacheline_aligned;
-	u16 rx_buf;
+	u8 rx_buf[3];
 };
 
-#define ADS8344_VOLTAGE_CHANNEL(chan, si)				\
+#define ADS8344_VOLTAGE_CHANNEL(chan, addr)				\
 	{								\
 		.type = IIO_VOLTAGE,					\
 		.indexed = 1,						\
 		.channel = chan,					\
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),		\
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),	\
+		.address = addr,					\
 	}
 
-#define ADS8344_VOLTAGE_CHANNEL_DIFF(chan1, chan2, si)			\
+#define ADS8344_VOLTAGE_CHANNEL_DIFF(chan1, chan2, addr)		\
 	{								\
 		.type = IIO_VOLTAGE,					\
 		.indexed = 1,						\
@@ -50,6 +51,7 @@ struct ads8344 {
 		.differential = 1,					\
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),		\
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),	\
+		.address = addr,					\
 	}
 
 static const struct iio_chan_spec ads8344_channels[] = {
@@ -89,11 +91,11 @@ static int ads8344_adc_conversion(struct ads8344 *adc, int channel,
 
 	udelay(9);
 
-	ret = spi_read(spi, &adc->rx_buf, 2);
+	ret = spi_read(spi, adc->rx_buf, sizeof(adc->rx_buf));
 	if (ret)
 		return ret;
 
-	return adc->rx_buf;
+	return adc->rx_buf[0] << 9 | adc->rx_buf[1] << 1 | adc->rx_buf[2] >> 7;
 }
 
 static int ads8344_read_raw(struct iio_dev *iio,
@@ -105,7 +107,7 @@ static int ads8344_read_raw(struct iio_dev *iio,
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
 		mutex_lock(&adc->lock);
-		*value = ads8344_adc_conversion(adc, channel->scan_index,
+		*value = ads8344_adc_conversion(adc, channel->address,
 						channel->differential);
 		mutex_unlock(&adc->lock);
 		if (*value < 0)
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index ec227b358cd6..6fd06e4eff73 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -102,6 +102,16 @@ static const unsigned int XADC_ZYNQ_UNMASK_TIMEOUT = 500;
 
 #define XADC_FLAGS_BUFFERED BIT(0)
 
+/*
+ * The XADC hardware supports a samplerate of up to 1MSPS. Unfortunately it does
+ * not have a hardware FIFO. Which means an interrupt is generated for each
+ * conversion sequence. At 1MSPS sample rate the CPU in ZYNQ7000 is completely
+ * overloaded by the interrupts that it soft-lockups. For this reason the driver
+ * limits the maximum samplerate 150kSPS. At this rate the CPU is fairly busy,
+ * but still responsive.
+ */
+#define XADC_MAX_SAMPLERATE 150000
+
 static void xadc_write_reg(struct xadc *xadc, unsigned int reg,
 	uint32_t val)
 {
@@ -674,7 +684,7 @@ static int xadc_trigger_set_state(struct iio_trigger *trigger, bool state)
 
 	spin_lock_irqsave(&xadc->lock, flags);
 	xadc_read_reg(xadc, XADC_AXI_REG_IPIER, &val);
-	xadc_write_reg(xadc, XADC_AXI_REG_IPISR, val & XADC_AXI_INT_EOS);
+	xadc_write_reg(xadc, XADC_AXI_REG_IPISR, XADC_AXI_INT_EOS);
 	if (state)
 		val |= XADC_AXI_INT_EOS;
 	else
@@ -722,13 +732,14 @@ static int xadc_power_adc_b(struct xadc *xadc, unsigned int seq_mode)
 {
 	uint16_t val;
 
+	/* Powerdown the ADC-B when it is not needed. */
 	switch (seq_mode) {
 	case XADC_CONF1_SEQ_SIMULTANEOUS:
 	case XADC_CONF1_SEQ_INDEPENDENT:
-		val = XADC_CONF2_PD_ADC_B;
+		val = 0;
 		break;
 	default:
-		val = 0;
+		val = XADC_CONF2_PD_ADC_B;
 		break;
 	}
 
@@ -797,6 +808,16 @@ static int xadc_preenable(struct iio_dev *indio_dev)
 	if (ret)
 		goto err;
 
+	/*
+	 * In simultaneous mode the upper and lower aux channels are samples at
+	 * the same time. In this mode the upper 8 bits in the sequencer
+	 * register are don't care and the lower 8 bits control two channels
+	 * each. As such we must set the bit if either the channel in the lower
+	 * group or the upper group is enabled.
+	 */
+	if (seq_mode == XADC_CONF1_SEQ_SIMULTANEOUS)
+		scan_mask = ((scan_mask >> 8) | scan_mask) & 0xff0000;
+
 	ret = xadc_write_adc_reg(xadc, XADC_REG_SEQ(1), scan_mask >> 16);
 	if (ret)
 		goto err;
@@ -823,11 +844,27 @@ static const struct iio_buffer_setup_ops xadc_buffer_ops = {
 	.postdisable = &xadc_postdisable,
 };
 
+static int xadc_read_samplerate(struct xadc *xadc)
+{
+	unsigned int div;
+	uint16_t val16;
+	int ret;
+
+	ret = xadc_read_adc_reg(xadc, XADC_REG_CONF2, &val16);
+	if (ret)
+		return ret;
+
+	div = (val16 & XADC_CONF2_DIV_MASK) >> XADC_CONF2_DIV_OFFSET;
+	if (div < 2)
+		div = 2;
+
+	return xadc_get_dclk_rate(xadc) / div / 26;
+}
+
 static int xadc_read_raw(struct iio_dev *indio_dev,
 	struct iio_chan_spec const *chan, int *val, int *val2, long info)
 {
 	struct xadc *xadc = iio_priv(indio_dev);
-	unsigned int div;
 	uint16_t val16;
 	int ret;
 
@@ -880,41 +917,31 @@ static int xadc_read_raw(struct iio_dev *indio_dev,
 		*val = -((273150 << 12) / 503975);
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		ret = xadc_read_adc_reg(xadc, XADC_REG_CONF2, &val16);
-		if (ret)
+		ret = xadc_read_samplerate(xadc);
+		if (ret < 0)
 			return ret;
 
-		div = (val16 & XADC_CONF2_DIV_MASK) >> XADC_CONF2_DIV_OFFSET;
-		if (div < 2)
-			div = 2;
-
-		*val = xadc_get_dclk_rate(xadc) / div / 26;
-
+		*val = ret;
 		return IIO_VAL_INT;
 	default:
 		return -EINVAL;
 	}
 }
 
-static int xadc_write_raw(struct iio_dev *indio_dev,
-	struct iio_chan_spec const *chan, int val, int val2, long info)
+static int xadc_write_samplerate(struct xadc *xadc, int val)
 {
-	struct xadc *xadc = iio_priv(indio_dev);
 	unsigned long clk_rate = xadc_get_dclk_rate(xadc);
 	unsigned int div;
 
 	if (!clk_rate)
 		return -EINVAL;
 
-	if (info != IIO_CHAN_INFO_SAMP_FREQ)
-		return -EINVAL;
-
 	if (val <= 0)
 		return -EINVAL;
 
 	/* Max. 150 kSPS */
-	if (val > 150000)
-		val = 150000;
+	if (val > XADC_MAX_SAMPLERATE)
+		val = XADC_MAX_SAMPLERATE;
 
 	val *= 26;
 
@@ -927,7 +954,7 @@ static int xadc_write_raw(struct iio_dev *indio_dev,
 	 * limit.
 	 */
 	div = clk_rate / val;
-	if (clk_rate / div / 26 > 150000)
+	if (clk_rate / div / 26 > XADC_MAX_SAMPLERATE)
 		div++;
 	if (div < 2)
 		div = 2;
@@ -938,6 +965,17 @@ static int xadc_write_raw(struct iio_dev *indio_dev,
 		div << XADC_CONF2_DIV_OFFSET);
 }
 
+static int xadc_write_raw(struct iio_dev *indio_dev,
+	struct iio_chan_spec const *chan, int val, int val2, long info)
+{
+	struct xadc *xadc = iio_priv(indio_dev);
+
+	if (info != IIO_CHAN_INFO_SAMP_FREQ)
+		return -EINVAL;
+
+	return xadc_write_samplerate(xadc, val);
+}
+
 static const struct iio_event_spec xadc_temp_events[] = {
 	{
 		.type = IIO_EV_TYPE_THRESH,
@@ -1223,6 +1261,21 @@ static int xadc_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_free_samplerate_trigger;
 
+	/*
+	 * Make sure not to exceed the maximum samplerate since otherwise the
+	 * resulting interrupt storm will soft-lock the system.
+	 */
+	if (xadc->ops->flags & XADC_FLAGS_BUFFERED) {
+		ret = xadc_read_samplerate(xadc);
+		if (ret < 0)
+			goto err_free_samplerate_trigger;
+		if (ret > XADC_MAX_SAMPLERATE) {
+			ret = xadc_write_samplerate(xadc, XADC_MAX_SAMPLERATE);
+			if (ret < 0)
+				goto err_free_samplerate_trigger;
+		}
+	}
+
 	ret = request_irq(xadc->irq, xadc->ops->interrupt_handler, 0,
 			dev_name(&pdev->dev), indio_dev);
 	if (ret)
diff --git a/drivers/iio/chemical/atlas-sensor.c b/drivers/iio/chemical/atlas-sensor.c
index 82d470561ad3..7b199ce16ecf 100644
--- a/drivers/iio/chemical/atlas-sensor.c
+++ b/drivers/iio/chemical/atlas-sensor.c
@@ -194,7 +194,19 @@ static const struct iio_chan_spec atlas_orp_channels[] = {
 };
 
 static const struct iio_chan_spec atlas_do_channels[] = {
-	ATLAS_CONCENTRATION_CHANNEL(0, ATLAS_REG_DO_DATA),
+	{
+		.type = IIO_CONCENTRATION,
+		.address = ATLAS_REG_DO_DATA,
+		.info_mask_separate =
+			BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE),
+		.scan_index = 0,
+		.scan_type = {
+			.sign = 'u',
+			.realbits = 32,
+			.storagebits = 32,
+			.endianness = IIO_BE,
+		},
+	},
 	IIO_CHAN_SOFT_TIMESTAMP(1),
 	{
 		.type = IIO_TEMP,
diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index 0e35ff06f9af..13bdfbbf5f71 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -79,7 +79,7 @@ int st_sensors_set_odr(struct iio_dev *indio_dev, unsigned int odr)
 	struct st_sensor_odr_avl odr_out = {0, 0};
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
 
-	if (!sdata->sensor_settings->odr.addr)
+	if (!sdata->sensor_settings->odr.mask)
 		return 0;
 
 	err = st_sensors_match_odr(sdata->sensor_settings, odr, &odr_out);
diff --git a/drivers/iio/dac/ad5770r.c b/drivers/iio/dac/ad5770r.c
index a98ea76732e7..2d7623b9b2c0 100644
--- a/drivers/iio/dac/ad5770r.c
+++ b/drivers/iio/dac/ad5770r.c
@@ -525,7 +525,7 @@ static int ad5770r_channel_config(struct ad5770r_state *st)
 		ret = fwnode_property_read_u32(child, "num", &num);
 		if (ret)
 			return ret;
-		if (num > AD5770R_MAX_CHANNELS)
+		if (num >= AD5770R_MAX_CHANNELS)
 			return -EINVAL;
 
 		ret = fwnode_property_read_u32_array(child,
diff --git a/drivers/iio/dac/vf610_dac.c b/drivers/iio/dac/vf610_dac.c
index 71f8a5c471c4..7f1e9317c3f3 100644
--- a/drivers/iio/dac/vf610_dac.c
+++ b/drivers/iio/dac/vf610_dac.c
@@ -223,6 +223,7 @@ static int vf610_dac_probe(struct platform_device *pdev)
 	return 0;
 
 error_iio_device_register:
+	vf610_dac_exit(info);
 	clk_disable_unprepare(info->clk);
 
 	return ret;
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index 7cb9ff3d3e94..0b8d2f7a0165 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -1617,6 +1617,10 @@ static int __maybe_unused inv_mpu_resume(struct device *dev)
 	if (result)
 		goto out_unlock;
 
+	pm_runtime_disable(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
 	result = inv_mpu6050_switch_engine(st, true, st->suspended_sensors);
 	if (result)
 		goto out_unlock;
@@ -1638,13 +1642,18 @@ static int __maybe_unused inv_mpu_suspend(struct device *dev)
 
 	mutex_lock(&st->lock);
 
+	st->suspended_sensors = 0;
+	if (pm_runtime_suspended(dev)) {
+		result = 0;
+		goto out_unlock;
+	}
+
 	if (iio_buffer_enabled(indio_dev)) {
 		result = inv_mpu6050_prepare_fifo(st, false);
 		if (result)
 			goto out_unlock;
 	}
 
-	st->suspended_sensors = 0;
 	if (st->chip_config.accl_en)
 		st->suspended_sensors |= INV_MPU6050_SENSOR_ACCL;
 	if (st->chip_config.gyro_en)
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h
index f2113a63721a..41cb20cb3809 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h
@@ -337,6 +337,7 @@ enum st_lsm6dsx_fifo_mode {
  * @gain: Configured sensor sensitivity.
  * @odr: Output data rate of the sensor [Hz].
  * @watermark: Sensor watermark level.
+ * @decimator: Sensor decimation factor.
  * @sip: Number of samples in a given pattern.
  * @ts_ref: Sensor timestamp reference for hw one.
  * @ext_info: Sensor settings if it is connected to i2c controller
@@ -350,11 +351,13 @@ struct st_lsm6dsx_sensor {
 	u32 odr;
 
 	u16 watermark;
+	u8 decimator;
 	u8 sip;
 	s64 ts_ref;
 
 	struct {
 		const struct st_lsm6dsx_ext_dev_settings *settings;
+		u32 slv_odr;
 		u8 addr;
 	} ext_info;
 };
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index bb899345f2bb..afd00daeefb2 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -93,6 +93,7 @@ st_lsm6dsx_get_decimator_val(struct st_lsm6dsx_sensor *sensor, u32 max_odr)
 			break;
 	}
 
+	sensor->decimator = decimator;
 	return i == max_size ? 0 : st_lsm6dsx_decimator_table[i].val;
 }
 
@@ -337,7 +338,7 @@ static inline int st_lsm6dsx_read_block(struct st_lsm6dsx_hw *hw, u8 addr,
 int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw)
 {
 	struct st_lsm6dsx_sensor *acc_sensor, *gyro_sensor, *ext_sensor = NULL;
-	int err, acc_sip, gyro_sip, ts_sip, ext_sip, read_len, offset;
+	int err, sip, acc_sip, gyro_sip, ts_sip, ext_sip, read_len, offset;
 	u16 fifo_len, pattern_len = hw->sip * ST_LSM6DSX_SAMPLE_SIZE;
 	u16 fifo_diff_mask = hw->settings->fifo_ops.fifo_diff.mask;
 	u8 gyro_buff[ST_LSM6DSX_IIO_BUFF_SIZE];
@@ -399,19 +400,20 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw)
 		acc_sip = acc_sensor->sip;
 		ts_sip = hw->ts_sip;
 		offset = 0;
+		sip = 0;
 
 		while (acc_sip > 0 || gyro_sip > 0 || ext_sip > 0) {
-			if (gyro_sip > 0) {
+			if (gyro_sip > 0 && !(sip % gyro_sensor->decimator)) {
 				memcpy(gyro_buff, &hw->buff[offset],
 				       ST_LSM6DSX_SAMPLE_SIZE);
 				offset += ST_LSM6DSX_SAMPLE_SIZE;
 			}
-			if (acc_sip > 0) {
+			if (acc_sip > 0 && !(sip % acc_sensor->decimator)) {
 				memcpy(acc_buff, &hw->buff[offset],
 				       ST_LSM6DSX_SAMPLE_SIZE);
 				offset += ST_LSM6DSX_SAMPLE_SIZE;
 			}
-			if (ext_sip > 0) {
+			if (ext_sip > 0 && !(sip % ext_sensor->decimator)) {
 				memcpy(ext_buff, &hw->buff[offset],
 				       ST_LSM6DSX_SAMPLE_SIZE);
 				offset += ST_LSM6DSX_SAMPLE_SIZE;
@@ -441,18 +443,25 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw)
 				offset += ST_LSM6DSX_SAMPLE_SIZE;
 			}
 
-			if (gyro_sip-- > 0)
+			if (gyro_sip > 0 && !(sip % gyro_sensor->decimator)) {
 				iio_push_to_buffers_with_timestamp(
 					hw->iio_devs[ST_LSM6DSX_ID_GYRO],
 					gyro_buff, gyro_sensor->ts_ref + ts);
-			if (acc_sip-- > 0)
+				gyro_sip--;
+			}
+			if (acc_sip > 0 && !(sip % acc_sensor->decimator)) {
 				iio_push_to_buffers_with_timestamp(
 					hw->iio_devs[ST_LSM6DSX_ID_ACC],
 					acc_buff, acc_sensor->ts_ref + ts);
-			if (ext_sip-- > 0)
+				acc_sip--;
+			}
+			if (ext_sip > 0 && !(sip % ext_sensor->decimator)) {
 				iio_push_to_buffers_with_timestamp(
 					hw->iio_devs[ST_LSM6DSX_ID_EXT0],
 					ext_buff, ext_sensor->ts_ref + ts);
+				ext_sip--;
+			}
+			sip++;
 		}
 	}
 
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
index 84d219ae6aee..4426524b59f2 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
@@ -2036,11 +2036,21 @@ static int st_lsm6dsx_init_hw_timer(struct st_lsm6dsx_hw *hw)
 	return 0;
 }
 
-static int st_lsm6dsx_init_device(struct st_lsm6dsx_hw *hw)
+static int st_lsm6dsx_reset_device(struct st_lsm6dsx_hw *hw)
 {
 	const struct st_lsm6dsx_reg *reg;
 	int err;
 
+	/*
+	 * flush hw FIFO before device reset in order to avoid
+	 * possible races on interrupt line 1. If the first interrupt
+	 * line is asserted during hw reset the device will work in
+	 * I3C-only mode (if it is supported)
+	 */
+	err = st_lsm6dsx_flush_fifo(hw);
+	if (err < 0 && err != -ENOTSUPP)
+		return err;
+
 	/* device sw reset */
 	reg = &hw->settings->reset;
 	err = regmap_update_bits(hw->regmap, reg->addr, reg->mask,
@@ -2059,6 +2069,18 @@ static int st_lsm6dsx_init_device(struct st_lsm6dsx_hw *hw)
 
 	msleep(50);
 
+	return 0;
+}
+
+static int st_lsm6dsx_init_device(struct st_lsm6dsx_hw *hw)
+{
+	const struct st_lsm6dsx_reg *reg;
+	int err;
+
+	err = st_lsm6dsx_reset_device(hw);
+	if (err < 0)
+		return err;
+
 	/* enable Block Data Update */
 	reg = &hw->settings->bdu;
 	err = regmap_update_bits(hw->regmap, reg->addr, reg->mask,
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c
index 95ddd19d1aa7..1cf98195f84d 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c
@@ -421,7 +421,8 @@ int st_lsm6dsx_shub_set_enable(struct st_lsm6dsx_sensor *sensor, bool enable)
 
 	settings = sensor->ext_info.settings;
 	if (enable) {
-		err = st_lsm6dsx_shub_set_odr(sensor, sensor->odr);
+		err = st_lsm6dsx_shub_set_odr(sensor,
+					      sensor->ext_info.slv_odr);
 		if (err < 0)
 			return err;
 	} else {
@@ -459,7 +460,7 @@ st_lsm6dsx_shub_read_oneshot(struct st_lsm6dsx_sensor *sensor,
 	if (err < 0)
 		return err;
 
-	delay = 1000000000 / sensor->odr;
+	delay = 1000000000 / sensor->ext_info.slv_odr;
 	usleep_range(delay, 2 * delay);
 
 	len = min_t(int, sizeof(data), ch->scan_type.realbits >> 3);
@@ -500,8 +501,8 @@ st_lsm6dsx_shub_read_raw(struct iio_dev *iio_dev,
 		iio_device_release_direct_mode(iio_dev);
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		*val = sensor->odr / 1000;
-		*val2 = (sensor->odr % 1000) * 1000;
+		*val = sensor->ext_info.slv_odr / 1000;
+		*val2 = (sensor->ext_info.slv_odr % 1000) * 1000;
 		ret = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	case IIO_CHAN_INFO_SCALE:
@@ -535,8 +536,22 @@ st_lsm6dsx_shub_write_raw(struct iio_dev *iio_dev,
 
 		val = val * 1000 + val2 / 1000;
 		err = st_lsm6dsx_shub_get_odr_val(sensor, val, &data);
-		if (!err)
-			sensor->odr = val;
+		if (!err) {
+			struct st_lsm6dsx_hw *hw = sensor->hw;
+			struct st_lsm6dsx_sensor *ref_sensor;
+			u8 odr_val;
+			int odr;
+
+			ref_sensor = iio_priv(hw->iio_devs[ST_LSM6DSX_ID_ACC]);
+			odr = st_lsm6dsx_check_odr(ref_sensor, val, &odr_val);
+			if (odr < 0) {
+				err = odr;
+				goto release;
+			}
+
+			sensor->ext_info.slv_odr = val;
+			sensor->odr = odr;
+		}
 		break;
 	}
 	default:
@@ -544,6 +559,7 @@ st_lsm6dsx_shub_write_raw(struct iio_dev *iio_dev,
 		break;
 	}
 
+release:
 	iio_device_release_direct_mode(iio_dev);
 
 	return err;
@@ -613,6 +629,7 @@ st_lsm6dsx_shub_alloc_iiodev(struct st_lsm6dsx_hw *hw,
 			     const struct st_lsm6dsx_ext_dev_settings *info,
 			     u8 i2c_addr, const char *name)
 {
+	enum st_lsm6dsx_sensor_id ref_id = ST_LSM6DSX_ID_ACC;
 	struct iio_chan_spec *ext_channels;
 	struct st_lsm6dsx_sensor *sensor;
 	struct iio_dev *iio_dev;
@@ -628,7 +645,8 @@ st_lsm6dsx_shub_alloc_iiodev(struct st_lsm6dsx_hw *hw,
 	sensor = iio_priv(iio_dev);
 	sensor->id = id;
 	sensor->hw = hw;
-	sensor->odr = info->odr_table.odr_avl[0].milli_hz;
+	sensor->odr = hw->settings->odr_table[ref_id].odr_avl[0].milli_hz;
+	sensor->ext_info.slv_odr = info->odr_table.odr_avl[0].milli_hz;
 	sensor->gain = info->fs_table.fs_avl[0].gain;
 	sensor->ext_info.settings = info;
 	sensor->ext_info.addr = i2c_addr;
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 2352c426bfb5..24f7bbff4938 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -915,14 +915,11 @@ static ssize_t iio_write_channel_info(struct device *dev,
 			return -EINVAL;
 		integer = ch;
 	} else {
-		ret = iio_str_to_fixpoint(buf, fract_mult, &integer, &fract);
+		ret = __iio_str_to_fixpoint(buf, fract_mult, &integer, &fract,
+					    scale_db);
 		if (ret)
 			return ret;
 	}
-	ret = __iio_str_to_fixpoint(buf, fract_mult, &integer, &fract,
-				    scale_db);
-	if (ret)
-		return ret;
 
 	ret = indio_dev->info->write_raw(indio_dev, this_attr->c,
 					 integer, fract, this_attr->address);
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 717b798cddad..a670209bbce6 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -1553,8 +1553,11 @@ int ib_cache_setup_one(struct ib_device *device)
 	if (err)
 		return err;
 
-	rdma_for_each_port (device, p)
-		ib_cache_update(device, p, true);
+	rdma_for_each_port (device, p) {
+		err = ib_cache_update(device, p, true);
+		if (err)
+			return err;
+	}
 
 	return 0;
 }
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 4794113ecd59..17f14e0eafe4 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -862,7 +862,7 @@ static struct cm_id_private *cm_alloc_id_priv(struct ib_device *device,
 
 	ret = xa_alloc_cyclic_irq(&cm.local_id_table, &id, NULL, xa_limit_32b,
 				  &cm.local_id_next, GFP_KERNEL);
-	if (ret)
+	if (ret < 0)
 		goto error;
 	cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand;
 
@@ -1828,11 +1828,9 @@ static void cm_format_mra(struct cm_mra_msg *mra_msg,
 
 static void cm_format_rej(struct cm_rej_msg *rej_msg,
 			  struct cm_id_private *cm_id_priv,
-			  enum ib_cm_rej_reason reason,
-			  void *ari,
-			  u8 ari_length,
-			  const void *private_data,
-			  u8 private_data_len)
+			  enum ib_cm_rej_reason reason, void *ari,
+			  u8 ari_length, const void *private_data,
+			  u8 private_data_len, enum ib_cm_state state)
 {
 	lockdep_assert_held(&cm_id_priv->lock);
 
@@ -1840,7 +1838,7 @@ static void cm_format_rej(struct cm_rej_msg *rej_msg,
 	IBA_SET(CM_REJ_REMOTE_COMM_ID, rej_msg,
 		be32_to_cpu(cm_id_priv->id.remote_id));
 
-	switch(cm_id_priv->id.state) {
+	switch (state) {
 	case IB_CM_REQ_RCVD:
 		IBA_SET(CM_REJ_LOCAL_COMM_ID, rej_msg, be32_to_cpu(0));
 		IBA_SET(CM_REJ_MESSAGE_REJECTED, rej_msg, CM_MSG_RESPONSE_REQ);
@@ -1905,8 +1903,9 @@ static void cm_dup_req_handler(struct cm_work *work,
 			      cm_id_priv->private_data_len);
 		break;
 	case IB_CM_TIMEWAIT:
-		cm_format_rej((struct cm_rej_msg *) msg->mad, cm_id_priv,
-			      IB_CM_REJ_STALE_CONN, NULL, 0, NULL, 0);
+		cm_format_rej((struct cm_rej_msg *)msg->mad, cm_id_priv,
+			      IB_CM_REJ_STALE_CONN, NULL, 0, NULL, 0,
+			      IB_CM_TIMEWAIT);
 		break;
 	default:
 		goto unlock;
@@ -2904,6 +2903,7 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv,
 			      u8 ari_length, const void *private_data,
 			      u8 private_data_len)
 {
+	enum ib_cm_state state = cm_id_priv->id.state;
 	struct ib_mad_send_buf *msg;
 	int ret;
 
@@ -2913,7 +2913,7 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv,
 	    (ari && ari_length > IB_CM_REJ_ARI_LENGTH))
 		return -EINVAL;
 
-	switch (cm_id_priv->id.state) {
+	switch (state) {
 	case IB_CM_REQ_SENT:
 	case IB_CM_MRA_REQ_RCVD:
 	case IB_CM_REQ_RCVD:
@@ -2925,7 +2925,8 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv,
 		if (ret)
 			return ret;
 		cm_format_rej((struct cm_rej_msg *)msg->mad, cm_id_priv, reason,
-			      ari, ari_length, private_data, private_data_len);
+			      ari, ari_length, private_data, private_data_len,
+			      state);
 		break;
 	case IB_CM_REP_SENT:
 	case IB_CM_MRA_REP_RCVD:
@@ -2934,7 +2935,8 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv,
 		if (ret)
 			return ret;
 		cm_format_rej((struct cm_rej_msg *)msg->mad, cm_id_priv, reason,
-			      ari, ari_length, private_data, private_data_len);
+			      ari, ari_length, private_data, private_data_len,
+			      state);
 		break;
 	default:
 		pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 9eec26d10d7b..e16105be2eb2 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1292,11 +1292,10 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	has_cap_net_admin = netlink_capable(skb, CAP_NET_ADMIN);
 
 	ret = fill_func(msg, has_cap_net_admin, res, port);
-
-	rdma_restrack_put(res);
 	if (ret)
 		goto err_free;
 
+	rdma_restrack_put(res);
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
 	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 5128cb16bb48..e0a5e897e4b1 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -153,9 +153,9 @@ static int uverbs_destroy_uobject(struct ib_uobject *uobj,
 	uobj->context = NULL;
 
 	/*
-	 * For DESTROY the usecnt is held write locked, the caller is expected
-	 * to put it unlock and put the object when done with it. Only DESTROY
-	 * can remove the IDR handle.
+	 * For DESTROY the usecnt is not changed, the caller is expected to
+	 * manage it via uobj_put_destroy(). Only DESTROY can remove the IDR
+	 * handle.
 	 */
 	if (reason != RDMA_REMOVE_DESTROY)
 		atomic_set(&uobj->usecnt, 0);
@@ -187,7 +187,7 @@ static int uverbs_destroy_uobject(struct ib_uobject *uobj,
 /*
  * This calls uverbs_destroy_uobject() using the RDMA_REMOVE_DESTROY
  * sequence. It should only be used from command callbacks. On success the
- * caller must pair this with rdma_lookup_put_uobject(LOOKUP_WRITE). This
+ * caller must pair this with uobj_put_destroy(). This
  * version requires the caller to have already obtained an
  * LOOKUP_DESTROY uobject kref.
  */
@@ -198,6 +198,13 @@ int uobj_destroy(struct ib_uobject *uobj, struct uverbs_attr_bundle *attrs)
 
 	down_read(&ufile->hw_destroy_rwsem);
 
+	/*
+	 * Once the uobject is destroyed by RDMA_REMOVE_DESTROY then it is left
+	 * write locked as the callers put it back with UVERBS_LOOKUP_DESTROY.
+	 * This is because any other concurrent thread can still see the object
+	 * in the xarray due to RCU. Leaving it locked ensures nothing else will
+	 * touch it.
+	 */
 	ret = uverbs_try_lock_object(uobj, UVERBS_LOOKUP_WRITE);
 	if (ret)
 		goto out_unlock;
@@ -216,7 +223,7 @@ out_unlock:
 /*
  * uobj_get_destroy destroys the HW object and returns a handle to the uobj
  * with a NULL object pointer. The caller must pair this with
- * uverbs_put_destroy.
+ * uobj_put_destroy().
  */
 struct ib_uobject *__uobj_get_destroy(const struct uverbs_api_object *obj,
 				      u32 id, struct uverbs_attr_bundle *attrs)
@@ -250,8 +257,7 @@ int __uobj_perform_destroy(const struct uverbs_api_object *obj, u32 id,
 	uobj = __uobj_get_destroy(obj, id, attrs);
 	if (IS_ERR(uobj))
 		return PTR_ERR(uobj);
-
-	rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_WRITE);
+	uobj_put_destroy(uobj);
 	return 0;
 }
 
@@ -360,7 +366,7 @@ lookup_get_fd_uobject(const struct uverbs_api_object *obj,
 	 * uverbs_uobject_fd_release(), and the caller is expected to ensure
 	 * that release is never done while a call to lookup is possible.
 	 */
-	if (f->f_op != fd_type->fops) {
+	if (f->f_op != fd_type->fops || uobject->ufile != ufile) {
 		fput(f);
 		return ERR_PTR(-EBADF);
 	}
@@ -459,7 +465,8 @@ alloc_begin_fd_uobject(const struct uverbs_api_object *obj,
 	struct ib_uobject *uobj;
 	struct file *filp;
 
-	if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release))
+	if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release &&
+		    fd_type->fops->release != &uverbs_async_event_release))
 		return ERR_PTR(-EINVAL);
 
 	new_fd = get_unused_fd_flags(O_CLOEXEC);
@@ -474,16 +481,15 @@ alloc_begin_fd_uobject(const struct uverbs_api_object *obj,
 	filp = anon_inode_getfile(fd_type->name, fd_type->fops, NULL,
 				  fd_type->flags);
 	if (IS_ERR(filp)) {
+		uverbs_uobject_put(uobj);
 		uobj = ERR_CAST(filp);
-		goto err_uobj;
+		goto err_fd;
 	}
 	uobj->object = filp;
 
 	uobj->id = new_fd;
 	return uobj;
 
-err_uobj:
-	uverbs_uobject_put(uobj);
 err_fd:
 	put_unused_fd(new_fd);
 	return uobj;
@@ -679,7 +685,6 @@ void rdma_lookup_put_uobject(struct ib_uobject *uobj,
 			     enum rdma_lookup_mode mode)
 {
 	assert_uverbs_usecnt(uobj, mode);
-	uobj->uapi_object->type_class->lookup_put(uobj, mode);
 	/*
 	 * In order to unlock an object, either decrease its usecnt for
 	 * read access or zero it in case of exclusive access. See
@@ -696,6 +701,7 @@ void rdma_lookup_put_uobject(struct ib_uobject *uobj,
 		break;
 	}
 
+	uobj->uapi_object->type_class->lookup_put(uobj, mode);
 	/* Pairs with the kref obtained by type->lookup_get */
 	uverbs_uobject_put(uobj);
 }
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 7df71983212d..3d189c7ee59e 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -219,6 +219,7 @@ void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue);
 void ib_uverbs_init_async_event_file(struct ib_uverbs_async_event_file *ev_file);
 void ib_uverbs_free_event_queue(struct ib_uverbs_event_queue *event_queue);
 void ib_uverbs_flow_resources_free(struct ib_uflow_resources *uflow_res);
+int uverbs_async_event_release(struct inode *inode, struct file *filp);
 
 int ib_alloc_ucontext(struct uverbs_attr_bundle *attrs);
 int ib_init_ucontext(struct uverbs_attr_bundle *attrs);
@@ -227,6 +228,9 @@ void ib_uverbs_release_ucq(struct ib_uverbs_completion_event_file *ev_file,
 			   struct ib_ucq_object *uobj);
 void ib_uverbs_release_uevent(struct ib_uevent_object *uobj);
 void ib_uverbs_release_file(struct kref *ref);
+void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file,
+			     __u64 element, __u64 event,
+			     struct list_head *obj_list, u32 *counter);
 
 void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context);
 void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr);
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 2d4083bf4a04..1bab8de14757 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -346,7 +346,7 @@ const struct file_operations uverbs_async_event_fops = {
 	.owner	 = THIS_MODULE,
 	.read	 = ib_uverbs_async_event_read,
 	.poll    = ib_uverbs_async_event_poll,
-	.release = uverbs_uobject_fd_release,
+	.release = uverbs_async_event_release,
 	.fasync  = ib_uverbs_async_event_fasync,
 	.llseek	 = no_llseek,
 };
@@ -386,10 +386,9 @@ void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context)
 	kill_fasync(&ev_queue->async_queue, SIGIO, POLL_IN);
 }
 
-static void
-ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file,
-			__u64 element, __u64 event, struct list_head *obj_list,
-			u32 *counter)
+void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file,
+			     __u64 element, __u64 event,
+			     struct list_head *obj_list, u32 *counter)
 {
 	struct ib_uverbs_event *entry;
 	unsigned long flags;
@@ -820,6 +819,10 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 			ret = mmget_not_zero(mm);
 			if (!ret) {
 				list_del_init(&priv->list);
+				if (priv->entry) {
+					rdma_user_mmap_entry_put(priv->entry);
+					priv->entry = NULL;
+				}
 				mm = NULL;
 				continue;
 			}
@@ -1183,9 +1186,6 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev,
 		 */
 		mutex_unlock(&uverbs_dev->lists_mutex);
 
-		ib_uverbs_async_handler(READ_ONCE(file->async_file), 0,
-					IB_EVENT_DEVICE_FATAL, NULL, NULL);
-
 		uverbs_destroy_ufile_hw(file, RDMA_REMOVE_DRIVER_REMOVE);
 		kref_put(&file->ref, ib_uverbs_release_file);
 
diff --git a/drivers/infiniband/core/uverbs_std_types_async_fd.c b/drivers/infiniband/core/uverbs_std_types_async_fd.c
index 82ec0806b34b..61899eaf1f91 100644
--- a/drivers/infiniband/core/uverbs_std_types_async_fd.c
+++ b/drivers/infiniband/core/uverbs_std_types_async_fd.c
@@ -26,10 +26,38 @@ static int uverbs_async_event_destroy_uobj(struct ib_uobject *uobj,
 		container_of(uobj, struct ib_uverbs_async_event_file, uobj);
 
 	ib_unregister_event_handler(&event_file->event_handler);
-	ib_uverbs_free_event_queue(&event_file->ev_queue);
+
+	if (why == RDMA_REMOVE_DRIVER_REMOVE)
+		ib_uverbs_async_handler(event_file, 0, IB_EVENT_DEVICE_FATAL,
+					NULL, NULL);
 	return 0;
 }
 
+int uverbs_async_event_release(struct inode *inode, struct file *filp)
+{
+	struct ib_uverbs_async_event_file *event_file;
+	struct ib_uobject *uobj = filp->private_data;
+	int ret;
+
+	if (!uobj)
+		return uverbs_uobject_fd_release(inode, filp);
+
+	event_file =
+		container_of(uobj, struct ib_uverbs_async_event_file, uobj);
+
+	/*
+	 * The async event FD has to deliver IB_EVENT_DEVICE_FATAL even after
+	 * disassociation, so cleaning the event list must only happen after
+	 * release. The user knows it has reached the end of the event stream
+	 * when it sees IB_EVENT_DEVICE_FATAL.
+	 */
+	uverbs_uobject_get(uobj);
+	ret = uverbs_uobject_fd_release(inode, filp);
+	ib_uverbs_free_event_queue(&event_file->ev_queue);
+	uverbs_uobject_put(uobj);
+	return ret;
+}
+
 DECLARE_UVERBS_NAMED_METHOD(
 	UVERBS_METHOD_ASYNC_EVENT_ALLOC,
 	UVERBS_ATTR_FD(UVERBS_ATTR_ASYNC_EVENT_ALLOC_FD_HANDLE,
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index d69dece3b1d5..30e08bcc9afb 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2891,8 +2891,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 			srqidx = ABORT_RSS_SRQIDX_G(
 					be32_to_cpu(req->srqidx_status));
 			if (srqidx) {
-				complete_cached_srq_buffers(ep,
-							    req->srqidx_status);
+				complete_cached_srq_buffers(ep, srqidx);
 			} else {
 				/* Hold ep ref until finish_peer_abort() */
 				c4iw_get_ep(&ep->com);
@@ -3878,8 +3877,8 @@ static int read_tcb_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 		return 0;
 	}
 
-	ep->srqe_idx = t4_tcb_get_field32(tcb, TCB_RQ_START_W, TCB_RQ_START_W,
-			TCB_RQ_START_S);
+	ep->srqe_idx = t4_tcb_get_field32(tcb, TCB_RQ_START_W, TCB_RQ_START_M,
+					  TCB_RQ_START_S);
 cleanup:
 	pr_debug("ep %p tid %u %016x\n", ep, ep->hwtid, ep->srqe_idx);
 
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index 13e4203497b3..a92346e88628 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -589,10 +589,6 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 
 	set_comp_state(pq, cq, info.comp_idx, QUEUED, 0);
 	pq->state = SDMA_PKT_Q_ACTIVE;
-	/* Send the first N packets in the request to buy us some time */
-	ret = user_sdma_send_pkts(req, pcount);
-	if (unlikely(ret < 0 && ret != -EBUSY))
-		goto free_req;
 
 	/*
 	 * This is a somewhat blocking send implementation.
diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c
index bb78d3280acc..fa7a5ff498c7 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_cm.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c
@@ -1987,7 +1987,6 @@ static int i40iw_addr_resolve_neigh(struct i40iw_device *iwdev,
 	struct rtable *rt;
 	struct neighbour *neigh;
 	int rc = arpindex;
-	struct net_device *netdev = iwdev->netdev;
 	__be32 dst_ipaddr = htonl(dst_ip);
 	__be32 src_ipaddr = htonl(src_ip);
 
@@ -1997,9 +1996,6 @@ static int i40iw_addr_resolve_neigh(struct i40iw_device *iwdev,
 		return rc;
 	}
 
-	if (netif_is_bond_slave(netdev))
-		netdev = netdev_master_upper_dev_get(netdev);
-
 	neigh = dst_neigh_lookup(&rt->dst, &dst_ipaddr);
 
 	rcu_read_lock();
@@ -2065,7 +2061,6 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev,
 {
 	struct neighbour *neigh;
 	int rc = arpindex;
-	struct net_device *netdev = iwdev->netdev;
 	struct dst_entry *dst;
 	struct sockaddr_in6 dst_addr;
 	struct sockaddr_in6 src_addr;
@@ -2086,9 +2081,6 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev,
 		return rc;
 	}
 
-	if (netif_is_bond_slave(netdev))
-		netdev = netdev_master_upper_dev_get(netdev);
-
 	neigh = dst_neigh_lookup(dst, dst_addr.sin6_addr.in6_u.u6_addr32);
 
 	rcu_read_lock();
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index e8b4b3743661..688f19667221 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -1046,7 +1046,7 @@ i40iw_sc_query_rdma_features(struct i40iw_sc_cqp *cqp,
 	u64 header;
 
 	wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, scratch);
-	if (wqe)
+	if (!wqe)
 		return I40IW_ERR_RING_FULL;
 
 	set_64bit_val(wqe, 32, feat_mem->pa);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c
index 55a1fbf0e670..ae8b97c30665 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_hw.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c
@@ -534,7 +534,7 @@ void i40iw_manage_arp_cache(struct i40iw_device *iwdev,
 	int arp_index;
 
 	arp_index = i40iw_arp_table(iwdev, ip_addr, ipv4, mac_addr, action);
-	if (arp_index == -1)
+	if (arp_index < 0)
 		return;
 	cqp_request = i40iw_get_cqp_request(&iwdev->cqp, false);
 	if (!cqp_request)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index a66518a5c938..275722cec8c6 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1499,8 +1499,9 @@ static int __mlx4_ib_create_default_rules(
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(pdefault_rules->rules_create_list); i++) {
+		union ib_flow_spec ib_spec = {};
 		int ret;
-		union ib_flow_spec ib_spec;
+
 		switch (pdefault_rules->rules_create_list[i]) {
 		case 0:
 			/* no rule */
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 2f9f78912267..cf51e3cbd969 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -2891,6 +2891,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
 	int send_size;
 	int header_size;
 	int spc;
+	int err;
 	int i;
 
 	if (wr->wr.opcode != IB_WR_SEND)
@@ -2925,7 +2926,9 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
 
 	sqp->ud_header.lrh.virtual_lane    = 0;
 	sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED);
-	ib_get_cached_pkey(ib_dev, sqp->qp.port, 0, &pkey);
+	err = ib_get_cached_pkey(ib_dev, sqp->qp.port, 0, &pkey);
+	if (err)
+		return err;
 	sqp->ud_header.bth.pkey = cpu_to_be16(pkey);
 	if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_TUN_SMI_OWNER)
 		sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn);
@@ -3212,9 +3215,14 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
 	}
 	sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED);
 	if (!sqp->qp.ibqp.qp_num)
-		ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index, &pkey);
+		err = ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index,
+					 &pkey);
 	else
-		ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index, &pkey);
+		err = ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index,
+					 &pkey);
+	if (err)
+		return err;
+
 	sqp->ud_header.bth.pkey = cpu_to_be16(pkey);
 	sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn);
 	sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1));
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index a401931189b7..44683073be0c 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1439,6 +1439,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	if (is_odp_mr(mr)) {
 		to_ib_umem_odp(mr->umem)->private = mr;
+		init_waitqueue_head(&mr->q_deferred_work);
 		atomic_set(&mr->num_deferred_work, 0);
 		err = xa_err(xa_store(&dev->odp_mkeys,
 				      mlx5_base_mkey(mr->mmkey.key), &mr->mmkey,
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 1456db4b6295..2210759843ba 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -5558,7 +5558,9 @@ static void to_rdma_ah_attr(struct mlx5_ib_dev *ibdev,
 	rdma_ah_set_path_bits(ah_attr, path->grh_mlid & 0x7f);
 	rdma_ah_set_static_rate(ah_attr,
 				path->static_rate ? path->static_rate - 5 : 0);
-	if (path->grh_mlid & (1 << 7)) {
+
+	if (path->grh_mlid & (1 << 7) ||
+	    ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) {
 		u32 tc_fl = be32_to_cpu(path->tclass_flowlabel);
 
 		rdma_ah_set_grh(ah_attr, NULL,
diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c
index 568b21eb6ea1..021df0654ba7 100644
--- a/drivers/infiniband/hw/qib/qib_sysfs.c
+++ b/drivers/infiniband/hw/qib/qib_sysfs.c
@@ -760,7 +760,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 			"Skipping linkcontrol sysfs info, (err %d) port %u\n",
 			ret, port_num);
-		goto bail;
+		goto bail_link;
 	}
 	kobject_uevent(&ppd->pport_kobj, KOBJ_ADD);
 
@@ -770,7 +770,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 			"Skipping sl2vl sysfs info, (err %d) port %u\n",
 			ret, port_num);
-		goto bail_link;
+		goto bail_sl;
 	}
 	kobject_uevent(&ppd->sl2vl_kobj, KOBJ_ADD);
 
@@ -780,7 +780,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 			"Skipping diag_counters sysfs info, (err %d) port %u\n",
 			ret, port_num);
-		goto bail_sl;
+		goto bail_diagc;
 	}
 	kobject_uevent(&ppd->diagc_kobj, KOBJ_ADD);
 
@@ -793,7 +793,7 @@ int qib_create_port_files(struct ib_device *ibdev, u8 port_num,
 		qib_dev_err(dd,
 		 "Skipping Congestion Control sysfs info, (err %d) port %u\n",
 		 ret, port_num);
-		goto bail_diagc;
+		goto bail_cc;
 	}
 
 	kobject_uevent(&ppd->pport_cc_kobj, KOBJ_ADD);
@@ -854,6 +854,7 @@ void qib_verbs_unregister_sysfs(struct qib_devdata *dd)
 				&cc_table_bin_attr);
 			kobject_put(&ppd->pport_cc_kobj);
 		}
+		kobject_put(&ppd->diagc_kobj);
 		kobject_put(&ppd->sl2vl_kobj);
 		kobject_put(&ppd->pport_kobj);
 	}
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index e580ae9cc55a..780fd2dfc07e 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -829,7 +829,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 	    !(pci_resource_flags(pdev, 1) & IORESOURCE_MEM)) {
 		dev_err(&pdev->dev, "PCI BAR region not MMIO\n");
 		ret = -ENOMEM;
-		goto err_free_device;
+		goto err_disable_pdev;
 	}
 
 	ret = pci_request_regions(pdev, DRV_NAME);
diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index 5724cbbe38b1..04d2e72017fe 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -248,8 +248,8 @@ int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	 */
 	if (udata && udata->outlen >= sizeof(__u64)) {
 		cq->ip = rvt_create_mmap_info(rdi, sz, udata, u_wc);
-		if (!cq->ip) {
-			err = -ENOMEM;
+		if (IS_ERR(cq->ip)) {
+			err = PTR_ERR(cq->ip);
 			goto bail_wc;
 		}
 
diff --git a/drivers/infiniband/sw/rdmavt/mmap.c b/drivers/infiniband/sw/rdmavt/mmap.c
index 652f4a7efc1b..37853aa3bcf7 100644
--- a/drivers/infiniband/sw/rdmavt/mmap.c
+++ b/drivers/infiniband/sw/rdmavt/mmap.c
@@ -154,7 +154,7 @@ done:
  * @udata: user data (must be valid!)
  * @obj: opaque pointer to a cq, wq etc
  *
- * Return: rvt_mmap struct on success
+ * Return: rvt_mmap struct on success, ERR_PTR on failure
  */
 struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi, u32 size,
 					   struct ib_udata *udata, void *obj)
@@ -166,7 +166,7 @@ struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi, u32 size,
 
 	ip = kmalloc_node(sizeof(*ip), GFP_KERNEL, rdi->dparms.node);
 	if (!ip)
-		return ip;
+		return ERR_PTR(-ENOMEM);
 
 	size = PAGE_ALIGN(size);
 
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 0e1b291d2cec..500a7ee04c44 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -1244,8 +1244,8 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd,
 
 			qp->ip = rvt_create_mmap_info(rdi, s, udata,
 						      qp->r_rq.wq);
-			if (!qp->ip) {
-				ret = ERR_PTR(-ENOMEM);
+			if (IS_ERR(qp->ip)) {
+				ret = ERR_CAST(qp->ip);
 				goto bail_qpn;
 			}
 
diff --git a/drivers/infiniband/sw/rdmavt/srq.c b/drivers/infiniband/sw/rdmavt/srq.c
index 24fef021d51d..f547c115af03 100644
--- a/drivers/infiniband/sw/rdmavt/srq.c
+++ b/drivers/infiniband/sw/rdmavt/srq.c
@@ -111,8 +111,8 @@ int rvt_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *srq_init_attr,
 		u32 s = sizeof(struct rvt_rwq) + srq->rq.size * sz;
 
 		srq->ip = rvt_create_mmap_info(dev, s, udata, srq->rq.wq);
-		if (!srq->ip) {
-			ret = -ENOMEM;
+		if (IS_ERR(srq->ip)) {
+			ret = PTR_ERR(srq->ip);
 			goto bail_wq;
 		}
 
diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c
index 48f48122ddcb..6a413d73b95d 100644
--- a/drivers/infiniband/sw/rxe/rxe_mmap.c
+++ b/drivers/infiniband/sw/rxe/rxe_mmap.c
@@ -151,7 +151,7 @@ struct rxe_mmap_info *rxe_create_mmap_info(struct rxe_dev *rxe, u32 size,
 
 	ip = kmalloc(sizeof(*ip), GFP_KERNEL);
 	if (!ip)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	size = PAGE_ALIGN(size);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_queue.c b/drivers/infiniband/sw/rxe/rxe_queue.c
index ff92704de32f..245040c3a35d 100644
--- a/drivers/infiniband/sw/rxe/rxe_queue.c
+++ b/drivers/infiniband/sw/rxe/rxe_queue.c
@@ -45,12 +45,15 @@ int do_mmap_info(struct rxe_dev *rxe, struct mminfo __user *outbuf,
 
 	if (outbuf) {
 		ip = rxe_create_mmap_info(rxe, buf_size, udata, buf);
-		if (!ip)
+		if (IS_ERR(ip)) {
+			err = PTR_ERR(ip);
 			goto err1;
+		}
 
-		err = copy_to_user(outbuf, &ip->info, sizeof(ip->info));
-		if (err)
+		if (copy_to_user(outbuf, &ip->info, sizeof(ip->info))) {
+			err = -EFAULT;
 			goto err2;
+		}
 
 		spin_lock_bh(&rxe->pending_lock);
 		list_add(&ip->pending_mmaps, &rxe->pending_mmaps);
@@ -64,7 +67,7 @@ int do_mmap_info(struct rxe_dev *rxe, struct mminfo __user *outbuf,
 err2:
 	kfree(ip);
 err1:
-	return -EINVAL;
+	return err;
 }
 
 inline void rxe_queue_reset(struct rxe_queue *q)
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index ae92c8080967..9f53aa4feb87 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -920,20 +920,27 @@ static int siw_fastreg_mr(struct ib_pd *pd, struct siw_sqe *sqe)
 {
 	struct ib_mr *base_mr = (struct ib_mr *)(uintptr_t)sqe->base_mr;
 	struct siw_device *sdev = to_siw_dev(pd->device);
-	struct siw_mem *mem = siw_mem_id2obj(sdev, sqe->rkey  >> 8);
+	struct siw_mem *mem;
 	int rv = 0;
 
 	siw_dbg_pd(pd, "STag 0x%08x\n", sqe->rkey);
 
-	if (unlikely(!mem || !base_mr)) {
+	if (unlikely(!base_mr)) {
 		pr_warn("siw: fastreg: STag 0x%08x unknown\n", sqe->rkey);
 		return -EINVAL;
 	}
+
 	if (unlikely(base_mr->rkey >> 8 != sqe->rkey  >> 8)) {
 		pr_warn("siw: fastreg: STag 0x%08x: bad MR\n", sqe->rkey);
-		rv = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
+
+	mem = siw_mem_id2obj(sdev, sqe->rkey  >> 8);
+	if (unlikely(!mem)) {
+		pr_warn("siw: fastreg: STag 0x%08x unknown\n", sqe->rkey);
+		return -EINVAL;
+	}
+
 	if (unlikely(mem->pd != pd)) {
 		pr_warn("siw: fastreg: PD mismatch\n");
 		rv = -EINVAL;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index e188a95984b5..9a3379c49541 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -377,8 +377,12 @@ struct ipoib_dev_priv {
 	struct ipoib_rx_buf *rx_ring;
 
 	struct ipoib_tx_buf *tx_ring;
+	/* cyclic ring variables for managing tx_ring, for UD only */
 	unsigned int	     tx_head;
 	unsigned int	     tx_tail;
+	/* cyclic ring variables for counting overall outstanding send WRs */
+	unsigned int	     global_tx_head;
+	unsigned int	     global_tx_tail;
 	struct ib_sge	     tx_sge[MAX_SKB_FRAGS + 1];
 	struct ib_ud_wr      tx_wr;
 	struct ib_wc	     send_wc[MAX_SEND_CQE];
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index c59e00a0881f..9bf0fa30df28 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -756,7 +756,8 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 		return;
 	}
 
-	if ((priv->tx_head - priv->tx_tail) == ipoib_sendq_size - 1) {
+	if ((priv->global_tx_head - priv->global_tx_tail) ==
+	    ipoib_sendq_size - 1) {
 		ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n",
 			  tx->qp->qp_num);
 		netif_stop_queue(dev);
@@ -786,7 +787,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_
 	} else {
 		netif_trans_update(dev);
 		++tx->tx_head;
-		++priv->tx_head;
+		++priv->global_tx_head;
 	}
 }
 
@@ -820,10 +821,11 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 	netif_tx_lock(dev);
 
 	++tx->tx_tail;
-	++priv->tx_tail;
+	++priv->global_tx_tail;
 
 	if (unlikely(netif_queue_stopped(dev) &&
-		     (priv->tx_head - priv->tx_tail) <= ipoib_sendq_size >> 1 &&
+		     ((priv->global_tx_head - priv->global_tx_tail) <=
+		      ipoib_sendq_size >> 1) &&
 		     test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)))
 		netif_wake_queue(dev);
 
@@ -1232,8 +1234,9 @@ timeout:
 		dev_kfree_skb_any(tx_req->skb);
 		netif_tx_lock_bh(p->dev);
 		++p->tx_tail;
-		++priv->tx_tail;
-		if (unlikely(priv->tx_head - priv->tx_tail == ipoib_sendq_size >> 1) &&
+		++priv->global_tx_tail;
+		if (unlikely((priv->global_tx_head - priv->global_tx_tail) <=
+			     ipoib_sendq_size >> 1) &&
 		    netif_queue_stopped(p->dev) &&
 		    test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
 			netif_wake_queue(p->dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index c332b4761816..da3c5315bbb5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -407,9 +407,11 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
 	dev_kfree_skb_any(tx_req->skb);
 
 	++priv->tx_tail;
+	++priv->global_tx_tail;
 
 	if (unlikely(netif_queue_stopped(dev) &&
-		     ((priv->tx_head - priv->tx_tail) <= ipoib_sendq_size >> 1) &&
+		     ((priv->global_tx_head - priv->global_tx_tail) <=
+		      ipoib_sendq_size >> 1) &&
 		     test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)))
 		netif_wake_queue(dev);
 
@@ -634,7 +636,8 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb,
 	else
 		priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;
 	/* increase the tx_head after send success, but use it for queue state */
-	if (priv->tx_head - priv->tx_tail == ipoib_sendq_size - 1) {
+	if ((priv->global_tx_head - priv->global_tx_tail) ==
+	    ipoib_sendq_size - 1) {
 		ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n");
 		netif_stop_queue(dev);
 	}
@@ -662,6 +665,7 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb,
 
 		rc = priv->tx_head;
 		++priv->tx_head;
+		++priv->global_tx_head;
 	}
 	return rc;
 }
@@ -807,6 +811,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 				ipoib_dma_unmap_tx(priv, tx_req);
 				dev_kfree_skb_any(tx_req->skb);
 				++priv->tx_tail;
+				++priv->global_tx_tail;
 			}
 
 			for (i = 0; i < ipoib_recvq_size; ++i) {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 81b8227214f1..ceec24d45185 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1184,9 +1184,11 @@ static void ipoib_timeout(struct net_device *dev, unsigned int txqueue)
 
 	ipoib_warn(priv, "transmit timeout: latency %d msecs\n",
 		   jiffies_to_msecs(jiffies - dev_trans_start(dev)));
-	ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u\n",
-		   netif_queue_stopped(dev),
-		   priv->tx_head, priv->tx_tail);
+	ipoib_warn(priv,
+		   "queue stopped %d, tx_head %u, tx_tail %u, global_tx_head %u, global_tx_tail %u\n",
+		   netif_queue_stopped(dev), priv->tx_head, priv->tx_tail,
+		   priv->global_tx_head, priv->global_tx_tail);
+
 	/* XXX reset QP, etc. */
 }
 
@@ -1701,7 +1703,7 @@ static int ipoib_dev_init_default(struct net_device *dev)
 		goto out_rx_ring_cleanup;
 	}
 
-	/* priv->tx_head, tx_tail & tx_outstanding are already 0 */
+	/* priv->tx_head, tx_tail and global_tx_tail/head are already 0 */
 
 	if (ipoib_transport_dev_init(dev, priv->ca)) {
 		pr_warn("%s: ipoib_transport_dev_init failed\n",
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index cb6e3a5f509c..0d57e51b8ba1 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -326,20 +326,6 @@ static int evdev_fasync(int fd, struct file *file, int on)
 	return fasync_helper(fd, file, on, &client->fasync);
 }
 
-static int evdev_flush(struct file *file, fl_owner_t id)
-{
-	struct evdev_client *client = file->private_data;
-	struct evdev *evdev = client->evdev;
-
-	mutex_lock(&evdev->mutex);
-
-	if (evdev->exist && !client->revoked)
-		input_flush_device(&evdev->handle, file);
-
-	mutex_unlock(&evdev->mutex);
-	return 0;
-}
-
 static void evdev_free(struct device *dev)
 {
 	struct evdev *evdev = container_of(dev, struct evdev, dev);
@@ -453,6 +439,10 @@ static int evdev_release(struct inode *inode, struct file *file)
 	unsigned int i;
 
 	mutex_lock(&evdev->mutex);
+
+	if (evdev->exist && !client->revoked)
+		input_flush_device(&evdev->handle, file);
+
 	evdev_ungrab(evdev, client);
 	mutex_unlock(&evdev->mutex);
 
@@ -1310,7 +1300,6 @@ static const struct file_operations evdev_fops = {
 	.compat_ioctl	= evdev_ioctl_compat,
 #endif
 	.fasync		= evdev_fasync,
-	.flush		= evdev_flush,
 	.llseek		= no_llseek,
 };
 
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 6b40a1c68f9f..c77cdb3b62b5 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -459,6 +459,16 @@ static const u8 xboxone_fw2015_init[] = {
 };
 
 /*
+ * This packet is required for Xbox One S (0x045e:0x02ea)
+ * and Xbox One Elite Series 2 (0x045e:0x0b00) pads to
+ * initialize the controller that was previously used in
+ * Bluetooth mode.
+ */
+static const u8 xboxone_s_init[] = {
+	0x05, 0x20, 0x00, 0x0f, 0x06
+};
+
+/*
  * This packet is required for the Titanfall 2 Xbox One pads
  * (0x0e6f:0x0165) to finish initialization and for Hori pads
  * (0x0f0d:0x0067) to make the analog sticks work.
@@ -516,6 +526,8 @@ static const struct xboxone_init_packet xboxone_init_packets[] = {
 	XBOXONE_INIT_PKT(0x0e6f, 0x0165, xboxone_hori_init),
 	XBOXONE_INIT_PKT(0x0f0d, 0x0067, xboxone_hori_init),
 	XBOXONE_INIT_PKT(0x0000, 0x0000, xboxone_fw2015_init),
+	XBOXONE_INIT_PKT(0x045e, 0x02ea, xboxone_s_init),
+	XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_init1),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_init2),
 	XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init),
diff --git a/drivers/input/keyboard/applespi.c b/drivers/input/keyboard/applespi.c
index d38398526965..14362ebab9a9 100644
--- a/drivers/input/keyboard/applespi.c
+++ b/drivers/input/keyboard/applespi.c
@@ -186,7 +186,7 @@ struct touchpad_protocol {
 	u8			number_of_fingers;
 	u8			clicked2;
 	u8			unknown3[16];
-	struct tp_finger	fingers[0];
+	struct tp_finger	fingers[];
 };
 
 /**
diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c
index 2b71c5a51f90..fc1793ca2f17 100644
--- a/drivers/input/keyboard/cros_ec_keyb.c
+++ b/drivers/input/keyboard/cros_ec_keyb.c
@@ -347,18 +347,14 @@ static int cros_ec_keyb_info(struct cros_ec_device *ec_dev,
 	params->info_type = info_type;
 	params->event_type = event_type;
 
-	ret = cros_ec_cmd_xfer(ec_dev, msg);
-	if (ret < 0) {
-		dev_warn(ec_dev->dev, "Transfer error %d/%d: %d\n",
-			 (int)info_type, (int)event_type, ret);
-	} else if (msg->result == EC_RES_INVALID_VERSION) {
+	ret = cros_ec_cmd_xfer_status(ec_dev, msg);
+	if (ret == -ENOTSUPP) {
 		/* With older ECs we just return 0 for everything */
 		memset(result, 0, result_size);
 		ret = 0;
-	} else if (msg->result != EC_RES_SUCCESS) {
-		dev_warn(ec_dev->dev, "Error getting info %d/%d: %d\n",
-			 (int)info_type, (int)event_type, msg->result);
-		ret = -EPROTO;
+	} else if (ret < 0) {
+		dev_warn(ec_dev->dev, "Transfer error %d/%d: %d\n",
+			 (int)info_type, (int)event_type, ret);
 	} else if (ret != result_size) {
 		dev_warn(ec_dev->dev, "Wrong size %d/%d: %d != %zu\n",
 			 (int)info_type, (int)event_type,
diff --git a/drivers/input/keyboard/dlink-dir685-touchkeys.c b/drivers/input/keyboard/dlink-dir685-touchkeys.c
index b0ead7199c40..a69dcc3bd30c 100644
--- a/drivers/input/keyboard/dlink-dir685-touchkeys.c
+++ b/drivers/input/keyboard/dlink-dir685-touchkeys.c
@@ -143,7 +143,7 @@ MODULE_DEVICE_TABLE(of, dir685_tk_of_match);
 
 static struct i2c_driver dir685_tk_i2c_driver = {
 	.driver = {
-		.name	= "dlin-dir685-touchkeys",
+		.name	= "dlink-dir685-touchkeys",
 		.of_match_table = of_match_ptr(dir685_tk_of_match),
 	},
 	.probe		= dir685_tk_probe,
diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c
index c8f87df93a50..9c6386b2af33 100644
--- a/drivers/input/misc/axp20x-pek.c
+++ b/drivers/input/misc/axp20x-pek.c
@@ -205,8 +205,11 @@ ATTRIBUTE_GROUPS(axp20x);
 
 static irqreturn_t axp20x_pek_irq(int irq, void *pwr)
 {
-	struct input_dev *idev = pwr;
-	struct axp20x_pek *axp20x_pek = input_get_drvdata(idev);
+	struct axp20x_pek *axp20x_pek = pwr;
+	struct input_dev *idev = axp20x_pek->input;
+
+	if (!idev)
+		return IRQ_HANDLED;
 
 	/*
 	 * The power-button is connected to ground so a falling edge (dbf)
@@ -225,22 +228,9 @@ static irqreturn_t axp20x_pek_irq(int irq, void *pwr)
 static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek,
 					 struct platform_device *pdev)
 {
-	struct axp20x_dev *axp20x = axp20x_pek->axp20x;
 	struct input_dev *idev;
 	int error;
 
-	axp20x_pek->irq_dbr = platform_get_irq_byname(pdev, "PEK_DBR");
-	if (axp20x_pek->irq_dbr < 0)
-		return axp20x_pek->irq_dbr;
-	axp20x_pek->irq_dbr = regmap_irq_get_virq(axp20x->regmap_irqc,
-						  axp20x_pek->irq_dbr);
-
-	axp20x_pek->irq_dbf = platform_get_irq_byname(pdev, "PEK_DBF");
-	if (axp20x_pek->irq_dbf < 0)
-		return axp20x_pek->irq_dbf;
-	axp20x_pek->irq_dbf = regmap_irq_get_virq(axp20x->regmap_irqc,
-						  axp20x_pek->irq_dbf);
-
 	axp20x_pek->input = devm_input_allocate_device(&pdev->dev);
 	if (!axp20x_pek->input)
 		return -ENOMEM;
@@ -255,24 +245,6 @@ static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek,
 
 	input_set_drvdata(idev, axp20x_pek);
 
-	error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbr,
-					     axp20x_pek_irq, 0,
-					     "axp20x-pek-dbr", idev);
-	if (error < 0) {
-		dev_err(&pdev->dev, "Failed to request dbr IRQ#%d: %d\n",
-			axp20x_pek->irq_dbr, error);
-		return error;
-	}
-
-	error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbf,
-					  axp20x_pek_irq, 0,
-					  "axp20x-pek-dbf", idev);
-	if (error < 0) {
-		dev_err(&pdev->dev, "Failed to request dbf IRQ#%d: %d\n",
-			axp20x_pek->irq_dbf, error);
-		return error;
-	}
-
 	error = input_register_device(idev);
 	if (error) {
 		dev_err(&pdev->dev, "Can't register input device: %d\n",
@@ -280,8 +252,6 @@ static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek,
 		return error;
 	}
 
-	device_init_wakeup(&pdev->dev, true);
-
 	return 0;
 }
 
@@ -339,6 +309,18 @@ static int axp20x_pek_probe(struct platform_device *pdev)
 
 	axp20x_pek->axp20x = dev_get_drvdata(pdev->dev.parent);
 
+	axp20x_pek->irq_dbr = platform_get_irq_byname(pdev, "PEK_DBR");
+	if (axp20x_pek->irq_dbr < 0)
+		return axp20x_pek->irq_dbr;
+	axp20x_pek->irq_dbr = regmap_irq_get_virq(
+			axp20x_pek->axp20x->regmap_irqc, axp20x_pek->irq_dbr);
+
+	axp20x_pek->irq_dbf = platform_get_irq_byname(pdev, "PEK_DBF");
+	if (axp20x_pek->irq_dbf < 0)
+		return axp20x_pek->irq_dbf;
+	axp20x_pek->irq_dbf = regmap_irq_get_virq(
+			axp20x_pek->axp20x->regmap_irqc, axp20x_pek->irq_dbf);
+
 	if (axp20x_pek_should_register_input(axp20x_pek, pdev)) {
 		error = axp20x_pek_probe_input_device(axp20x_pek, pdev);
 		if (error)
@@ -347,6 +329,26 @@ static int axp20x_pek_probe(struct platform_device *pdev)
 
 	axp20x_pek->info = (struct axp20x_info *)match->driver_data;
 
+	error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbr,
+					     axp20x_pek_irq, 0,
+					     "axp20x-pek-dbr", axp20x_pek);
+	if (error < 0) {
+		dev_err(&pdev->dev, "Failed to request dbr IRQ#%d: %d\n",
+			axp20x_pek->irq_dbr, error);
+		return error;
+	}
+
+	error = devm_request_any_context_irq(&pdev->dev, axp20x_pek->irq_dbf,
+					  axp20x_pek_irq, 0,
+					  "axp20x-pek-dbf", axp20x_pek);
+	if (error < 0) {
+		dev_err(&pdev->dev, "Failed to request dbf IRQ#%d: %d\n",
+			axp20x_pek->irq_dbf, error);
+		return error;
+	}
+
+	device_init_wakeup(&pdev->dev, true);
+
 	platform_set_drvdata(pdev, axp20x_pek);
 
 	return 0;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 4d2036209b45..758dae8d6500 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -170,6 +170,7 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN005b", /* P50 */
 	"LEN005e", /* T560 */
 	"LEN006c", /* T470s */
+	"LEN007a", /* T470s */
 	"LEN0071", /* T480 */
 	"LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */
 	"LEN0073", /* X1 Carbon G5 (Elantech) */
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 190b9974526b..258d5fe3d395 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -205,7 +205,7 @@ static irqreturn_t rmi_irq_fn(int irq, void *dev_id)
 
 	if (count) {
 		kfree(attn_data.data);
-		attn_data.data = NULL;
+		drvdata->attn_data.data = NULL;
 	}
 
 	if (!kfifo_is_empty(&drvdata->attn_fifo))
@@ -1210,7 +1210,8 @@ static int rmi_driver_probe(struct device *dev)
 	if (data->input) {
 		rmi_driver_set_input_name(rmi_dev, data->input);
 		if (!rmi_dev->xport->input) {
-			if (input_register_device(data->input)) {
+			retval = input_register_device(data->input);
+			if (retval) {
 				dev_err(dev, "%s: Failed to register input device.\n",
 					__func__);
 				goto err_destroy_functions;
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 08e919dbeb5d..7e048b557462 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -662,6 +662,13 @@ static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
 		},
 	},
+	{
+		/* Lenovo ThinkPad Twist S230u */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "33474HU"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c
index 14c577c16b16..2289f9638116 100644
--- a/drivers/input/touchscreen/elants_i2c.c
+++ b/drivers/input/touchscreen/elants_i2c.c
@@ -19,6 +19,7 @@
  */
 
 
+#include <linux/bits.h>
 #include <linux/module.h>
 #include <linux/input.h>
 #include <linux/interrupt.h>
@@ -73,6 +74,7 @@
 #define FW_POS_STATE		1
 #define FW_POS_TOTAL		2
 #define FW_POS_XY		3
+#define FW_POS_TOOL_TYPE	33
 #define FW_POS_CHECKSUM		34
 #define FW_POS_WIDTH		35
 #define FW_POS_PRESSURE		45
@@ -842,6 +844,7 @@ static void elants_i2c_mt_event(struct elants_data *ts, u8 *buf)
 {
 	struct input_dev *input = ts->input;
 	unsigned int n_fingers;
+	unsigned int tool_type;
 	u16 finger_state;
 	int i;
 
@@ -852,6 +855,10 @@ static void elants_i2c_mt_event(struct elants_data *ts, u8 *buf)
 	dev_dbg(&ts->client->dev,
 		"n_fingers: %u, state: %04x\n",  n_fingers, finger_state);
 
+	/* Note: all fingers have the same tool type */
+	tool_type = buf[FW_POS_TOOL_TYPE] & BIT(0) ?
+			MT_TOOL_FINGER : MT_TOOL_PALM;
+
 	for (i = 0; i < MAX_CONTACT_NUM && n_fingers; i++) {
 		if (finger_state & 1) {
 			unsigned int x, y, p, w;
@@ -867,7 +874,7 @@ static void elants_i2c_mt_event(struct elants_data *ts, u8 *buf)
 				i, x, y, p, w);
 
 			input_mt_slot(input, i);
-			input_mt_report_slot_state(input, MT_TOOL_FINGER, true);
+			input_mt_report_slot_state(input, tool_type, true);
 			input_event(input, EV_ABS, ABS_MT_POSITION_X, x);
 			input_event(input, EV_ABS, ABS_MT_POSITION_Y, y);
 			input_event(input, EV_ABS, ABS_MT_PRESSURE, p);
@@ -1307,6 +1314,8 @@ static int elants_i2c_probe(struct i2c_client *client,
 	input_set_abs_params(ts->input, ABS_MT_POSITION_Y, 0, ts->y_max, 0, 0);
 	input_set_abs_params(ts->input, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0);
 	input_set_abs_params(ts->input, ABS_MT_PRESSURE, 0, 255, 0, 0);
+	input_set_abs_params(ts->input, ABS_MT_TOOL_TYPE,
+			     0, MT_TOOL_PALM, 0, 0);
 	input_abs_set_res(ts->input, ABS_MT_POSITION_X, ts->x_res);
 	input_abs_set_res(ts->input, ABS_MT_POSITION_Y, ts->y_res);
 	input_abs_set_res(ts->input, ABS_MT_TOUCH_MAJOR, 1);
diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c
index 69c6d559eeb0..2ef1adaed9af 100644
--- a/drivers/input/touchscreen/mms114.c
+++ b/drivers/input/touchscreen/mms114.c
@@ -91,15 +91,15 @@ static int __mms114_read_reg(struct mms114_data *data, unsigned int reg,
 	if (reg <= MMS114_MODE_CONTROL && reg + len > MMS114_MODE_CONTROL)
 		BUG();
 
-	/* Write register: use repeated start */
+	/* Write register */
 	xfer[0].addr = client->addr;
-	xfer[0].flags = I2C_M_TEN | I2C_M_NOSTART;
+	xfer[0].flags = client->flags & I2C_M_TEN;
 	xfer[0].len = 1;
 	xfer[0].buf = &buf;
 
 	/* Read data */
 	xfer[1].addr = client->addr;
-	xfer[1].flags = I2C_M_RD;
+	xfer[1].flags = (client->flags & I2C_M_TEN) | I2C_M_RD;
 	xfer[1].len = len;
 	xfer[1].buf = val;
 
@@ -428,10 +428,8 @@ static int mms114_probe(struct i2c_client *client,
 	const void *match_data;
 	int error;
 
-	if (!i2c_check_functionality(client->adapter,
-				I2C_FUNC_PROTOCOL_MANGLING)) {
-		dev_err(&client->dev,
-			"Need i2c bus that supports protocol mangling\n");
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+		dev_err(&client->dev, "Not supported I2C adapter\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index 16d70201de4a..397cb1d3f481 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -182,6 +182,7 @@ static const struct usb_device_id usbtouch_devices[] = {
 #endif
 
 #ifdef CONFIG_TOUCHSCREEN_USB_IRTOUCH
+	{USB_DEVICE(0x255e, 0x0001), .driver_info = DEVTYPE_IRTOUCH},
 	{USB_DEVICE(0x595a, 0x0001), .driver_info = DEVTYPE_IRTOUCH},
 	{USB_DEVICE(0x6615, 0x0001), .driver_info = DEVTYPE_IRTOUCH},
 	{USB_DEVICE(0x6615, 0x0012), .driver_info = DEVTYPE_IRTOUCH_HIRES},
diff --git a/drivers/interconnect/qcom/bcm-voter.c b/drivers/interconnect/qcom/bcm-voter.c
index 2adfde8cdf19..2a11a63e7217 100644
--- a/drivers/interconnect/qcom/bcm-voter.c
+++ b/drivers/interconnect/qcom/bcm-voter.c
@@ -96,6 +96,8 @@ static inline void tcs_cmd_gen(struct tcs_cmd *cmd, u64 vote_x, u64 vote_y,
 	if (!cmd)
 		return;
 
+	memset(cmd, 0, sizeof(*cmd));
+
 	if (vote_x == 0 && vote_y == 0)
 		valid = false;
 
@@ -112,8 +114,7 @@ static inline void tcs_cmd_gen(struct tcs_cmd *cmd, u64 vote_x, u64 vote_y,
 	 * Set the wait for completion flag on command that need to be completed
 	 * before the next command.
 	 */
-	if (commit)
-		cmd->wait = true;
+	cmd->wait = commit;
 }
 
 static void tcs_list_gen(struct list_head *bcm_list, int bucket,
diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c
index a03c6d6833df..96fb9ff5ff2e 100644
--- a/drivers/interconnect/qcom/osm-l3.c
+++ b/drivers/interconnect/qcom/osm-l3.c
@@ -78,7 +78,7 @@ static struct qcom_icc_node *sdm845_osm_l3_nodes[] = {
 	[SLAVE_OSM_L3] = &sdm845_osm_l3,
 };
 
-const static struct qcom_icc_desc sdm845_icc_osm_l3 = {
+static const struct qcom_icc_desc sdm845_icc_osm_l3 = {
 	.nodes = sdm845_osm_l3_nodes,
 	.num_nodes = ARRAY_SIZE(sdm845_osm_l3_nodes),
 };
@@ -91,7 +91,7 @@ static struct qcom_icc_node *sc7180_osm_l3_nodes[] = {
 	[SLAVE_OSM_L3] = &sc7180_osm_l3,
 };
 
-const static struct qcom_icc_desc sc7180_icc_osm_l3 = {
+static const struct qcom_icc_desc sc7180_icc_osm_l3 = {
 	.nodes = sc7180_osm_l3_nodes,
 	.num_nodes = ARRAY_SIZE(sc7180_osm_l3_nodes),
 };
diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c
index b013b80caa45..f6c7b969520d 100644
--- a/drivers/interconnect/qcom/sdm845.c
+++ b/drivers/interconnect/qcom/sdm845.c
@@ -192,7 +192,7 @@ static struct qcom_icc_node *aggre1_noc_nodes[] = {
 	[SLAVE_ANOC_PCIE_A1NOC_SNOC] = &qns_pcie_a1noc_snoc,
 };
 
-const static struct qcom_icc_desc sdm845_aggre1_noc = {
+static const struct qcom_icc_desc sdm845_aggre1_noc = {
 	.nodes = aggre1_noc_nodes,
 	.num_nodes = ARRAY_SIZE(aggre1_noc_nodes),
 	.bcms = aggre1_noc_bcms,
@@ -220,7 +220,7 @@ static struct qcom_icc_node *aggre2_noc_nodes[] = {
 	[SLAVE_SERVICE_A2NOC] = &srvc_aggre2_noc,
 };
 
-const static struct qcom_icc_desc sdm845_aggre2_noc = {
+static const struct qcom_icc_desc sdm845_aggre2_noc = {
 	.nodes = aggre2_noc_nodes,
 	.num_nodes = ARRAY_SIZE(aggre2_noc_nodes),
 	.bcms = aggre2_noc_bcms,
@@ -281,7 +281,7 @@ static struct qcom_icc_node *config_noc_nodes[] = {
 	[SLAVE_SERVICE_CNOC] = &srvc_cnoc,
 };
 
-const static struct qcom_icc_desc sdm845_config_noc = {
+static const struct qcom_icc_desc sdm845_config_noc = {
 	.nodes = config_noc_nodes,
 	.num_nodes = ARRAY_SIZE(config_noc_nodes),
 	.bcms = config_noc_bcms,
@@ -297,7 +297,7 @@ static struct qcom_icc_node *dc_noc_nodes[] = {
 	[SLAVE_MEM_NOC_CFG] = &qhs_memnoc,
 };
 
-const static struct qcom_icc_desc sdm845_dc_noc = {
+static const struct qcom_icc_desc sdm845_dc_noc = {
 	.nodes = dc_noc_nodes,
 	.num_nodes = ARRAY_SIZE(dc_noc_nodes),
 	.bcms = dc_noc_bcms,
@@ -315,7 +315,7 @@ static struct qcom_icc_node *gladiator_noc_nodes[] = {
 	[SLAVE_SERVICE_GNOC] = &srvc_gnoc,
 };
 
-const static struct qcom_icc_desc sdm845_gladiator_noc = {
+static const struct qcom_icc_desc sdm845_gladiator_noc = {
 	.nodes = gladiator_noc_nodes,
 	.num_nodes = ARRAY_SIZE(gladiator_noc_nodes),
 	.bcms = gladiator_noc_bcms,
@@ -350,7 +350,7 @@ static struct qcom_icc_node *mem_noc_nodes[] = {
 	[SLAVE_EBI1] = &ebi,
 };
 
-const static struct qcom_icc_desc sdm845_mem_noc = {
+static const struct qcom_icc_desc sdm845_mem_noc = {
 	.nodes = mem_noc_nodes,
 	.num_nodes = ARRAY_SIZE(mem_noc_nodes),
 	.bcms = mem_noc_bcms,
@@ -384,7 +384,7 @@ static struct qcom_icc_node *mmss_noc_nodes[] = {
 	[SLAVE_CAMNOC_UNCOMP] = &qns_camnoc_uncomp,
 };
 
-const static struct qcom_icc_desc sdm845_mmss_noc = {
+static const struct qcom_icc_desc sdm845_mmss_noc = {
 	.nodes = mmss_noc_nodes,
 	.num_nodes = ARRAY_SIZE(mmss_noc_nodes),
 	.bcms = mmss_noc_bcms,
@@ -430,7 +430,7 @@ static struct qcom_icc_node *system_noc_nodes[] = {
 	[SLAVE_TCU] = &xs_sys_tcu_cfg,
 };
 
-const static struct qcom_icc_desc sdm845_system_noc = {
+static const struct qcom_icc_desc sdm845_system_noc = {
 	.nodes = system_noc_nodes,
 	.num_nodes = ARRAY_SIZE(system_noc_nodes),
 	.bcms = system_noc_bcms,
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 58b4a4dbfc78..2ab07ce17abb 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -362,7 +362,7 @@ config IPMMU_VMSA
 
 config SPAPR_TCE_IOMMU
 	bool "sPAPR TCE IOMMU Support"
-	depends on PPC_POWERNV || PPC_PSERIES || (PPC && COMPILE_TEST)
+	depends on PPC_POWERNV || PPC_PSERIES
 	select IOMMU_API
 	help
 	  Enables bits of IOMMU API required by VFIO. The iommu_ops
@@ -457,7 +457,7 @@ config S390_AP_IOMMU
 
 config MTK_IOMMU
 	bool "MTK IOMMU Support"
-	depends on ARM || ARM64 || COMPILE_TEST
+	depends on HAS_DMA
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	select ARM_DMA_USE_IOMMU
 	select IOMMU_API
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 20cce366e951..2883ac389abb 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -101,6 +101,8 @@ struct kmem_cache *amd_iommu_irq_cache;
 static void update_domain(struct protection_domain *domain);
 static int protection_domain_init(struct protection_domain *domain);
 static void detach_device(struct device *dev);
+static void update_and_flush_device_table(struct protection_domain *domain,
+					  struct domain_pgtable *pgtable);
 
 /****************************************************************************
  *
@@ -125,7 +127,8 @@ static inline int get_acpihid_device_id(struct device *dev,
 		return -ENODEV;
 
 	list_for_each_entry(p, &acpihid_map, list) {
-		if (acpi_dev_hid_uid_match(adev, p->hid, p->uid)) {
+		if (acpi_dev_hid_uid_match(adev, p->hid,
+					   p->uid[0] ? p->uid : NULL)) {
 			if (entry)
 				*entry = p;
 			return p->devid;
@@ -151,6 +154,26 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom)
 	return container_of(dom, struct protection_domain, domain);
 }
 
+static void amd_iommu_domain_get_pgtable(struct protection_domain *domain,
+					 struct domain_pgtable *pgtable)
+{
+	u64 pt_root = atomic64_read(&domain->pt_root);
+
+	pgtable->root = (u64 *)(pt_root & PAGE_MASK);
+	pgtable->mode = pt_root & 7; /* lowest 3 bits encode pgtable mode */
+}
+
+static u64 amd_iommu_domain_encode_pgtable(u64 *root, int mode)
+{
+	u64 pt_root;
+
+	/* lowest 3 bits encode pgtable mode */
+	pt_root = mode & 7;
+	pt_root |= (u64)root;
+
+	return pt_root;
+}
+
 static struct iommu_dev_data *alloc_dev_data(u16 devid)
 {
 	struct iommu_dev_data *dev_data;
@@ -1397,13 +1420,18 @@ static struct page *free_sub_pt(unsigned long root, int mode,
 
 static void free_pagetable(struct protection_domain *domain)
 {
-	unsigned long root = (unsigned long)domain->pt_root;
+	struct domain_pgtable pgtable;
 	struct page *freelist = NULL;
+	unsigned long root;
 
-	BUG_ON(domain->mode < PAGE_MODE_NONE ||
-	       domain->mode > PAGE_MODE_6_LEVEL);
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+	atomic64_set(&domain->pt_root, 0);
 
-	freelist = free_sub_pt(root, domain->mode, freelist);
+	BUG_ON(pgtable.mode < PAGE_MODE_NONE ||
+	       pgtable.mode > PAGE_MODE_6_LEVEL);
+
+	root = (unsigned long)pgtable.root;
+	freelist = free_sub_pt(root, pgtable.mode, freelist);
 
 	free_page_list(freelist);
 }
@@ -1417,24 +1445,39 @@ static bool increase_address_space(struct protection_domain *domain,
 				   unsigned long address,
 				   gfp_t gfp)
 {
+	struct domain_pgtable pgtable;
 	unsigned long flags;
-	bool ret = false;
-	u64 *pte;
+	bool ret = true;
+	u64 *pte, root;
 
 	spin_lock_irqsave(&domain->lock, flags);
 
-	if (address <= PM_LEVEL_SIZE(domain->mode) ||
-	    WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+
+	if (address <= PM_LEVEL_SIZE(pgtable.mode))
+		goto out;
+
+	ret = false;
+	if (WARN_ON_ONCE(pgtable.mode == PAGE_MODE_6_LEVEL))
 		goto out;
 
 	pte = (void *)get_zeroed_page(gfp);
 	if (!pte)
 		goto out;
 
-	*pte             = PM_LEVEL_PDE(domain->mode,
-					iommu_virt_to_phys(domain->pt_root));
-	domain->pt_root  = pte;
-	domain->mode    += 1;
+	*pte = PM_LEVEL_PDE(pgtable.mode, iommu_virt_to_phys(pgtable.root));
+
+	pgtable.root  = pte;
+	pgtable.mode += 1;
+	update_and_flush_device_table(domain, &pgtable);
+	domain_flush_complete(domain);
+
+	/*
+	 * Device Table needs to be updated and flushed before the new root can
+	 * be published.
+	 */
+	root = amd_iommu_domain_encode_pgtable(pte, pgtable.mode);
+	atomic64_set(&domain->pt_root, root);
 
 	ret = true;
 
@@ -1451,16 +1494,29 @@ static u64 *alloc_pte(struct protection_domain *domain,
 		      gfp_t gfp,
 		      bool *updated)
 {
+	struct domain_pgtable pgtable;
 	int level, end_lvl;
 	u64 *pte, *page;
 
 	BUG_ON(!is_power_of_2(page_size));
 
-	while (address > PM_LEVEL_SIZE(domain->mode))
-		*updated = increase_address_space(domain, address, gfp) || *updated;
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+
+	while (address > PM_LEVEL_SIZE(pgtable.mode)) {
+		/*
+		 * Return an error if there is no memory to update the
+		 * page-table.
+		 */
+		if (!increase_address_space(domain, address, gfp))
+			return NULL;
+
+		/* Read new values to check if update was successful */
+		amd_iommu_domain_get_pgtable(domain, &pgtable);
+	}
+
 
-	level   = domain->mode - 1;
-	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
+	level   = pgtable.mode - 1;
+	pte     = &pgtable.root[PM_LEVEL_INDEX(level, address)];
 	address = PAGE_SIZE_ALIGN(address, page_size);
 	end_lvl = PAGE_SIZE_LEVEL(page_size);
 
@@ -1536,16 +1592,19 @@ static u64 *fetch_pte(struct protection_domain *domain,
 		      unsigned long address,
 		      unsigned long *page_size)
 {
+	struct domain_pgtable pgtable;
 	int level;
 	u64 *pte;
 
 	*page_size = 0;
 
-	if (address > PM_LEVEL_SIZE(domain->mode))
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+
+	if (address > PM_LEVEL_SIZE(pgtable.mode))
 		return NULL;
 
-	level	   =  domain->mode - 1;
-	pte	   = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
+	level	   =  pgtable.mode - 1;
+	pte	   = &pgtable.root[PM_LEVEL_INDEX(level, address)];
 	*page_size =  PTE_LEVEL_PAGE_SIZE(level);
 
 	while (level > 0) {
@@ -1660,7 +1719,13 @@ out:
 		unsigned long flags;
 
 		spin_lock_irqsave(&dom->lock, flags);
-		update_domain(dom);
+		/*
+		 * Flush domain TLB(s) and wait for completion. Any Device-Table
+		 * Updates and flushing already happened in
+		 * increase_address_space().
+		 */
+		domain_flush_tlb_pde(dom);
+		domain_flush_complete(dom);
 		spin_unlock_irqrestore(&dom->lock, flags);
 	}
 
@@ -1806,6 +1871,7 @@ static void dma_ops_domain_free(struct protection_domain *domain)
 static struct protection_domain *dma_ops_domain_alloc(void)
 {
 	struct protection_domain *domain;
+	u64 *pt_root, root;
 
 	domain = kzalloc(sizeof(struct protection_domain), GFP_KERNEL);
 	if (!domain)
@@ -1814,12 +1880,14 @@ static struct protection_domain *dma_ops_domain_alloc(void)
 	if (protection_domain_init(domain))
 		goto free_domain;
 
-	domain->mode = PAGE_MODE_3_LEVEL;
-	domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
-	domain->flags = PD_DMA_OPS_MASK;
-	if (!domain->pt_root)
+	pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!pt_root)
 		goto free_domain;
 
+	root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL);
+	atomic64_set(&domain->pt_root, root);
+	domain->flags = PD_DMA_OPS_MASK;
+
 	if (iommu_get_dma_cookie(&domain->domain) == -ENOMEM)
 		goto free_domain;
 
@@ -1841,16 +1909,17 @@ static bool dma_ops_domain(struct protection_domain *domain)
 }
 
 static void set_dte_entry(u16 devid, struct protection_domain *domain,
+			  struct domain_pgtable *pgtable,
 			  bool ats, bool ppr)
 {
 	u64 pte_root = 0;
 	u64 flags = 0;
 	u32 old_domid;
 
-	if (domain->mode != PAGE_MODE_NONE)
-		pte_root = iommu_virt_to_phys(domain->pt_root);
+	if (pgtable->mode != PAGE_MODE_NONE)
+		pte_root = iommu_virt_to_phys(pgtable->root);
 
-	pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
+	pte_root |= (pgtable->mode & DEV_ENTRY_MODE_MASK)
 		    << DEV_ENTRY_MODE_SHIFT;
 	pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V | DTE_FLAG_TV;
 
@@ -1923,6 +1992,7 @@ static void clear_dte_entry(u16 devid)
 static void do_attach(struct iommu_dev_data *dev_data,
 		      struct protection_domain *domain)
 {
+	struct domain_pgtable pgtable;
 	struct amd_iommu *iommu;
 	bool ats;
 
@@ -1938,7 +2008,9 @@ static void do_attach(struct iommu_dev_data *dev_data,
 	domain->dev_cnt                 += 1;
 
 	/* Update device table */
-	set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2);
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+	set_dte_entry(dev_data->devid, domain, &pgtable,
+		      ats, dev_data->iommu_v2);
 	clone_aliases(dev_data->pdev);
 
 	device_flush_dte(dev_data);
@@ -2249,23 +2321,36 @@ static int amd_iommu_domain_get_attr(struct iommu_domain *domain,
  *
  *****************************************************************************/
 
-static void update_device_table(struct protection_domain *domain)
+static void update_device_table(struct protection_domain *domain,
+				struct domain_pgtable *pgtable)
 {
 	struct iommu_dev_data *dev_data;
 
 	list_for_each_entry(dev_data, &domain->dev_list, list) {
-		set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled,
-			      dev_data->iommu_v2);
+		set_dte_entry(dev_data->devid, domain, pgtable,
+			      dev_data->ats.enabled, dev_data->iommu_v2);
 		clone_aliases(dev_data->pdev);
 	}
 }
 
+static void update_and_flush_device_table(struct protection_domain *domain,
+					  struct domain_pgtable *pgtable)
+{
+	update_device_table(domain, pgtable);
+	domain_flush_devices(domain);
+}
+
 static void update_domain(struct protection_domain *domain)
 {
-	update_device_table(domain);
+	struct domain_pgtable pgtable;
 
-	domain_flush_devices(domain);
+	/* Update device table */
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+	update_and_flush_device_table(domain, &pgtable);
+
+	/* Flush domain TLB(s) and wait for completion */
 	domain_flush_tlb_pde(domain);
+	domain_flush_complete(domain);
 }
 
 int __init amd_iommu_init_api(void)
@@ -2375,6 +2460,7 @@ out_err:
 static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 {
 	struct protection_domain *pdomain;
+	u64 *pt_root, root;
 
 	switch (type) {
 	case IOMMU_DOMAIN_UNMANAGED:
@@ -2382,13 +2468,15 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 		if (!pdomain)
 			return NULL;
 
-		pdomain->mode    = PAGE_MODE_3_LEVEL;
-		pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
-		if (!pdomain->pt_root) {
+		pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+		if (!pt_root) {
 			protection_domain_free(pdomain);
 			return NULL;
 		}
 
+		root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL);
+		atomic64_set(&pdomain->pt_root, root);
+
 		pdomain->domain.geometry.aperture_start = 0;
 		pdomain->domain.geometry.aperture_end   = ~0ULL;
 		pdomain->domain.geometry.force_aperture = true;
@@ -2406,7 +2494,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 		if (!pdomain)
 			return NULL;
 
-		pdomain->mode = PAGE_MODE_NONE;
+		atomic64_set(&pdomain->pt_root, PAGE_MODE_NONE);
 		break;
 	default:
 		return NULL;
@@ -2418,6 +2506,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 static void amd_iommu_domain_free(struct iommu_domain *dom)
 {
 	struct protection_domain *domain;
+	struct domain_pgtable pgtable;
 
 	domain = to_pdomain(dom);
 
@@ -2435,7 +2524,9 @@ static void amd_iommu_domain_free(struct iommu_domain *dom)
 		dma_ops_domain_free(domain);
 		break;
 	default:
-		if (domain->mode != PAGE_MODE_NONE)
+		amd_iommu_domain_get_pgtable(domain, &pgtable);
+
+		if (pgtable.mode != PAGE_MODE_NONE)
 			free_pagetable(domain);
 
 		if (domain->flags & PD_IOMMUV2_MASK)
@@ -2518,10 +2609,12 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
 			 gfp_t gfp)
 {
 	struct protection_domain *domain = to_pdomain(dom);
+	struct domain_pgtable pgtable;
 	int prot = 0;
 	int ret;
 
-	if (domain->mode == PAGE_MODE_NONE)
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+	if (pgtable.mode == PAGE_MODE_NONE)
 		return -EINVAL;
 
 	if (iommu_prot & IOMMU_READ)
@@ -2541,8 +2634,10 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 			      struct iommu_iotlb_gather *gather)
 {
 	struct protection_domain *domain = to_pdomain(dom);
+	struct domain_pgtable pgtable;
 
-	if (domain->mode == PAGE_MODE_NONE)
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+	if (pgtable.mode == PAGE_MODE_NONE)
 		return 0;
 
 	return iommu_unmap_page(domain, iova, page_size);
@@ -2553,9 +2648,11 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long offset_mask, pte_pgsize;
+	struct domain_pgtable pgtable;
 	u64 *pte, __pte;
 
-	if (domain->mode == PAGE_MODE_NONE)
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+	if (pgtable.mode == PAGE_MODE_NONE)
 		return iova;
 
 	pte = fetch_pte(domain, iova, &pte_pgsize);
@@ -2708,16 +2805,26 @@ EXPORT_SYMBOL(amd_iommu_unregister_ppr_notifier);
 void amd_iommu_domain_direct_map(struct iommu_domain *dom)
 {
 	struct protection_domain *domain = to_pdomain(dom);
+	struct domain_pgtable pgtable;
 	unsigned long flags;
+	u64 pt_root;
 
 	spin_lock_irqsave(&domain->lock, flags);
 
+	/* First save pgtable configuration*/
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+
 	/* Update data structure */
-	domain->mode    = PAGE_MODE_NONE;
+	pt_root = amd_iommu_domain_encode_pgtable(NULL, PAGE_MODE_NONE);
+	atomic64_set(&domain->pt_root, pt_root);
 
 	/* Make changes visible to IOMMUs */
 	update_domain(domain);
 
+	/* Restore old pgtable in domain->ptroot to free page-table */
+	pt_root = amd_iommu_domain_encode_pgtable(pgtable.root, pgtable.mode);
+	atomic64_set(&domain->pt_root, pt_root);
+
 	/* Page-table is not visible to IOMMU anymore, so free it */
 	free_pagetable(domain);
 
@@ -2908,9 +3015,11 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
 static int __set_gcr3(struct protection_domain *domain, int pasid,
 		      unsigned long cr3)
 {
+	struct domain_pgtable pgtable;
 	u64 *pte;
 
-	if (domain->mode != PAGE_MODE_NONE)
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+	if (pgtable.mode != PAGE_MODE_NONE)
 		return -EINVAL;
 
 	pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, true);
@@ -2924,9 +3033,11 @@ static int __set_gcr3(struct protection_domain *domain, int pasid,
 
 static int __clear_gcr3(struct protection_domain *domain, int pasid)
 {
+	struct domain_pgtable pgtable;
 	u64 *pte;
 
-	if (domain->mode != PAGE_MODE_NONE)
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+	if (pgtable.mode != PAGE_MODE_NONE)
 		return -EINVAL;
 
 	pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, false);
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 6be3853a5d97..5b81fd16f5fa 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1329,8 +1329,8 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 		}
 		case IVHD_DEV_ACPI_HID: {
 			u16 devid;
-			u8 hid[ACPIHID_HID_LEN] = {0};
-			u8 uid[ACPIHID_UID_LEN] = {0};
+			u8 hid[ACPIHID_HID_LEN];
+			u8 uid[ACPIHID_UID_LEN];
 			int ret;
 
 			if (h->type != 0x40) {
@@ -1347,6 +1347,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 				break;
 			}
 
+			uid[0] = '\0';
 			switch (e->uidf) {
 			case UID_NOT_PRESENT:
 
@@ -1361,8 +1362,8 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 				break;
 			case UID_IS_CHARACTER:
 
-				memcpy(uid, (u8 *)(&e->uid), ACPIHID_UID_LEN - 1);
-				uid[ACPIHID_UID_LEN - 1] = '\0';
+				memcpy(uid, &e->uid, e->uidl);
+				uid[e->uidl] = '\0';
 
 				break;
 			default:
@@ -2936,7 +2937,7 @@ static int __init parse_amd_iommu_intr(char *str)
 {
 	for (; *str; ++str) {
 		if (strncmp(str, "legacy", 6) == 0) {
-			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
 			break;
 		}
 		if (strncmp(str, "vapic", 5) == 0) {
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index ca8c4522045b..7a8fdec138bd 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -468,8 +468,7 @@ struct protection_domain {
 				       iommu core code */
 	spinlock_t lock;	/* mostly used to lock the page table*/
 	u16 id;			/* the domain id written to the device table */
-	int mode;		/* paging mode (0-6 levels) */
-	u64 *pt_root;		/* page table root pointer */
+	atomic64_t pt_root;	/* pgtable root and pgtable mode */
 	int glx;		/* Number of levels for GCR3 table */
 	u64 *gcr3_tbl;		/* Guest CR3 table */
 	unsigned long flags;	/* flags to find out type of domain */
@@ -477,6 +476,12 @@ struct protection_domain {
 	unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */
 };
 
+/* For decocded pt_root */
+struct domain_pgtable {
+	int mode;
+	u64 *root;
+};
+
 /*
  * Structure where we save information about one hardware AMD IOMMU in the
  * system.
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index ef0a5246700e..0182cff2c7ac 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -371,11 +371,11 @@ int dmar_disabled = 0;
 int dmar_disabled = 1;
 #endif /* CONFIG_INTEL_IOMMU_DEFAULT_ON */
 
-#ifdef INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
+#ifdef CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
 int intel_iommu_sm = 1;
 #else
 int intel_iommu_sm;
-#endif /* INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON */
+#endif /* CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON */
 
 int intel_iommu_enabled = 0;
 EXPORT_SYMBOL_GPL(intel_iommu_enabled);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 2b471419e26c..03d6a26687bc 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -170,6 +170,7 @@ static struct dev_iommu *dev_iommu_get(struct device *dev)
 
 static void dev_iommu_free(struct device *dev)
 {
+	iommu_fwspec_free(dev);
 	kfree(dev->iommu);
 	dev->iommu = NULL;
 }
@@ -509,7 +510,7 @@ struct iommu_group *iommu_group_alloc(void)
 				   NULL, "%d", group->id);
 	if (ret) {
 		ida_simple_remove(&iommu_group_ida, group->id);
-		kfree(group);
+		kobject_put(&group->kobj);
 		return ERR_PTR(ret);
 	}
 
@@ -692,6 +693,15 @@ out:
 	return ret;
 }
 
+static bool iommu_is_attach_deferred(struct iommu_domain *domain,
+				     struct device *dev)
+{
+	if (domain->ops->is_attach_deferred)
+		return domain->ops->is_attach_deferred(domain, dev);
+
+	return false;
+}
+
 /**
  * iommu_group_add_device - add a device to an iommu group
  * @group: the group into which to add the device (reference should be held)
@@ -746,7 +756,7 @@ rename:
 
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
-	if (group->domain)
+	if (group->domain  && !iommu_is_attach_deferred(group->domain, dev))
 		ret = __iommu_attach_device(group->domain, dev);
 	mutex_unlock(&group->mutex);
 	if (ret)
@@ -1428,7 +1438,7 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 
 	return group;
 }
-EXPORT_SYMBOL(iommu_group_get_for_dev);
+EXPORT_SYMBOL_GPL(iommu_group_get_for_dev);
 
 struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
 {
@@ -1652,9 +1662,6 @@ static int __iommu_attach_device(struct iommu_domain *domain,
 				 struct device *dev)
 {
 	int ret;
-	if ((domain->ops->is_attach_deferred != NULL) &&
-	    domain->ops->is_attach_deferred(domain, dev))
-		return 0;
 
 	if (unlikely(domain->ops->attach_dev == NULL))
 		return -ENODEV;
@@ -1726,8 +1733,7 @@ EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
 {
-	if ((domain->ops->is_attach_deferred != NULL) &&
-	    domain->ops->is_attach_deferred(domain, dev))
+	if (iommu_is_attach_deferred(domain, dev))
 		return;
 
 	if (unlikely(domain->ops->detach_dev == NULL))
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 0e2a96467767..5b3b270972f8 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -824,8 +824,11 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
 	qcom_iommu->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res)
+	if (res) {
 		qcom_iommu->local_base = devm_ioremap_resource(dev, res);
+		if (IS_ERR(qcom_iommu->local_base))
+			return PTR_ERR(qcom_iommu->local_base);
+	}
 
 	qcom_iommu->iface_clk = devm_clk_get(dev, "iface");
 	if (IS_ERR(qcom_iommu->iface_clk)) {
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index d5cac4f46ca5..4e1d11af23c8 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -453,7 +453,7 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev,
 	if (!region)
 		return -ENOMEM;
 
-	list_add(&vdev->resv_regions, &region->list);
+	list_add(&region->list, &vdev->resv_regions);
 	return 0;
 }
 
diff --git a/drivers/ipack/carriers/tpci200.c b/drivers/ipack/carriers/tpci200.c
index 23445ebfda5c..ec71063fff76 100644
--- a/drivers/ipack/carriers/tpci200.c
+++ b/drivers/ipack/carriers/tpci200.c
@@ -306,6 +306,7 @@ static int tpci200_register(struct tpci200_board *tpci200)
 			"(bn 0x%X, sn 0x%X) failed to map driver user space!",
 			tpci200->info->pdev->bus->number,
 			tpci200->info->pdev->devfn);
+		res = -ENOMEM;
 		goto out_release_mem8_space;
 	}
 
diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c
index eb9bce93cd05..fd7c537fb42a 100644
--- a/drivers/irqchip/irq-bcm7038-l1.c
+++ b/drivers/irqchip/irq-bcm7038-l1.c
@@ -416,7 +416,7 @@ static const struct irq_domain_ops bcm7038_l1_domain_ops = {
 	.map			= bcm7038_l1_map,
 };
 
-int __init bcm7038_l1_of_init(struct device_node *dn,
+static int __init bcm7038_l1_of_init(struct device_node *dn,
 			      struct device_node *parent)
 {
 	struct bcm7038_l1_chip *intc;
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 54d142ccc63a..124251b0ccba 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -14,6 +14,7 @@
 #include <linux/dma-iommu.h>
 #include <linux/efi.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 #include <linux/irqdomain.h>
 #include <linux/list.h>
 #include <linux/log2.h>
@@ -3672,6 +3673,20 @@ out:
 	return IRQ_SET_MASK_OK_DONE;
 }
 
+static void its_wait_vpt_parse_complete(void)
+{
+	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val;
+
+	if (!gic_rdists->has_vpend_valid_dirty)
+		return;
+
+	WARN_ON_ONCE(readq_relaxed_poll_timeout(vlpi_base + GICR_VPENDBASER,
+						val,
+						!(val & GICR_VPENDBASER_Dirty),
+						10, 500));
+}
+
 static void its_vpe_schedule(struct its_vpe *vpe)
 {
 	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
@@ -3702,6 +3717,8 @@ static void its_vpe_schedule(struct its_vpe *vpe)
 	val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0;
 	val |= GICR_VPENDBASER_Valid;
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_deschedule(struct its_vpe *vpe)
@@ -3910,6 +3927,8 @@ static void its_vpe_4_1_schedule(struct its_vpe *vpe,
 	val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id);
 
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
@@ -4035,6 +4054,7 @@ static int its_sgi_set_affinity(struct irq_data *d,
 	 * not on the host (since they can only be targetting a vPE).
 	 * Tell the kernel we've done whatever it asked for.
 	 */
+	irq_data_update_effective_affinity(d, mask_val);
 	return IRQ_SET_MASK_OK;
 }
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 9dbc81b6f62e..d7006ef18a0d 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -873,6 +873,7 @@ static int __gic_update_rdist_properties(struct redist_region *region,
 	gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID);
 	gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) |
 					   gic_data.rdists.has_rvpeid);
+	gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY);
 
 	/* Detect non-sensical configurations */
 	if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) {
@@ -893,10 +894,11 @@ static void gic_update_rdist_properties(void)
 	if (WARN_ON(gic_data.ppi_nr == UINT_MAX))
 		gic_data.ppi_nr = 0;
 	pr_info("%d PPIs implemented\n", gic_data.ppi_nr);
-	pr_info("%sVLPI support, %sdirect LPI support, %sRVPEID support\n",
-		!gic_data.rdists.has_vlpis ? "no " : "",
-		!gic_data.rdists.has_direct_lpi ? "no " : "",
-		!gic_data.rdists.has_rvpeid ? "no " : "");
+	if (gic_data.rdists.has_vlpis)
+		pr_info("GICv4 features: %s%s%s\n",
+			gic_data.rdists.has_direct_lpi ? "DirectLPI " : "",
+			gic_data.rdists.has_rvpeid ? "RVPEID " : "",
+			gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : "");
 }
 
 /* Check whether it's single security state view */
@@ -1620,6 +1622,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	gic_data.rdists.has_rvpeid = true;
 	gic_data.rdists.has_vlpis = true;
 	gic_data.rdists.has_direct_lpi = true;
+	gic_data.rdists.has_vpend_valid_dirty = true;
 
 	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) {
 		err = -ENOMEM;
diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
index 6b566bba263b..ff7627b57772 100644
--- a/drivers/irqchip/irq-mbigen.c
+++ b/drivers/irqchip/irq-mbigen.c
@@ -220,10 +220,16 @@ static int mbigen_irq_domain_alloc(struct irq_domain *domain,
 	return 0;
 }
 
+static void mbigen_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+				   unsigned int nr_irqs)
+{
+	platform_msi_domain_free(domain, virq, nr_irqs);
+}
+
 static const struct irq_domain_ops mbigen_domain_ops = {
 	.translate	= mbigen_domain_translate,
 	.alloc		= mbigen_irq_domain_alloc,
-	.free		= irq_domain_free_irqs_common,
+	.free		= mbigen_irq_domain_free,
 };
 
 static int mbigen_of_create_domain(struct platform_device *pdev,
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index ccc7f823911b..bc7aebcc96e9 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -144,12 +144,17 @@ struct meson_gpio_irq_controller {
 static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl,
 				       unsigned int reg, u32 mask, u32 val)
 {
+	unsigned long flags;
 	u32 tmp;
 
+	spin_lock_irqsave(&ctl->lock, flags);
+
 	tmp = readl_relaxed(ctl->base + reg);
 	tmp &= ~mask;
 	tmp |= val;
 	writel_relaxed(tmp, ctl->base + reg);
+
+	spin_unlock_irqrestore(&ctl->lock, flags);
 }
 
 static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl)
@@ -196,14 +201,15 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 			       unsigned long  hwirq,
 			       u32 **channel_hwirq)
 {
+	unsigned long flags;
 	unsigned int idx;
 
-	spin_lock(&ctl->lock);
+	spin_lock_irqsave(&ctl->lock, flags);
 
 	/* Find a free channel */
 	idx = find_first_zero_bit(ctl->channel_map, NUM_CHANNEL);
 	if (idx >= NUM_CHANNEL) {
-		spin_unlock(&ctl->lock);
+		spin_unlock_irqrestore(&ctl->lock, flags);
 		pr_err("No channel available\n");
 		return -ENOSPC;
 	}
@@ -211,6 +217,8 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 	/* Mark the channel as used */
 	set_bit(idx, ctl->channel_map);
 
+	spin_unlock_irqrestore(&ctl->lock, flags);
+
 	/*
 	 * Setup the mux of the channel to route the signal of the pad
 	 * to the appropriate input of the GIC
@@ -225,8 +233,6 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
 	 */
 	*channel_hwirq = &(ctl->channel_irqs[idx]);
 
-	spin_unlock(&ctl->lock);
-
 	pr_debug("hwirq %lu assigned to channel %d - irq %u\n",
 		 hwirq, idx, **channel_hwirq);
 
@@ -287,13 +293,9 @@ static int meson_gpio_irq_type_setup(struct meson_gpio_irq_controller *ctl,
 			val |= REG_EDGE_POL_LOW(params, idx);
 	}
 
-	spin_lock(&ctl->lock);
-
 	meson_gpio_irq_update_bits(ctl, REG_EDGE_POL,
 				   REG_EDGE_POL_MASK(params, idx), val);
 
-	spin_unlock(&ctl->lock);
-
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c
index 547045d89c4b..91adf771f185 100644
--- a/drivers/irqchip/irq-mvebu-icu.c
+++ b/drivers/irqchip/irq-mvebu-icu.c
@@ -66,7 +66,7 @@ struct mvebu_icu_irq_data {
 	unsigned int type;
 };
 
-DEFINE_STATIC_KEY_FALSE(legacy_bindings);
+static DEFINE_STATIC_KEY_FALSE(legacy_bindings);
 
 static void mvebu_icu_init(struct mvebu_icu *icu,
 			   struct mvebu_icu_msi_data *msi_data,
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index c34fb3ae0ff8..d0a71febdadc 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -56,7 +56,7 @@
 #define     CONTEXT_THRESHOLD		0x00
 #define     CONTEXT_CLAIM		0x04
 
-#define	PLIC_DISABLE_THRESHOLD		0xf
+#define	PLIC_DISABLE_THRESHOLD		0x7
 #define	PLIC_ENABLE_THRESHOLD		0
 
 struct plic_priv {
diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c
index 8f6e6b08eadf..7e3ebf6ed2cd 100644
--- a/drivers/irqchip/irq-ti-sci-inta.c
+++ b/drivers/irqchip/irq-ti-sci-inta.c
@@ -37,6 +37,7 @@
 #define VINT_ENABLE_SET_OFFSET	0x0
 #define VINT_ENABLE_CLR_OFFSET	0x8
 #define VINT_STATUS_OFFSET	0x18
+#define VINT_STATUS_MASKED_OFFSET	0x20
 
 /**
  * struct ti_sci_inta_event_desc - Description of an event coming to
@@ -116,7 +117,7 @@ static void ti_sci_inta_irq_handler(struct irq_desc *desc)
 	chained_irq_enter(irq_desc_get_chip(desc), desc);
 
 	val = readq_relaxed(inta->base + vint_desc->vint_id * 0x1000 +
-			    VINT_STATUS_OFFSET);
+			    VINT_STATUS_MASKED_OFFSET);
 
 	for_each_set_bit(bit, &val, MAX_EVENTS_PER_VINT) {
 		virq = irq_find_mapping(domain, vint_desc->events[bit].hwirq);
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index e325e87c0593..11e8c7d8b6e8 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -743,10 +743,10 @@ check_send(struct isar_hw *isar, u8 rdm)
 	}
 }
 
-const char *dmril[] = {"NO SPEED", "1200/75", "NODEF2", "75/1200", "NODEF4",
+static const char *dmril[] = {"NO SPEED", "1200/75", "NODEF2", "75/1200", "NODEF4",
 		       "300", "600", "1200", "2400", "4800", "7200",
 		       "9600nt", "9600t", "12000", "14400", "WRONG"};
-const char *dmrim[] = {"NO MOD", "NO DEF", "V32/V32b", "V22", "V21",
+static const char *dmrim[] = {"NO MOD", "NO DEF", "V32/V32b", "V22", "V21",
 		       "Bell103", "V23", "Bell202", "V17", "V29", "V27ter"};
 
 static void
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 58fd137b6ae1..3e500098132f 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -585,10 +585,12 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio)
 
 	/* Do we need to select a new pgpath? */
 	pgpath = READ_ONCE(m->current_pgpath);
-	queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
-	if (!pgpath || !queue_io)
+	if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags))
 		pgpath = choose_pgpath(m, bio->bi_iter.bi_size);
 
+	/* MPATHF_QUEUE_IO might have been cleared by choose_pgpath. */
+	queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
+
 	if ((pgpath && queue_io) ||
 	    (!pgpath && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))) {
 		/* Queue for the daemon to resubmit */
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 49147e634046..fb41b4f23c48 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -435,7 +435,7 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io,
 	fio->level++;
 
 	if (type == DM_VERITY_BLOCK_TYPE_METADATA)
-		block += v->data_blocks;
+		block = block - v->hash_start + v->data_blocks;
 
 	/*
 	 * For RS(M, N), the continuous FEC data is divided into blocks of N
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 114927da9cc9..613c171b1b6d 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -931,6 +931,24 @@ static int writecache_alloc_entries(struct dm_writecache *wc)
 	return 0;
 }
 
+static int writecache_read_metadata(struct dm_writecache *wc, sector_t n_sectors)
+{
+	struct dm_io_region region;
+	struct dm_io_request req;
+
+	region.bdev = wc->ssd_dev->bdev;
+	region.sector = wc->start_sector;
+	region.count = n_sectors;
+	req.bi_op = REQ_OP_READ;
+	req.bi_op_flags = REQ_SYNC;
+	req.mem.type = DM_IO_VMA;
+	req.mem.ptr.vma = (char *)wc->memory_map;
+	req.client = wc->dm_io;
+	req.notify.fn = NULL;
+
+	return dm_io(&req, 1, &region, NULL);
+}
+
 static void writecache_resume(struct dm_target *ti)
 {
 	struct dm_writecache *wc = ti->private;
@@ -941,8 +959,18 @@ static void writecache_resume(struct dm_target *ti)
 
 	wc_lock(wc);
 
-	if (WC_MODE_PMEM(wc))
+	if (WC_MODE_PMEM(wc)) {
 		persistent_memory_invalidate_cache(wc->memory_map, wc->memory_map_size);
+	} else {
+		r = writecache_read_metadata(wc, wc->metadata_sectors);
+		if (r) {
+			size_t sb_entries_offset;
+			writecache_error(wc, r, "unable to read metadata: %d", r);
+			sb_entries_offset = offsetof(struct wc_memory_superblock, entries);
+			memset((char *)wc->memory_map + sb_entries_offset, -1,
+			       (wc->metadata_sectors << SECTOR_SHIFT) - sb_entries_offset);
+		}
+	}
 
 	wc->tree = RB_ROOT;
 	INIT_LIST_HEAD(&wc->lru);
@@ -2102,6 +2130,12 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		ti->error = "Invalid block size";
 		goto bad;
 	}
+	if (wc->block_size < bdev_logical_block_size(wc->dev->bdev) ||
+	    wc->block_size < bdev_logical_block_size(wc->ssd_dev->bdev)) {
+		r = -EINVAL;
+		ti->error = "Block size is smaller than device logical block size";
+		goto bad;
+	}
 	wc->block_size_bits = __ffs(wc->block_size);
 
 	wc->max_writeback_jobs = MAX_WRITEBACK_JOBS;
@@ -2200,8 +2234,6 @@ invalid_optional:
 			goto bad;
 		}
 	} else {
-		struct dm_io_region region;
-		struct dm_io_request req;
 		size_t n_blocks, n_metadata_blocks;
 		uint64_t n_bitmap_bits;
 
@@ -2258,19 +2290,9 @@ invalid_optional:
 			goto bad;
 		}
 
-		region.bdev = wc->ssd_dev->bdev;
-		region.sector = wc->start_sector;
-		region.count = wc->metadata_sectors;
-		req.bi_op = REQ_OP_READ;
-		req.bi_op_flags = REQ_SYNC;
-		req.mem.type = DM_IO_VMA;
-		req.mem.ptr.vma = (char *)wc->memory_map;
-		req.client = wc->dm_io;
-		req.notify.fn = NULL;
-
-		r = dm_io(&req, 1, &region, NULL);
+		r = writecache_read_metadata(wc, wc->block_size >> SECTOR_SHIFT);
 		if (r) {
-			ti->error = "Unable to read metadata";
+			ti->error = "Unable to read first block of metadata";
 			goto bad;
 		}
 	}
diff --git a/drivers/media/cec/cec-notifier.c b/drivers/media/cec/cec-notifier.c
index e748cd54b45d..517e0035fc99 100644
--- a/drivers/media/cec/cec-notifier.c
+++ b/drivers/media/cec/cec-notifier.c
@@ -2,7 +2,7 @@
 /*
  * cec-notifier.c - notify CEC drivers of physical address changes
  *
- * Copyright 2016 Russell King <rmk+kernel@arm.linux.org.uk>
+ * Copyright 2016 Russell King.
  * Copyright 2016-2017 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
  */
 
diff --git a/drivers/media/usb/pulse8-cec/pulse8-cec.c b/drivers/media/usb/pulse8-cec/pulse8-cec.c
index 0655aa9ecf28..beae6aa12638 100644
--- a/drivers/media/usb/pulse8-cec/pulse8-cec.c
+++ b/drivers/media/usb/pulse8-cec/pulse8-cec.c
@@ -661,7 +661,6 @@ static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio,
 	u8 *data = pulse8->data + 1;
 	u8 cmd[2];
 	int err;
-	struct tm tm;
 	time64_t date;
 
 	pulse8->vers = 0;
@@ -682,10 +681,7 @@ static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio,
 	if (err)
 		return err;
 	date = (data[0] << 24) | (data[1] << 16) | (data[2] << 8) | data[3];
-	time64_to_tm(date, 0, &tm);
-	dev_info(pulse8->dev, "Firmware build date %04ld.%02d.%02d %02d:%02d:%02d\n",
-		 tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
-		 tm.tm_hour, tm.tm_min, tm.tm_sec);
+	dev_info(pulse8->dev, "Firmware build date %ptT\n", &date);
 
 	dev_dbg(pulse8->dev, "Persistent config:\n");
 	cmd[0] = MSGCODE_GET_AUTO_ENABLED;
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 0a59249198d3..05448e78e5b8 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -407,6 +407,21 @@ config MFD_EXYNOS_LPASS
 	  Select this option to enable support for Samsung Exynos Low Power
 	  Audio Subsystem.
 
+config MFD_GATEWORKS_GSC
+	tristate "Gateworks System Controller"
+	depends on (I2C && OF)
+	select MFD_CORE
+	select REGMAP_I2C
+	select REGMAP_IRQ
+	help
+	  Enable support for the Gateworks System Controller (GSC) found
+	  on Gateworks Single Board Computers supporting system functions
+	  such as push-button monitor, multiple ADC's for voltage and
+	  temperature monitoring, fan controller and watchdog monitor.
+	  This driver provides common support for accessing the device.
+	  Additional drivers must be enabled in order to use the
+	  functionality of the device.
+
 config MFD_MC13XXX
 	tristate
 	depends on (SPI_MASTER || I2C)
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index f935d10cbf0f..ed433aed7010 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_MFD_BCM590XX)	+= bcm590xx.o
 obj-$(CONFIG_MFD_BD9571MWV)	+= bd9571mwv.o
 obj-$(CONFIG_MFD_CROS_EC_DEV)	+= cros_ec_dev.o
 obj-$(CONFIG_MFD_EXYNOS_LPASS)	+= exynos-lpass.o
+obj-$(CONFIG_MFD_GATEWORKS_GSC)	+= gateworks-gsc.o
 
 obj-$(CONFIG_HTC_PASIC3)	+= htc-pasic3.o
 obj-$(CONFIG_HTC_I2CPLD)	+= htc-i2cpld.o
diff --git a/drivers/mfd/gateworks-gsc.c b/drivers/mfd/gateworks-gsc.c
new file mode 100644
index 000000000000..576da62fbb0c
--- /dev/null
+++ b/drivers/mfd/gateworks-gsc.c
@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * The Gateworks System Controller (GSC) is a multi-function
+ * device designed for use in Gateworks Single Board Computers.
+ * The control interface is I2C, with an interrupt. The device supports
+ * system functions such as push-button monitoring, multiple ADC's for
+ * voltage and temperature monitoring, fan controller and watchdog monitor.
+ *
+ * Copyright (C) 2020 Gateworks Corporation
+ */
+
+#include <linux/device.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/gsc.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <asm/unaligned.h>
+
+/*
+ * The GSC suffers from an errata where occasionally during
+ * ADC cycles the chip can NAK I2C transactions. To ensure we have reliable
+ * register access we place retries around register access.
+ */
+#define I2C_RETRIES	3
+
+int gsc_write(void *context, unsigned int reg, unsigned int val)
+{
+	struct i2c_client *client = context;
+	int retry, ret;
+
+	for (retry = 0; retry < I2C_RETRIES; retry++) {
+		ret = i2c_smbus_write_byte_data(client, reg, val);
+		/*
+		 * -EAGAIN returned when the i2c host controller is busy
+		 * -EIO returned when i2c device is busy
+		 */
+		if (ret != -EAGAIN && ret != -EIO)
+			break;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gsc_write);
+
+int gsc_read(void *context, unsigned int reg, unsigned int *val)
+{
+	struct i2c_client *client = context;
+	int retry, ret;
+
+	for (retry = 0; retry < I2C_RETRIES; retry++) {
+		ret = i2c_smbus_read_byte_data(client, reg);
+		/*
+		 * -EAGAIN returned when the i2c host controller is busy
+		 * -EIO returned when i2c device is busy
+		 */
+		if (ret != -EAGAIN && ret != -EIO)
+			break;
+	}
+	*val = ret & 0xff;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gsc_read);
+
+/*
+ * gsc_powerdown - API to use GSC to power down board for a specific time
+ *
+ * secs - number of seconds to remain powered off
+ */
+static int gsc_powerdown(struct gsc_dev *gsc, unsigned long secs)
+{
+	int ret;
+	unsigned char regs[4];
+
+	dev_info(&gsc->i2c->dev, "GSC powerdown for %ld seconds\n",
+		 secs);
+
+	put_unaligned_le32(secs, regs);
+	ret = regmap_bulk_write(gsc->regmap, GSC_TIME_ADD, regs, 4);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(gsc->regmap, GSC_CTRL_1,
+				 BIT(GSC_CTRL_1_SLEEP_ADD),
+				 BIT(GSC_CTRL_1_SLEEP_ADD));
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(gsc->regmap, GSC_CTRL_1,
+				 BIT(GSC_CTRL_1_SLEEP_ACTIVATE) |
+				 BIT(GSC_CTRL_1_SLEEP_ENABLE),
+				 BIT(GSC_CTRL_1_SLEEP_ACTIVATE) |
+				 BIT(GSC_CTRL_1_SLEEP_ENABLE));
+
+
+	return ret;
+}
+
+static ssize_t gsc_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct gsc_dev *gsc = dev_get_drvdata(dev);
+	const char *name = attr->attr.name;
+	int rz = 0;
+
+	if (strcasecmp(name, "fw_version") == 0)
+		rz = sprintf(buf, "%d\n", gsc->fwver);
+	else if (strcasecmp(name, "fw_crc") == 0)
+		rz = sprintf(buf, "0x%04x\n", gsc->fwcrc);
+	else
+		dev_err(dev, "invalid command: '%s'\n", name);
+
+	return rz;
+}
+
+static ssize_t gsc_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
+{
+	struct gsc_dev *gsc = dev_get_drvdata(dev);
+	const char *name = attr->attr.name;
+	long value;
+
+	if (strcasecmp(name, "powerdown") == 0) {
+		if (kstrtol(buf, 0, &value) == 0)
+			gsc_powerdown(gsc, value);
+	} else {
+		dev_err(dev, "invalid command: '%s\n", name);
+	}
+
+	return count;
+}
+
+static struct device_attribute attr_fwver =
+	__ATTR(fw_version, 0440, gsc_show, NULL);
+static struct device_attribute attr_fwcrc =
+	__ATTR(fw_crc, 0440, gsc_show, NULL);
+static struct device_attribute attr_pwrdown =
+	__ATTR(powerdown, 0220, NULL, gsc_store);
+
+static struct attribute *gsc_attrs[] = {
+	&attr_fwver.attr,
+	&attr_fwcrc.attr,
+	&attr_pwrdown.attr,
+	NULL,
+};
+
+static struct attribute_group attr_group = {
+	.attrs = gsc_attrs,
+};
+
+static const struct of_device_id gsc_of_match[] = {
+	{ .compatible = "gw,gsc", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, gsc_of_match);
+
+static struct regmap_bus gsc_regmap_bus = {
+	.reg_read = gsc_read,
+	.reg_write = gsc_write,
+};
+
+static const struct regmap_config gsc_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.cache_type = REGCACHE_NONE,
+	.max_register = GSC_WP,
+};
+
+static const struct regmap_irq gsc_irqs[] = {
+	REGMAP_IRQ_REG(GSC_IRQ_PB, 0, BIT(GSC_IRQ_PB)),
+	REGMAP_IRQ_REG(GSC_IRQ_KEY_ERASED, 0, BIT(GSC_IRQ_KEY_ERASED)),
+	REGMAP_IRQ_REG(GSC_IRQ_EEPROM_WP, 0, BIT(GSC_IRQ_EEPROM_WP)),
+	REGMAP_IRQ_REG(GSC_IRQ_RESV, 0, BIT(GSC_IRQ_RESV)),
+	REGMAP_IRQ_REG(GSC_IRQ_GPIO, 0, BIT(GSC_IRQ_GPIO)),
+	REGMAP_IRQ_REG(GSC_IRQ_TAMPER, 0, BIT(GSC_IRQ_TAMPER)),
+	REGMAP_IRQ_REG(GSC_IRQ_WDT_TIMEOUT, 0, BIT(GSC_IRQ_WDT_TIMEOUT)),
+	REGMAP_IRQ_REG(GSC_IRQ_SWITCH_HOLD, 0, BIT(GSC_IRQ_SWITCH_HOLD)),
+};
+
+static const struct regmap_irq_chip gsc_irq_chip = {
+	.name = "gateworks-gsc",
+	.irqs = gsc_irqs,
+	.num_irqs = ARRAY_SIZE(gsc_irqs),
+	.num_regs = 1,
+	.status_base = GSC_IRQ_STATUS,
+	.mask_base = GSC_IRQ_ENABLE,
+	.mask_invert = true,
+	.ack_base = GSC_IRQ_STATUS,
+	.ack_invert = true,
+};
+
+static int gsc_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct gsc_dev *gsc;
+	struct regmap_irq_chip_data *irq_data;
+	int ret;
+	unsigned int reg;
+
+	gsc = devm_kzalloc(dev, sizeof(*gsc), GFP_KERNEL);
+	if (!gsc)
+		return -ENOMEM;
+
+	gsc->dev = &client->dev;
+	gsc->i2c = client;
+	i2c_set_clientdata(client, gsc);
+
+	gsc->regmap = devm_regmap_init(dev, &gsc_regmap_bus, client,
+				       &gsc_regmap_config);
+	if (IS_ERR(gsc->regmap))
+		return PTR_ERR(gsc->regmap);
+
+	if (regmap_read(gsc->regmap, GSC_FW_VER, &reg))
+		return -EIO;
+	gsc->fwver = reg;
+
+	regmap_read(gsc->regmap, GSC_FW_CRC, &reg);
+	gsc->fwcrc = reg;
+	regmap_read(gsc->regmap, GSC_FW_CRC + 1, &reg);
+	gsc->fwcrc |= reg << 8;
+
+	gsc->i2c_hwmon = devm_i2c_new_dummy_device(dev, client->adapter,
+						   GSC_HWMON);
+	if (IS_ERR(gsc->i2c_hwmon)) {
+		dev_err(dev, "Failed to allocate I2C device for HWMON\n");
+		return PTR_ERR(gsc->i2c_hwmon);
+	}
+
+	ret = devm_regmap_add_irq_chip(dev, gsc->regmap, client->irq,
+				       IRQF_ONESHOT | IRQF_SHARED |
+				       IRQF_TRIGGER_FALLING, 0,
+				       &gsc_irq_chip, &irq_data);
+	if (ret)
+		return ret;
+
+	dev_info(dev, "Gateworks System Controller v%d: fw 0x%04x\n",
+		 gsc->fwver, gsc->fwcrc);
+
+	ret = sysfs_create_group(&dev->kobj, &attr_group);
+	if (ret)
+		dev_err(dev, "failed to create sysfs attrs\n");
+
+	ret = devm_of_platform_populate(dev);
+	if (ret) {
+		sysfs_remove_group(&dev->kobj, &attr_group);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int gsc_remove(struct i2c_client *client)
+{
+	sysfs_remove_group(&client->dev.kobj, &attr_group);
+
+	return 0;
+}
+
+static struct i2c_driver gsc_driver = {
+	.driver = {
+		.name	= "gateworks-gsc",
+		.of_match_table = gsc_of_match,
+	},
+	.probe_new	= gsc_probe,
+	.remove		= gsc_remove,
+};
+module_i2c_driver(gsc_driver);
+
+MODULE_AUTHOR("Tim Harvey <tharvey@gateworks.com>");
+MODULE_DESCRIPTION("I2C Core interface for GSC");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 06038b325b02..55da6428ceb0 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -142,6 +142,9 @@ static void rtsx_comm_pm_full_on(struct rtsx_pcr *pcr)
 
 	rtsx_disable_aspm(pcr);
 
+	/* Fixes DMA transfer timout issue after disabling ASPM on RTS5260 */
+	msleep(1);
+
 	if (option->ltr_enabled)
 		rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
 
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 204d807e755b..b32c825a0945 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -266,6 +266,7 @@ void mei_me_cl_rm_by_uuid(struct mei_device *dev, const uuid_le *uuid)
 	down_write(&dev->me_clients_rwsem);
 	me_cl = __mei_me_cl_by_uuid(dev, uuid);
 	__mei_me_cl_del(dev, me_cl);
+	mei_me_cl_put(me_cl);
 	up_write(&dev->me_clients_rwsem);
 }
 
@@ -287,6 +288,7 @@ void mei_me_cl_rm_by_uuid_id(struct mei_device *dev, const uuid_le *uuid, u8 id)
 	down_write(&dev->me_clients_rwsem);
 	me_cl = __mei_me_cl_by_uuid_id(dev, uuid, id);
 	__mei_me_cl_del(dev, me_cl);
+	mei_me_cl_put(me_cl);
 	up_write(&dev->me_clients_rwsem);
 }
 
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 668418d7ea77..f620442addf5 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -1465,6 +1465,13 @@ static const struct mei_cfg mei_me_pch12_cfg = {
 	MEI_CFG_DMA_128,
 };
 
+/* LBG with quirk for SPS Firmware exclusion */
+static const struct mei_cfg mei_me_pch12_sps_cfg = {
+	MEI_CFG_PCH8_HFS,
+	MEI_CFG_FW_VER_SUPP,
+	MEI_CFG_FW_SPS,
+};
+
 /* Tiger Lake and newer devices */
 static const struct mei_cfg mei_me_pch15_cfg = {
 	MEI_CFG_PCH8_HFS,
@@ -1487,6 +1494,7 @@ static const struct mei_cfg *const mei_cfg_list[] = {
 	[MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg,
 	[MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg,
 	[MEI_ME_PCH12_CFG] = &mei_me_pch12_cfg,
+	[MEI_ME_PCH12_SPS_CFG] = &mei_me_pch12_sps_cfg,
 	[MEI_ME_PCH15_CFG] = &mei_me_pch15_cfg,
 };
 
diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h
index 4a8d4dcd5a91..b6b94e211464 100644
--- a/drivers/misc/mei/hw-me.h
+++ b/drivers/misc/mei/hw-me.h
@@ -80,6 +80,9 @@ struct mei_me_hw {
  *                         servers platforms with quirk for
  *                         SPS firmware exclusion.
  * @MEI_ME_PCH12_CFG:      Platform Controller Hub Gen12 and newer
+ * @MEI_ME_PCH12_SPS_CFG:  Platform Controller Hub Gen12 and newer
+ *                         servers platforms with quirk for
+ *                         SPS firmware exclusion.
  * @MEI_ME_PCH15_CFG:      Platform Controller Hub Gen15 and newer
  * @MEI_ME_NUM_CFG:        Upper Sentinel.
  */
@@ -93,6 +96,7 @@ enum mei_cfg_idx {
 	MEI_ME_PCH8_CFG,
 	MEI_ME_PCH8_SPS_CFG,
 	MEI_ME_PCH12_CFG,
+	MEI_ME_PCH12_SPS_CFG,
 	MEI_ME_PCH15_CFG,
 	MEI_ME_NUM_CFG,
 };
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 3d21c38e2dbb..a1ed375fed37 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -70,7 +70,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 	{MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, MEI_ME_PCH8_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_CFG)},
-	{MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_CFG)},
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)},
@@ -203,11 +203,12 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	hw = to_me_hw(dev);
 	hw->mem_addr = pcim_iomap_table(pdev)[0];
-	hw->irq = pdev->irq;
 	hw->read_fws = mei_me_read_fws;
 
 	pci_enable_msi(pdev);
 
+	hw->irq = pdev->irq;
+
 	 /* request and enable interrupt */
 	irqflags = pci_dev_msi_enabled(pdev) ? IRQF_ONESHOT : IRQF_SHARED;
 
diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
index 8f201d019f5a..3bfe72c59864 100644
--- a/drivers/misc/mic/Kconfig
+++ b/drivers/misc/mic/Kconfig
@@ -116,7 +116,7 @@ config MIC_COSM
 
 config VOP
 	tristate "VOP Driver"
-	depends on VOP_BUS
+	depends on VOP_BUS && VHOST_DPN
 	select VHOST_RING
 	select VIRTIO
 	help
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 8499b56a15a8..7896952de1ac 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1370,6 +1370,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req)
 	struct mmc_request *mrq = &mqrq->brq.mrq;
 	struct request_queue *q = req->q;
 	struct mmc_host *host = mq->card->host;
+	enum mmc_issue_type issue_type = mmc_issue_type(mq, req);
 	unsigned long flags;
 	bool put_card;
 	int err;
@@ -1399,7 +1400,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req)
 
 	spin_lock_irqsave(&mq->lock, flags);
 
-	mq->in_flight[mmc_issue_type(mq, req)] -= 1;
+	mq->in_flight[issue_type] -= 1;
 
 	put_card = (mmc_tot_in_flight(mq) == 0);
 
@@ -2483,8 +2484,8 @@ static int mmc_rpmb_chrdev_release(struct inode *inode, struct file *filp)
 	struct mmc_rpmb_data *rpmb = container_of(inode->i_cdev,
 						  struct mmc_rpmb_data, chrdev);
 
-	put_device(&rpmb->dev);
 	mmc_blk_put(rpmb->md);
+	put_device(&rpmb->dev);
 
 	return 0;
 }
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 5bd0ab8b236a..baa6314f69b4 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -878,7 +878,7 @@ static int mmc_send_hpi_cmd(struct mmc_card *card)
  *	Issued High Priority Interrupt, and check for card status
  *	until out-of prg-state.
  */
-int mmc_interrupt_hpi(struct mmc_card *card)
+static int mmc_interrupt_hpi(struct mmc_card *card)
 {
 	int err;
 	u32 status;
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 25bee3daf9e2..4b1eb89b401d 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -107,11 +107,10 @@ static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
 	case MMC_ISSUE_DCMD:
 		if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) {
 			if (recovery_needed)
-				__mmc_cqe_recovery_notifier(mq);
+				mmc_cqe_recovery_notifier(mrq);
 			return BLK_EH_RESET_TIMER;
 		}
-		/* No timeout (XXX: huh? comment doesn't make much sense) */
-		blk_mq_complete_request(req);
+		/* The request has gone already */
 		return BLK_EH_DONE;
 	default:
 		/* Timeout is handled by mmc core */
@@ -127,18 +126,13 @@ static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req,
 	struct mmc_card *card = mq->card;
 	struct mmc_host *host = card->host;
 	unsigned long flags;
-	int ret;
+	bool ignore_tout;
 
 	spin_lock_irqsave(&mq->lock, flags);
-
-	if (mq->recovery_needed || !mq->use_cqe || host->hsq_enabled)
-		ret = BLK_EH_RESET_TIMER;
-	else
-		ret = mmc_cqe_timed_out(req);
-
+	ignore_tout = mq->recovery_needed || !mq->use_cqe || host->hsq_enabled;
 	spin_unlock_irqrestore(&mq->lock, flags);
 
-	return ret;
+	return ignore_tout ? BLK_EH_RESET_TIMER : mmc_cqe_timed_out(req);
 }
 
 static void mmc_mq_recovery_handler(struct work_struct *work)
diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c
index 1aee485d56d4..026ca9194ce5 100644
--- a/drivers/mmc/host/alcor.c
+++ b/drivers/mmc/host/alcor.c
@@ -1104,7 +1104,7 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev)
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to get irq for data line\n");
-		return ret;
+		goto free_host;
 	}
 
 	mutex_init(&host->cmd_mutex);
@@ -1116,6 +1116,10 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev)
 	dev_set_drvdata(&pdev->dev, host);
 	mmc_add_host(mmc);
 	return 0;
+
+free_host:
+	mmc_free_host(mmc);
+	return ret;
 }
 
 static int alcor_pci_sdmmc_drv_remove(struct platform_device *pdev)
diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c
index c2239ee2c0ef..75934f3c117e 100644
--- a/drivers/mmc/host/cqhci.c
+++ b/drivers/mmc/host/cqhci.c
@@ -5,6 +5,7 @@
 #include <linux/delay.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
@@ -349,12 +350,16 @@ static int cqhci_enable(struct mmc_host *mmc, struct mmc_card *card)
 /* CQHCI is idle and should halt immediately, so set a small timeout */
 #define CQHCI_OFF_TIMEOUT 100
 
+static u32 cqhci_read_ctl(struct cqhci_host *cq_host)
+{
+	return cqhci_readl(cq_host, CQHCI_CTL);
+}
+
 static void cqhci_off(struct mmc_host *mmc)
 {
 	struct cqhci_host *cq_host = mmc->cqe_private;
-	ktime_t timeout;
-	bool timed_out;
 	u32 reg;
+	int err;
 
 	if (!cq_host->enabled || !mmc->cqe_on || cq_host->recovery_halt)
 		return;
@@ -364,15 +369,9 @@ static void cqhci_off(struct mmc_host *mmc)
 
 	cqhci_writel(cq_host, CQHCI_HALT, CQHCI_CTL);
 
-	timeout = ktime_add_us(ktime_get(), CQHCI_OFF_TIMEOUT);
-	while (1) {
-		timed_out = ktime_compare(ktime_get(), timeout) > 0;
-		reg = cqhci_readl(cq_host, CQHCI_CTL);
-		if ((reg & CQHCI_HALT) || timed_out)
-			break;
-	}
-
-	if (timed_out)
+	err = readx_poll_timeout(cqhci_read_ctl, cq_host, reg,
+				 reg & CQHCI_HALT, 0, CQHCI_OFF_TIMEOUT);
+	if (err < 0)
 		pr_err("%s: cqhci: CQE stuck on\n", mmc_hostname(mmc));
 	else
 		pr_debug("%s: cqhci: CQE off\n", mmc_hostname(mmc));
diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c
index 8b038e7b2cd3..2e58743d83bb 100644
--- a/drivers/mmc/host/meson-mx-sdio.c
+++ b/drivers/mmc/host/meson-mx-sdio.c
@@ -357,14 +357,6 @@ static void meson_mx_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		meson_mx_mmc_start_cmd(mmc, mrq->cmd);
 }
 
-static int meson_mx_mmc_card_busy(struct mmc_host *mmc)
-{
-	struct meson_mx_mmc_host *host = mmc_priv(mmc);
-	u32 irqc = readl(host->base + MESON_MX_SDIO_IRQC);
-
-	return !!(irqc & MESON_MX_SDIO_IRQC_FORCE_DATA_DAT_MASK);
-}
-
 static void meson_mx_mmc_read_response(struct mmc_host *mmc,
 				       struct mmc_command *cmd)
 {
@@ -506,7 +498,6 @@ static void meson_mx_mmc_timeout(struct timer_list *t)
 static struct mmc_host_ops meson_mx_mmc_ops = {
 	.request		= meson_mx_mmc_request,
 	.set_ios		= meson_mx_mmc_set_ios,
-	.card_busy		= meson_mx_mmc_card_busy,
 	.get_cd			= mmc_gpio_get_cd,
 	.get_ro			= mmc_gpio_get_ro,
 };
@@ -570,7 +561,7 @@ static int meson_mx_mmc_add_host(struct meson_mx_mmc_host *host)
 	mmc->f_max = clk_round_rate(host->cfg_div_clk,
 				    clk_get_rate(host->parent_clk));
 
-	mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23;
+	mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_WAIT_WHILE_BUSY;
 	mmc->ops = &meson_mx_mmc_ops;
 
 	ret = mmc_of_parse(mmc);
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index faba53cf139b..d8b76cb8698a 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -605,10 +605,12 @@ static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev,
 }
 
 static const struct sdhci_acpi_slot sdhci_acpi_slot_amd_emmc = {
-	.chip   = &sdhci_acpi_chip_amd,
-	.caps   = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
-	.quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | SDHCI_QUIRK_32BIT_DMA_SIZE |
-			SDHCI_QUIRK_32BIT_ADMA_SIZE,
+	.chip		= &sdhci_acpi_chip_amd,
+	.caps		= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
+	.quirks		= SDHCI_QUIRK_32BIT_DMA_ADDR |
+			  SDHCI_QUIRK_32BIT_DMA_SIZE |
+			  SDHCI_QUIRK_32BIT_ADMA_SIZE,
+	.quirks2	= SDHCI_QUIRK2_BROKEN_64_BIT_DMA,
 	.probe_slot     = sdhci_acpi_emmc_amd_probe_slot,
 };
 
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 09ff7315eb5e..a8bcb3f16aa4 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -2087,6 +2087,8 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 		goto clk_disable;
 	}
 
+	msm_host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_NEED_RSP_BUSY;
+
 	pm_runtime_get_noresume(&pdev->dev);
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 525de2454a4d..2527244c2ae1 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -601,6 +601,9 @@ static int intel_select_drive_strength(struct mmc_card *card,
 	struct sdhci_pci_slot *slot = sdhci_priv(host);
 	struct intel_host *intel_host = sdhci_pci_priv(slot);
 
+	if (!(mmc_driver_type_mask(intel_host->drv_strength) & card_drv))
+		return 0;
+
 	return intel_host->drv_strength;
 }
 
diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
index ce15a05f23d4..fd76aa672e02 100644
--- a/drivers/mmc/host/sdhci-pci-gli.c
+++ b/drivers/mmc/host/sdhci-pci-gli.c
@@ -26,6 +26,9 @@
 #define   SDHCI_GLI_9750_DRIVING_2    GENMASK(27, 26)
 #define   GLI_9750_DRIVING_1_VALUE    0xFFF
 #define   GLI_9750_DRIVING_2_VALUE    0x3
+#define   SDHCI_GLI_9750_SEL_1        BIT(29)
+#define   SDHCI_GLI_9750_SEL_2        BIT(31)
+#define   SDHCI_GLI_9750_ALL_RST      (BIT(24)|BIT(25)|BIT(28)|BIT(30))
 
 #define SDHCI_GLI_9750_PLL	      0x864
 #define   SDHCI_GLI_9750_PLL_TX2_INV    BIT(23)
@@ -122,6 +125,8 @@ static void gli_set_9750(struct sdhci_host *host)
 				    GLI_9750_DRIVING_1_VALUE);
 	driving_value |= FIELD_PREP(SDHCI_GLI_9750_DRIVING_2,
 				    GLI_9750_DRIVING_2_VALUE);
+	driving_value &= ~(SDHCI_GLI_9750_SEL_1|SDHCI_GLI_9750_SEL_2|SDHCI_GLI_9750_ALL_RST);
+	driving_value |= SDHCI_GLI_9750_SEL_2;
 	sdhci_writel(host, driving_value, SDHCI_GLI_9750_DRIVING);
 
 	sw_ctrl_value &= ~SDHCI_GLI_9750_SW_CTRL_4;
@@ -334,6 +339,18 @@ static u32 sdhci_gl9750_readl(struct sdhci_host *host, int reg)
 	return value;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int sdhci_pci_gli_resume(struct sdhci_pci_chip *chip)
+{
+	struct sdhci_pci_slot *slot = chip->slots[0];
+
+	pci_free_irq_vectors(slot->chip->pdev);
+	gli_pcie_enable_msi(slot);
+
+	return sdhci_pci_resume_host(chip);
+}
+#endif
+
 static const struct sdhci_ops sdhci_gl9755_ops = {
 	.set_clock		= sdhci_set_clock,
 	.enable_dma		= sdhci_pci_enable_dma,
@@ -348,6 +365,9 @@ const struct sdhci_pci_fixes sdhci_gl9755 = {
 	.quirks2	= SDHCI_QUIRK2_BROKEN_DDR50,
 	.probe_slot	= gli_probe_slot_gl9755,
 	.ops            = &sdhci_gl9755_ops,
+#ifdef CONFIG_PM_SLEEP
+	.resume         = sdhci_pci_gli_resume,
+#endif
 };
 
 static const struct sdhci_ops sdhci_gl9750_ops = {
@@ -366,4 +386,7 @@ const struct sdhci_pci_fixes sdhci_gl9750 = {
 	.quirks2	= SDHCI_QUIRK2_BROKEN_DDR50,
 	.probe_slot	= gli_probe_slot_gl9750,
 	.ops            = &sdhci_gl9750_ops,
+#ifdef CONFIG_PM_SLEEP
+	.resume         = sdhci_pci_gli_resume,
+#endif
 };
diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c
index 1dea1ba66f7b..4703cd540c7f 100644
--- a/drivers/mmc/host/sdhci-xenon.c
+++ b/drivers/mmc/host/sdhci-xenon.c
@@ -235,6 +235,16 @@ static void xenon_voltage_switch(struct sdhci_host *host)
 {
 	/* Wait for 5ms after set 1.8V signal enable bit */
 	usleep_range(5000, 5500);
+
+	/*
+	 * For some reason the controller's Host Control2 register reports
+	 * the bit representing 1.8V signaling as 0 when read after it was
+	 * written as 1. Subsequent read reports 1.
+	 *
+	 * Since this may cause some issues, do an empty read of the Host
+	 * Control2 register here to circumvent this.
+	 */
+	sdhci_readw(host, SDHCI_HOST_CONTROL2);
 }
 
 static const struct sdhci_ops sdhci_xenon_ops = {
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 3f716466fcfd..e368f2dabf20 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -4000,9 +4000,6 @@ int sdhci_setup_host(struct sdhci_host *host)
 		       mmc_hostname(mmc), host->version);
 	}
 
-	if (host->quirks & SDHCI_QUIRK_BROKEN_CQE)
-		mmc->caps2 &= ~MMC_CAP2_CQE;
-
 	if (host->quirks & SDHCI_QUIRK_FORCE_DMA)
 		host->flags |= SDHCI_USE_SDMA;
 	else if (!(host->caps & SDHCI_CAN_DO_SDMA))
@@ -4539,6 +4536,12 @@ int __sdhci_add_host(struct sdhci_host *host)
 	struct mmc_host *mmc = host->mmc;
 	int ret;
 
+	if ((mmc->caps2 & MMC_CAP2_CQE) &&
+	    (host->quirks & SDHCI_QUIRK_BROKEN_CQE)) {
+		mmc->caps2 &= ~MMC_CAP2_CQE;
+		mmc->cqe_ops = NULL;
+	}
+
 	host->complete_wq = alloc_workqueue("sdhci", flags, 0);
 	if (!host->complete_wq)
 		return -ENOMEM;
diff --git a/drivers/most/core.c b/drivers/most/core.c
index 06426fc5c990..f781c46cd4af 100644
--- a/drivers/most/core.c
+++ b/drivers/most/core.c
@@ -1483,7 +1483,7 @@ static void __exit most_exit(void)
 	ida_destroy(&mdev_id);
 }
 
-module_init(most_init);
+subsys_initcall(most_init);
 module_exit(most_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Christian Gromm <christian.gromm@microchip.com>");
diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index 42d401ea60ee..6ddab796216d 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -170,6 +170,16 @@ config MTD_OOPS
 	  buffer in a flash partition where it can be read back at some
 	  later point.
 
+config MTD_PSTORE
+	tristate "Log panic/oops to an MTD buffer based on pstore"
+	depends on PSTORE_BLK
+	help
+	  This enables panic and oops messages to be logged to a circular
+	  buffer in a flash partition where it can be read back as files after
+	  mounting pstore filesystem.
+
+	  If unsure, say N.
+
 config MTD_SWAP
 	tristate "Swap on MTD device support"
 	depends on MTD && SWAP
diff --git a/drivers/mtd/Makefile b/drivers/mtd/Makefile
index 56cc60ccc477..593d0593a038 100644
--- a/drivers/mtd/Makefile
+++ b/drivers/mtd/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_RFD_FTL)		+= rfd_ftl.o
 obj-$(CONFIG_SSFDC)		+= ssfdc.o
 obj-$(CONFIG_SM_FTL)		+= sm_ftl.o
 obj-$(CONFIG_MTD_OOPS)		+= mtdoops.o
+obj-$(CONFIG_MTD_PSTORE)	+= mtdpstore.o
 obj-$(CONFIG_MTD_SWAP)		+= mtdswap.o
 
 nftl-objs		:= nftlcore.o nftlmount.o
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 2916674208b3..29d41003d6e0 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -555,7 +555,7 @@ static int mtd_nvmem_add(struct mtd_info *mtd)
 
 	config.id = -1;
 	config.dev = &mtd->dev;
-	config.name = mtd->name;
+	config.name = dev_name(&mtd->dev);
 	config.owner = THIS_MODULE;
 	config.reg_read = mtd_nvmem_reg_read;
 	config.size = mtd->size;
diff --git a/drivers/mtd/mtdpstore.c b/drivers/mtd/mtdpstore.c
new file mode 100644
index 000000000000..a4fe6060b960
--- /dev/null
+++ b/drivers/mtd/mtdpstore.c
@@ -0,0 +1,578 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define dev_fmt(fmt) "mtdoops-pstore: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pstore_blk.h>
+#include <linux/mtd/mtd.h>
+#include <linux/bitops.h>
+
+static struct mtdpstore_context {
+	int index;
+	struct pstore_blk_config info;
+	struct pstore_device_info dev;
+	struct mtd_info *mtd;
+	unsigned long *rmmap;		/* removed bit map */
+	unsigned long *usedmap;		/* used bit map */
+	/*
+	 * used for panic write
+	 * As there are no block_isbad for panic case, we should keep this
+	 * status before panic to ensure panic_write not failed.
+	 */
+	unsigned long *badmap;		/* bad block bit map */
+} oops_cxt;
+
+static int mtdpstore_block_isbad(struct mtdpstore_context *cxt, loff_t off)
+{
+	int ret;
+	struct mtd_info *mtd = cxt->mtd;
+	u64 blknum;
+
+	off = ALIGN_DOWN(off, mtd->erasesize);
+	blknum = div_u64(off, mtd->erasesize);
+
+	if (test_bit(blknum, cxt->badmap))
+		return true;
+	ret = mtd_block_isbad(mtd, off);
+	if (ret < 0) {
+		dev_err(&mtd->dev, "mtd_block_isbad failed, aborting\n");
+		return ret;
+	} else if (ret > 0) {
+		set_bit(blknum, cxt->badmap);
+		return true;
+	}
+	return false;
+}
+
+static inline int mtdpstore_panic_block_isbad(struct mtdpstore_context *cxt,
+		loff_t off)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	u64 blknum;
+
+	off = ALIGN_DOWN(off, mtd->erasesize);
+	blknum = div_u64(off, mtd->erasesize);
+	return test_bit(blknum, cxt->badmap);
+}
+
+static inline void mtdpstore_mark_used(struct mtdpstore_context *cxt,
+		loff_t off)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	u64 zonenum = div_u64(off, cxt->info.kmsg_size);
+
+	dev_dbg(&mtd->dev, "mark zone %llu used\n", zonenum);
+	set_bit(zonenum, cxt->usedmap);
+}
+
+static inline void mtdpstore_mark_unused(struct mtdpstore_context *cxt,
+		loff_t off)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	u64 zonenum = div_u64(off, cxt->info.kmsg_size);
+
+	dev_dbg(&mtd->dev, "mark zone %llu unused\n", zonenum);
+	clear_bit(zonenum, cxt->usedmap);
+}
+
+static inline void mtdpstore_block_mark_unused(struct mtdpstore_context *cxt,
+		loff_t off)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size;
+	u64 zonenum;
+
+	off = ALIGN_DOWN(off, mtd->erasesize);
+	zonenum = div_u64(off, cxt->info.kmsg_size);
+	while (zonecnt > 0) {
+		dev_dbg(&mtd->dev, "mark zone %llu unused\n", zonenum);
+		clear_bit(zonenum, cxt->usedmap);
+		zonenum++;
+		zonecnt--;
+	}
+}
+
+static inline int mtdpstore_is_used(struct mtdpstore_context *cxt, loff_t off)
+{
+	u64 zonenum = div_u64(off, cxt->info.kmsg_size);
+	u64 blknum = div_u64(off, cxt->mtd->erasesize);
+
+	if (test_bit(blknum, cxt->badmap))
+		return true;
+	return test_bit(zonenum, cxt->usedmap);
+}
+
+static int mtdpstore_block_is_used(struct mtdpstore_context *cxt,
+		loff_t off)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size;
+	u64 zonenum;
+
+	off = ALIGN_DOWN(off, mtd->erasesize);
+	zonenum = div_u64(off, cxt->info.kmsg_size);
+	while (zonecnt > 0) {
+		if (test_bit(zonenum, cxt->usedmap))
+			return true;
+		zonenum++;
+		zonecnt--;
+	}
+	return false;
+}
+
+static int mtdpstore_is_empty(struct mtdpstore_context *cxt, char *buf,
+		size_t size)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	size_t sz;
+	int i;
+
+	sz = min_t(uint32_t, size, mtd->writesize / 4);
+	for (i = 0; i < sz; i++) {
+		if (buf[i] != (char)0xFF)
+			return false;
+	}
+	return true;
+}
+
+static void mtdpstore_mark_removed(struct mtdpstore_context *cxt, loff_t off)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	u64 zonenum = div_u64(off, cxt->info.kmsg_size);
+
+	dev_dbg(&mtd->dev, "mark zone %llu removed\n", zonenum);
+	set_bit(zonenum, cxt->rmmap);
+}
+
+static void mtdpstore_block_clear_removed(struct mtdpstore_context *cxt,
+		loff_t off)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size;
+	u64 zonenum;
+
+	off = ALIGN_DOWN(off, mtd->erasesize);
+	zonenum = div_u64(off, cxt->info.kmsg_size);
+	while (zonecnt > 0) {
+		clear_bit(zonenum, cxt->rmmap);
+		zonenum++;
+		zonecnt--;
+	}
+}
+
+static int mtdpstore_block_is_removed(struct mtdpstore_context *cxt,
+		loff_t off)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size;
+	u64 zonenum;
+
+	off = ALIGN_DOWN(off, mtd->erasesize);
+	zonenum = div_u64(off, cxt->info.kmsg_size);
+	while (zonecnt > 0) {
+		if (test_bit(zonenum, cxt->rmmap))
+			return true;
+		zonenum++;
+		zonecnt--;
+	}
+	return false;
+}
+
+static int mtdpstore_erase_do(struct mtdpstore_context *cxt, loff_t off)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	struct erase_info erase;
+	int ret;
+
+	off = ALIGN_DOWN(off, cxt->mtd->erasesize);
+	dev_dbg(&mtd->dev, "try to erase off 0x%llx\n", off);
+	erase.len = cxt->mtd->erasesize;
+	erase.addr = off;
+	ret = mtd_erase(cxt->mtd, &erase);
+	if (!ret)
+		mtdpstore_block_clear_removed(cxt, off);
+	else
+		dev_err(&mtd->dev, "erase of region [0x%llx, 0x%llx] on \"%s\" failed\n",
+		       (unsigned long long)erase.addr,
+		       (unsigned long long)erase.len, cxt->info.device);
+	return ret;
+}
+
+/*
+ * called while removing file
+ *
+ * Avoiding over erasing, do erase block only when the whole block is unused.
+ * If the block contains valid log, do erase lazily on flush_removed() when
+ * unregister.
+ */
+static ssize_t mtdpstore_erase(size_t size, loff_t off)
+{
+	struct mtdpstore_context *cxt = &oops_cxt;
+
+	if (mtdpstore_block_isbad(cxt, off))
+		return -EIO;
+
+	mtdpstore_mark_unused(cxt, off);
+
+	/* If the block still has valid data, mtdpstore do erase lazily */
+	if (likely(mtdpstore_block_is_used(cxt, off))) {
+		mtdpstore_mark_removed(cxt, off);
+		return 0;
+	}
+
+	/* all zones are unused, erase it */
+	return mtdpstore_erase_do(cxt, off);
+}
+
+/*
+ * What is security for mtdpstore?
+ * As there is no erase for panic case, we should ensure at least one zone
+ * is writable. Otherwise, panic write will fail.
+ * If zone is used, write operation will return -ENOMSG, which means that
+ * pstore/blk will try one by one until gets an empty zone. So, it is not
+ * needed to ensure the next zone is empty, but at least one.
+ */
+static int mtdpstore_security(struct mtdpstore_context *cxt, loff_t off)
+{
+	int ret = 0, i;
+	struct mtd_info *mtd = cxt->mtd;
+	u32 zonenum = (u32)div_u64(off, cxt->info.kmsg_size);
+	u32 zonecnt = (u32)div_u64(cxt->mtd->size, cxt->info.kmsg_size);
+	u32 blkcnt = (u32)div_u64(cxt->mtd->size, cxt->mtd->erasesize);
+	u32 erasesize = cxt->mtd->erasesize;
+
+	for (i = 0; i < zonecnt; i++) {
+		u32 num = (zonenum + i) % zonecnt;
+
+		/* found empty zone */
+		if (!test_bit(num, cxt->usedmap))
+			return 0;
+	}
+
+	/* If there is no any empty zone, we have no way but to do erase */
+	while (blkcnt--) {
+		div64_u64_rem(off + erasesize, cxt->mtd->size, (u64 *)&off);
+
+		if (mtdpstore_block_isbad(cxt, off))
+			continue;
+
+		ret = mtdpstore_erase_do(cxt, off);
+		if (!ret) {
+			mtdpstore_block_mark_unused(cxt, off);
+			break;
+		}
+	}
+
+	if (ret)
+		dev_err(&mtd->dev, "all blocks bad!\n");
+	dev_dbg(&mtd->dev, "end security\n");
+	return ret;
+}
+
+static ssize_t mtdpstore_write(const char *buf, size_t size, loff_t off)
+{
+	struct mtdpstore_context *cxt = &oops_cxt;
+	struct mtd_info *mtd = cxt->mtd;
+	size_t retlen;
+	int ret;
+
+	if (mtdpstore_block_isbad(cxt, off))
+		return -ENOMSG;
+
+	/* zone is used, please try next one */
+	if (mtdpstore_is_used(cxt, off))
+		return -ENOMSG;
+
+	dev_dbg(&mtd->dev, "try to write off 0x%llx size %zu\n", off, size);
+	ret = mtd_write(cxt->mtd, off, size, &retlen, (u_char *)buf);
+	if (ret < 0 || retlen != size) {
+		dev_err(&mtd->dev, "write failure at %lld (%zu of %zu written), err %d\n",
+				off, retlen, size, ret);
+		return -EIO;
+	}
+	mtdpstore_mark_used(cxt, off);
+
+	mtdpstore_security(cxt, off);
+	return retlen;
+}
+
+static inline bool mtdpstore_is_io_error(int ret)
+{
+	return ret < 0 && !mtd_is_bitflip(ret) && !mtd_is_eccerr(ret);
+}
+
+/*
+ * All zones will be read as pstore/blk will read zone one by one when do
+ * recover.
+ */
+static ssize_t mtdpstore_read(char *buf, size_t size, loff_t off)
+{
+	struct mtdpstore_context *cxt = &oops_cxt;
+	struct mtd_info *mtd = cxt->mtd;
+	size_t retlen, done;
+	int ret;
+
+	if (mtdpstore_block_isbad(cxt, off))
+		return -ENOMSG;
+
+	dev_dbg(&mtd->dev, "try to read off 0x%llx size %zu\n", off, size);
+	for (done = 0, retlen = 0; done < size; done += retlen) {
+		retlen = 0;
+
+		ret = mtd_read(cxt->mtd, off + done, size - done, &retlen,
+				(u_char *)buf + done);
+		if (mtdpstore_is_io_error(ret)) {
+			dev_err(&mtd->dev, "read failure at %lld (%zu of %zu read), err %d\n",
+					off + done, retlen, size - done, ret);
+			/* the zone may be broken, try next one */
+			return -ENOMSG;
+		}
+
+		/*
+		 * ECC error. The impact on log data is so small. Maybe we can
+		 * still read it and try to understand. So mtdpstore just hands
+		 * over what it gets and user can judge whether the data is
+		 * valid or not.
+		 */
+		if (mtd_is_eccerr(ret)) {
+			dev_err(&mtd->dev, "ecc error at %lld (%zu of %zu read), err %d\n",
+					off + done, retlen, size - done, ret);
+			/* driver may not set retlen when ecc error */
+			retlen = retlen == 0 ? size - done : retlen;
+		}
+	}
+
+	if (mtdpstore_is_empty(cxt, buf, size))
+		mtdpstore_mark_unused(cxt, off);
+	else
+		mtdpstore_mark_used(cxt, off);
+
+	mtdpstore_security(cxt, off);
+	return retlen;
+}
+
+static ssize_t mtdpstore_panic_write(const char *buf, size_t size, loff_t off)
+{
+	struct mtdpstore_context *cxt = &oops_cxt;
+	struct mtd_info *mtd = cxt->mtd;
+	size_t retlen;
+	int ret;
+
+	if (mtdpstore_panic_block_isbad(cxt, off))
+		return -ENOMSG;
+
+	/* zone is used, please try next one */
+	if (mtdpstore_is_used(cxt, off))
+		return -ENOMSG;
+
+	ret = mtd_panic_write(cxt->mtd, off, size, &retlen, (u_char *)buf);
+	if (ret < 0 || size != retlen) {
+		dev_err(&mtd->dev, "panic write failure at %lld (%zu of %zu read), err %d\n",
+				off, retlen, size, ret);
+		return -EIO;
+	}
+	mtdpstore_mark_used(cxt, off);
+
+	return retlen;
+}
+
+static void mtdpstore_notify_add(struct mtd_info *mtd)
+{
+	int ret;
+	struct mtdpstore_context *cxt = &oops_cxt;
+	struct pstore_blk_config *info = &cxt->info;
+	unsigned long longcnt;
+
+	if (!strcmp(mtd->name, info->device))
+		cxt->index = mtd->index;
+
+	if (mtd->index != cxt->index || cxt->index < 0)
+		return;
+
+	dev_dbg(&mtd->dev, "found matching MTD device %s\n", mtd->name);
+
+	if (mtd->size < info->kmsg_size * 2) {
+		dev_err(&mtd->dev, "MTD partition %d not big enough\n",
+				mtd->index);
+		return;
+	}
+	/*
+	 * kmsg_size must be aligned to 4096 Bytes, which is limited by
+	 * psblk. The default value of kmsg_size is 64KB. If kmsg_size
+	 * is larger than erasesize, some errors will occur since mtdpsotre
+	 * is designed on it.
+	 */
+	if (mtd->erasesize < info->kmsg_size) {
+		dev_err(&mtd->dev, "eraseblock size of MTD partition %d too small\n",
+				mtd->index);
+		return;
+	}
+	if (unlikely(info->kmsg_size % mtd->writesize)) {
+		dev_err(&mtd->dev, "record size %lu KB must align to write size %d KB\n",
+				info->kmsg_size / 1024,
+				mtd->writesize / 1024);
+		return;
+	}
+
+	longcnt = BITS_TO_LONGS(div_u64(mtd->size, info->kmsg_size));
+	cxt->rmmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL);
+	cxt->usedmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL);
+
+	longcnt = BITS_TO_LONGS(div_u64(mtd->size, mtd->erasesize));
+	cxt->badmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL);
+
+	cxt->dev.total_size = mtd->size;
+	/* just support dmesg right now */
+	cxt->dev.flags = PSTORE_FLAGS_DMESG;
+	cxt->dev.read = mtdpstore_read;
+	cxt->dev.write = mtdpstore_write;
+	cxt->dev.erase = mtdpstore_erase;
+	cxt->dev.panic_write = mtdpstore_panic_write;
+
+	ret = register_pstore_device(&cxt->dev);
+	if (ret) {
+		dev_err(&mtd->dev, "mtd%d register to psblk failed\n",
+				mtd->index);
+		return;
+	}
+	cxt->mtd = mtd;
+	dev_info(&mtd->dev, "Attached to MTD device %d\n", mtd->index);
+}
+
+static int mtdpstore_flush_removed_do(struct mtdpstore_context *cxt,
+		loff_t off, size_t size)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	u_char *buf;
+	int ret;
+	size_t retlen;
+	struct erase_info erase;
+
+	buf = kmalloc(mtd->erasesize, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* 1st. read to cache */
+	ret = mtd_read(mtd, off, mtd->erasesize, &retlen, buf);
+	if (mtdpstore_is_io_error(ret))
+		goto free;
+
+	/* 2nd. erase block */
+	erase.len = mtd->erasesize;
+	erase.addr = off;
+	ret = mtd_erase(mtd, &erase);
+	if (ret)
+		goto free;
+
+	/* 3rd. write back */
+	while (size) {
+		unsigned int zonesize = cxt->info.kmsg_size;
+
+		/* there is valid data on block, write back */
+		if (mtdpstore_is_used(cxt, off)) {
+			ret = mtd_write(mtd, off, zonesize, &retlen, buf);
+			if (ret)
+				dev_err(&mtd->dev, "write failure at %lld (%zu of %u written), err %d\n",
+						off, retlen, zonesize, ret);
+		}
+
+		off += zonesize;
+		size -= min_t(unsigned int, zonesize, size);
+	}
+
+free:
+	kfree(buf);
+	return ret;
+}
+
+/*
+ * What does mtdpstore_flush_removed() do?
+ * When user remove any log file on pstore filesystem, mtdpstore should do
+ * something to ensure log file removed. If the whole block is no longer used,
+ * it's nice to erase the block. However if the block still contains valid log,
+ * what mtdpstore can do is to erase and write the valid log back.
+ */
+static int mtdpstore_flush_removed(struct mtdpstore_context *cxt)
+{
+	struct mtd_info *mtd = cxt->mtd;
+	int ret;
+	loff_t off;
+	u32 blkcnt = (u32)div_u64(mtd->size, mtd->erasesize);
+
+	for (off = 0; blkcnt > 0; blkcnt--, off += mtd->erasesize) {
+		ret = mtdpstore_block_isbad(cxt, off);
+		if (ret)
+			continue;
+
+		ret = mtdpstore_block_is_removed(cxt, off);
+		if (!ret)
+			continue;
+
+		ret = mtdpstore_flush_removed_do(cxt, off, mtd->erasesize);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static void mtdpstore_notify_remove(struct mtd_info *mtd)
+{
+	struct mtdpstore_context *cxt = &oops_cxt;
+
+	if (mtd->index != cxt->index || cxt->index < 0)
+		return;
+
+	mtdpstore_flush_removed(cxt);
+
+	unregister_pstore_device(&cxt->dev);
+	kfree(cxt->badmap);
+	kfree(cxt->usedmap);
+	kfree(cxt->rmmap);
+	cxt->mtd = NULL;
+	cxt->index = -1;
+}
+
+static struct mtd_notifier mtdpstore_notifier = {
+	.add	= mtdpstore_notify_add,
+	.remove	= mtdpstore_notify_remove,
+};
+
+static int __init mtdpstore_init(void)
+{
+	int ret;
+	struct mtdpstore_context *cxt = &oops_cxt;
+	struct pstore_blk_config *info = &cxt->info;
+
+	ret = pstore_blk_get_config(info);
+	if (unlikely(ret))
+		return ret;
+
+	if (strlen(info->device) == 0) {
+		pr_err("mtd device must be supplied (device name is empty)\n");
+		return -EINVAL;
+	}
+	if (!info->kmsg_size) {
+		pr_err("no backend enabled (kmsg_size is 0)\n");
+		return -EINVAL;
+	}
+
+	/* Setup the MTD device to use */
+	ret = kstrtoint((char *)info->device, 0, &cxt->index);
+	if (ret)
+		cxt->index = -1;
+
+	register_mtd_user(&mtdpstore_notifier);
+	return 0;
+}
+module_init(mtdpstore_init);
+
+static void __exit mtdpstore_exit(void)
+{
+	unregister_mtd_user(&mtdpstore_notifier);
+}
+module_exit(mtdpstore_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("WeiXiong Liao <liaoweixiong@allwinnertech.com>");
+MODULE_DESCRIPTION("MTD backend for pstore/blk");
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index e4e3ceeac38f..8f9ffb46a09f 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -2728,9 +2728,8 @@ static int brcmnand_resume(struct device *dev)
 		flash_dma_writel(ctrl, FLASH_DMA_ERROR_STATUS, 0);
 	}
 
-	if (has_edu(ctrl))
+	if (has_edu(ctrl)) {
 		ctrl->edu_config = edu_readl(ctrl, EDU_CONFIG);
-	else {
 		edu_writel(ctrl, EDU_CONFIG, ctrl->edu_config);
 		edu_readl(ctrl, EDU_CONFIG);
 		brcmnand_edu_init(ctrl);
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index b6bb358b96ce..e2c382ffc5b6 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -1089,6 +1089,10 @@ static int spinand_init(struct spinand_device *spinand)
 
 	mtd->oobavail = ret;
 
+	/* Propagate ECC information to mtd_info */
+	mtd->ecc_strength = nand->eccreq.strength;
+	mtd->ecc_step_size = nand->eccreq.step_size;
+
 	return 0;
 
 err_cleanup_nanddev:
diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile
index 7ddb742de1fe..653923896205 100644
--- a/drivers/mtd/spi-nor/Makefile
+++ b/drivers/mtd/spi-nor/Makefile
@@ -18,3 +18,5 @@ spi-nor-objs			+= winbond.o
 spi-nor-objs			+= xilinx.o
 spi-nor-objs			+= xmc.o
 obj-$(CONFIG_MTD_SPI_NOR)	+= spi-nor.o
+
+obj-$(CONFIG_MTD_SPI_NOR)	+= controllers/
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index 54646c2c2744..ac2bdba8bb1a 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -393,9 +393,6 @@ static void *eraseblk_count_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct ubi_device *ubi = s->private;
 
-	if (*pos == 0)
-		return SEQ_START_TOKEN;
-
 	if (*pos < ubi->peb_count)
 		return pos;
 
@@ -409,8 +406,6 @@ static void *eraseblk_count_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
 	struct ubi_device *ubi = s->private;
 
-	if (v == SEQ_START_TOKEN)
-		return pos;
 	(*pos)++;
 
 	if (*pos < ubi->peb_count)
@@ -432,11 +427,8 @@ static int eraseblk_count_seq_show(struct seq_file *s, void *iter)
 	int err;
 
 	/* If this is the start, print a header */
-	if (iter == SEQ_START_TOKEN) {
-		seq_puts(s,
-			 "physical_block_number\terase_count\tblock_status\tread_status\n");
-		return 0;
-	}
+	if (*block_number == 0)
+		seq_puts(s, "physical_block_number\terase_count\n");
 
 	err = ubi_io_is_bad(ubi, *block_number);
 	if (err)
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index cc0703c3d57f..efd1a1d1f35e 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -136,25 +136,21 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	oiph = skb_network_header(skb);
 	skb_reset_network_header(skb);
 
-	if (family == AF_INET)
+	if (!IS_ENABLED(CONFIG_IPV6) || family == AF_INET)
 		err = IP_ECN_decapsulate(oiph, skb);
-#if IS_ENABLED(CONFIG_IPV6)
 	else
 		err = IP6_ECN_decapsulate(oiph, skb);
-#endif
 
 	if (unlikely(err)) {
 		if (log_ecn_error) {
-			if  (family == AF_INET)
+			if  (!IS_ENABLED(CONFIG_IPV6) || family == AF_INET)
 				net_info_ratelimited("non-ECT from %pI4 "
 						     "with TOS=%#x\n",
 						     &((struct iphdr *)oiph)->saddr,
 						     ((struct iphdr *)oiph)->tos);
-#if IS_ENABLED(CONFIG_IPV6)
 			else
 				net_info_ratelimited("non-ECT from %pI6\n",
 						     &((struct ipv6hdr *)oiph)->saddr);
-#endif
 		}
 		if (err > 1) {
 			++bareudp->dev->stats.rx_frame_errors;
@@ -350,7 +346,6 @@ free_dst:
 	return err;
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
 static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 			     struct bareudp_dev *bareudp,
 			     const struct ip_tunnel_info *info)
@@ -411,7 +406,6 @@ free_dst:
 	dst_release(dst);
 	return err;
 }
-#endif
 
 static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev)
 {
@@ -435,11 +429,9 @@ static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	rcu_read_lock();
-#if IS_ENABLED(CONFIG_IPV6)
-	if (info->mode & IP_TUNNEL_INFO_IPV6)
+	if (IS_ENABLED(CONFIG_IPV6) && info->mode & IP_TUNNEL_INFO_IPV6)
 		err = bareudp6_xmit_skb(skb, dev, bareudp, info);
 	else
-#endif
 		err = bareudp_xmit_skb(skb, dev, bareudp, info);
 
 	rcu_read_unlock();
@@ -467,7 +459,7 @@ static int bareudp_fill_metadata_dst(struct net_device *dev,
 
 	use_cache = ip_tunnel_dst_cache_usable(skb, info);
 
-	if (ip_tunnel_info_af(info) == AF_INET) {
+	if (!IS_ENABLED(CONFIG_IPV6) || ip_tunnel_info_af(info) == AF_INET) {
 		struct rtable *rt;
 		__be32 saddr;
 
@@ -478,7 +470,6 @@ static int bareudp_fill_metadata_dst(struct net_device *dev,
 
 		ip_rt_put(rt);
 		info->key.u.ipv4.src = saddr;
-#if IS_ENABLED(CONFIG_IPV6)
 	} else if (ip_tunnel_info_af(info) == AF_INET6) {
 		struct dst_entry *dst;
 		struct in6_addr saddr;
@@ -492,7 +483,6 @@ static int bareudp_fill_metadata_dst(struct net_device *dev,
 
 		dst_release(dst);
 		info->key.u.ipv6.src = saddr;
-#endif
 	} else {
 		return -EINVAL;
 	}
diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c
index 007481557191..9b8346638f69 100644
--- a/drivers/net/bonding/bond_sysfs_slave.c
+++ b/drivers/net/bonding/bond_sysfs_slave.c
@@ -149,8 +149,10 @@ int bond_sysfs_slave_add(struct slave *slave)
 
 	err = kobject_init_and_add(&slave->kobj, &slave_ktype,
 				   &(slave->dev->dev.kobj), "bonding_slave");
-	if (err)
+	if (err) {
+		kobject_put(&slave->kobj);
 		return err;
+	}
 
 	for (a = slave_attrs; *a; ++a) {
 		err = sysfs_create_file(&slave->kobj, &((*a)->attr));
diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig
index 9db0570c5beb..661c25eb1c46 100644
--- a/drivers/net/caif/Kconfig
+++ b/drivers/net/caif/Kconfig
@@ -50,7 +50,7 @@ config CAIF_HSI
 
 config CAIF_VIRTIO
 	tristate "CAIF virtio transport driver"
-	depends on CAIF && HAS_DMA
+	depends on CAIF && HAS_DMA && VHOST_DPN
 	select VHOST_RING
 	select VIRTIO
 	select GENERIC_ALLOCATOR
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index 04d59bede5ea..74503cacf594 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -947,8 +947,11 @@ static int ifi_canfd_plat_probe(struct platform_device *pdev)
 	u32 id, rev;
 
 	addr = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+
 	irq = platform_get_irq(pdev, 0);
-	if (IS_ERR(addr) || irq < 0)
+	if (irq < 0)
 		return -EINVAL;
 
 	id = readl(addr + IFI_CANFD_IP_ID);
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index e3ba8ab0cbf4..e2c6cf4b2228 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -792,7 +792,7 @@ static int sun4ican_probe(struct platform_device *pdev)
 
 	addr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(addr)) {
-		err = -EBUSY;
+		err = PTR_ERR(addr);
 		goto exit;
 	}
 
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 68e2381694b9..c283593bef17 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1474,6 +1474,10 @@ static int b53_arl_rw_op(struct b53_device *dev, unsigned int op)
 		reg |= ARLTBL_RW;
 	else
 		reg &= ~ARLTBL_RW;
+	if (dev->vlan_enabled)
+		reg &= ~ARLTBL_IVL_SVL_SELECT;
+	else
+		reg |= ARLTBL_IVL_SVL_SELECT;
 	b53_write8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, reg);
 
 	return b53_arl_op_wait(dev);
@@ -1483,6 +1487,7 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			u16 vid, struct b53_arl_entry *ent, u8 *idx,
 			bool is_valid)
 {
+	DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES);
 	unsigned int i;
 	int ret;
 
@@ -1490,6 +1495,8 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 	if (ret)
 		return ret;
 
+	bitmap_zero(free_bins, dev->num_arl_entries);
+
 	/* Read the bins */
 	for (i = 0; i < dev->num_arl_entries; i++) {
 		u64 mac_vid;
@@ -1501,13 +1508,24 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			   B53_ARLTBL_DATA_ENTRY(i), &fwd_entry);
 		b53_arl_to_entry(ent, mac_vid, fwd_entry);
 
-		if (!(fwd_entry & ARLTBL_VALID))
+		if (!(fwd_entry & ARLTBL_VALID)) {
+			set_bit(i, free_bins);
 			continue;
+		}
 		if ((mac_vid & ARLTBL_MAC_MASK) != mac)
 			continue;
+		if (dev->vlan_enabled &&
+		    ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid)
+			continue;
 		*idx = i;
+		return 0;
 	}
 
+	if (bitmap_weight(free_bins, dev->num_arl_entries) == 0)
+		return -ENOSPC;
+
+	*idx = find_first_bit(free_bins, dev->num_arl_entries);
+
 	return -ENOENT;
 }
 
@@ -1537,10 +1555,21 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 	if (op)
 		return ret;
 
-	/* We could not find a matching MAC, so reset to a new entry */
-	if (ret) {
+	switch (ret) {
+	case -ENOSPC:
+		dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n",
+			addr, vid);
+		return is_valid ? ret : 0;
+	case -ENOENT:
+		/* We could not find a matching MAC, so reset to a new entry */
+		dev_dbg(dev->dev, "{%pM,%.4d} not found, using idx: %d\n",
+			addr, vid, idx);
 		fwd_entry = 0;
-		idx = 1;
+		break;
+	default:
+		dev_dbg(dev->dev, "{%pM,%.4d} found, using idx: %d\n",
+			addr, vid, idx);
+		break;
 	}
 
 	/* For multicast address, the port is a bitmask and the validity
@@ -1558,7 +1587,6 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 		ent.is_valid = !!(ent.port);
 	}
 
-	ent.is_valid = is_valid;
 	ent.vid = vid;
 	ent.is_static = true;
 	ent.is_age = false;
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index 2a9f421680aa..c90985c294a2 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -292,6 +292,7 @@
 /* ARL Table Read/Write Register (8 bit) */
 #define B53_ARLTBL_RW_CTRL		0x00
 #define    ARLTBL_RW			BIT(0)
+#define    ARLTBL_IVL_SVL_SELECT	BIT(6)
 #define    ARLTBL_START_DONE		BIT(7)
 
 /* MAC Address Index Register (48 bit) */
@@ -304,7 +305,7 @@
  *
  * BCM5325 and BCM5365 share most definitions below
  */
-#define B53_ARLTBL_MAC_VID_ENTRY(n)	(0x10 * (n))
+#define B53_ARLTBL_MAC_VID_ENTRY(n)	((0x10 * (n)) + 0x10)
 #define   ARLTBL_MAC_MASK		0xffffffffffffULL
 #define   ARLTBL_VID_S			48
 #define   ARLTBL_VID_MASK_25		0xff
@@ -316,13 +317,16 @@
 #define   ARLTBL_VALID_25		BIT(63)
 
 /* ARL Table Data Entry N Registers (32 bit) */
-#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x08)
+#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x18)
 #define   ARLTBL_DATA_PORT_ID_MASK	0x1ff
 #define   ARLTBL_TC(tc)			((3 & tc) << 11)
 #define   ARLTBL_AGE			BIT(14)
 #define   ARLTBL_STATIC			BIT(15)
 #define   ARLTBL_VALID			BIT(16)
 
+/* Maximum number of bin entries in the ARL for all switches */
+#define B53_ARLTBL_MAX_BIN_ENTRIES	4
+
 /* ARL Search Control Register (8 bit) */
 #define B53_ARL_SRCH_CTL		0x50
 #define B53_ARL_SRCH_CTL_25		0x20
diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c
index 0a1be5259be0..38cd8285ac67 100644
--- a/drivers/net/dsa/b53/b53_srab.c
+++ b/drivers/net/dsa/b53/b53_srab.c
@@ -609,7 +609,7 @@ static int b53_srab_probe(struct platform_device *pdev)
 
 	priv->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->regs))
-		return -ENOMEM;
+		return PTR_ERR(priv->regs);
 
 	dev = b53_switch_alloc(&pdev->dev, &b53_srab_ops, priv);
 	if (!dev)
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index fdcb70b9f0e4..400207c5c7de 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -360,6 +360,7 @@ static void __exit dsa_loop_exit(void)
 }
 module_exit(dsa_loop_exit);
 
+MODULE_SOFTDEP("pre: dsa_loop_bdinfo");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Florian Fainelli");
 MODULE_DESCRIPTION("DSA loopback driver");
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 2d0d91db0ddb..34e4aadfa705 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -67,58 +67,6 @@ static const struct mt7530_mib_desc mt7530_mib[] = {
 };
 
 static int
-mt7623_trgmii_write(struct mt7530_priv *priv,  u32 reg, u32 val)
-{
-	int ret;
-
-	ret =  regmap_write(priv->ethernet, TRGMII_BASE(reg), val);
-	if (ret < 0)
-		dev_err(priv->dev,
-			"failed to priv write register\n");
-	return ret;
-}
-
-static u32
-mt7623_trgmii_read(struct mt7530_priv *priv, u32 reg)
-{
-	int ret;
-	u32 val;
-
-	ret = regmap_read(priv->ethernet, TRGMII_BASE(reg), &val);
-	if (ret < 0) {
-		dev_err(priv->dev,
-			"failed to priv read register\n");
-		return ret;
-	}
-
-	return val;
-}
-
-static void
-mt7623_trgmii_rmw(struct mt7530_priv *priv, u32 reg,
-		  u32 mask, u32 set)
-{
-	u32 val;
-
-	val = mt7623_trgmii_read(priv, reg);
-	val &= ~mask;
-	val |= set;
-	mt7623_trgmii_write(priv, reg, val);
-}
-
-static void
-mt7623_trgmii_set(struct mt7530_priv *priv, u32 reg, u32 val)
-{
-	mt7623_trgmii_rmw(priv, reg, 0, val);
-}
-
-static void
-mt7623_trgmii_clear(struct mt7530_priv *priv, u32 reg, u32 val)
-{
-	mt7623_trgmii_rmw(priv, reg, val, 0);
-}
-
-static int
 core_read_mmd_indirect(struct mt7530_priv *priv, int prtad, int devad)
 {
 	struct mii_bus *bus = priv->bus;
@@ -530,27 +478,6 @@ mt7530_pad_clk_setup(struct dsa_switch *ds, int mode)
 		for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
 			mt7530_rmw(priv, MT7530_TRGMII_RD(i),
 				   RD_TAP_MASK, RD_TAP(16));
-	else
-		if (priv->id != ID_MT7621)
-			mt7623_trgmii_set(priv, GSW_INTF_MODE,
-					  INTF_MODE_TRGMII);
-
-	return 0;
-}
-
-static int
-mt7623_pad_clk_setup(struct dsa_switch *ds)
-{
-	struct mt7530_priv *priv = ds->priv;
-	int i;
-
-	for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
-		mt7623_trgmii_write(priv, GSW_TRGMII_TD_ODT(i),
-				    TD_DM_DRVP(8) | TD_DM_DRVN(8));
-
-	mt7623_trgmii_set(priv, GSW_TRGMII_RCK_CTRL, RX_RST | RXC_DQSISEL);
-	mt7623_trgmii_clear(priv, GSW_TRGMII_RCK_CTRL, RX_RST);
-
 	return 0;
 }
 
@@ -701,11 +628,8 @@ mt7530_cpu_port_enable(struct mt7530_priv *priv,
 	mt7530_write(priv, MT7530_PVC_P(port),
 		     PORT_SPEC_TAG);
 
-	/* Disable auto learning on the cpu port */
-	mt7530_set(priv, MT7530_PSC_P(port), SA_DIS);
-
-	/* Unknown unicast frame fordwarding to the cpu port */
-	mt7530_set(priv, MT7530_MFC, UNU_FFP(BIT(port)));
+	/* Unknown multicast frame forwarding to the cpu port */
+	mt7530_rmw(priv, MT7530_MFC, UNM_FFP_MASK, UNM_FFP(BIT(port)));
 
 	/* Set CPU port number */
 	if (priv->id == ID_MT7621)
@@ -846,8 +770,9 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
 	 */
 	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
 		   MT7530_PORT_MATRIX_MODE);
-	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
-		   VLAN_ATTR(MT7530_VLAN_TRANSPARENT));
+	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+		   VLAN_ATTR(MT7530_VLAN_TRANSPARENT) |
+		   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 
 	for (i = 0; i < MT7530_NUM_PORTS; i++) {
 		if (dsa_is_user_port(ds, i) &&
@@ -863,8 +788,8 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
 	if (all_user_ports_removed) {
 		mt7530_write(priv, MT7530_PCR_P(MT7530_CPU_PORT),
 			     PCR_MATRIX(dsa_user_ports(priv->ds)));
-		mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT),
-			     PORT_SPEC_TAG);
+		mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT), PORT_SPEC_TAG
+			     | PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 }
 
@@ -890,8 +815,9 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port)
 	/* Set the port as a user port which is to be able to recognize VID
 	 * from incoming packets before fetching entry within the VLAN table.
 	 */
-	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
-		   VLAN_ATTR(MT7530_VLAN_USER));
+	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+		   VLAN_ATTR(MT7530_VLAN_USER) |
+		   PVC_EG_TAG(MT7530_VLAN_EG_DISABLED));
 }
 
 static void
@@ -1303,10 +1229,6 @@ mt7530_setup(struct dsa_switch *ds)
 	dn = dsa_to_port(ds, MT7530_CPU_PORT)->master->dev.of_node->parent;
 
 	if (priv->id == ID_MT7530) {
-		priv->ethernet = syscon_node_to_regmap(dn);
-		if (IS_ERR(priv->ethernet))
-			return PTR_ERR(priv->ethernet);
-
 		regulator_set_voltage(priv->core_pwr, 1000000, 1000000);
 		ret = regulator_enable(priv->core_pwr);
 		if (ret < 0) {
@@ -1369,8 +1291,6 @@ mt7530_setup(struct dsa_switch *ds)
 	/* Enable and reset MIB counters */
 	mt7530_mib_reset(ds);
 
-	mt7530_clear(priv, MT7530_MFC, UNU_FFP_MASK);
-
 	for (i = 0; i < MT7530_NUM_PORTS; i++) {
 		/* Disable forwarding by default on all ports */
 		mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
@@ -1380,6 +1300,10 @@ mt7530_setup(struct dsa_switch *ds)
 			mt7530_cpu_port_enable(priv, i);
 		else
 			mt7530_port_disable(ds, i);
+
+		/* Enable consistent egress tag */
+		mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK,
+			   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 
 	/* Setup port 5 */
@@ -1468,14 +1392,6 @@ static void mt7530_phylink_mac_config(struct dsa_switch *ds, int port,
 		/* Setup TX circuit incluing relevant PAD and driving */
 		mt7530_pad_clk_setup(ds, state->interface);
 
-		if (priv->id == ID_MT7530) {
-			/* Setup RX circuit, relevant PAD and driving on the
-			 * host which must be placed after the setup on the
-			 * device side is all finished.
-			 */
-			mt7623_pad_clk_setup(ds);
-		}
-
 		priv->p6_interface = state->interface;
 		break;
 	default:
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index ef9b52f3152b..82af4d2d406e 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -31,6 +31,7 @@ enum {
 #define MT7530_MFC			0x10
 #define  BC_FFP(x)			(((x) & 0xff) << 24)
 #define  UNM_FFP(x)			(((x) & 0xff) << 16)
+#define  UNM_FFP_MASK			UNM_FFP(~0)
 #define  UNU_FFP(x)			(((x) & 0xff) << 8)
 #define  UNU_FFP_MASK			UNU_FFP(~0)
 #define  CPU_EN				BIT(7)
@@ -172,9 +173,16 @@ enum mt7530_port_mode {
 /* Register for port vlan control */
 #define MT7530_PVC_P(x)			(0x2010 + ((x) * 0x100))
 #define  PORT_SPEC_TAG			BIT(5)
+#define  PVC_EG_TAG(x)			(((x) & 0x7) << 8)
+#define  PVC_EG_TAG_MASK		PVC_EG_TAG(7)
 #define  VLAN_ATTR(x)			(((x) & 0x3) << 6)
 #define  VLAN_ATTR_MASK			VLAN_ATTR(3)
 
+enum mt7530_vlan_port_eg_tag {
+	MT7530_VLAN_EG_DISABLED = 0,
+	MT7530_VLAN_EG_CONSISTENT = 1,
+};
+
 enum mt7530_vlan_port_attr {
 	MT7530_VLAN_USER = 0,
 	MT7530_VLAN_TRANSPARENT = 3,
@@ -277,7 +285,6 @@ enum mt7530_vlan_port_attr {
 
 /* Registers for TRGMII on the both side */
 #define MT7530_TRGMII_RCK_CTRL		0x7a00
-#define GSW_TRGMII_RCK_CTRL		0x300
 #define  RX_RST				BIT(31)
 #define  RXC_DQSISEL			BIT(30)
 #define  DQSI1_TAP_MASK			(0x7f << 8)
@@ -286,31 +293,24 @@ enum mt7530_vlan_port_attr {
 #define  DQSI0_TAP(x)			((x) & 0x7f)
 
 #define MT7530_TRGMII_RCK_RTT		0x7a04
-#define GSW_TRGMII_RCK_RTT		0x304
 #define  DQS1_GATE			BIT(31)
 #define  DQS0_GATE			BIT(30)
 
 #define MT7530_TRGMII_RD(x)		(0x7a10 + (x) * 8)
-#define GSW_TRGMII_RD(x)		(0x310 + (x) * 8)
 #define  BSLIP_EN			BIT(31)
 #define  EDGE_CHK			BIT(30)
 #define  RD_TAP_MASK			0x7f
 #define  RD_TAP(x)			((x) & 0x7f)
 
-#define GSW_TRGMII_TXCTRL		0x340
 #define MT7530_TRGMII_TXCTRL		0x7a40
 #define  TRAIN_TXEN			BIT(31)
 #define  TXC_INV			BIT(30)
 #define  TX_RST				BIT(28)
 
 #define MT7530_TRGMII_TD_ODT(i)		(0x7a54 + 8 * (i))
-#define GSW_TRGMII_TD_ODT(i)		(0x354 + 8 * (i))
 #define  TD_DM_DRVP(x)			((x) & 0xf)
 #define  TD_DM_DRVN(x)			(((x) & 0xf) << 4)
 
-#define GSW_INTF_MODE			0x390
-#define  INTF_MODE_TRGMII		BIT(1)
-
 #define MT7530_TRGMII_TCK_CTRL		0x7a78
 #define  TCK_TAP(x)			(((x) & 0xf) << 8)
 
@@ -443,7 +443,6 @@ static const char *p5_intf_modes(unsigned int p5_interface)
  * @ds:			The pointer to the dsa core structure
  * @bus:		The bus used for the device and built-in PHY
  * @rstc:		The pointer to reset control used by MCM
- * @ethernet:		The regmap used for access TRGMII-based registers
  * @core_pwr:		The power supplied into the core
  * @io_pwr:		The power supplied into the I/O
  * @reset:		The descriptor for GPIO line tied to its reset pin
@@ -460,7 +459,6 @@ struct mt7530_priv {
 	struct dsa_switch	*ds;
 	struct mii_bus		*bus;
 	struct reset_control	*rstc;
-	struct regmap		*ethernet;
 	struct regulator	*core_pwr;
 	struct regulator	*io_pwr;
 	struct gpio_desc	*reset;
diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig
index 6435020d690d..51185e4d7d15 100644
--- a/drivers/net/dsa/mv88e6xxx/Kconfig
+++ b/drivers/net/dsa/mv88e6xxx/Kconfig
@@ -24,8 +24,8 @@ config NET_DSA_MV88E6XXX_PTP
 	bool "PTP support for Marvell 88E6xxx"
 	default n
 	depends on NET_DSA_MV88E6XXX_GLOBAL2
+	depends on PTP_1588_CLOCK
 	imply NETWORK_PHY_TIMESTAMPING
-	imply PTP_1588_CLOCK
 	help
 	  Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch
 	  chips that support it.
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 221593261e8f..2b4a723c8306 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -709,7 +709,8 @@ static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port,
 	ops = chip->info->ops;
 
 	mv88e6xxx_reg_lock(chip);
-	if (!mv88e6xxx_port_ppu_updates(chip, port) && ops->port_set_link)
+	if ((!mv88e6xxx_port_ppu_updates(chip, port) ||
+	     mode == MLO_AN_FIXED) && ops->port_set_link)
 		err = ops->port_set_link(chip, port, LINK_FORCED_DOWN);
 	mv88e6xxx_reg_unlock(chip);
 
@@ -731,7 +732,7 @@ static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port,
 	ops = chip->info->ops;
 
 	mv88e6xxx_reg_lock(chip);
-	if (!mv88e6xxx_port_ppu_updates(chip, port)) {
+	if (!mv88e6xxx_port_ppu_updates(chip, port) || mode == MLO_AN_FIXED) {
 		/* FIXME: for an automedia port, should we force the link
 		 * down here - what if the link comes up due to "other" media
 		 * while we're bringing the port up, how is the exclusivity
@@ -3961,7 +3962,6 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.serdes_get_stats = mv88e6390_serdes_get_stats,
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6390_serdes_get_regs,
-	.phylink_validate = mv88e6390_phylink_validate,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_validate = mv88e6390_phylink_validate,
 };
@@ -4020,7 +4020,6 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.serdes_get_stats = mv88e6390_serdes_get_stats,
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6390_serdes_get_regs,
-	.phylink_validate = mv88e6390_phylink_validate,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_validate = mv88e6390x_phylink_validate,
 };
@@ -4078,7 +4077,6 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.serdes_get_stats = mv88e6390_serdes_get_stats,
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6390_serdes_get_regs,
-	.phylink_validate = mv88e6390_phylink_validate,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
 	.phylink_validate = mv88e6390_phylink_validate,
@@ -4234,7 +4232,6 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.serdes_get_stats = mv88e6390_serdes_get_stats,
 	.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
 	.serdes_get_regs = mv88e6390_serdes_get_regs,
-	.phylink_validate = mv88e6390_phylink_validate,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 79ca3aadb864..e113269c220a 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -46,11 +46,8 @@ static int felix_fdb_add(struct dsa_switch *ds, int port,
 			 const unsigned char *addr, u16 vid)
 {
 	struct ocelot *ocelot = ds->priv;
-	bool vlan_aware;
 
-	vlan_aware = dsa_port_is_vlan_filtering(dsa_to_port(ds, port));
-
-	return ocelot_fdb_add(ocelot, port, addr, vid, vlan_aware);
+	return ocelot_fdb_add(ocelot, port, addr, vid);
 }
 
 static int felix_fdb_del(struct dsa_switch *ds, int port,
@@ -105,13 +102,17 @@ static void felix_vlan_add(struct dsa_switch *ds, int port,
 			   const struct switchdev_obj_port_vlan *vlan)
 {
 	struct ocelot *ocelot = ds->priv;
+	u16 flags = vlan->flags;
 	u16 vid;
 	int err;
 
+	if (dsa_is_cpu_port(ds, port))
+		flags &= ~BRIDGE_VLAN_INFO_UNTAGGED;
+
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
 		err = ocelot_vlan_add(ocelot, port, vid,
-				      vlan->flags & BRIDGE_VLAN_INFO_PVID,
-				      vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+				      flags & BRIDGE_VLAN_INFO_PVID,
+				      flags & BRIDGE_VLAN_INFO_UNTAGGED);
 		if (err) {
 			dev_err(ds->dev, "Failed to add VLAN %d to port %d: %d\n",
 				vid, port, err);
@@ -391,6 +392,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	struct ocelot *ocelot = &felix->ocelot;
 	phy_interface_t *port_phy_modes;
 	resource_size_t switch_base;
+	struct resource res;
 	int port, i, err;
 
 	ocelot->num_phys_ports = num_phys_ports;
@@ -403,6 +405,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	ocelot->stats_layout	= felix->info->stats_layout;
 	ocelot->num_stats	= felix->info->num_stats;
 	ocelot->shared_queue_sz	= felix->info->shared_queue_sz;
+	ocelot->num_mact_rows	= felix->info->num_mact_rows;
 	ocelot->vcap_is2_keys	= felix->info->vcap_is2_keys;
 	ocelot->vcap_is2_actions= felix->info->vcap_is2_actions;
 	ocelot->vcap		= felix->info->vcap;
@@ -424,17 +427,16 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 
 	for (i = 0; i < TARGET_MAX; i++) {
 		struct regmap *target;
-		struct resource *res;
 
 		if (!felix->info->target_io_res[i].name)
 			continue;
 
-		res = &felix->info->target_io_res[i];
-		res->flags = IORESOURCE_MEM;
-		res->start += switch_base;
-		res->end += switch_base;
+		memcpy(&res, &felix->info->target_io_res[i], sizeof(res));
+		res.flags = IORESOURCE_MEM;
+		res.start += switch_base;
+		res.end += switch_base;
 
-		target = ocelot_regmap_init(ocelot, res);
+		target = ocelot_regmap_init(ocelot, &res);
 		if (IS_ERR(target)) {
 			dev_err(ocelot->dev,
 				"Failed to map device memory space\n");
@@ -455,7 +457,6 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	for (port = 0; port < num_phys_ports; port++) {
 		struct ocelot_port *ocelot_port;
 		void __iomem *port_regs;
-		struct resource *res;
 
 		ocelot_port = devm_kzalloc(ocelot->dev,
 					   sizeof(struct ocelot_port),
@@ -467,12 +468,12 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 			return -ENOMEM;
 		}
 
-		res = &felix->info->port_io_res[port];
-		res->flags = IORESOURCE_MEM;
-		res->start += switch_base;
-		res->end += switch_base;
+		memcpy(&res, &felix->info->port_io_res[port], sizeof(res));
+		res.flags = IORESOURCE_MEM;
+		res.start += switch_base;
+		res.end += switch_base;
 
-		port_regs = devm_ioremap_resource(ocelot->dev, res);
+		port_regs = devm_ioremap_resource(ocelot->dev, &res);
 		if (IS_ERR(port_regs)) {
 			dev_err(ocelot->dev,
 				"failed to map registers for port %d\n", port);
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 82d46f260041..730a8a90e1f7 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -8,13 +8,14 @@
 
 /* Platform-specific information */
 struct felix_info {
-	struct resource			*target_io_res;
-	struct resource			*port_io_res;
-	struct resource			*imdio_res;
+	const struct resource		*target_io_res;
+	const struct resource		*port_io_res;
+	const struct resource		*imdio_res;
 	const struct reg_field		*regfields;
 	const u32 *const		*map;
 	const struct ocelot_ops		*ops;
 	int				shared_queue_sz;
+	int				num_mact_rows;
 	const struct ocelot_stat_layout	*stats_layout;
 	unsigned int			num_stats;
 	int				num_ports;
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index b4078f3c5c38..5211f05ef2fb 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -333,10 +333,8 @@ static const u32 *vsc9959_regmap[] = {
 	[GCB]	= vsc9959_gcb_regmap,
 };
 
-/* Addresses are relative to the PCI device's base address and
- * will be fixed up at ioremap time.
- */
-static struct resource vsc9959_target_io_res[] = {
+/* Addresses are relative to the PCI device's base address */
+static const struct resource vsc9959_target_io_res[] = {
 	[ANA] = {
 		.start	= 0x0280000,
 		.end	= 0x028ffff,
@@ -379,7 +377,7 @@ static struct resource vsc9959_target_io_res[] = {
 	},
 };
 
-static struct resource vsc9959_port_io_res[] = {
+static const struct resource vsc9959_port_io_res[] = {
 	{
 		.start	= 0x0100000,
 		.end	= 0x010ffff,
@@ -415,7 +413,7 @@ static struct resource vsc9959_port_io_res[] = {
 /* Port MAC 0 Internal MDIO bus through which the SerDes acting as an
  * SGMII/QSGMII MAC PCS can be found.
  */
-static struct resource vsc9959_imdio_res = {
+static const struct resource vsc9959_imdio_res = {
 	.start		= 0x8030,
 	.end		= 0x8040,
 	.name		= "imdio",
@@ -1111,7 +1109,7 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot)
 	struct device *dev = ocelot->dev;
 	resource_size_t imdio_base;
 	void __iomem *imdio_regs;
-	struct resource *res;
+	struct resource res;
 	struct enetc_hw *hw;
 	struct mii_bus *bus;
 	int port;
@@ -1128,12 +1126,12 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot)
 	imdio_base = pci_resource_start(felix->pdev,
 					felix->info->imdio_pci_bar);
 
-	res = felix->info->imdio_res;
-	res->flags = IORESOURCE_MEM;
-	res->start += imdio_base;
-	res->end += imdio_base;
+	memcpy(&res, felix->info->imdio_res, sizeof(res));
+	res.flags = IORESOURCE_MEM;
+	res.start += imdio_base;
+	res.end += imdio_base;
 
-	imdio_regs = devm_ioremap_resource(dev, res);
+	imdio_regs = devm_ioremap_resource(dev, &res);
 	if (IS_ERR(imdio_regs)) {
 		dev_err(dev, "failed to map internal MDIO registers\n");
 		return PTR_ERR(imdio_regs);
@@ -1220,6 +1218,7 @@ struct felix_info felix_info_vsc9959 = {
 	.vcap_is2_actions	= vsc9959_vcap_is2_actions,
 	.vcap			= vsc9959_vcap_props,
 	.shared_queue_sz	= 128 * 1024,
+	.num_mact_rows		= 2048,
 	.num_ports		= 6,
 	.switch_pci_bar		= 4,
 	.imdio_pci_bar		= 0,
diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig
index 0fe1ae173aa1..68c3086af9af 100644
--- a/drivers/net/dsa/sja1105/Kconfig
+++ b/drivers/net/dsa/sja1105/Kconfig
@@ -20,6 +20,7 @@ tristate "NXP SJA1105 Ethernet switch family support"
 config NET_DSA_SJA1105_PTP
 	bool "Support for the PTP clock on the NXP SJA1105 Ethernet switch"
 	depends on NET_DSA_SJA1105
+	depends on PTP_1588_CLOCK
 	help
 	  This enables support for timestamping and PTP clock manipulations in
 	  the SJA1105 DSA driver.
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c
index a22f8e3fc06b..bc0e47c1dbb9 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.c
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.c
@@ -16,14 +16,15 @@
 
 /* PTPSYNCTS has no interrupt or update mechanism, because the intended
  * hardware use case is for the timestamp to be collected synchronously,
- * immediately after the CAS_MASTER SJA1105 switch has triggered a CASSYNC
- * pulse on the PTP_CLK pin. When used as a generic extts source, it needs
- * polling and a comparison with the old value. The polling interval is just
- * the Nyquist rate of a canonical PPS input (e.g. from a GPS module).
- * Anything of higher frequency than 1 Hz will be lost, since there is no
- * timestamp FIFO.
+ * immediately after the CAS_MASTER SJA1105 switch has performed a CASSYNC
+ * one-shot toggle (no return to level) on the PTP_CLK pin. When used as a
+ * generic extts source, the PTPSYNCTS register needs polling and a comparison
+ * with the old value. The polling interval is configured as the Nyquist rate
+ * of a signal with 50% duty cycle and 1Hz frequency, which is sadly all that
+ * this hardware can do (but may be enough for some setups). Anything of higher
+ * frequency than 1 Hz will be lost, since there is no timestamp FIFO.
  */
-#define SJA1105_EXTTS_INTERVAL		(HZ / 2)
+#define SJA1105_EXTTS_INTERVAL		(HZ / 4)
 
 /*            This range is actually +/- SJA1105_MAX_ADJ_PPB
  *            divided by 1000 (ppb -> ppm) and with a 16-bit
@@ -754,7 +755,16 @@ static int sja1105_extts_enable(struct sja1105_private *priv,
 		return -EOPNOTSUPP;
 
 	/* Reject requests with unsupported flags */
-	if (extts->flags)
+	if (extts->flags & ~(PTP_ENABLE_FEATURE |
+			     PTP_RISING_EDGE |
+			     PTP_FALLING_EDGE |
+			     PTP_STRICT_FLAGS))
+		return -EOPNOTSUPP;
+
+	/* We can only enable time stamping on both edges, sadly. */
+	if ((extts->flags & PTP_STRICT_FLAGS) &&
+	    (extts->flags & PTP_ENABLE_FEATURE) &&
+	    (extts->flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES)
 		return -EOPNOTSUPP;
 
 	rc = sja1105_change_ptp_clk_pin_func(priv, PTP_PF_EXTTS);
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 97dfd0c67e84..9e1860d81908 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -69,7 +69,7 @@
  * 16kB.
  */
 #if PAGE_SIZE > SZ_16K
-#define ENA_PAGE_SIZE SZ_16K
+#define ENA_PAGE_SIZE (_AC(SZ_16K, UL))
 #else
 #define ENA_PAGE_SIZE PAGE_SIZE
 #endif
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index b71f9b04a51e..a87264f95f1a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -514,7 +514,7 @@ static void xgbe_isr_task(unsigned long data)
 				xgbe_disable_rx_tx_ints(pdata);
 
 				/* Turn on polling */
-				__napi_schedule_irqoff(&pdata->napi);
+				__napi_schedule(&pdata->napi);
 			}
 		} else {
 			/* Don't clear Rx/Tx status if doing per channel DMA
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index a58185b1d8bf..3e3711b60d01 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -1182,7 +1182,7 @@ bmac_get_station_address(struct net_device *dev, unsigned char *ea)
 	int i;
 	unsigned short data;
 
-	for (i = 0; i < 6; i++)
+	for (i = 0; i < 3; i++)
 		{
 			reset_and_select_srom(dev);
 			data = read_srom(dev, i + EnetAddressOffset/2, SROMAddressBits);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 2edf137a7030..8a70ffe1d326 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -57,7 +57,7 @@ static const struct aq_board_revision_s hw_atl_boards[] = {
 	{ AQ_DEVICE_ID_D108,	AQ_HWREV_2,	&hw_atl_ops_b0, &hw_atl_b0_caps_aqc108, },
 	{ AQ_DEVICE_ID_D109,	AQ_HWREV_2,	&hw_atl_ops_b0, &hw_atl_b0_caps_aqc109, },
 
-	{ AQ_DEVICE_ID_AQC100,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, },
+	{ AQ_DEVICE_ID_AQC100,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc100, },
 	{ AQ_DEVICE_ID_AQC107,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, },
 	{ AQ_DEVICE_ID_AQC108,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc108, },
 	{ AQ_DEVICE_ID_AQC109,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc109, },
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 53055ce5dfd6..2a69c0d06f3c 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -69,6 +69,7 @@ config BCMGENET
 	select BCM7XXX_PHY
 	select MDIO_BCM_UNIMAC
 	select DIMLIB
+	select BROADCOM_PHY if ARCH_BCM2835
 	help
 	  This driver supports the built-in Ethernet MACs found in the
 	  Broadcom BCM7xxx Set Top Box family chipset.
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index af7ce5c5488c..b25356e21a1e 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -664,7 +664,8 @@ static struct sk_buff *bcm_sysport_rx_refill(struct bcm_sysport_priv *priv,
 	dma_addr_t mapping;
 
 	/* Allocate a new SKB for a new packet */
-	skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH);
+	skb = __netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH,
+				 GFP_ATOMIC | __GFP_NOWARN);
 	if (!skb) {
 		priv->mib.alloc_rx_buff_failed++;
 		netif_err(priv, rx_err, ndev, "SKB alloc failed\n");
@@ -2475,7 +2476,6 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 		priv->wol_irq = platform_get_irq(pdev, 1);
 	}
 	if (priv->irq0 <= 0 || (priv->irq1 <= 0 && !priv->is_lite)) {
-		dev_err(&pdev->dev, "invalid interrupts\n");
 		ret = -EINVAL;
 		goto err_free_netdev;
 	}
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index c46c1b1416f7..6795b6d95f54 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -202,13 +202,8 @@ static int bgmac_probe(struct platform_device *pdev)
 	if (bgmac->irq < 0)
 		return bgmac->irq;
 
-	regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "amac_base");
-	if (!regs) {
-		dev_err(&pdev->dev, "Unable to obtain base resource\n");
-		return -EINVAL;
-	}
-
-	bgmac->plat.base = devm_ioremap_resource(&pdev->dev, regs);
+	bgmac->plat.base =
+		devm_platform_ioremap_resource_byname(pdev, "amac_base");
 	if (IS_ERR(bgmac->plat.base))
 		return PTR_ERR(bgmac->plat.base);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fead64f1ad90..58e0d9a781e9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4176,14 +4176,12 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	int i, intr_process, rc, tmo_count;
 	struct input *req = msg;
 	u32 *data = msg;
-	__le32 *resp_len;
 	u8 *valid;
 	u16 cp_ring_id, len = 0;
 	struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN;
 	struct hwrm_short_input short_input = {0};
 	u32 doorbell_offset = BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER;
-	u8 *resp_addr = (u8 *)bp->hwrm_cmd_resp_addr;
 	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
 	u16 dst = BNXT_HWRM_CHNL_CHIMP;
 
@@ -4201,7 +4199,6 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		bar_offset = BNXT_GRCPF_REG_KONG_COMM;
 		doorbell_offset = BNXT_GRCPF_REG_KONG_COMM_TRIGGER;
 		resp = bp->hwrm_cmd_kong_resp_addr;
-		resp_addr = (u8 *)bp->hwrm_cmd_kong_resp_addr;
 	}
 
 	memset(resp, 0, PAGE_SIZE);
@@ -4270,7 +4267,6 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	tmo_count = HWRM_SHORT_TIMEOUT_COUNTER;
 	timeout = timeout - HWRM_SHORT_MIN_TIMEOUT * HWRM_SHORT_TIMEOUT_COUNTER;
 	tmo_count += DIV_ROUND_UP(timeout, HWRM_MIN_TIMEOUT);
-	resp_len = (__le32 *)(resp_addr + HWRM_RESP_LEN_OFFSET);
 
 	if (intr_process) {
 		u16 seq_id = bp->hwrm_intr_seq_id;
@@ -4298,9 +4294,8 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 					   le16_to_cpu(req->req_type));
 			return -EBUSY;
 		}
-		len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >>
-		      HWRM_RESP_LEN_SFT;
-		valid = resp_addr + len - 1;
+		len = le16_to_cpu(resp->resp_len);
+		valid = ((u8 *)resp) + len - 1;
 	} else {
 		int j;
 
@@ -4311,8 +4306,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 			 */
 			if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
 				return -EBUSY;
-			len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >>
-			      HWRM_RESP_LEN_SFT;
+			len = le16_to_cpu(resp->resp_len);
 			if (len)
 				break;
 			/* on first few passes, just barely sleep */
@@ -4334,7 +4328,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		}
 
 		/* Last byte of resp contains valid bit */
-		valid = resp_addr + len - 1;
+		valid = ((u8 *)resp) + len - 1;
 		for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) {
 			/* make sure we read from updated DMA memory */
 			dma_rmb();
@@ -6642,7 +6636,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 	int rc;
 
 	if (!mem_size)
-		return 0;
+		return -EINVAL;
 
 	ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
 	if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) {
@@ -9310,7 +9304,7 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
-	if (bp->bnapi)
+	if (bp->bnapi && irq_re_init)
 		bnxt_get_ring_stats(bp, &bp->net_stats_prev);
 	if (irq_re_init) {
 		bnxt_free_irq(bp);
@@ -9780,6 +9774,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 					   netdev_features_t features)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	netdev_features_t vlan_features;
 
 	if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp))
 		features &= ~NETIF_F_NTUPLE;
@@ -9796,12 +9791,14 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 	/* Both CTAG and STAG VLAN accelaration on the RX side have to be
 	 * turned on or off together.
 	 */
-	if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) !=
-	    (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) {
+	vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX |
+				    NETIF_F_HW_VLAN_STAG_RX);
+	if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX |
+			      NETIF_F_HW_VLAN_STAG_RX)) {
 		if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
 			features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
 				      NETIF_F_HW_VLAN_STAG_RX);
-		else
+		else if (vlan_features)
 			features |= NETIF_F_HW_VLAN_CTAG_RX |
 				    NETIF_F_HW_VLAN_STAG_RX;
 	}
@@ -12212,12 +12209,15 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 		bnxt_ulp_start(bp, err);
 	}
 
-	if (result != PCI_ERS_RESULT_RECOVERED && netif_running(netdev))
-		dev_close(netdev);
+	if (result != PCI_ERS_RESULT_RECOVERED) {
+		if (netif_running(netdev))
+			dev_close(netdev);
+		pci_disable_device(pdev);
+	}
 
 	rtnl_unlock();
 
-	return PCI_ERS_RESULT_RECOVERED;
+	return result;
 }
 
 /**
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index f2caa2756f5b..3d39638521d6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -656,11 +656,6 @@ struct nqe_cn {
 #define HWRM_CMD_TIMEOUT		(bp->hwrm_cmd_timeout)
 #define HWRM_RESET_TIMEOUT		((HWRM_CMD_TIMEOUT) * 4)
 #define HWRM_COREDUMP_TIMEOUT		((HWRM_CMD_TIMEOUT) * 12)
-#define HWRM_RESP_ERR_CODE_MASK		0xffff
-#define HWRM_RESP_LEN_OFFSET		4
-#define HWRM_RESP_LEN_MASK		0xffff0000
-#define HWRM_RESP_LEN_SFT		16
-#define HWRM_RESP_VALID_MASK		0xff000000
 #define BNXT_HWRM_REQ_MAX_SIZE		128
 #define BNXT_HWRM_REQS_PER_PAGE		(BNXT_PAGE_SIZE /	\
 					 BNXT_HWRM_REQ_MAX_SIZE)
@@ -1066,7 +1061,6 @@ struct bnxt_vf_info {
 #define BNXT_VF_LINK_FORCED	0x4
 #define BNXT_VF_LINK_UP		0x8
 #define BNXT_VF_TRUST		0x10
-	u32	func_flags; /* func cfg flags */
 	u32	min_tx_rate;
 	u32	max_tx_rate;
 	void	*hwrm_cmd_req_addr;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index 95f893f2a74d..d5c8bd49383a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -43,7 +43,7 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
 #define BNXT_NVM_CFG_VER_BITS		24
 #define BNXT_NVM_CFG_VER_BYTES		4
 
-#define BNXT_MSIX_VEC_MAX	1280
+#define BNXT_MSIX_VEC_MAX	512
 #define BNXT_MSIX_VEC_MIN_MAX	128
 
 enum bnxt_nvm_dir_type {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 34046a6286e8..360f9a95c1d5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2012,11 +2012,12 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename,
 
 	bnxt_hwrm_fw_set_time(bp);
 
-	if (bnxt_find_nvram_item(dev, BNX_DIR_TYPE_UPDATE,
-				 BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE,
-				 &index, &item_len, NULL) != 0) {
+	rc = bnxt_find_nvram_item(dev, BNX_DIR_TYPE_UPDATE,
+				  BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE,
+				  &index, &item_len, NULL);
+	if (rc) {
 		netdev_err(dev, "PKG update area not created in nvram\n");
-		return -ENOBUFS;
+		return rc;
 	}
 
 	rc = request_firmware(&fw, filename, &dev->dev);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 6ea3df6da18c..cea2f9958a1d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -85,11 +85,10 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	if (old_setting == setting)
 		return 0;
 
-	func_flags = vf->func_flags;
 	if (setting)
-		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE;
+		func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE;
 	else
-		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE;
+		func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE;
 	/*TODO: if the driver supports VLAN filter on guest VLAN,
 	 * the spoof check should also include vlan anti-spoofing
 	 */
@@ -98,7 +97,6 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	req.flags = cpu_to_le32(func_flags);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
-		vf->func_flags = func_flags;
 		if (setting)
 			vf->flags |= BNXT_VF_SPOOFCHK;
 		else
@@ -228,7 +226,6 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac)
 	memcpy(vf->mac_addr, mac, ETH_ALEN);
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
 	memcpy(req.dflt_mac_addr, mac, ETH_ALEN);
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -266,7 +263,6 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos,
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 	req.dflt_vlan = cpu_to_le16(vlan_tag);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -305,7 +301,6 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate,
 		return 0;
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW);
 	req.max_bw = cpu_to_le32(max_tx_rate);
 	req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW);
@@ -477,7 +472,6 @@ static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id)
 	vf = &bp->pf.vf[vf_id];
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 
 	if (is_valid_ether_addr(vf->mac_addr)) {
 		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index d975338bf78d..79636c78127c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -934,6 +934,8 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 	if (netif_running(dev))
 		bcmgenet_update_mib_counters(priv);
 
+	dev->netdev_ops->ndo_get_stats(dev);
+
 	for (i = 0; i < BCMGENET_STATS_LEN; i++) {
 		const struct bcmgenet_stats *s;
 		char *p;
@@ -1622,7 +1624,8 @@ static struct sk_buff *bcmgenet_rx_refill(struct bcmgenet_priv *priv,
 	dma_addr_t mapping;
 
 	/* Allocate a new Rx skb */
-	skb = netdev_alloc_skb(priv->dev, priv->rx_buf_len + SKB_ALIGNMENT);
+	skb = __netdev_alloc_skb(priv->dev, priv->rx_buf_len + SKB_ALIGNMENT,
+				 GFP_ATOMIC | __GFP_NOWARN);
 	if (!skb) {
 		priv->mib.alloc_rx_buff_failed++;
 		netif_err(priv, rx_err, priv->dev,
@@ -3156,6 +3159,7 @@ static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
 	dev->stats.rx_packets = rx_packets;
 	dev->stats.rx_errors = rx_errors;
 	dev->stats.rx_missed_errors = rx_errors;
+	dev->stats.rx_dropped = rx_dropped;
 	return &dev->stats;
 }
 
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index 53b50c24d9c9..2c4c12b03502 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -35,8 +35,8 @@ config MACB
 config MACB_USE_HWSTAMP
 	bool "Use IEEE 1588 hwstamp"
 	depends on MACB
+	depends on PTP_1588_CLOCK
 	default y
-	imply PTP_1588_CLOCK
 	---help---
 	  Enable IEEE 1588 Precision Time Protocol (PTP) support for MACB.
 
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index a0e8c5bbabc0..36290a8e2a84 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -334,8 +334,10 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	int status;
 
 	status = pm_runtime_get_sync(&bp->pdev->dev);
-	if (status < 0)
+	if (status < 0) {
+		pm_runtime_put_noidle(&bp->pdev->dev);
 		goto mdio_pm_exit;
+	}
 
 	status = macb_mdio_wait_for_idle(bp);
 	if (status < 0)
@@ -386,8 +388,10 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	int status;
 
 	status = pm_runtime_get_sync(&bp->pdev->dev);
-	if (status < 0)
+	if (status < 0) {
+		pm_runtime_put_noidle(&bp->pdev->dev);
 		goto mdio_pm_exit;
+	}
 
 	status = macb_mdio_wait_for_idle(bp);
 	if (status < 0)
@@ -3816,8 +3820,10 @@ static int at91ether_open(struct net_device *dev)
 	int ret;
 
 	ret = pm_runtime_get_sync(&lp->pdev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(&lp->pdev->dev);
 		return ret;
+	}
 
 	/* Clear internal statistics */
 	ctl = macb_readl(lp, NCR);
@@ -4172,15 +4178,9 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk,
 
 static int fu540_c000_init(struct platform_device *pdev)
 {
-	struct resource *res;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (!res)
-		return -ENODEV;
-
-	mgmt->reg = ioremap(res->start, resource_size(res));
-	if (!mgmt->reg)
-		return -ENOMEM;
+	mgmt->reg = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(mgmt->reg))
+		return PTR_ERR(mgmt->reg);
 
 	return macb_init(pdev);
 }
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 6a700d34019e..4520e7ee00fe 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -54,7 +54,7 @@ config	THUNDER_NIC_RGX
 config CAVIUM_PTP
 	tristate "Cavium PTP coprocessor as PTP clock"
 	depends on 64BIT && PCI
-	imply PTP_1588_CLOCK
+	depends on PTP_1588_CLOCK
 	---help---
 	  This driver adds support for the Precision Time Protocol Clocks and
 	  Timestamping coprocessor (PTP) found on Cavium processors.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index 19c11568113a..7b9cd69f9844 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -1049,9 +1049,9 @@ static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init,
 	}
 }
 
-static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init,
-					   struct cudbg_error *cudbg_err,
-					   u8 mem_type)
+static int cudbg_mem_region_size(struct cudbg_init *pdbg_init,
+				 struct cudbg_error *cudbg_err,
+				 u8 mem_type, unsigned long *region_size)
 {
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_meminfo mem_info;
@@ -1060,15 +1060,23 @@ static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init,
 
 	memset(&mem_info, 0, sizeof(struct cudbg_meminfo));
 	rc = cudbg_fill_meminfo(padap, &mem_info);
-	if (rc)
+	if (rc) {
+		cudbg_err->sys_err = rc;
 		return rc;
+	}
 
 	cudbg_t4_fwcache(pdbg_init, cudbg_err);
 	rc = cudbg_meminfo_get_mem_index(padap, &mem_info, mem_type, &mc_idx);
-	if (rc)
+	if (rc) {
+		cudbg_err->sys_err = rc;
 		return rc;
+	}
+
+	if (region_size)
+		*region_size = mem_info.avail[mc_idx].limit -
+			       mem_info.avail[mc_idx].base;
 
-	return mem_info.avail[mc_idx].limit - mem_info.avail[mc_idx].base;
+	return 0;
 }
 
 static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
@@ -1076,7 +1084,12 @@ static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
 				    struct cudbg_error *cudbg_err,
 				    u8 mem_type)
 {
-	unsigned long size = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type);
+	unsigned long size = 0;
+	int rc;
+
+	rc = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type, &size);
+	if (rc)
+		return rc;
 
 	return cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type, size,
 				 cudbg_err);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
index af1f40cbccc8..f5bc996ac77d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
@@ -311,32 +311,17 @@ static int cxgb4_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
  */
 static int cxgb4_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 {
-	struct adapter *adapter = (struct adapter *)container_of(ptp,
-				   struct adapter, ptp_clock_info);
-	struct fw_ptp_cmd c;
+	struct adapter *adapter = container_of(ptp, struct adapter,
+					       ptp_clock_info);
 	u64 ns;
-	int err;
-
-	memset(&c, 0, sizeof(c));
-	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
-				     FW_CMD_REQUEST_F |
-				     FW_CMD_READ_F |
-				     FW_PTP_CMD_PORTID_V(0));
-	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
-	c.u.ts.sc = FW_PTP_SC_GET_TIME;
 
-	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), &c);
-	if (err < 0) {
-		dev_err(adapter->pdev_dev,
-			"PTP: %s error %d\n", __func__, -err);
-		return err;
-	}
+	ns = t4_read_reg(adapter, T5_PORT_REG(0, MAC_PORT_PTP_SUM_LO_A));
+	ns |= (u64)t4_read_reg(adapter,
+			       T5_PORT_REG(0, MAC_PORT_PTP_SUM_HI_A)) << 32;
 
 	/* convert to timespec*/
-	ns = be64_to_cpu(c.u.ts.tm);
 	*ts = ns_to_timespec64(ns);
-
-	return err;
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index f5dd34db4b54..6516c45864b3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2207,6 +2207,9 @@ static void ethofld_hard_xmit(struct net_device *dev,
 	if (unlikely(skip_eotx_wr)) {
 		start = (u64 *)wr;
 		eosw_txq->state = next_state;
+		eosw_txq->cred -= wrlen16;
+		eosw_txq->ncompl++;
+		eosw_txq->last_compl = 0;
 		goto write_wr_headers;
 	}
 
@@ -2365,6 +2368,34 @@ netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return cxgb4_eth_xmit(skb, dev);
 }
 
+static void eosw_txq_flush_pending_skbs(struct sge_eosw_txq *eosw_txq)
+{
+	int pktcount = eosw_txq->pidx - eosw_txq->last_pidx;
+	int pidx = eosw_txq->pidx;
+	struct sk_buff *skb;
+
+	if (!pktcount)
+		return;
+
+	if (pktcount < 0)
+		pktcount += eosw_txq->ndesc;
+
+	while (pktcount--) {
+		pidx--;
+		if (pidx < 0)
+			pidx += eosw_txq->ndesc;
+
+		skb = eosw_txq->desc[pidx].skb;
+		if (skb) {
+			dev_consume_skb_any(skb);
+			eosw_txq->desc[pidx].skb = NULL;
+			eosw_txq->inuse--;
+		}
+	}
+
+	eosw_txq->pidx = eosw_txq->last_pidx + 1;
+}
+
 /**
  * cxgb4_ethofld_send_flowc - Send ETHOFLD flowc request to bind eotid to tc.
  * @dev - netdevice
@@ -2440,9 +2471,11 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc)
 					    FW_FLOWC_MNEM_EOSTATE_CLOSING :
 					    FW_FLOWC_MNEM_EOSTATE_ESTABLISHED);
 
-	eosw_txq->cred -= len16;
-	eosw_txq->ncompl++;
-	eosw_txq->last_compl = 0;
+	/* Free up any pending skbs to ensure there's room for
+	 * termination FLOWC.
+	 */
+	if (tc == FW_SCHED_CLS_NONE)
+		eosw_txq_flush_pending_skbs(eosw_txq);
 
 	ret = eosw_txq_enqueue(eosw_txq, skb);
 	if (ret) {
@@ -2695,6 +2728,7 @@ static void ofldtxq_stop(struct sge_uld_txq *q, struct fw_wr_hdr *wr)
  *	is ever running at a time ...
  */
 static void service_ofldq(struct sge_uld_txq *q)
+	__must_hold(&q->sendq.lock)
 {
 	u64 *pos, *before, *end;
 	int credits;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 239f678a94ed..2a3480fc1d91 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3742,7 +3742,7 @@ int t4_phy_fw_ver(struct adapter *adap, int *phy_fw_ver)
 		 FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_VERSION));
 	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1,
 			      &param, &val);
-	if (ret < 0)
+	if (ret)
 		return ret;
 	*phy_fw_ver = val;
 	return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index bb20e50ddb84..4a9fcd6c226c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1906,6 +1906,9 @@
 
 #define MAC_PORT_CFG2_A 0x818
 
+#define MAC_PORT_PTP_SUM_LO_A 0x990
+#define MAC_PORT_PTP_SUM_HI_A 0x994
+
 #define MPS_CMN_CTL_A	0x9000
 
 #define COUNTPAUSEMCRX_S    5
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 48ea658aa1a6..15efc294f513 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -1277,7 +1277,7 @@ static const struct net_device_ops tulip_netdev_ops = {
 #endif
 };
 
-const struct pci_device_id early_486_chipsets[] = {
+static const struct pci_device_id early_486_chipsets[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82424) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_SI, PCI_DEVICE_ID_SI_496) },
 	{ },
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index 2bd7ace0a953..bfc6bfe94d0a 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -77,6 +77,7 @@ config UCC_GETH
 	depends on QUICC_ENGINE && PPC32
 	select FSL_PQ_MDIO
 	select PHYLIB
+	select FIXED_PHY
 	---help---
 	  This driver supports the Gigabit Ethernet mode of the QUICC Engine,
 	  which is available on some Freescale SOCs.
@@ -90,6 +91,7 @@ config GIANFAR
 	depends on HAS_DMA
 	select FSL_PQ_MDIO
 	select PHYLIB
+	select FIXED_PHY
 	select CRC32
 	---help---
 	  This driver supports the Gigabit TSEC on the MPC83xx, MPC85xx,
diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig
index 3b325733a4f8..0a54c7e0e4ae 100644
--- a/drivers/net/ethernet/freescale/dpaa/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa/Kconfig
@@ -3,6 +3,7 @@ menuconfig FSL_DPAA_ETH
 	tristate "DPAA Ethernet"
 	depends on FSL_DPAA && FSL_FMAN
 	select PHYLIB
+	select FIXED_PHY
 	select FSL_FMAN_MAC
 	---help---
 	  Data Path Acceleration Architecture Ethernet driver,
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 2cd1f8efdfa3..6bfa7575af94 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2914,7 +2914,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	}
 
 	/* Do this here, so we can be verbose early */
-	SET_NETDEV_DEV(net_dev, dev);
+	SET_NETDEV_DEV(net_dev, dev->parent);
 	dev_set_drvdata(dev, net_dev);
 
 	priv = netdev_priv(net_dev);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index b6c46639aa4c..d97c320a2dc0 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -86,7 +86,7 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv,
 	for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) {
 		addr = dpaa2_sg_get_addr(&sgt[i]);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 
 		free_pages((unsigned long)sg_vaddr, 0);
@@ -144,7 +144,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 		/* Get the address and length from the S/G entry */
 		sg_addr = dpaa2_sg_get_addr(sge);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr);
-		dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, sg_addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 
 		sg_length = dpaa2_sg_get_len(sge);
@@ -185,7 +185,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 				(page_address(page) - page_address(head_page));
 
 			skb_add_rx_frag(skb, i - 1, head_page, page_offset,
-					sg_length, DPAA2_ETH_RX_BUF_SIZE);
+					sg_length, priv->rx_buf_size);
 		}
 
 		if (dpaa2_sg_is_final(sge))
@@ -211,7 +211,7 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
 
 	for (i = 0; i < count; i++) {
 		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, buf_array[i], priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		free_pages((unsigned long)vaddr, 0);
 	}
@@ -335,7 +335,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		break;
 	case XDP_REDIRECT:
 		dma_unmap_page(priv->net_dev->dev.parent, addr,
-			       DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL);
+			       priv->rx_buf_size, DMA_BIDIRECTIONAL);
 		ch->buf_count--;
 		xdp.data_hard_start = vaddr;
 		err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog);
@@ -374,7 +374,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	trace_dpaa2_rx_fd(priv->net_dev, fd);
 
 	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-	dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+	dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size,
 				DMA_BIDIRECTIONAL);
 
 	fas = dpaa2_get_fas(vaddr, false);
@@ -393,13 +393,13 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			return;
 		}
 
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
 
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		skb = build_frag_skb(priv, ch, buf_data);
 		free_pages((unsigned long)vaddr, 0);
@@ -974,7 +974,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		if (!page)
 			goto err_alloc;
 
-		addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE,
+		addr = dma_map_page(dev, page, 0, priv->rx_buf_size,
 				    DMA_BIDIRECTIONAL);
 		if (unlikely(dma_mapping_error(dev, addr)))
 			goto err_map;
@@ -984,7 +984,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		/* tracing point */
 		trace_dpaa2_eth_buf_seed(priv->net_dev,
 					 page, DPAA2_ETH_RX_BUF_RAW_SIZE,
-					 addr, DPAA2_ETH_RX_BUF_SIZE,
+					 addr, priv->rx_buf_size,
 					 bpid);
 	}
 
@@ -1720,7 +1720,7 @@ static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu)
 	int mfl, linear_mfl;
 
 	mfl = DPAA2_ETH_L2_MAX_FRM(mtu);
-	linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE -
+	linear_mfl = priv->rx_buf_size - DPAA2_ETH_RX_HWA_SIZE -
 		     dpaa2_eth_rx_head_room(priv) - XDP_PACKET_HEADROOM;
 
 	if (mfl > linear_mfl) {
@@ -2462,6 +2462,11 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	else
 		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
 
+	/* We need to ensure that the buffer size seen by WRIOP is a multiple
+	 * of 64 or 256 bytes depending on the WRIOP version.
+	 */
+	priv->rx_buf_size = ALIGN_DOWN(DPAA2_ETH_RX_BUF_SIZE, rx_buf_align);
+
 	/* tx buffer */
 	buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE;
 	buf_layout.pass_timestamp = true;
@@ -3126,7 +3131,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv)
 	pools_params.num_dpbp = 1;
 	pools_params.pools[0].dpbp_id = priv->dpbp_dev->obj_desc.id;
 	pools_params.pools[0].backup_pool = 0;
-	pools_params.pools[0].buffer_size = DPAA2_ETH_RX_BUF_SIZE;
+	pools_params.pools[0].buffer_size = priv->rx_buf_size;
 	err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params);
 	if (err) {
 		dev_err(dev, "dpni_set_pools() failed\n");
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 7635db3ef903..13242bf5b427 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -382,6 +382,7 @@ struct dpaa2_eth_priv {
 	u16 tx_data_offset;
 
 	struct fsl_mc_device *dpbp_dev;
+	u16 rx_buf_size;
 	u16 bpid;
 	struct iommu_domain *iommu_domain;
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 94347c695233..b7141fdc279e 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -635,7 +635,7 @@ static int num_rules(struct dpaa2_eth_priv *priv)
 
 static int update_cls_rule(struct net_device *net_dev,
 			   struct ethtool_rx_flow_spec *new_fs,
-			   int location)
+			   unsigned int location)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	struct dpaa2_eth_cls_rule *rule;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c
index ebc635f8a4cc..15f37c5b8dc1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c
@@ -74,8 +74,8 @@ err_pci_mem_reg:
 	pci_disable_device(pdev);
 err_pci_enable:
 err_mdiobus_alloc:
-	iounmap(port_regs);
 err_hw_alloc:
+	iounmap(port_regs);
 err_ioremap:
 	return err;
 }
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index bd898f5b4da5..e74dd1f86bba 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -488,6 +488,12 @@ struct fec_enet_priv_rx_q {
 	struct  sk_buff *rx_skbuff[RX_RING_SIZE];
 };
 
+struct fec_stop_mode_gpr {
+	struct regmap *gpr;
+	u8 reg;
+	u8 bit;
+};
+
 /* The FEC buffer descriptors track the ring buffers.  The rx_bd_base and
  * tx_bd_base always point to the base of the buffer descriptors.  The
  * cur_rx and cur_tx point to the currently available buffer.
@@ -562,6 +568,7 @@ struct fec_enet_private {
 	int hwts_tx_en;
 	struct delayed_work time_keep;
 	struct regulator *reg_phy;
+	struct fec_stop_mode_gpr stop_gpr;
 
 	unsigned int tx_align;
 	unsigned int rx_align;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c1c267b61647..dc6f8763a5d4 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -62,6 +62,8 @@
 #include <linux/if_vlan.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/prefetch.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 #include <soc/imx/cpuidle.h>
 
 #include <asm/cacheflush.h>
@@ -84,6 +86,56 @@ static void fec_enet_itr_coal_init(struct net_device *ndev);
 #define FEC_ENET_OPD_V	0xFFF0
 #define FEC_MDIO_PM_TIMEOUT  100 /* ms */
 
+struct fec_devinfo {
+	u32 quirks;
+	u8 stop_gpr_reg;
+	u8 stop_gpr_bit;
+};
+
+static const struct fec_devinfo fec_imx25_info = {
+	.quirks = FEC_QUIRK_USE_GASKET | FEC_QUIRK_MIB_CLEAR |
+		  FEC_QUIRK_HAS_FRREG,
+};
+
+static const struct fec_devinfo fec_imx27_info = {
+	.quirks = FEC_QUIRK_MIB_CLEAR | FEC_QUIRK_HAS_FRREG,
+};
+
+static const struct fec_devinfo fec_imx28_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
+		  FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC |
+		  FEC_QUIRK_HAS_FRREG,
+};
+
+static const struct fec_devinfo fec_imx6q_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
+		  FEC_QUIRK_HAS_RACC,
+	.stop_gpr_reg = 0x34,
+	.stop_gpr_bit = 27,
+};
+
+static const struct fec_devinfo fec_mvf600_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC,
+};
+
+static const struct fec_devinfo fec_imx6x_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
+		  FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
+		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
+};
+
+static const struct fec_devinfo fec_imx6ul_info = {
+	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 |
+		  FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC |
+		  FEC_QUIRK_HAS_COALESCE,
+};
+
 static struct platform_device_id fec_devtype[] = {
 	{
 		/* keep it for coldfire */
@@ -91,39 +143,25 @@ static struct platform_device_id fec_devtype[] = {
 		.driver_data = 0,
 	}, {
 		.name = "imx25-fec",
-		.driver_data = FEC_QUIRK_USE_GASKET | FEC_QUIRK_MIB_CLEAR |
-			       FEC_QUIRK_HAS_FRREG,
+		.driver_data = (kernel_ulong_t)&fec_imx25_info,
 	}, {
 		.name = "imx27-fec",
-		.driver_data = FEC_QUIRK_MIB_CLEAR | FEC_QUIRK_HAS_FRREG,
+		.driver_data = (kernel_ulong_t)&fec_imx27_info,
 	}, {
 		.name = "imx28-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
-				FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC |
-				FEC_QUIRK_HAS_FRREG,
+		.driver_data = (kernel_ulong_t)&fec_imx28_info,
 	}, {
 		.name = "imx6q-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
-				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
-				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
-				FEC_QUIRK_HAS_RACC,
+		.driver_data = (kernel_ulong_t)&fec_imx6q_info,
 	}, {
 		.name = "mvf600-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC,
+		.driver_data = (kernel_ulong_t)&fec_mvf600_info,
 	}, {
 		.name = "imx6sx-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
-				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
-				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
-				FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
-				FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
+		.driver_data = (kernel_ulong_t)&fec_imx6x_info,
 	}, {
 		.name = "imx6ul-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
-				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
-				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 |
-				FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC |
-				FEC_QUIRK_HAS_COALESCE,
+		.driver_data = (kernel_ulong_t)&fec_imx6ul_info,
 	}, {
 		/* sentinel */
 	}
@@ -1092,11 +1130,28 @@ fec_restart(struct net_device *ndev)
 
 }
 
+static void fec_enet_stop_mode(struct fec_enet_private *fep, bool enabled)
+{
+	struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
+	struct fec_stop_mode_gpr *stop_gpr = &fep->stop_gpr;
+
+	if (stop_gpr->gpr) {
+		if (enabled)
+			regmap_update_bits(stop_gpr->gpr, stop_gpr->reg,
+					   BIT(stop_gpr->bit),
+					   BIT(stop_gpr->bit));
+		else
+			regmap_update_bits(stop_gpr->gpr, stop_gpr->reg,
+					   BIT(stop_gpr->bit), 0);
+	} else if (pdata && pdata->sleep_mode_enable) {
+		pdata->sleep_mode_enable(enabled);
+	}
+}
+
 static void
 fec_stop(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
 	u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8);
 	u32 val;
 
@@ -1125,9 +1180,7 @@ fec_stop(struct net_device *ndev)
 		val = readl(fep->hwp + FEC_ECNTRL);
 		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
 		writel(val, fep->hwp + FEC_ECNTRL);
-
-		if (pdata && pdata->sleep_mode_enable)
-			pdata->sleep_mode_enable(true);
+		fec_enet_stop_mode(fep, true);
 	}
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
@@ -3398,6 +3451,37 @@ static int fec_enet_get_irq_cnt(struct platform_device *pdev)
 	return irq_cnt;
 }
 
+static int fec_enet_init_stop_mode(struct fec_enet_private *fep,
+				   struct fec_devinfo *dev_info,
+				   struct device_node *np)
+{
+	struct device_node *gpr_np;
+	int ret = 0;
+
+	if (!dev_info)
+		return 0;
+
+	gpr_np = of_parse_phandle(np, "gpr", 0);
+	if (!gpr_np)
+		return 0;
+
+	fep->stop_gpr.gpr = syscon_node_to_regmap(gpr_np);
+	if (IS_ERR(fep->stop_gpr.gpr)) {
+		dev_err(&fep->pdev->dev, "could not find gpr regmap\n");
+		ret = PTR_ERR(fep->stop_gpr.gpr);
+		fep->stop_gpr.gpr = NULL;
+		goto out;
+	}
+
+	fep->stop_gpr.reg = dev_info->stop_gpr_reg;
+	fep->stop_gpr.bit = dev_info->stop_gpr_bit;
+
+out:
+	of_node_put(gpr_np);
+
+	return ret;
+}
+
 static int
 fec_probe(struct platform_device *pdev)
 {
@@ -3413,6 +3497,7 @@ fec_probe(struct platform_device *pdev)
 	int num_rx_qs;
 	char irq_name[8];
 	int irq_cnt;
+	struct fec_devinfo *dev_info;
 
 	fec_enet_get_queue_num(pdev, &num_tx_qs, &num_rx_qs);
 
@@ -3430,7 +3515,9 @@ fec_probe(struct platform_device *pdev)
 	of_id = of_match_device(fec_dt_ids, &pdev->dev);
 	if (of_id)
 		pdev->id_entry = of_id->data;
-	fep->quirks = pdev->id_entry->driver_data;
+	dev_info = (struct fec_devinfo *)pdev->id_entry->driver_data;
+	if (dev_info)
+		fep->quirks = dev_info->quirks;
 
 	fep->netdev = ndev;
 	fep->num_rx_queues = num_rx_qs;
@@ -3464,6 +3551,10 @@ fec_probe(struct platform_device *pdev)
 	if (of_get_property(np, "fsl,magic-packet", NULL))
 		fep->wol_flag |= FEC_WOL_HAS_MAGIC_PACKET;
 
+	ret = fec_enet_init_stop_mode(fep, dev_info, np);
+	if (ret)
+		goto failed_stop_mode;
+
 	phy_node = of_parse_phandle(np, "phy-handle", 0);
 	if (!phy_node && of_phy_is_fixed_link(np)) {
 		ret = of_phy_register_fixed_link(np);
@@ -3632,6 +3723,7 @@ failed_clk:
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(phy_node);
+failed_stop_mode:
 failed_phy:
 	dev_id--;
 failed_ioremap:
@@ -3709,7 +3801,6 @@ static int __maybe_unused fec_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
 	int ret;
 	int val;
 
@@ -3727,8 +3818,8 @@ static int __maybe_unused fec_resume(struct device *dev)
 			goto failed_clk;
 		}
 		if (fep->wol_flag & FEC_WOL_FLAG_ENABLE) {
-			if (pdata && pdata->sleep_mode_enable)
-				pdata->sleep_mode_enable(false);
+			fec_enet_stop_mode(fep, false);
+
 			val = readl(fep->hwp + FEC_ECNTRL);
 			val &= ~(FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
 			writel(val, fep->hwp + FEC_ECNTRL);
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 6e5f6dd169b5..552e7554a9f8 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -42,6 +42,7 @@
 #include <soc/fsl/qe/ucc.h>
 #include <soc/fsl/qe/ucc_fast.h>
 #include <asm/machdep.h>
+#include <net/sch_generic.h>
 
 #include "ucc_geth.h"
 
@@ -1548,11 +1549,8 @@ static int ugeth_disable(struct ucc_geth_private *ugeth, enum comm_dir mode)
 
 static void ugeth_quiesce(struct ucc_geth_private *ugeth)
 {
-	/* Prevent any further xmits, plus detach the device. */
-	netif_device_detach(ugeth->ndev);
-
-	/* Wait for any current xmits to finish. */
-	netif_tx_disable(ugeth->ndev);
+	/* Prevent any further xmits */
+	netif_tx_stop_all_queues(ugeth->ndev);
 
 	/* Disable the interrupt to avoid NAPI rescheduling. */
 	disable_irq(ugeth->ug_info->uf_info.irq);
@@ -1565,7 +1563,10 @@ static void ugeth_activate(struct ucc_geth_private *ugeth)
 {
 	napi_enable(&ugeth->napi);
 	enable_irq(ugeth->ug_info->uf_info.irq);
-	netif_device_attach(ugeth->ndev);
+
+	/* allow to xmit again  */
+	netif_tx_wake_all_queues(ugeth->ndev);
+	__netdev_watchdog_up(ugeth->ndev);
 }
 
 /* Called every time the controller might need to be made
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 3892a2062404..2fff43509098 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -64,7 +64,7 @@ config HNS_MDIO
 	  the PHY
 
 config HNS
-	tristate "Hisilicon Network Subsystem Support (Framework)"
+	tristate
 	---help---
 	  This selects the framework support for Hisilicon Network Subsystem. It
 	  is needed by any driver which provides HNS acceleration engine or make
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index 8995e32dd1c0..992908e6eebf 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -45,6 +45,8 @@
 
 #define MGMT_MSG_TIMEOUT                5000
 
+#define SET_FUNC_PORT_MGMT_TIMEOUT	25000
+
 #define mgmt_to_pfhwdev(pf_mgmt)        \
 		container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt)
 
@@ -238,12 +240,13 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
 			    u8 *buf_in, u16 in_size,
 			    u8 *buf_out, u16 *out_size,
 			    enum mgmt_direction_type direction,
-			    u16 resp_msg_id)
+			    u16 resp_msg_id, u32 timeout)
 {
 	struct hinic_hwif *hwif = pf_to_mgmt->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_recv_msg *recv_msg;
 	struct completion *recv_done;
+	unsigned long timeo;
 	u16 msg_id;
 	int err;
 
@@ -267,8 +270,9 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		goto unlock_sync_msg;
 	}
 
-	if (!wait_for_completion_timeout(recv_done,
-					 msecs_to_jiffies(MGMT_MSG_TIMEOUT))) {
+	timeo = msecs_to_jiffies(timeout ? timeout : MGMT_MSG_TIMEOUT);
+
+	if (!wait_for_completion_timeout(recv_done, timeo)) {
 		dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id);
 		err = -ETIMEDOUT;
 		goto unlock_sync_msg;
@@ -342,6 +346,7 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 {
 	struct hinic_hwif *hwif = pf_to_mgmt->hwif;
 	struct pci_dev *pdev = hwif->pdev;
+	u32 timeout = 0;
 
 	if (sync != HINIC_MGMT_MSG_SYNC) {
 		dev_err(&pdev->dev, "Invalid MGMT msg type\n");
@@ -353,9 +358,12 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		return -EINVAL;
 	}
 
+	if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
+		timeout = SET_FUNC_PORT_MGMT_TIMEOUT;
+
 	return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size,
 				buf_out, out_size, MGMT_DIRECT_SEND,
-				MSG_NOT_RESP);
+				MSG_NOT_RESP, timeout);
 }
 
 /**
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 13560975c103..63b92f6cc856 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -483,7 +483,6 @@ static int hinic_close(struct net_device *netdev)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	unsigned int flags;
-	int err;
 
 	down(&nic_dev->mgmt_lock);
 
@@ -497,20 +496,9 @@ static int hinic_close(struct net_device *netdev)
 
 	up(&nic_dev->mgmt_lock);
 
-	err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);
-	if (err) {
-		netif_err(nic_dev, drv, netdev,
-			  "Failed to set func port state\n");
-		nic_dev->flags |= (flags & HINIC_INTF_UP);
-		return err;
-	}
+	hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
 
-	err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
-	if (err) {
-		netif_err(nic_dev, drv, netdev, "Failed to set port state\n");
-		nic_dev->flags |= (flags & HINIC_INTF_UP);
-		return err;
-	}
+	hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);
 
 	if (nic_dev->flags & HINIC_RSS_ENABLE) {
 		hinic_rss_deinit(nic_dev);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 4bd33245bad6..197dc5b2c090 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2189,7 +2189,8 @@ static void __ibmvnic_reset(struct work_struct *work)
 				rc = do_hard_reset(adapter, rwi, reset_state);
 				rtnl_unlock();
 			}
-		} else {
+		} else if (!(rwi->reset_reason == VNIC_RESET_FATAL &&
+				adapter->from_passive_init)) {
 			rc = do_reset(adapter, rwi, reset_state);
 		}
 		kfree(rwi);
@@ -4677,12 +4678,10 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			dev_err(dev, "Error %ld in VERSION_EXCHG_RSP\n", rc);
 			break;
 		}
-		dev_info(dev, "Partner protocol version is %d\n",
-			 crq->version_exchange_rsp.version);
-		if (be16_to_cpu(crq->version_exchange_rsp.version) <
-		    ibmvnic_version)
-			ibmvnic_version =
+		ibmvnic_version =
 			    be16_to_cpu(crq->version_exchange_rsp.version);
+		dev_info(dev, "Partner protocol version is %d\n",
+			 ibmvnic_version);
 		send_cap_queries(adapter);
 		break;
 	case QUERY_CAPABILITY_RSP:
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index f7103356ef56..0d51cbc88028 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -1476,7 +1476,7 @@ static bool e1000_check_64k_bound(struct e1000_adapter *adapter, void *start,
 	if (hw->mac_type == e1000_82545 ||
 	    hw->mac_type == e1000_ce4100 ||
 	    hw->mac_type == e1000_82546) {
-		return ((begin ^ (end - 1)) >> 16) != 0 ? false : true;
+		return ((begin ^ (end - 1)) >> 16) == 0;
 	}
 
 	return true;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 8c3e753bfb9d..2a037ec244b9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1611,7 +1611,7 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
 		}
 	}
 	if (lut) {
-		bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false;
+		bool pf_lut = vsi->type == I40E_VSI_MAIN;
 
 		ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size);
 		if (ret) {
@@ -11436,7 +11436,7 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
 	}
 
 	if (lut) {
-		bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false;
+		bool pf_lut = vsi->type == I40E_VSI_MAIN;
 
 		ret = i40e_aq_get_rss_lut(hw, vsi->id, pf_lut, lut, lut_size);
 		if (ret) {
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 5be61f73b6ab..51889770958d 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -5383,7 +5383,7 @@ static int __init mvneta_driver_init(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "net/mvmeta:online",
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "net/mvneta:online",
 				      mvneta_cpu_online,
 				      mvneta_cpu_down_prepare);
 	if (ret < 0)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 8972cdd559e8..d4a4e241333d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1070,7 +1070,7 @@ void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 		    (port->first_rxq >> MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS));
 
 	val = mvpp2_read(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG);
-	val |= MVPP2_CLS_SWFWD_PCTRL_MASK(port->id);
+	val &= ~MVPP2_CLS_SWFWD_PCTRL_MASK(port->id);
 	mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);
 }
 
@@ -1428,6 +1428,9 @@ int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port,
 	struct mvpp2_ethtool_fs *efs;
 	int ret;
 
+	if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW)
+		return -EINVAL;
+
 	efs = port->rfs_rules[info->fs.location];
 	if (!efs)
 		return -EINVAL;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 1fa60e985b43..2b5dad2ec650 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -4329,6 +4329,8 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir,
 
 	if (!mvpp22_rss_is_supported())
 		return -EOPNOTSUPP;
+	if (rss_context >= MVPP22_N_RSS_TABLES)
+		return -EINVAL;
 
 	if (hfunc)
 		*hfunc = ETH_RSS_HASH_CRC32;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 187c633a7af5..f4227517dc8e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -497,13 +497,17 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE,
 					  GFP_KERNEL);
-	if (!hw->irq_name)
+	if (!hw->irq_name) {
+		err = -ENOMEM;
 		goto err_free_netdev;
+	}
 
 	hw->affinity_mask = devm_kcalloc(&hw->pdev->dev, num_vec,
 					 sizeof(cpumask_var_t), GFP_KERNEL);
-	if (!hw->affinity_mask)
+	if (!hw->affinity_mask) {
+		err = -ENOMEM;
 		goto err_free_netdev;
+	}
 
 	err = pci_alloc_irq_vectors(hw->pdev, num_vec, num_vec, PCI_IRQ_MSIX);
 	if (err < 0) {
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 7a0d785b826c..17243bb5ba91 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1418,7 +1418,7 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 
 	pep->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(pep->base)) {
-		err = -ENOMEM;
+		err = PTR_ERR(pep->base);
 		goto err_netdev;
 	}
 
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 8d28f90acfe7..09047109d0da 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -65,6 +65,17 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg)
 	return __raw_readl(eth->base + reg);
 }
 
+u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned reg)
+{
+	u32 val;
+
+	val = mtk_r32(eth, reg);
+	val &= ~mask;
+	val |= set;
+	mtk_w32(eth, val, reg);
+	return reg;
+}
+
 static int mtk_mdio_busy_wait(struct mtk_eth *eth)
 {
 	unsigned long t_start = jiffies;
@@ -193,7 +204,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 	struct mtk_mac *mac = container_of(config, struct mtk_mac,
 					   phylink_config);
 	struct mtk_eth *eth = mac->hw;
-	u32 mcr_cur, mcr_new, sid;
+	u32 mcr_cur, mcr_new, sid, i;
 	int val, ge_mode, err;
 
 	/* MT76x8 has no hardware settings between for the MAC */
@@ -255,6 +266,17 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 				    PHY_INTERFACE_MODE_TRGMII)
 					mtk_gmac0_rgmii_adjust(mac->hw,
 							       state->speed);
+
+				/* mt7623_pad_clk_setup */
+				for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
+					mtk_w32(mac->hw,
+						TD_DM_DRVP(8) | TD_DM_DRVN(8),
+						TRGMII_TD_ODT(i));
+
+				/* Assert/release MT7623 RXC reset */
+				mtk_m32(mac->hw, 0, RXC_RST | RXC_DQSISEL,
+					TRGMII_RCK_CTRL);
+				mtk_m32(mac->hw, RXC_RST, 0, TRGMII_RCK_CTRL);
 			}
 		}
 
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 85830fe14a1b..454cfcd465fd 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -352,10 +352,13 @@
 #define DQSI0(x)		((x << 0) & GENMASK(6, 0))
 #define DQSI1(x)		((x << 8) & GENMASK(14, 8))
 #define RXCTL_DMWTLAT(x)	((x << 16) & GENMASK(18, 16))
+#define RXC_RST			BIT(31)
 #define RXC_DQSISEL		BIT(30)
 #define RCK_CTRL_RGMII_1000	(RXC_DQSISEL | RXCTL_DMWTLAT(2) | DQSI1(16))
 #define RCK_CTRL_RGMII_10_100	RXCTL_DMWTLAT(2)
 
+#define NUM_TRGMII_CTRL		5
+
 /* TRGMII RXC control register */
 #define TRGMII_TCK_CTRL		0x10340
 #define TXCTL_DMWTLAT(x)	((x << 16) & GENMASK(18, 16))
@@ -363,6 +366,11 @@
 #define TCK_CTRL_RGMII_1000	TXCTL_DMWTLAT(2)
 #define TCK_CTRL_RGMII_10_100	(TXC_INV | TXCTL_DMWTLAT(2))
 
+/* TRGMII TX Drive Strength */
+#define TRGMII_TD_ODT(i)	(0x10354 + 8 * (i))
+#define  TD_DM_DRVP(x)		((x) & 0xf)
+#define  TD_DM_DRVN(x)		(((x) & 0xf) << 4)
+
 /* TRGMII Interface mode register */
 #define INTF_MODE		0x10390
 #define TRGMII_INTF_DIS		BIT(0)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4d5ca302c067..a30edb436f4a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -43,6 +43,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/moduleparam.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include "mlx4_en.h"
 
@@ -261,6 +262,10 @@ static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 	}
 }
 
+INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
+						   struct mlx4_en_tx_ring *ring,
+						   int index, u64 timestamp,
+						   int napi_mode));
 
 u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 			 struct mlx4_en_tx_ring *ring,
@@ -329,6 +334,11 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 	return tx_info->nr_txbb;
 }
 
+INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
+						      struct mlx4_en_tx_ring *ring,
+						      int index, u64 timestamp,
+						      int napi_mode));
+
 u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    struct mlx4_en_tx_ring *ring,
 			    int index, u64 timestamp,
@@ -449,7 +459,9 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
-			last_nr_txbb = ring->free_tx_desc(
+			last_nr_txbb = INDIRECT_CALL_2(ring->free_tx_desc,
+						       mlx4_en_free_tx_desc,
+						       mlx4_en_recycle_tx_desc,
 					priv, ring, ring_index,
 					timestamp, napi_budget);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 6e501af0e532..f6ff9620a137 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -2734,7 +2734,7 @@ void mlx4_opreq_action(struct work_struct *work)
 		if (err) {
 			mlx4_err(dev, "Failed to retrieve required operation: %d\n",
 				 err);
-			return;
+			goto out;
 		}
 		MLX4_GET(modifier, outbox, GET_OP_REQ_MODIFIER_OFFSET);
 		MLX4_GET(token, outbox, GET_OP_REQ_TOKEN_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 5716c3d2bb86..c72c4e1ea383 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2550,6 +2550,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev)
 
 		if (!err || err == -ENOSPC) {
 			priv->def_counter[port] = idx;
+			err = 0;
 		} else if (err == -ENOENT) {
 			err = 0;
 			continue;
@@ -2600,7 +2601,8 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage)
 				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 		if (!err)
 			*idx = get_param_l(&out_param);
-
+		if (WARN_ON(err == -ENOSPC))
+			err = -EINVAL;
 		return err;
 	}
 	return __mlx4_counter_alloc(dev, idx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 312e0a1ad43d..fd375cbe586e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -7,10 +7,10 @@ config MLX5_CORE
 	tristate "Mellanox 5th generation network adapters (ConnectX series) core driver"
 	depends on PCI
 	select NET_DEVLINK
-	imply PTP_1588_CLOCK
-	imply VXLAN
-	imply MLXFW
-	imply PCI_HYPERV_INTERFACE
+	depends on VXLAN || !VXLAN
+	depends on MLXFW || !MLXFW
+	depends on PTP_1588_CLOCK || !PTP_1588_CLOCK
+	depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE
 	default n
 	---help---
 	  Core driver for low level functionality of the ConnectX-4 and
@@ -80,7 +80,7 @@ config MLX5_ESWITCH
 
 config MLX5_TC_CT
 	bool "MLX5 TC connection tracking offload support"
-	depends on MLX5_CORE_EN && NET_SWITCHDEV && NF_FLOW_TABLE && NET_ACT_CT && NET_TC_SKB_EXT
+	depends on MLX5_ESWITCH && NF_FLOW_TABLE && NET_ACT_CT && NET_TC_SKB_EXT
 	default y
 	help
 	  Say Y here if you want to support offloading connection tracking rules
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 34cba97f7bf4..7a77fe40af3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -848,6 +848,14 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg);
 static void mlx5_free_cmd_msg(struct mlx5_core_dev *dev,
 			      struct mlx5_cmd_msg *msg);
 
+static bool opcode_allowed(struct mlx5_cmd *cmd, u16 opcode)
+{
+	if (cmd->allowed_opcode == CMD_ALLOWED_OPCODE_ALL)
+		return true;
+
+	return cmd->allowed_opcode == opcode;
+}
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
@@ -861,6 +869,7 @@ static void cmd_work_handler(struct work_struct *work)
 	int alloc_ret;
 	int cmd_mode;
 
+	complete(&ent->handling);
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
 	if (!ent->page_queue) {
@@ -888,7 +897,6 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 
 	cmd->ent_arr[ent->idx] = ent;
-	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -910,10 +918,13 @@ static void cmd_work_handler(struct work_struct *work)
 
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 
 	/* Skip sending command to fw if internal error */
 	if (pci_channel_offline(dev->pdev) ||
-	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
+	    cmd->state != MLX5_CMDIF_STATE_UP ||
+	    !opcode_allowed(&dev->cmd, ent->op)) {
 		u8 status = 0;
 		u32 drv_synd;
 
@@ -922,6 +933,10 @@ static void cmd_work_handler(struct work_struct *work)
 		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
 
 		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		/* no doorbell, no need to keep the entry */
+		free_ent(cmd, ent->idx);
+		if (ent->callback)
+			free_cmd(ent);
 		return;
 	}
 
@@ -974,6 +989,11 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int err;
 
+	if (!wait_for_completion_timeout(&ent->handling, timeout) &&
+	    cancel_work_sync(&ent->work)) {
+		ent->ret = -ECANCELED;
+		goto out_err;
+	}
 	if (cmd->mode == CMD_MODE_POLLING || ent->polling) {
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
@@ -981,12 +1001,17 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
+out_err:
 	err = ent->ret;
 
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
 			       msg_to_opcode(ent->in));
+	} else if (err == -ECANCELED) {
+		mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n",
+			       mlx5_command_str(msg_to_opcode(ent->in)),
+			       msg_to_opcode(ent->in));
 	}
 	mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n",
 		      err, deliv_status_to_str(ent->status), ent->status);
@@ -1022,6 +1047,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	ent->token = token;
 	ent->polling = force_polling;
 
+	init_completion(&ent->handling);
 	if (!callback)
 		init_completion(&ent->done);
 
@@ -1041,6 +1067,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	err = wait_func(dev, ent);
 	if (err == -ETIMEDOUT)
 		goto out;
+	if (err == -ECANCELED)
+		goto out_free;
 
 	ds = ent->ts2 - ent->ts1;
 	op = MLX5_GET(mbox_in, in->first.data, opcode);
@@ -1387,6 +1415,22 @@ static void create_debugfs_files(struct mlx5_core_dev *dev)
 	mlx5_cmdif_debugfs_init(dev);
 }
 
+void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode)
+{
+	struct mlx5_cmd *cmd = &dev->cmd;
+	int i;
+
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		down(&cmd->sem);
+	down(&cmd->pages_sem);
+
+	cmd->allowed_opcode = opcode;
+
+	up(&cmd->pages_sem);
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		up(&cmd->sem);
+}
+
 static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
@@ -1663,12 +1707,14 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	int err;
 	u8 status = 0;
 	u32 drv_synd;
+	u16 opcode;
 	u8 token;
 
+	opcode = MLX5_GET(mbox_in, in, opcode);
 	if (pci_channel_offline(dev->pdev) ||
-	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-		u16 opcode = MLX5_GET(mbox_in, in, opcode);
-
+	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
+	    dev->cmd.state != MLX5_CMDIF_STATE_UP ||
+	    !opcode_allowed(&dev->cmd, opcode)) {
 		err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status);
 		MLX5_SET(mbox_out, out, status, status);
 		MLX5_SET(mbox_out, out, syndrome, drv_synd);
@@ -1933,6 +1979,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 		goto err_free_page;
 	}
 
+	cmd->state = MLX5_CMDIF_STATE_DOWN;
 	cmd->checksum_disabled = 1;
 	cmd->max_reg_cmds = (1 << cmd->log_sz) - 1;
 	cmd->bitmask = (1UL << cmd->max_reg_cmds) - 1;
@@ -1970,6 +2017,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	mlx5_core_dbg(dev, "descriptor at dma 0x%llx\n", (unsigned long long)(cmd->dma));
 
 	cmd->mode = CMD_MODE_POLLING;
+	cmd->allowed_opcode = CMD_ALLOWED_OPCODE_ALL;
 
 	create_msg_cache(dev);
 
@@ -2009,3 +2057,10 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
 	dma_pool_destroy(cmd->pool);
 }
 EXPORT_SYMBOL(mlx5_cmd_cleanup);
+
+void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
+			enum mlx5_cmdif_state cmdif_state)
+{
+	dev->cmd.state = cmdif_state;
+}
+EXPORT_SYMBOL(mlx5_cmd_set_state);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index bdeb291f6b67..e94f0c4d74a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -23,7 +23,10 @@ static int mlx5_devlink_flash_update(struct devlink *devlink,
 	if (err)
 		return err;
 
-	return mlx5_firmware_flash(dev, fw, extack);
+	err = mlx5_firmware_flash(dev, fw, extack);
+	release_firmware(fw);
+
+	return err;
 }
 
 static u8 mlx5_fw_ver_major(u32 version)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index c9c9b479bda5..5ce6ebbc7f10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -935,7 +935,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 		return NULL;
 	}
 
-	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
+	tracer = kvzalloc(sizeof(*tracer), GFP_KERNEL);
 	if (!tracer)
 		return ERR_PTR(-ENOMEM);
 
@@ -982,7 +982,7 @@ destroy_workqueue:
 	tracer->dev = NULL;
 	destroy_workqueue(tracer->work_queue);
 free_tracer:
-	kfree(tracer);
+	kvfree(tracer);
 	return ERR_PTR(err);
 }
 
@@ -1061,7 +1061,7 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 	mlx5_fw_tracer_destroy_log_buf(tracer);
 	flush_workqueue(tracer->work_queue);
 	destroy_workqueue(tracer->work_queue);
-	kfree(tracer);
+	kvfree(tracer);
 }
 
 static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 12a61bf82c14..0a5aada0f50f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -367,6 +367,7 @@ enum {
 	MLX5E_SQ_STATE_AM,
 	MLX5E_SQ_STATE_TLS,
 	MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE,
+	MLX5E_SQ_STATE_PENDING_XSK_TX,
 };
 
 struct mlx5e_sq_wqe_info {
@@ -960,7 +961,7 @@ void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
-void mlx5e_poll_ico_cq(struct mlx5e_cq *cq);
+int mlx5e_poll_ico_cq(struct mlx5e_cq *cq);
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
@@ -1067,10 +1068,12 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
 
 void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
 				   int num_channels);
-void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params,
-				 u8 cq_period_mode);
-void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
-				 u8 cq_period_mode);
+
+void mlx5e_reset_tx_moderation(struct mlx5e_params *params, u8 cq_period_mode);
+void mlx5e_reset_rx_moderation(struct mlx5e_params *params, u8 cq_period_mode);
+void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode);
+void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode);
+
 void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params);
@@ -1120,7 +1123,7 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq);
 int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
 
 int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv);
 
 int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
 void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 2c4a670c8ffd..2a8950b3056f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -369,17 +369,19 @@ enum mlx5e_fec_supported_link_mode {
 			*_policy = MLX5_GET(pplm_reg, _buf, fec_override_admin_##link);	\
 	} while (0)
 
-#define MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(buf, policy, write, link)		\
-	do {									\
-		u16 *__policy = &(policy);					\
-		bool _write = (write);						\
-										\
-		if (_write && *__policy)					\
-			*__policy = find_first_bit((u_long *)__policy,		\
-						   sizeof(u16) * BITS_PER_BYTE);\
-		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, *__policy, _write, link);	\
-		if (!_write && *__policy)					\
-			*__policy = 1 << *__policy;				\
+#define MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(buf, policy, write, link)			\
+	do {										\
+		unsigned long policy_long;						\
+		u16 *__policy = &(policy);						\
+		bool _write = (write);							\
+											\
+		policy_long = *__policy;						\
+		if (_write && *__policy)						\
+			*__policy = find_first_bit(&policy_long,			\
+						   sizeof(policy_long) * BITS_PER_BYTE);\
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, *__policy, _write, link);		\
+		if (!_write && *__policy)						\
+			*__policy = 1 << *__policy;					\
 	} while (0)
 
 /* get/set FEC admin field for a given speed */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index ad3e3a65d403..4eb305af0106 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -12,6 +12,7 @@
 #include <net/flow_offload.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <linux/workqueue.h>
+#include <linux/xarray.h>
 
 #include "esw/chains.h"
 #include "en/tc_ct.h"
@@ -35,7 +36,7 @@ struct mlx5_tc_ct_priv {
 	struct mlx5_eswitch *esw;
 	const struct net_device *netdev;
 	struct idr fte_ids;
-	struct idr tuple_ids;
+	struct xarray tuple_ids;
 	struct rhashtable zone_ht;
 	struct mlx5_flow_table *ct;
 	struct mlx5_flow_table *ct_nat;
@@ -67,11 +68,9 @@ struct mlx5_ct_ft {
 	struct nf_flowtable *nf_ft;
 	struct mlx5_tc_ct_priv *ct_priv;
 	struct rhashtable ct_entries_ht;
-	struct list_head ct_entries_list;
 };
 
 struct mlx5_ct_entry {
-	struct list_head list;
 	u16 zone;
 	struct rhash_head node;
 	struct flow_rule *flow_rule;
@@ -240,7 +239,7 @@ mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv,
 
 	mlx5_eswitch_del_offloaded_rule(esw, zone_rule->rule, attr);
 	mlx5_modify_header_dealloc(esw->dev, attr->modify_hdr);
-	idr_remove(&ct_priv->tuple_ids, zone_rule->tupleid);
+	xa_erase(&ct_priv->tuple_ids, zone_rule->tupleid);
 }
 
 static void
@@ -485,7 +484,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 	struct mlx5_esw_flow_attr *attr = &zone_rule->attr;
 	struct mlx5_eswitch *esw = ct_priv->esw;
 	struct mlx5_flow_spec *spec = NULL;
-	u32 tupleid = 1;
+	u32 tupleid;
 	int err;
 
 	zone_rule->nat = nat;
@@ -495,12 +494,12 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 		return -ENOMEM;
 
 	/* Get tuple unique id */
-	err = idr_alloc_u32(&ct_priv->tuple_ids, zone_rule, &tupleid,
-			    TUPLE_ID_MAX, GFP_KERNEL);
+	err = xa_alloc(&ct_priv->tuple_ids, &tupleid, zone_rule,
+		       XA_LIMIT(1, TUPLE_ID_MAX), GFP_KERNEL);
 	if (err) {
 		netdev_warn(ct_priv->netdev,
 			    "Failed to allocate tuple id, err: %d\n", err);
-		goto err_idr_alloc;
+		goto err_xa_alloc;
 	}
 	zone_rule->tupleid = tupleid;
 
@@ -541,8 +540,8 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 err_rule:
 	mlx5_modify_header_dealloc(esw->dev, attr->modify_hdr);
 err_mod_hdr:
-	idr_remove(&ct_priv->tuple_ids, zone_rule->tupleid);
-err_idr_alloc:
+	xa_erase(&ct_priv->tuple_ids, zone_rule->tupleid);
+err_xa_alloc:
 	kfree(spec);
 	return err;
 }
@@ -617,8 +616,6 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft,
 	if (err)
 		goto err_insert;
 
-	list_add(&entry->list, &ft->ct_entries_list);
-
 	return 0;
 
 err_insert:
@@ -646,7 +643,6 @@ mlx5_tc_ct_block_flow_offload_del(struct mlx5_ct_ft *ft,
 	WARN_ON(rhashtable_remove_fast(&ft->ct_entries_ht,
 				       &entry->node,
 				       cts_ht_params));
-	list_del(&entry->list);
 	kfree(entry);
 
 	return 0;
@@ -703,6 +699,7 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
 		       struct netlink_ext_ack *extack)
 {
 	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector_key_ct *mask, *key;
 	bool trk, est, untrk, unest, new;
 	u32 ctstate = 0, ctstate_mask = 0;
@@ -710,7 +707,7 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
 	u16 ct_state, ct_state_mask;
 	struct flow_match_ct match;
 
-	if (!flow_rule_match_key(f->rule, FLOW_DISSECTOR_KEY_CT))
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CT))
 		return 0;
 
 	if (!ct_priv) {
@@ -719,7 +716,7 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
-	flow_rule_match_ct(f->rule, &match);
+	flow_rule_match_ct(rule, &match);
 
 	key = match.key;
 	mask = match.mask;
@@ -818,7 +815,6 @@ mlx5_tc_ct_add_ft_cb(struct mlx5_tc_ct_priv *ct_priv, u16 zone,
 	ft->zone = zone;
 	ft->nf_ft = nf_ft;
 	ft->ct_priv = ct_priv;
-	INIT_LIST_HEAD(&ft->ct_entries_list);
 	refcount_set(&ft->refcount, 1);
 
 	err = rhashtable_init(&ft->ct_entries_ht, &cts_ht_params);
@@ -847,12 +843,12 @@ err_init:
 }
 
 static void
-mlx5_tc_ct_flush_ft(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)
+mlx5_tc_ct_flush_ft_entry(void *ptr, void *arg)
 {
-	struct mlx5_ct_entry *entry;
+	struct mlx5_tc_ct_priv *ct_priv = arg;
+	struct mlx5_ct_entry *entry = ptr;
 
-	list_for_each_entry(entry, &ft->ct_entries_list, list)
-		mlx5_tc_ct_entry_del_rules(ft->ct_priv, entry);
+	mlx5_tc_ct_entry_del_rules(ct_priv, entry);
 }
 
 static void
@@ -863,9 +859,10 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)
 
 	nf_flow_table_offload_del_cb(ft->nf_ft,
 				     mlx5_tc_ct_block_flow_offload, ft);
-	mlx5_tc_ct_flush_ft(ct_priv, ft);
 	rhashtable_remove_fast(&ct_priv->zone_ht, &ft->node, zone_params);
-	rhashtable_destroy(&ft->ct_entries_ht);
+	rhashtable_free_and_destroy(&ft->ct_entries_ht,
+				    mlx5_tc_ct_flush_ft_entry,
+				    ct_priv);
 	kfree(ft);
 }
 
@@ -1304,7 +1301,7 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv)
 	}
 
 	idr_init(&ct_priv->fte_ids);
-	idr_init(&ct_priv->tuple_ids);
+	xa_init_flags(&ct_priv->tuple_ids, XA_FLAGS_ALLOC1);
 	mutex_init(&ct_priv->control_lock);
 	rhashtable_init(&ct_priv->zone_ht, &zone_params);
 
@@ -1339,7 +1336,7 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv)
 
 	rhashtable_destroy(&ct_priv->zone_ht);
 	mutex_destroy(&ct_priv->control_lock);
-	idr_destroy(&ct_priv->tuple_ids);
+	xa_destroy(&ct_priv->tuple_ids);
 	idr_destroy(&ct_priv->fte_ids);
 	kfree(ct_priv);
 
@@ -1357,7 +1354,7 @@ mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv,
 	if (!ct_priv || !tupleid)
 		return true;
 
-	zone_rule = idr_find(&ct_priv->tuple_ids, tupleid);
+	zone_rule = xa_load(&ct_priv->tuple_ids, tupleid);
 	if (!zone_rule)
 		return false;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
index 091d305b633e..626f6c04882e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -130,7 +130,9 @@ mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
 		       struct flow_cls_offload *f,
 		       struct netlink_ext_ack *extack)
 {
-	if (!flow_rule_match_key(f->rule, FLOW_DISSECTOR_KEY_CT))
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CT))
 		return 0;
 
 	NL_SET_ERR_MSG_MOD(extack, "mlx5 tc ct offload isn't enabled.");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index fe2d596cb361..3bcdb5b2fc20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -33,6 +33,9 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 		if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &c->xskicosq.state)))
 			return 0;
 
+		if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->xskicosq.state))
+			return 0;
+
 		spin_lock(&c->xskicosq_lock);
 		mlx5e_trigger_irq(&c->xskicosq);
 		spin_unlock(&c->xskicosq_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
index 46725cd743a3..7d1985fa0d4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -69,8 +69,8 @@ static void mlx5e_ktls_del(struct net_device *netdev,
 	struct mlx5e_ktls_offload_context_tx *tx_priv =
 		mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
 
-	mlx5_ktls_destroy_key(priv->mdev, tx_priv->key_id);
 	mlx5e_destroy_tis(priv->mdev, tx_priv->tisn);
+	mlx5_ktls_destroy_key(priv->mdev, tx_priv->key_id);
 	kvfree(tx_priv);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 6d703ddee4e2..bc290ae80a53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -527,8 +527,8 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 	struct dim_cq_moder *rx_moder, *tx_moder;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_channels new_channels = {};
+	bool reset_rx, reset_tx;
 	int err = 0;
-	bool reset;
 
 	if (!MLX5_CAP_GEN(mdev, cq_moderation))
 		return -EOPNOTSUPP;
@@ -566,15 +566,28 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 	}
 	/* we are opened */
 
-	reset = (!!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled) ||
-		(!!coal->use_adaptive_tx_coalesce != priv->channels.params.tx_dim_enabled);
+	reset_rx = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled;
+	reset_tx = !!coal->use_adaptive_tx_coalesce != priv->channels.params.tx_dim_enabled;
 
-	if (!reset) {
+	if (!reset_rx && !reset_tx) {
 		mlx5e_set_priv_channels_coalesce(priv, coal);
 		priv->channels.params = new_channels.params;
 		goto out;
 	}
 
+	if (reset_rx) {
+		u8 mode = MLX5E_GET_PFLAG(&new_channels.params,
+					  MLX5E_PFLAG_RX_CQE_BASED_MODER);
+
+		mlx5e_reset_rx_moderation(&new_channels.params, mode);
+	}
+	if (reset_tx) {
+		u8 mode = MLX5E_GET_PFLAG(&new_channels.params,
+					  MLX5E_PFLAG_TX_CQE_BASED_MODER);
+
+		mlx5e_reset_tx_moderation(&new_channels.params, mode);
+	}
+
 	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL);
 
 out:
@@ -665,11 +678,12 @@ static const u32 pplm_fec_2_ethtool_linkmodes[] = {
 static int get_fec_supported_advertised(struct mlx5_core_dev *dev,
 					struct ethtool_link_ksettings *link_ksettings)
 {
-	u_long active_fec = 0;
+	unsigned long active_fec_long;
+	u32 active_fec;
 	u32 bitn;
 	int err;
 
-	err = mlx5e_get_fec_mode(dev, (u32 *)&active_fec, NULL);
+	err = mlx5e_get_fec_mode(dev, &active_fec, NULL);
 	if (err)
 		return (err == -EOPNOTSUPP) ? 0 : err;
 
@@ -682,10 +696,11 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev,
 	MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_LLRS_272_257_1,
 				      ETHTOOL_LINK_MODE_FEC_LLRS_BIT);
 
+	active_fec_long = active_fec;
 	/* active fec is a bit set, find out which bit is set and
 	 * advertise the corresponding ethtool bit
 	 */
-	bitn = find_first_bit(&active_fec, sizeof(u32) * BITS_PER_BYTE);
+	bitn = find_first_bit(&active_fec_long, sizeof(active_fec_long) * BITS_PER_BYTE);
 	if (bitn < ARRAY_SIZE(pplm_fec_2_ethtool_linkmodes))
 		__set_bit(pplm_fec_2_ethtool_linkmodes[bitn],
 			  link_ksettings->link_modes.advertising);
@@ -1517,8 +1532,8 @@ static int mlx5e_get_fecparam(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 fec_configured = 0;
-	u32 fec_active = 0;
+	u16 fec_configured;
+	u32 fec_active;
 	int err;
 
 	err = mlx5e_get_fec_mode(mdev, &fec_active, &fec_configured);
@@ -1526,14 +1541,14 @@ static int mlx5e_get_fecparam(struct net_device *netdev,
 	if (err)
 		return err;
 
-	fecparam->active_fec = pplm2ethtool_fec((u_long)fec_active,
-						sizeof(u32) * BITS_PER_BYTE);
+	fecparam->active_fec = pplm2ethtool_fec((unsigned long)fec_active,
+						sizeof(unsigned long) * BITS_PER_BYTE);
 
 	if (!fecparam->active_fec)
 		return -EOPNOTSUPP;
 
-	fecparam->fec = pplm2ethtool_fec((u_long)fec_configured,
-					 sizeof(u16) * BITS_PER_BYTE);
+	fecparam->fec = pplm2ethtool_fec((unsigned long)fec_configured,
+					 sizeof(unsigned long) * BITS_PER_BYTE);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index dd7f338425eb..bd8d0e096085 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2717,7 +2717,8 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
 	}
 
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
 		return;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
@@ -3408,14 +3409,15 @@ out:
 	return err;
 }
 
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv)
 {
 	int i;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
 		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]);
 
-	if (!inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
 		return;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
@@ -3583,7 +3585,12 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
-	if (!mlx5e_monitor_counter_supported(priv)) {
+	/* In switchdev mode, monitor counters doesn't monitor
+	 * rx/tx stats of 802_3. The update stats mechanism
+	 * should keep the 802_3 layout counters updated
+	 */
+	if (!mlx5e_monitor_counter_supported(priv) ||
+	    mlx5e_is_uplink_rep(priv)) {
 		/* update HW stats in background for next time */
 		mlx5e_queue_update_stats(priv);
 	}
@@ -4709,7 +4716,7 @@ static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode)
 		DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 }
 
-void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+void mlx5e_reset_tx_moderation(struct mlx5e_params *params, u8 cq_period_mode)
 {
 	if (params->tx_dim_enabled) {
 		u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
@@ -4718,13 +4725,9 @@ void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
 	} else {
 		params->tx_cq_moderation = mlx5e_get_def_tx_moderation(cq_period_mode);
 	}
-
-	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER,
-			params->tx_cq_moderation.cq_period_mode ==
-				MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
 }
 
-void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+void mlx5e_reset_rx_moderation(struct mlx5e_params *params, u8 cq_period_mode)
 {
 	if (params->rx_dim_enabled) {
 		u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode);
@@ -4733,7 +4736,19 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
 	} else {
 		params->rx_cq_moderation = mlx5e_get_def_rx_moderation(cq_period_mode);
 	}
+}
+
+void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+{
+	mlx5e_reset_tx_moderation(params, cq_period_mode);
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER,
+			params->tx_cq_moderation.cq_period_mode ==
+				MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
+}
 
+void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
+{
+	mlx5e_reset_rx_moderation(params, cq_period_mode);
 	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
 			params->rx_cq_moderation.cq_period_mode ==
 				MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
@@ -5118,7 +5133,7 @@ err_destroy_xsk_rqts:
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
@@ -5137,7 +5152,7 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
 	mlx5e_destroy_direct_tirs(priv, priv->xsk_tir);
 	mlx5e_destroy_direct_rqts(priv, priv->xsk_tir);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
@@ -5526,8 +5541,8 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_delete_app(priv);
 #endif
-	mlx5e_devlink_port_unregister(priv);
 	unregister_netdev(priv->netdev);
+	mlx5e_devlink_port_unregister(priv);
 	mlx5e_detach(mdev, vpriv);
 	mlx5e_destroy_netdev(priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2a0243e4af75..4a8e0dfdc5f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1484,13 +1484,9 @@ bool mlx5e_eswitch_uplink_rep(struct net_device *netdev)
 	return netdev->netdev_ops == &mlx5e_netdev_ops_uplink_rep;
 }
 
-bool mlx5e_eswitch_rep(struct net_device *netdev)
+bool mlx5e_eswitch_vf_rep(struct net_device *netdev)
 {
-	if (netdev->netdev_ops == &mlx5e_netdev_ops_rep ||
-	    netdev->netdev_ops == &mlx5e_netdev_ops_uplink_rep)
-		return true;
-
-	return false;
+	return netdev->netdev_ops == &mlx5e_netdev_ops_rep;
 }
 
 static void mlx5e_build_rep_params(struct net_device *netdev)
@@ -1747,7 +1743,7 @@ err_destroy_ttc_table:
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, false);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
@@ -1765,7 +1761,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 	mlx5e_destroy_rep_root_ft(priv);
 	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
-	mlx5e_destroy_indirect_tirs(priv, false);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
@@ -1773,19 +1769,14 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 
 static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv)
 {
-	int err = mlx5e_init_rep_rx(priv);
-
-	if (err)
-		return err;
-
 	mlx5e_create_q_counters(priv);
-	return 0;
+	return mlx5e_init_rep_rx(priv);
 }
 
 static void mlx5e_cleanup_ul_rep_rx(struct mlx5e_priv *priv)
 {
-	mlx5e_destroy_q_counters(priv);
 	mlx5e_cleanup_rep_rx(priv);
+	mlx5e_destroy_q_counters(priv);
 }
 
 static int mlx5e_init_uplink_rep_tx(struct mlx5e_rep_priv *rpriv)
@@ -2050,29 +2041,30 @@ static int register_devlink_port(struct mlx5_core_dev *dev,
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct netdev_phys_item_id ppid = {};
 	unsigned int dl_port_index = 0;
+	u16 pfnum;
 
 	if (!is_devlink_port_supported(dev, rpriv))
 		return 0;
 
 	mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
 
 	if (rep->vport == MLX5_VPORT_UPLINK) {
 		devlink_port_attrs_set(&rpriv->dl_port,
 				       DEVLINK_PORT_FLAVOUR_PHYSICAL,
-				       PCI_FUNC(dev->pdev->devfn), false, 0,
+				       pfnum, false, 0,
 				       &ppid.id[0], ppid.id_len);
 		dl_port_index = vport_to_devlink_port_index(dev, rep->vport);
 	} else if (rep->vport == MLX5_VPORT_PF) {
 		devlink_port_attrs_pci_pf_set(&rpriv->dl_port,
 					      &ppid.id[0], ppid.id_len,
-					      dev->pdev->devfn);
+					      pfnum);
 		dl_port_index = rep->vport;
 	} else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch,
 					    rpriv->rep->vport)) {
 		devlink_port_attrs_pci_vf_set(&rpriv->dl_port,
 					      &ppid.id[0], ppid.id_len,
-					      dev->pdev->devfn,
-					      rep->vport - 1);
+					      pfnum, rep->vport - 1);
 		dl_port_index = vport_to_devlink_port_index(dev, rep->vport);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 6a2337900420..612b5cf0673d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -210,8 +210,13 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 
 void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
 
-bool mlx5e_eswitch_rep(struct net_device *netdev);
+bool mlx5e_eswitch_vf_rep(struct net_device *netdev);
 bool mlx5e_eswitch_uplink_rep(struct net_device *netdev);
+static inline bool mlx5e_eswitch_rep(struct net_device *netdev)
+{
+	return mlx5e_eswitch_vf_rep(netdev) ||
+	       mlx5e_eswitch_uplink_rep(netdev);
+}
 
 #else /* CONFIG_MLX5_ESWITCH */
 static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 6173faf542b0..e2beb89c1832 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -589,7 +589,7 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 	return !!err;
 }
 
-void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
+int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 {
 	struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
 	struct mlx5_cqe64 *cqe;
@@ -597,11 +597,11 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 	int i;
 
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return;
+		return 0;
 
 	cqe = mlx5_cqwq_get_cqe(&cq->wq);
 	if (likely(!cqe))
-		return;
+		return 0;
 
 	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
 	 * otherwise a cq overrun may occur
@@ -650,6 +650,8 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 	sq->cc = sqcc;
 
 	mlx5_cqwq_update_db_record(&cq->wq);
+
+	return i;
 }
 
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 438128dde187..10f705761666 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1343,7 +1343,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		return err;
 
-	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
+	    !(attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR)) {
 		err = mlx5e_attach_mod_hdr(priv, flow, parse_attr);
 		dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
 		if (err)
@@ -2067,7 +2068,7 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev,
 	flow_rule_match_meta(rule, &match);
 	if (match.mask->ingress_ifindex != 0xFFFFFFFF) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask");
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	ingress_dev = __dev_get_by_index(dev_net(filter_dev),
@@ -2075,13 +2076,13 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev,
 	if (!ingress_dev) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't find the ingress port to match on");
-		return -EINVAL;
+		return -ENOENT;
 	}
 
 	if (ingress_dev != filter_dev) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't match on the ingress filter port");
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -3072,6 +3073,11 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 	return true;
 }
 
+static bool same_port_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
+{
+	return priv->mdev == peer_priv->mdev;
+}
+
 static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
 {
 	struct mlx5_core_dev *fmdev, *pmdev;
@@ -3290,7 +3296,7 @@ static inline int hash_encap_info(struct encap_key *key)
 }
 
 
-static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
+static bool is_merged_eswitch_vfs(struct mlx5e_priv *priv,
 				  struct net_device *peer_netdev)
 {
 	struct mlx5e_priv *peer_priv;
@@ -3298,13 +3304,11 @@ static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
 	peer_priv = netdev_priv(peer_netdev);
 
 	return (MLX5_CAP_ESW(priv->mdev, merged_eswitch) &&
-		mlx5e_eswitch_rep(priv->netdev) &&
-		mlx5e_eswitch_rep(peer_netdev) &&
+		mlx5e_eswitch_vf_rep(priv->netdev) &&
+		mlx5e_eswitch_vf_rep(peer_netdev) &&
 		same_hw_devs(priv, peer_priv));
 }
 
-
-
 bool mlx5e_encap_take(struct mlx5e_encap_entry *e)
 {
 	return refcount_inc_not_zero(&e->refcnt);
@@ -3558,12 +3562,13 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv,
 			       struct mlx5_esw_flow_attr *attr,
 			       u32 *action)
 {
-	int nest_level = attr->parse_attr->filter_dev->lower_level;
 	struct flow_action_entry vlan_act = {
 		.id = FLOW_ACTION_VLAN_POP,
 	};
-	int err = 0;
+	int nest_level, err = 0;
 
+	nest_level = attr->parse_attr->filter_dev->lower_level -
+						priv->netdev->lower_level;
 	while (nest_level--) {
 		err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
 		if (err)
@@ -3573,14 +3578,37 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv,
 	return err;
 }
 
+static bool same_hw_reps(struct mlx5e_priv *priv,
+			 struct net_device *peer_netdev)
+{
+	struct mlx5e_priv *peer_priv;
+
+	peer_priv = netdev_priv(peer_netdev);
+
+	return mlx5e_eswitch_rep(priv->netdev) &&
+	       mlx5e_eswitch_rep(peer_netdev) &&
+	       same_hw_devs(priv, peer_priv);
+}
+
+static bool is_lag_dev(struct mlx5e_priv *priv,
+		       struct net_device *peer_netdev)
+{
+	return ((mlx5_lag_is_sriov(priv->mdev) ||
+		 mlx5_lag_is_multipath(priv->mdev)) &&
+		 same_hw_reps(priv, peer_netdev));
+}
+
 bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv,
 				    struct net_device *out_dev)
 {
-	if (is_merged_eswitch_dev(priv, out_dev))
+	if (is_merged_eswitch_vfs(priv, out_dev))
+		return true;
+
+	if (is_lag_dev(priv, out_dev))
 		return true;
 
 	return mlx5e_eswitch_rep(out_dev) &&
-	       same_hw_devs(priv, netdev_priv(out_dev));
+	       same_port_devs(priv, netdev_priv(out_dev));
 }
 
 static bool is_duplicated_output_device(struct net_device *dev,
@@ -3821,10 +3849,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				if (!mlx5e_is_valid_eswitch_fwd_dev(priv, out_dev)) {
 					NL_SET_ERR_MSG_MOD(extack,
 							   "devices are not on same switch HW, can't offload forwarding");
-					netdev_warn(priv->netdev,
-						    "devices %s %s not on same switch HW, can't offload forwarding\n",
-						    priv->netdev->name,
-						    out_dev->name);
 					return -EOPNOTSUPP;
 				}
 
@@ -4586,7 +4610,7 @@ void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
 	dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets;
 	dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes;
 	rpriv->prev_vf_vport_stats = cur_stats;
-	flow_stats_update(&ma->stats, dpkts, dbytes, jiffies,
+	flow_stats_update(&ma->stats, dbytes, dpkts, jiffies,
 			  FLOW_ACTION_HW_STATS_DELAYED);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index fd6b2a1898c5..119a5c6cc167 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -537,10 +537,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
+	u32 dma_fifo_cc, nbytes = 0;
+	u16 ci, sqcc, npkts = 0;
 	struct sk_buff *skb;
-	u32 dma_fifo_cc;
-	u16 sqcc;
-	u16 ci;
 	int i;
 
 	sqcc = sq->cc;
@@ -565,11 +564,15 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 		}
 
 		dev_kfree_skb_any(skb);
+		npkts++;
+		nbytes += wi->num_bytes;
 		sqcc += wi->num_wqebbs;
 	}
 
 	sq->dma_fifo_cc = dma_fifo_cc;
 	sq->cc = sqcc;
+
+	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 }
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 87c49e7a164c..acb20215a33b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -152,7 +152,11 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 				mlx5e_post_rx_wqes,
 				rq);
 	if (xsk_open) {
-		mlx5e_poll_ico_cq(&c->xskicosq.cq);
+		if (mlx5e_poll_ico_cq(&c->xskicosq.cq))
+			/* Don't clear the flag if nothing was polled to prevent
+			 * queueing more WQEs and overflowing XSKICOSQ.
+			 */
+			clear_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->xskicosq.state);
 		busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq);
 		busy_xsk |= mlx5e_napi_xsk_post(xsksq, xskrq);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index cccea3a8eddd..ce6c621af043 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -611,11 +611,13 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 		.nent = MLX5_NUM_CMD_EQE,
 		.mask[0] = 1ull << MLX5_EVENT_TYPE_CMD,
 	};
+	mlx5_cmd_allowed_opcode(dev, MLX5_CMD_OP_CREATE_EQ);
 	err = setup_async_eq(dev, &table->cmd_eq, &param, "cmd");
 	if (err)
 		goto err1;
 
 	mlx5_cmd_use_events(dev);
+	mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL);
 
 	param = (struct mlx5_eq_param) {
 		.irq_index = 0,
@@ -645,6 +647,7 @@ err2:
 	mlx5_cmd_use_polling(dev);
 	cleanup_async_eq(dev, &table->cmd_eq, "cmd");
 err1:
+	mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL);
 	mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 39f42f985fbd..c1848b57f61c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -403,7 +403,6 @@ enum {
 	MLX5_ESW_ATTR_FLAG_VLAN_HANDLED  = BIT(0),
 	MLX5_ESW_ATTR_FLAG_SLOW_PATH     = BIT(1),
 	MLX5_ESW_ATTR_FLAG_NO_IN_PORT    = BIT(2),
-	MLX5_ESW_ATTR_FLAG_HAIRPIN	 = BIT(3),
 };
 
 struct mlx5_esw_flow_attr {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f171eb2234b0..5d9def18ae3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -300,7 +300,6 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	bool split = !!(attr->split_count);
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_table *fdb;
-	bool hairpin = false;
 	int j, i = 0;
 
 	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
@@ -398,21 +397,16 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		goto err_esw_get;
 	}
 
-	if (mlx5_eswitch_termtbl_required(esw, attr, &flow_act, spec)) {
+	if (mlx5_eswitch_termtbl_required(esw, attr, &flow_act, spec))
 		rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, attr,
 						     &flow_act, dest, i);
-		hairpin = true;
-	} else {
+	else
 		rule = mlx5_add_flow_rules(fdb, spec, &flow_act, dest, i);
-	}
 	if (IS_ERR(rule))
 		goto err_add_rule;
 	else
 		atomic64_inc(&esw->offloads.num_flows);
 
-	if (hairpin)
-		attr->flags |= MLX5_ESW_ATTR_FLAG_HAIRPIN;
-
 	return rule;
 
 err_add_rule:
@@ -501,7 +495,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 
 	mlx5_del_flow_rules(rule);
 
-	if (attr->flags & MLX5_ESW_ATTR_FLAG_HAIRPIN) {
+	if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)) {
 		/* unref the term table */
 		for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
 			if (attr->dests[i].termtbl)
@@ -1556,9 +1550,9 @@ static int esw_create_restore_table(struct mlx5_eswitch *esw)
 					   MLX5_FLOW_NAMESPACE_KERNEL, 1,
 					   modact);
 	if (IS_ERR(mod_hdr)) {
+		err = PTR_ERR(mod_hdr);
 		esw_warn(dev, "Failed to create restore mod header, err: %d\n",
 			 err);
-		err = PTR_ERR(mod_hdr);
 		goto err_mod_hdr;
 	}
 
@@ -2225,10 +2219,12 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 		total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev);
 
 	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
+	mutex_init(&esw->fdb_table.offloads.vports.lock);
+	hash_init(esw->fdb_table.offloads.vports.table);
 
 	err = esw_create_uplink_offloads_acl_tables(esw);
 	if (err)
-		return err;
+		goto create_acl_err;
 
 	err = esw_create_offloads_table(esw, total_vports);
 	if (err)
@@ -2246,9 +2242,6 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 	if (err)
 		goto create_fg_err;
 
-	mutex_init(&esw->fdb_table.offloads.vports.lock);
-	hash_init(esw->fdb_table.offloads.vports.table);
-
 	return 0;
 
 create_fg_err:
@@ -2259,18 +2252,19 @@ create_restore_err:
 	esw_destroy_offloads_table(esw);
 create_offloads_err:
 	esw_destroy_uplink_offloads_acl_tables(esw);
-
+create_acl_err:
+	mutex_destroy(&esw->fdb_table.offloads.vports.lock);
 	return err;
 }
 
 static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
 {
-	mutex_destroy(&esw->fdb_table.offloads.vports.lock);
 	esw_destroy_vport_rx_group(esw);
 	esw_destroy_offloads_fdb_tables(esw);
 	esw_destroy_restore_table(esw);
 	esw_destroy_offloads_table(esw);
 	esw_destroy_uplink_offloads_acl_tables(esw);
+	mutex_destroy(&esw->fdb_table.offloads.vports.lock);
 }
 
 static void
@@ -2383,9 +2377,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 err_vports:
 	esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
 err_uplink:
-	esw_set_passing_vport_metadata(esw, false);
-err_steering_init:
 	esw_offloads_steering_cleanup(esw);
+err_steering_init:
+	esw_set_passing_vport_metadata(esw, false);
 err_vport_metadata:
 	mlx5_rdma_disable_roce(esw->dev);
 	mutex_destroy(&esw->offloads.termtbl_mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 8bcf3426b9c6..3ce17c3d7a00 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -346,8 +346,10 @@ int mlx5_events_init(struct mlx5_core_dev *dev)
 	events->dev = dev;
 	dev->priv.events = events;
 	events->wq = create_singlethread_workqueue("mlx5_events");
-	if (!events->wq)
+	if (!events->wq) {
+		kfree(events);
 		return -ENOMEM;
+	}
 	INIT_WORK(&events->pcie_core_work, mlx5_pcie_event);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index d5defe09339a..9620c8650e13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -344,17 +344,12 @@ static void tree_put_node(struct fs_node *node, bool locked)
 		if (node->del_hw_func)
 			node->del_hw_func(node);
 		if (parent_node) {
-			/* Only root namespace doesn't have parent and we just
-			 * need to free its node.
-			 */
 			down_write_ref_node(parent_node, locked);
 			list_del_init(&node->list);
-			if (node->del_sw_func)
-				node->del_sw_func(node);
-			up_write_ref_node(parent_node, locked);
-		} else {
-			kfree(node);
 		}
+		node->del_sw_func(node);
+		if (parent_node)
+			up_write_ref_node(parent_node, locked);
 		node = NULL;
 	}
 	if (!node && parent_node)
@@ -468,8 +463,10 @@ static void del_sw_flow_table(struct fs_node *node)
 	fs_get_obj(ft, node);
 
 	rhltable_destroy(&ft->fgs_hash);
-	fs_get_obj(prio, ft->node.parent);
-	prio->num_ft--;
+	if (ft->node.parent) {
+		fs_get_obj(prio, ft->node.parent);
+		prio->num_ft--;
+	}
 	kfree(ft);
 }
 
@@ -2351,6 +2348,17 @@ static int init_root_tree(struct mlx5_flow_steering *steering,
 	return 0;
 }
 
+static void del_sw_root_ns(struct fs_node *node)
+{
+	struct mlx5_flow_root_namespace *root_ns;
+	struct mlx5_flow_namespace *ns;
+
+	fs_get_obj(ns, node);
+	root_ns = container_of(ns, struct mlx5_flow_root_namespace, ns);
+	mutex_destroy(&root_ns->chain_lock);
+	kfree(node);
+}
+
 static struct mlx5_flow_root_namespace
 *create_root_ns(struct mlx5_flow_steering *steering,
 		enum fs_flow_table_type table_type)
@@ -2377,7 +2385,7 @@ static struct mlx5_flow_root_namespace
 	ns = &root_ns->ns;
 	fs_init_namespace(ns);
 	mutex_init(&root_ns->chain_lock);
-	tree_init_node(&ns->node, NULL, NULL);
+	tree_init_node(&ns->node, NULL, del_sw_root_ns);
 	tree_add_node(&ns->node, NULL);
 
 	return root_ns;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index fa1665caac46..f99e1752d4e5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -243,7 +243,7 @@ recover_from_sw_reset:
 		if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
 			break;
 
-		cond_resched();
+		msleep(20);
 	} while (!time_after(jiffies, end));
 
 	if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 673aaa815f57..505cf6eeae25 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -396,7 +396,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
@@ -412,7 +412,7 @@ static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
 {
 	mlx5i_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7af4210c1b96..17f818a54090 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -965,6 +965,8 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 		goto err_cmd_cleanup;
 	}
 
+	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
+
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
 		mlx5_core_err(dev, "enable hca failed\n");
@@ -1026,6 +1028,7 @@ reclaim_boot_pages:
 err_disable_hca:
 	mlx5_core_disable_hca(dev, 0);
 err_cmd_cleanup:
+	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
 
 	return err;
@@ -1043,6 +1046,7 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 	}
 	mlx5_reclaim_startup_pages(dev);
 	mlx5_core_disable_hca(dev, 0);
+	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
 
 	return 0;
@@ -1191,7 +1195,7 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 
 	err = mlx5_function_setup(dev, boot);
 	if (err)
-		goto out;
+		goto err_function;
 
 	if (boot) {
 		err = mlx5_init_once(dev);
@@ -1229,6 +1233,7 @@ err_load:
 		mlx5_cleanup_once(dev);
 function_teardown:
 	mlx5_function_teardown(dev, boot);
+err_function:
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 	mutex_unlock(&dev->intf_state_mutex);
 
@@ -1544,6 +1549,22 @@ static void shutdown(struct pci_dev *pdev)
 	mlx5_pci_disable_device(dev);
 }
 
+static int mlx5_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+
+	mlx5_unload_one(dev, false);
+
+	return 0;
+}
+
+static int mlx5_resume(struct pci_dev *pdev)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+
+	return mlx5_load_one(dev, false);
+}
+
 static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_CONNECTIB) },
 	{ PCI_VDEVICE(MELLANOX, 0x1012), MLX5_PCI_DEV_IS_VF},	/* Connect-IB VF */
@@ -1587,6 +1608,8 @@ static struct pci_driver mlx5_core_driver = {
 	.id_table       = mlx5_core_pci_table,
 	.probe          = init_one,
 	.remove         = remove_one,
+	.suspend        = mlx5_suspend,
+	.resume         = mlx5_resume,
 	.shutdown	= shutdown,
 	.err_handler	= &mlx5_err_handler,
 	.sriov_configure   = mlx5_core_sriov_configure,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index c0ab9cf74929..18719acb7e54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -695,6 +695,12 @@ static void dr_cq_event(struct mlx5_core_cq *mcq,
 	pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn);
 }
 
+static void dr_cq_complete(struct mlx5_core_cq *mcq,
+			   struct mlx5_eqe *eqe)
+{
+	pr_err("CQ completion CQ: #%u\n", mcq->cqn);
+}
+
 static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 				      struct mlx5_uars_page *uar,
 				      size_t ncqe)
@@ -756,6 +762,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas);
 
 	cq->mcq.event = dr_cq_event;
+	cq->mcq.comp  = dr_cq_complete;
 
 	err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out));
 	kvfree(in);
@@ -767,7 +774,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	cq->mcq.set_ci_db = cq->wq_ctrl.db.db;
 	cq->mcq.arm_db = cq->wq_ctrl.db.db + 1;
 	*cq->mcq.set_ci_db = 0;
-	*cq->mcq.arm_db = 0;
+
+	/* set no-zero value, in order to avoid the HW to run db-recovery on
+	 * CQ that used in polling mode.
+	 */
+	*cq->mcq.arm_db = cpu_to_be32(2 << 28);
+
 	cq->mcq.vector = 0;
 	cq->mcq.irqn = irqn;
 	cq->mcq.uar = uar;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 70a104e728f6..c3d04319ff44 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -380,7 +380,7 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa)
 
 	block = kzalloc(sizeof(*block), GFP_KERNEL);
 	if (!block)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	INIT_LIST_HEAD(&block->resource_list);
 	block->afa = mlxsw_afa;
 
@@ -408,7 +408,7 @@ err_second_set_create:
 	mlxsw_afa_set_destroy(block->first_set);
 err_first_set_create:
 	kfree(block);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(mlxsw_afa_block_create);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 24ca8d5bc564..6b39978acd07 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3986,6 +3986,7 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
 			mlxsw_sp_port_remove(mlxsw_sp, i);
 	mlxsw_sp_cpu_port_remove(mlxsw_sp);
 	kfree(mlxsw_sp->ports);
+	mlxsw_sp->ports = NULL;
 }
 
 static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
@@ -4022,6 +4023,7 @@ err_port_create:
 	mlxsw_sp_cpu_port_remove(mlxsw_sp);
 err_cpu_port_create:
 	kfree(mlxsw_sp->ports);
+	mlxsw_sp->ports = NULL;
 	return err;
 }
 
@@ -4143,6 +4145,14 @@ static int mlxsw_sp_local_ports_offset(struct mlxsw_core *mlxsw_core,
 	return mlxsw_core_res_get(mlxsw_core, local_ports_in_x_res_id);
 }
 
+static struct mlxsw_sp_port *
+mlxsw_sp_port_get_by_local_port(struct mlxsw_sp *mlxsw_sp, u8 local_port)
+{
+	if (mlxsw_sp->ports && mlxsw_sp->ports[local_port])
+		return mlxsw_sp->ports[local_port];
+	return NULL;
+}
+
 static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 			       unsigned int count,
 			       struct netlink_ext_ack *extack)
@@ -4156,7 +4166,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 	int i;
 	int err;
 
-	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	mlxsw_sp_port = mlxsw_sp_port_get_by_local_port(mlxsw_sp, local_port);
 	if (!mlxsw_sp_port) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
 			local_port);
@@ -4251,7 +4261,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port,
 	int offset;
 	int i;
 
-	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	mlxsw_sp_port = mlxsw_sp_port_get_by_local_port(mlxsw_sp, local_port);
 	if (!mlxsw_sp_port) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
 			local_port);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 6c66a0f1b79e..ad69913f19c1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -88,8 +88,8 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
 	 * to be written using PEFA register to all indexes for all regions.
 	 */
 	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
-	if (!afa_block) {
-		err = -ENOMEM;
+	if (IS_ERR(afa_block)) {
+		err = PTR_ERR(afa_block);
 		goto err_afa_block;
 	}
 	err = mlxsw_afa_block_continue(afa_block);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 67ee880a8727..01cff711bbd2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -464,7 +464,7 @@ mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
 
 	rulei = kzalloc(sizeof(*rulei), GFP_KERNEL);
 	if (!rulei)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (afa_block) {
 		rulei->act_block = afa_block;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 430da69003d8..a6e30e020b5c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -986,8 +986,9 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
 				unsigned int priority,
 				struct mlxsw_afk_element_usage *elusage)
 {
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk, *vchunk2;
 	struct mlxsw_sp_acl_tcam_vregion *vregion;
-	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct list_head *pos;
 	int err;
 
 	if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO)
@@ -1025,7 +1026,14 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion);
-	list_add_tail(&vchunk->list, &vregion->vchunk_list);
+
+	/* Position the vchunk inside the list according to priority */
+	list_for_each(pos, &vregion->vchunk_list) {
+		vchunk2 = list_entry(pos, typeof(*vchunk2), list);
+		if (vchunk2->priority > priority)
+			break;
+	}
+	list_add_tail(&vchunk->list, pos);
 	mutex_unlock(&vregion->lock);
 
 	return vchunk;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 51117a5a6bbf..890b078851c9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -36,7 +36,8 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 		err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack);
 		if (err)
 			return err;
-	} else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED) {
+	} else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED &&
+		   act->hw_stats != FLOW_ACTION_HW_STATS_DONT_CARE) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported action HW stats type");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
index 346f4a5fe053..221aa6a474eb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -199,8 +199,8 @@ mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
-	if (!afa_block)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(afa_block))
+		return afa_block;
 
 	err = mlxsw_afa_block_append_allocated_counter(afa_block,
 						       counter_index);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 90535820b559..2503f61db5fb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1259,6 +1259,7 @@ static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
 		if (mlxsw_sx_port_created(mlxsw_sx, i))
 			mlxsw_sx_port_remove(mlxsw_sx, i);
 	kfree(mlxsw_sx->ports);
+	mlxsw_sx->ports = NULL;
 }
 
 static int mlxsw_sx_ports_create(struct mlxsw_sx *mlxsw_sx)
@@ -1293,6 +1294,7 @@ err_port_module_info_get:
 		if (mlxsw_sx_port_created(mlxsw_sx, i))
 			mlxsw_sx_port_remove(mlxsw_sx, i);
 	kfree(mlxsw_sx->ports);
+	mlxsw_sx->ports = NULL;
 	return err;
 }
 
@@ -1376,6 +1378,12 @@ static int mlxsw_sx_port_type_set(struct mlxsw_core *mlxsw_core, u8 local_port,
 	u8 module, width;
 	int err;
 
+	if (!mlxsw_sx->ports || !mlxsw_sx->ports[local_port]) {
+		dev_err(mlxsw_sx->bus_info->dev, "Port number \"%d\" does not exist\n",
+			local_port);
+		return -EINVAL;
+	}
+
 	if (new_type == DEVLINK_PORT_TYPE_AUTO)
 		return -EOPNOTSUPP;
 
diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c
index 39925e4bf2ec..b25a13da900a 100644
--- a/drivers/net/ethernet/microchip/encx24j600.c
+++ b/drivers/net/ethernet/microchip/encx24j600.c
@@ -1070,7 +1070,7 @@ static int encx24j600_spi_probe(struct spi_device *spi)
 	if (unlikely(ret)) {
 		netif_err(priv, probe, ndev, "Error %d initializing card encx24j600 card\n",
 			  ret);
-		goto out_free;
+		goto out_stop;
 	}
 
 	eidled = encx24j600_read_reg(priv, EIDLED);
@@ -1088,6 +1088,8 @@ static int encx24j600_spi_probe(struct spi_device *spi)
 
 out_unregister:
 	unregister_netdev(priv->ndev);
+out_stop:
+	kthread_stop(priv->kworker_task);
 out_free:
 	free_netdev(ndev);
 
@@ -1100,6 +1102,7 @@ static int encx24j600_spi_remove(struct spi_device *spi)
 	struct encx24j600_priv *priv = dev_get_drvdata(&spi->dev);
 
 	unregister_netdev(priv->ndev);
+	kthread_stop(priv->kworker_task);
 
 	free_netdev(priv->ndev);
 
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index e1651756bf9d..f70bb81e1ed6 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -564,7 +564,7 @@ static int moxart_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 
 	unregister_netdev(ndev);
-	free_irq(ndev->irq, ndev);
+	devm_free_irq(&pdev->dev, ndev->irq, ndev);
 	moxart_mac_free_memory(ndev);
 	free_netdev(ndev);
 
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index b4731df186f4..efb3965a3e42 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -183,44 +183,47 @@ static void ocelot_vlan_mode(struct ocelot *ocelot, int port,
 	ocelot_write(ocelot, val, ANA_VLANMASK);
 }
 
-void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
-				bool vlan_aware)
+static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port,
+				       u16 vid)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	u32 val;
+	u32 val = 0;
 
-	if (vlan_aware)
-		val = ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
-		      ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1);
-	else
-		val = 0;
-	ocelot_rmw_gix(ocelot, val,
-		       ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
-		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
-		       ANA_PORT_VLAN_CFG, port);
+	if (ocelot_port->vid != vid) {
+		/* Always permit deleting the native VLAN (vid = 0) */
+		if (ocelot_port->vid && vid) {
+			dev_err(ocelot->dev,
+				"Port already has a native VLAN: %d\n",
+				ocelot_port->vid);
+			return -EBUSY;
+		}
+		ocelot_port->vid = vid;
+	}
 
-	if (vlan_aware && !ocelot_port->vid)
+	ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid),
+		       REW_PORT_VLAN_CFG_PORT_VID_M,
+		       REW_PORT_VLAN_CFG, port);
+
+	if (ocelot_port->vlan_aware && !ocelot_port->vid)
 		/* If port is vlan-aware and tagged, drop untagged and priority
 		 * tagged frames.
 		 */
 		val = ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
 		      ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
 		      ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
-	else
-		val = 0;
 	ocelot_rmw_gix(ocelot, val,
 		       ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
 		       ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
 		       ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA,
 		       ANA_PORT_DROP_CFG, port);
 
-	if (vlan_aware) {
+	if (ocelot_port->vlan_aware) {
 		if (ocelot_port->vid)
 			/* Tag all frames except when VID == DEFAULT_VLAN */
-			val |= REW_TAG_CFG_TAG_CFG(1);
+			val = REW_TAG_CFG_TAG_CFG(1);
 		else
 			/* Tag all frames */
-			val |= REW_TAG_CFG_TAG_CFG(3);
+			val = REW_TAG_CFG_TAG_CFG(3);
 	} else {
 		/* Port tagging disabled. */
 		val = REW_TAG_CFG_TAG_CFG(0);
@@ -228,31 +231,31 @@ void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
 	ocelot_rmw_gix(ocelot, val,
 		       REW_TAG_CFG_TAG_CFG_M,
 		       REW_TAG_CFG, port);
+
+	return 0;
 }
-EXPORT_SYMBOL(ocelot_port_vlan_filtering);
 
-static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port,
-				       u16 vid)
+void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
+				bool vlan_aware)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	u32 val;
 
-	if (ocelot_port->vid != vid) {
-		/* Always permit deleting the native VLAN (vid = 0) */
-		if (ocelot_port->vid && vid) {
-			dev_err(ocelot->dev,
-				"Port already has a native VLAN: %d\n",
-				ocelot_port->vid);
-			return -EBUSY;
-		}
-		ocelot_port->vid = vid;
-	}
+	ocelot_port->vlan_aware = vlan_aware;
 
-	ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid),
-		       REW_PORT_VLAN_CFG_PORT_VID_M,
-		       REW_PORT_VLAN_CFG, port);
+	if (vlan_aware)
+		val = ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		      ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1);
+	else
+		val = 0;
+	ocelot_rmw_gix(ocelot, val,
+		       ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
+		       ANA_PORT_VLAN_CFG, port);
 
-	return 0;
+	ocelot_port_set_native_vlan(ocelot, port, ocelot_port->vid);
 }
+EXPORT_SYMBOL(ocelot_port_vlan_filtering);
 
 /* Default vlan to clasify for untagged frames (may be zero) */
 static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, u16 pvid)
@@ -873,12 +876,12 @@ static void ocelot_get_stats64(struct net_device *dev,
 }
 
 int ocelot_fdb_add(struct ocelot *ocelot, int port,
-		   const unsigned char *addr, u16 vid, bool vlan_aware)
+		   const unsigned char *addr, u16 vid)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 
 	if (!vid) {
-		if (!vlan_aware)
+		if (!ocelot_port->vlan_aware)
 			/* If the bridge is not VLAN aware and no VID was
 			 * provided, set it to pvid to ensure the MAC entry
 			 * matches incoming untagged packets
@@ -905,7 +908,7 @@ static int ocelot_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	struct ocelot *ocelot = priv->port.ocelot;
 	int port = priv->chip_port;
 
-	return ocelot_fdb_add(ocelot, port, addr, vid, priv->vlan_aware);
+	return ocelot_fdb_add(ocelot, port, addr, vid);
 }
 
 int ocelot_fdb_del(struct ocelot *ocelot, int port,
@@ -1028,10 +1031,8 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port,
 {
 	int i, j;
 
-	/* Loop through all the mac tables entries. There are 1024 rows of 4
-	 * entries.
-	 */
-	for (i = 0; i < 1024; i++) {
+	/* Loop through all the mac tables entries. */
+	for (i = 0; i < ocelot->num_mact_rows; i++) {
 		for (j = 0; j < 4; j++) {
 			struct ocelot_mact_entry entry;
 			bool is_static;
@@ -1450,8 +1451,15 @@ static void ocelot_port_attr_stp_state_set(struct ocelot *ocelot, int port,
 
 void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs)
 {
-	ocelot_write(ocelot, ANA_AUTOAGE_AGE_PERIOD(msecs / 2),
-		     ANA_AUTOAGE);
+	unsigned int age_period = ANA_AUTOAGE_AGE_PERIOD(msecs / 2000);
+
+	/* Setting AGE_PERIOD to zero effectively disables automatic aging,
+	 * which is clearly not what our intention is. So avoid that.
+	 */
+	if (!age_period)
+		age_period = 1;
+
+	ocelot_rmw(ocelot, age_period, ANA_AUTOAGE_AGE_PERIOD_M, ANA_AUTOAGE);
 }
 EXPORT_SYMBOL(ocelot_set_ageing_time);
 
@@ -1459,7 +1467,7 @@ static void ocelot_port_attr_ageing_set(struct ocelot *ocelot, int port,
 					unsigned long ageing_clock_t)
 {
 	unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock_t);
-	u32 ageing_time = jiffies_to_msecs(ageing_jiffies) / 1000;
+	u32 ageing_time = jiffies_to_msecs(ageing_jiffies);
 
 	ocelot_set_ageing_time(ocelot, ageing_time);
 }
@@ -1496,8 +1504,8 @@ static int ocelot_port_attr_set(struct net_device *dev,
 		ocelot_port_attr_ageing_set(ocelot, port, attr->u.ageing_time);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
-		priv->vlan_aware = attr->u.vlan_filtering;
-		ocelot_port_vlan_filtering(ocelot, port, priv->vlan_aware);
+		ocelot_port_vlan_filtering(ocelot, port,
+					   attr->u.vlan_filtering);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
 		ocelot_port_attr_mc_set(ocelot, port, !attr->u.mc_disabled);
@@ -1868,7 +1876,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 			} else {
 				err = ocelot_port_bridge_leave(ocelot, port,
 							       info->upper_dev);
-				priv->vlan_aware = false;
 			}
 		}
 		if (netif_is_lag_master(info->upper_dev)) {
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index e34ef8380eb3..641af929497f 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -56,8 +56,6 @@ struct ocelot_port_private {
 	struct phy_device *phy;
 	u8 chip_port;
 
-	u8 vlan_aware;
-
 	struct phy *serdes;
 
 	struct ocelot_port_tc tc;
diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c
index b88b5899b227..7d4fd1b6adda 100644
--- a/drivers/net/ethernet/mscc/ocelot_regs.c
+++ b/drivers/net/ethernet/mscc/ocelot_regs.c
@@ -431,6 +431,7 @@ int ocelot_chip_init(struct ocelot *ocelot, const struct ocelot_ops *ops)
 	ocelot->stats_layout = ocelot_stats_layout;
 	ocelot->num_stats = ARRAY_SIZE(ocelot_stats_layout);
 	ocelot->shared_queue_sz = 224 * 1024;
+	ocelot->num_mact_rows = 1024;
 	ocelot->ops = ops;
 
 	ret = ocelot_regfields_init(ocelot, ocelot_regfields);
diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c
index bfa0c0d39600..8b018ed37b1b 100644
--- a/drivers/net/ethernet/natsemi/jazzsonic.c
+++ b/drivers/net/ethernet/natsemi/jazzsonic.c
@@ -208,11 +208,13 @@ static int jazz_sonic_probe(struct platform_device *pdev)
 
 	err = register_netdev(dev);
 	if (err)
-		goto out1;
+		goto undo_probe1;
 
 	return 0;
 
-out1:
+undo_probe1:
+	dma_free_coherent(lp->device, SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+			  lp->descriptors, lp->descriptors_laddr);
 	release_mem_region(dev->base_addr, SONIC_MEM_SIZE);
 out:
 	free_netdev(dev);
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 0ec6b8e8b549..67e62603fe3b 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -5155,7 +5155,7 @@ static int do_s2io_delete_unicast_mc(struct s2io_nic *sp, u64 addr)
 /* read mac entries from CAM */
 static u64 do_s2io_read_unicast_mc(struct s2io_nic *sp, int offset)
 {
-	u64 tmp64 = 0xffffffffffff0000ULL, val64;
+	u64 tmp64, val64;
 	struct XENA_dev_config __iomem *bar0 = sp->bar0;
 
 	/* read mac addr */
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 9183b3e85d21..bdbf0726145e 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -283,6 +283,7 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn,
 	if (!nfp_nsp_has_hwinfo_lookup(nsp)) {
 		nfp_warn(pf->cpp, "NSP doesn't support PF MAC generation\n");
 		eth_hw_addr_random(nn->dp.netdev);
+		nfp_nsp_close(nsp);
 		return;
 	}
 
@@ -332,8 +333,10 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 		goto err_free_alink;
 
 	alink->prio_map = kzalloc(abm->prio_map_len, GFP_KERNEL);
-	if (!alink->prio_map)
+	if (!alink->prio_map) {
+		err = -ENOMEM;
 		goto err_free_alink;
+	}
 
 	/* This is a multi-host app, make sure MAC/PHY is up, but don't
 	 * make the MAC/PHY state follow the state of any of the ports.
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index c694dbc239d0..6b60771ccb19 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1440,7 +1440,8 @@ __nfp_flower_update_merge_stats(struct nfp_app *app,
 		ctx_id = be32_to_cpu(sub_flow->meta.host_ctx_id);
 		priv->stats[ctx_id].pkts += pkts;
 		priv->stats[ctx_id].bytes += bytes;
-		max_t(u64, priv->stats[ctx_id].used, used);
+		priv->stats[ctx_id].used = max_t(u64, used,
+						 priv->stats[ctx_id].used);
 	}
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
index 5f8fc58d42b3..11621ccc1faf 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
@@ -170,8 +170,7 @@ void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq)
 	debugfs_create_x64("base_pa", 0400, cq_dentry, &cq->base_pa);
 	debugfs_create_u32("num_descs", 0400, cq_dentry, &cq->num_descs);
 	debugfs_create_u32("desc_size", 0400, cq_dentry, &cq->desc_size);
-	debugfs_create_u8("done_color", 0400, cq_dentry,
-			  (u8 *)&cq->done_color);
+	debugfs_create_bool("done_color", 0400, cq_dentry, &cq->done_color);
 
 	debugfs_create_file("tail", 0400, cq_dentry, cq, &cq_tail_fops);
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 4b8a76098ca3..f8a9c1bcffc9 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -2101,6 +2101,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif)
 		ionic_txrx_free(lif);
 	}
 	ionic_lifs_deinit(ionic);
+	ionic_reset(ionic);
 	ionic_qcqs_free(lif);
 
 	dev_info(ionic->dev, "FW Down: LIFs stopped\n");
@@ -2116,6 +2117,8 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 
 	dev_info(ionic->dev, "FW Up: restarting LIFs\n");
 
+	ionic_init_devinfo(ionic);
+	ionic_port_init(ionic);
 	err = ionic_qcqs_alloc(lif);
 	if (err)
 		goto err_out;
@@ -2127,6 +2130,8 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 	if (lif->registered)
 		ionic_lif_set_netdev_info(lif);
 
+	ionic_rx_filter_replay(lif);
+
 	if (netif_running(lif->netdev)) {
 		err = ionic_txrx_alloc(lif);
 		if (err)
@@ -2206,9 +2211,9 @@ static void ionic_lif_deinit(struct ionic_lif *lif)
 	if (!test_bit(IONIC_LIF_F_FW_RESET, lif->state)) {
 		cancel_work_sync(&lif->deferred.work);
 		cancel_work_sync(&lif->tx_timeout_work);
+		ionic_rx_filters_deinit(lif);
 	}
 
-	ionic_rx_filters_deinit(lif);
 	if (lif->netdev->features & NETIF_F_RXHASH)
 		ionic_lif_rss_deinit(lif);
 
@@ -2339,24 +2344,34 @@ static int ionic_station_set(struct ionic_lif *lif)
 	err = ionic_adminq_post_wait(lif, &ctx);
 	if (err)
 		return err;
-
+	netdev_dbg(lif->netdev, "found initial MAC addr %pM\n",
+		   ctx.comp.lif_getattr.mac);
 	if (is_zero_ether_addr(ctx.comp.lif_getattr.mac))
 		return 0;
 
-	memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
-	addr.sa_family = AF_INET;
-	err = eth_prepare_mac_addr_change(netdev, &addr);
-	if (err) {
-		netdev_warn(lif->netdev, "ignoring bad MAC addr from NIC %pM - err %d\n",
-			    addr.sa_data, err);
-		return 0;
-	}
+	if (!is_zero_ether_addr(netdev->dev_addr)) {
+		/* If the netdev mac is non-zero and doesn't match the default
+		 * device address, it was set by something earlier and we're
+		 * likely here again after a fw-upgrade reset.  We need to be
+		 * sure the netdev mac is in our filter list.
+		 */
+		if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
+				      netdev->dev_addr))
+			ionic_lif_addr(lif, netdev->dev_addr, true);
+	} else {
+		/* Update the netdev mac with the device's mac */
+		memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
+		addr.sa_family = AF_INET;
+		err = eth_prepare_mac_addr_change(netdev, &addr);
+		if (err) {
+			netdev_warn(lif->netdev, "ignoring bad MAC addr from NIC %pM - err %d\n",
+				    addr.sa_data, err);
+			return 0;
+		}
 
-	netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n",
-		   netdev->dev_addr);
-	ionic_lif_addr(lif, netdev->dev_addr, false);
+		eth_commit_mac_addr_change(netdev, &addr);
+	}
 
-	eth_commit_mac_addr_change(netdev, &addr);
 	netdev_dbg(lif->netdev, "adding station MAC addr %pM\n",
 		   netdev->dev_addr);
 	ionic_lif_addr(lif, netdev->dev_addr, true);
@@ -2421,9 +2436,11 @@ static int ionic_lif_init(struct ionic_lif *lif)
 	if (err)
 		goto err_out_notifyq_deinit;
 
-	err = ionic_rx_filters_init(lif);
-	if (err)
-		goto err_out_notifyq_deinit;
+	if (!test_bit(IONIC_LIF_F_FW_RESET, lif->state)) {
+		err = ionic_rx_filters_init(lif);
+		if (err)
+			goto err_out_notifyq_deinit;
+	}
 
 	err = ionic_station_set(lif);
 	if (err)
@@ -2539,8 +2556,6 @@ int ionic_lifs_register(struct ionic *ionic)
 		dev_err(ionic->dev, "Cannot register net device, aborting\n");
 		return err;
 	}
-
-	ionic_link_status_check_request(ionic->master_lif);
 	ionic->master_lif->registered = true;
 
 	return 0;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 588c62e9add7..3344bc1f7671 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -509,16 +509,16 @@ int ionic_port_init(struct ionic *ionic)
 	size_t sz;
 	int err;
 
-	if (idev->port_info)
-		return 0;
-
-	idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE);
-	idev->port_info = dma_alloc_coherent(ionic->dev, idev->port_info_sz,
-					     &idev->port_info_pa,
-					     GFP_KERNEL);
 	if (!idev->port_info) {
-		dev_err(ionic->dev, "Failed to allocate port info, aborting\n");
-		return -ENOMEM;
+		idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE);
+		idev->port_info = dma_alloc_coherent(ionic->dev,
+						     idev->port_info_sz,
+						     &idev->port_info_pa,
+						     GFP_KERNEL);
+		if (!idev->port_info) {
+			dev_err(ionic->dev, "Failed to allocate port info\n");
+			return -ENOMEM;
+		}
 	}
 
 	sz = min(sizeof(ident->port.config), sizeof(idev->dev_cmd_regs->data));
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
index 7a093f148ee5..80eeb7696e01 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
 
 #include <linux/netdevice.h>
+#include <linux/dynamic_debug.h>
 #include <linux/etherdevice.h>
 
 #include "ionic.h"
@@ -17,17 +18,49 @@ void ionic_rx_filter_free(struct ionic_lif *lif, struct ionic_rx_filter *f)
 	devm_kfree(dev, f);
 }
 
-int ionic_rx_filter_del(struct ionic_lif *lif, struct ionic_rx_filter *f)
+void ionic_rx_filter_replay(struct ionic_lif *lif)
 {
-	struct ionic_admin_ctx ctx = {
-		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
-		.cmd.rx_filter_del = {
-			.opcode = IONIC_CMD_RX_FILTER_DEL,
-			.filter_id = cpu_to_le32(f->filter_id),
-		},
-	};
-
-	return ionic_adminq_post_wait(lif, &ctx);
+	struct ionic_rx_filter_add_cmd *ac;
+	struct ionic_admin_ctx ctx;
+	struct ionic_rx_filter *f;
+	struct hlist_head *head;
+	struct hlist_node *tmp;
+	unsigned int i;
+	int err;
+
+	ac = &ctx.cmd.rx_filter_add;
+
+	for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) {
+		head = &lif->rx_filters.by_id[i];
+		hlist_for_each_entry_safe(f, tmp, head, by_id) {
+			ctx.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work);
+			memcpy(ac, &f->cmd, sizeof(f->cmd));
+			dev_dbg(&lif->netdev->dev, "replay filter command:\n");
+			dynamic_hex_dump("cmd ", DUMP_PREFIX_OFFSET, 16, 1,
+					 &ctx.cmd, sizeof(ctx.cmd), true);
+
+			err = ionic_adminq_post_wait(lif, &ctx);
+			if (err) {
+				switch (le16_to_cpu(ac->match)) {
+				case IONIC_RX_FILTER_MATCH_VLAN:
+					netdev_info(lif->netdev, "Replay failed - %d: vlan %d\n",
+						    err,
+						    le16_to_cpu(ac->vlan.vlan));
+					break;
+				case IONIC_RX_FILTER_MATCH_MAC:
+					netdev_info(lif->netdev, "Replay failed - %d: mac %pM\n",
+						    err, ac->mac.addr);
+					break;
+				case IONIC_RX_FILTER_MATCH_MAC_VLAN:
+					netdev_info(lif->netdev, "Replay failed - %d: vlan %d mac %pM\n",
+						    err,
+						    le16_to_cpu(ac->vlan.vlan),
+						    ac->mac.addr);
+					break;
+				}
+			}
+		}
+	}
 }
 
 int ionic_rx_filters_init(struct ionic_lif *lif)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h
index b6aec9c19918..cf8f4c0a961c 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h
@@ -24,7 +24,7 @@ struct ionic_rx_filters {
 };
 
 void ionic_rx_filter_free(struct ionic_lif *lif, struct ionic_rx_filter *f);
-int ionic_rx_filter_del(struct ionic_lif *lif, struct ionic_rx_filter *f);
+void ionic_rx_filter_replay(struct ionic_lif *lif);
 int ionic_rx_filters_init(struct ionic_lif *lif);
 void ionic_rx_filters_deinit(struct ionic_lif *lif);
 int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index,
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 2a533280b124..29b9c728a65e 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -3651,7 +3651,7 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev)
 	ahw->diag_cnt = 0;
 	ret = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_INTRPT_TEST);
 	if (ret)
-		goto fail_diag_irq;
+		goto fail_mbx_args;
 
 	if (adapter->flags & QLCNIC_MSIX_ENABLED)
 		intrpt_id = ahw->intr_tbl[0].id;
@@ -3681,6 +3681,8 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev)
 
 done:
 	qlcnic_free_mbx_args(&cmd);
+
+fail_mbx_args:
 	qlcnic_83xx_diag_free_res(netdev, drv_sds_rings);
 
 fail_diag_irq:
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index bf5bf05970a2..c51b48dc3639 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1050,6 +1050,13 @@ static u16 rtl_ephy_read(struct rtl8169_private *tp, int reg_addr)
 		RTL_R32(tp, EPHYAR) & EPHYAR_DATA_MASK : ~0;
 }
 
+static void r8168fp_adjust_ocp_cmd(struct rtl8169_private *tp, u32 *cmd, int type)
+{
+	/* based on RTL8168FP_OOBMAC_BASE in vendor driver */
+	if (tp->mac_version == RTL_GIGA_MAC_VER_52 && type == ERIAR_OOB)
+		*cmd |= 0x7f0 << 18;
+}
+
 DECLARE_RTL_COND(rtl_eriar_cond)
 {
 	return RTL_R32(tp, ERIAR) & ERIAR_FLAG;
@@ -1058,9 +1065,12 @@ DECLARE_RTL_COND(rtl_eriar_cond)
 static void _rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
 			   u32 val, int type)
 {
+	u32 cmd = ERIAR_WRITE_CMD | type | mask | addr;
+
 	BUG_ON((addr & 3) || (mask == 0));
 	RTL_W32(tp, ERIDR, val);
-	RTL_W32(tp, ERIAR, ERIAR_WRITE_CMD | type | mask | addr);
+	r8168fp_adjust_ocp_cmd(tp, &cmd, type);
+	RTL_W32(tp, ERIAR, cmd);
 
 	rtl_udelay_loop_wait_low(tp, &rtl_eriar_cond, 100, 100);
 }
@@ -1073,7 +1083,10 @@ static void rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
 
 static u32 _rtl_eri_read(struct rtl8169_private *tp, int addr, int type)
 {
-	RTL_W32(tp, ERIAR, ERIAR_READ_CMD | type | ERIAR_MASK_1111 | addr);
+	u32 cmd = ERIAR_READ_CMD | type | ERIAR_MASK_1111 | addr;
+
+	r8168fp_adjust_ocp_cmd(tp, &cmd, type);
+	RTL_W32(tp, ERIAR, cmd);
 
 	return rtl_udelay_loop_wait_high(tp, &rtl_eriar_cond, 100, 100) ?
 		RTL_R32(tp, ERIDR) : ~0;
@@ -2127,6 +2140,8 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
 		{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07 },
 		{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07 },
 		{ 0x7cf, 0x340,	RTL_GIGA_MAC_VER_13 },
+		/* RTL8401, reportedly works if treated as RTL8101e */
+		{ 0x7cf, 0x240,	RTL_GIGA_MAC_VER_13 },
 		{ 0x7cf, 0x343,	RTL_GIGA_MAC_VER_10 },
 		{ 0x7cf, 0x342,	RTL_GIGA_MAC_VER_16 },
 		{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09 },
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 7305e8e86c51..6646eba9f57f 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -848,14 +848,14 @@ static int ioc3eth_probe(struct platform_device *pdev)
 	ip = netdev_priv(dev);
 	ip->dma_dev = pdev->dev.parent;
 	ip->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (!ip->regs) {
-		err = -ENOMEM;
+	if (IS_ERR(ip->regs)) {
+		err = PTR_ERR(ip->regs);
 		goto out_free;
 	}
 
 	ip->ssram = devm_platform_ioremap_resource(pdev, 1);
-	if (!ip->ssram) {
-		err = -ENOMEM;
+	if (IS_ERR(ip->ssram)) {
+		err = PTR_ERR(ip->ssram);
 		goto out_free;
 	}
 
diff --git a/drivers/net/ethernet/sgi/meth.h b/drivers/net/ethernet/sgi/meth.h
index 5b145c6bad60..2ba15c263e8b 100644
--- a/drivers/net/ethernet/sgi/meth.h
+++ b/drivers/net/ethernet/sgi/meth.h
@@ -1,19 +1,3 @@
-
-/*
- * snull.h -- definitions for the network module
- *
- * Copyright (C) 2001 Alessandro Rubini and Jonathan Corbet
- * Copyright (C) 2001 O'Reilly & Associates
- *
- * The source code in this file can be freely used, adapted,
- * and redistributed in source or binary form, so long as an
- * acknowledgment appears in derived source files.  The citation
- * should list that the code comes from the book "Linux Device
- * Drivers" by Alessandro Rubini and Jonathan Corbet, published
- * by O'Reilly & Associates.   No warranty is attached;
- * we cannot take responsibility for errors or fitness for use.
- */
-
 /* version dependencies have been confined to a separate file */
 
 /* Tunable parameters */
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 49a6a9167af4..fc168f85e7af 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -2493,20 +2493,20 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 
 	retval = smsc911x_init(dev);
 	if (retval < 0)
-		goto out_disable_resources;
+		goto out_init_fail;
 
 	netif_carrier_off(dev);
 
 	retval = smsc911x_mii_init(pdev, dev);
 	if (retval) {
 		SMSC_WARN(pdata, probe, "Error %i initialising mii", retval);
-		goto out_disable_resources;
+		goto out_init_fail;
 	}
 
 	retval = register_netdev(dev);
 	if (retval) {
 		SMSC_WARN(pdata, probe, "Error %i registering device", retval);
-		goto out_disable_resources;
+		goto out_init_fail;
 	} else {
 		SMSC_TRACE(pdata, probe,
 			   "Network interface: \"%s\"", dev->name);
@@ -2547,9 +2547,10 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 
 	return 0;
 
-out_disable_resources:
+out_init_fail:
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+out_disable_resources:
 	(void)smsc911x_disable_resources(pdev);
 out_enable_resources_fail:
 	smsc911x_free_resources(pdev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 5419d4e478c0..2e4aaedb93f5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -5,8 +5,13 @@
 #include <linux/clk-provider.h>
 #include <linux/pci.h>
 #include <linux/dmi.h>
+#include "dwmac-intel.h"
 #include "stmmac.h"
 
+struct intel_priv_data {
+	int mdio_adhoc_addr;	/* mdio address for serdes & etc */
+};
+
 /* This struct is used to associate PCI Function of MAC controller on a board,
  * discovered via DMI, with the address of PHY connected to the MAC. The
  * negative value of the address means that MAC controller is not connected
@@ -49,6 +54,172 @@ static int stmmac_pci_find_phy_addr(struct pci_dev *pdev,
 	return -ENODEV;
 }
 
+static int serdes_status_poll(struct stmmac_priv *priv, int phyaddr,
+			      int phyreg, u32 mask, u32 val)
+{
+	unsigned int retries = 10;
+	int val_rd;
+
+	do {
+		val_rd = mdiobus_read(priv->mii, phyaddr, phyreg);
+		if ((val_rd & mask) == (val & mask))
+			return 0;
+		udelay(POLL_DELAY_US);
+	} while (--retries);
+
+	return -ETIMEDOUT;
+}
+
+static int intel_serdes_powerup(struct net_device *ndev, void *priv_data)
+{
+	struct intel_priv_data *intel_priv = priv_data;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	int serdes_phy_addr = 0;
+	u32 data = 0;
+
+	if (!intel_priv->mdio_adhoc_addr)
+		return 0;
+
+	serdes_phy_addr = intel_priv->mdio_adhoc_addr;
+
+	/* assert clk_req */
+	data = mdiobus_read(priv->mii, serdes_phy_addr,
+			    SERDES_GCR0);
+
+	data |= SERDES_PLL_CLK;
+
+	mdiobus_write(priv->mii, serdes_phy_addr,
+		      SERDES_GCR0, data);
+
+	/* check for clk_ack assertion */
+	data = serdes_status_poll(priv, serdes_phy_addr,
+				  SERDES_GSR0,
+				  SERDES_PLL_CLK,
+				  SERDES_PLL_CLK);
+
+	if (data) {
+		dev_err(priv->device, "Serdes PLL clk request timeout\n");
+		return data;
+	}
+
+	/* assert lane reset */
+	data = mdiobus_read(priv->mii, serdes_phy_addr,
+			    SERDES_GCR0);
+
+	data |= SERDES_RST;
+
+	mdiobus_write(priv->mii, serdes_phy_addr,
+		      SERDES_GCR0, data);
+
+	/* check for assert lane reset reflection */
+	data = serdes_status_poll(priv, serdes_phy_addr,
+				  SERDES_GSR0,
+				  SERDES_RST,
+				  SERDES_RST);
+
+	if (data) {
+		dev_err(priv->device, "Serdes assert lane reset timeout\n");
+		return data;
+	}
+
+	/*  move power state to P0 */
+	data = mdiobus_read(priv->mii, serdes_phy_addr,
+			    SERDES_GCR0);
+
+	data &= ~SERDES_PWR_ST_MASK;
+	data |= SERDES_PWR_ST_P0 << SERDES_PWR_ST_SHIFT;
+
+	mdiobus_write(priv->mii, serdes_phy_addr,
+		      SERDES_GCR0, data);
+
+	/* Check for P0 state */
+	data = serdes_status_poll(priv, serdes_phy_addr,
+				  SERDES_GSR0,
+				  SERDES_PWR_ST_MASK,
+				  SERDES_PWR_ST_P0 << SERDES_PWR_ST_SHIFT);
+
+	if (data) {
+		dev_err(priv->device, "Serdes power state P0 timeout.\n");
+		return data;
+	}
+
+	return 0;
+}
+
+static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data)
+{
+	struct intel_priv_data *intel_priv = intel_data;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	int serdes_phy_addr = 0;
+	u32 data = 0;
+
+	if (!intel_priv->mdio_adhoc_addr)
+		return;
+
+	serdes_phy_addr = intel_priv->mdio_adhoc_addr;
+
+	/*  move power state to P3 */
+	data = mdiobus_read(priv->mii, serdes_phy_addr,
+			    SERDES_GCR0);
+
+	data &= ~SERDES_PWR_ST_MASK;
+	data |= SERDES_PWR_ST_P3 << SERDES_PWR_ST_SHIFT;
+
+	mdiobus_write(priv->mii, serdes_phy_addr,
+		      SERDES_GCR0, data);
+
+	/* Check for P3 state */
+	data = serdes_status_poll(priv, serdes_phy_addr,
+				  SERDES_GSR0,
+				  SERDES_PWR_ST_MASK,
+				  SERDES_PWR_ST_P3 << SERDES_PWR_ST_SHIFT);
+
+	if (data) {
+		dev_err(priv->device, "Serdes power state P3 timeout\n");
+		return;
+	}
+
+	/* de-assert clk_req */
+	data = mdiobus_read(priv->mii, serdes_phy_addr,
+			    SERDES_GCR0);
+
+	data &= ~SERDES_PLL_CLK;
+
+	mdiobus_write(priv->mii, serdes_phy_addr,
+		      SERDES_GCR0, data);
+
+	/* check for clk_ack de-assert */
+	data = serdes_status_poll(priv, serdes_phy_addr,
+				  SERDES_GSR0,
+				  SERDES_PLL_CLK,
+				  (u32)~SERDES_PLL_CLK);
+
+	if (data) {
+		dev_err(priv->device, "Serdes PLL clk de-assert timeout\n");
+		return;
+	}
+
+	/* de-assert lane reset */
+	data = mdiobus_read(priv->mii, serdes_phy_addr,
+			    SERDES_GCR0);
+
+	data &= ~SERDES_RST;
+
+	mdiobus_write(priv->mii, serdes_phy_addr,
+		      SERDES_GCR0, data);
+
+	/* check for de-assert lane reset reflection */
+	data = serdes_status_poll(priv, serdes_phy_addr,
+				  SERDES_GSR0,
+				  SERDES_RST,
+				  (u32)~SERDES_RST);
+
+	if (data) {
+		dev_err(priv->device, "Serdes de-assert lane reset timeout\n");
+		return;
+	}
+}
+
 static void common_default_data(struct plat_stmmacenet_data *plat)
 {
 	plat->clk_csr = 2;	/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
@@ -189,6 +360,9 @@ static int ehl_sgmii_data(struct pci_dev *pdev,
 	plat->phy_addr = 0;
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 
+	plat->serdes_powerup = intel_serdes_powerup;
+	plat->serdes_powerdown = intel_serdes_powerdown;
+
 	return ehl_common_data(pdev, plat);
 }
 
@@ -233,6 +407,8 @@ static int ehl_pse0_sgmii1g_data(struct pci_dev *pdev,
 				 struct plat_stmmacenet_data *plat)
 {
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->serdes_powerup = intel_serdes_powerup;
+	plat->serdes_powerdown = intel_serdes_powerdown;
 	return ehl_pse0_common_data(pdev, plat);
 }
 
@@ -263,6 +439,8 @@ static int ehl_pse1_sgmii1g_data(struct pci_dev *pdev,
 				 struct plat_stmmacenet_data *plat)
 {
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->serdes_powerup = intel_serdes_powerup;
+	plat->serdes_powerdown = intel_serdes_powerdown;
 	return ehl_pse1_common_data(pdev, plat);
 }
 
@@ -291,6 +469,8 @@ static int tgl_sgmii_data(struct pci_dev *pdev,
 	plat->bus_id = 1;
 	plat->phy_addr = 0;
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->serdes_powerup = intel_serdes_powerup;
+	plat->serdes_powerdown = intel_serdes_powerdown;
 	return tgl_common_data(pdev, plat);
 }
 
@@ -417,11 +597,17 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
 	struct stmmac_pci_info *info = (struct stmmac_pci_info *)id->driver_data;
+	struct intel_priv_data *intel_priv;
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_resources res;
 	int i;
 	int ret;
 
+	intel_priv = devm_kzalloc(&pdev->dev, sizeof(*intel_priv),
+				  GFP_KERNEL);
+	if (!intel_priv)
+		return -ENOMEM;
+
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
 		return -ENOMEM;
@@ -457,6 +643,9 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
+	plat->bsp_priv = intel_priv;
+	intel_priv->mdio_adhoc_addr = 0x15;
+
 	ret = info->setup(pdev, plat);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
new file mode 100644
index 000000000000..e723096c0b15
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020, Intel Corporation
+ * DWMAC Intel header file
+ */
+
+#ifndef __DWMAC_INTEL_H__
+#define __DWMAC_INTEL_H__
+
+#define POLL_DELAY_US 8
+
+/* SERDES Register */
+#define SERDES_GSR0	0x5	/* Global Status Reg0 */
+#define SERDES_GCR0	0xb	/* Global Configuration Reg0 */
+
+/* SERDES defines */
+#define SERDES_PLL_CLK		BIT(0)		/* PLL clk valid signal */
+#define SERDES_RST		BIT(2)		/* Serdes Reset */
+#define SERDES_PWR_ST_MASK	GENMASK(6, 4)	/* Serdes Power state*/
+#define SERDES_PWR_ST_SHIFT	4
+#define SERDES_PWR_ST_P0	0x0
+#define SERDES_PWR_ST_P3	0x3
+
+#endif /* __DWMAC_INTEL_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 6ae13dc19510..02102c781a8c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -319,6 +319,19 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 	/* Enable PTP clock */
 	regmap_read(gmac->nss_common, NSS_COMMON_CLK_GATE, &val);
 	val |= NSS_COMMON_CLK_GATE_PTP_EN(gmac->id);
+	switch (gmac->phy_mode) {
+	case PHY_INTERFACE_MODE_RGMII:
+		val |= NSS_COMMON_CLK_GATE_RGMII_RX_EN(gmac->id) |
+			NSS_COMMON_CLK_GATE_RGMII_TX_EN(gmac->id);
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		val |= NSS_COMMON_CLK_GATE_GMII_RX_EN(gmac->id) |
+				NSS_COMMON_CLK_GATE_GMII_TX_EN(gmac->id);
+		break;
+	default:
+		/* We don't get here; the switch above will have errored out */
+		unreachable();
+	}
 	regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val);
 
 	if (gmac->phy_mode == PHY_INTERFACE_MODE_SGMII) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 0e2fa14f1423..a3934ca6a043 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -119,6 +119,7 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 		{ .div = 5, .val = 5, },
 		{ .div = 6, .val = 6, },
 		{ .div = 7, .val = 7, },
+		{ /* end of array */ }
 	};
 
 	clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index e0a5fe83d8e0..bfc4a92f1d92 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -75,6 +75,11 @@ struct ethqos_emac_por {
 	unsigned int value;
 };
 
+struct ethqos_emac_driver_data {
+	const struct ethqos_emac_por *por;
+	unsigned int num_por;
+};
+
 struct qcom_ethqos {
 	struct platform_device *pdev;
 	void __iomem *rgmii_base;
@@ -171,6 +176,11 @@ static const struct ethqos_emac_por emac_v2_3_0_por[] = {
 	{ .offset = RGMII_IO_MACRO_CONFIG2,	.value = 0x00002060 },
 };
 
+static const struct ethqos_emac_driver_data emac_v2_3_0_data = {
+	.por = emac_v2_3_0_por,
+	.num_por = ARRAY_SIZE(emac_v2_3_0_por),
+};
+
 static int ethqos_dll_configure(struct qcom_ethqos *ethqos)
 {
 	unsigned int val;
@@ -442,6 +452,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat_dat;
 	struct stmmac_resources stmmac_res;
+	const struct ethqos_emac_driver_data *data;
 	struct qcom_ethqos *ethqos;
 	struct resource *res;
 	int ret;
@@ -471,7 +482,9 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 		goto err_mem;
 	}
 
-	ethqos->por = of_device_get_match_data(&pdev->dev);
+	data = of_device_get_match_data(&pdev->dev);
+	ethqos->por = data->por;
+	ethqos->num_por = data->num_por;
 
 	ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii");
 	if (IS_ERR(ethqos->rgmii_clk)) {
@@ -526,7 +539,7 @@ static int qcom_ethqos_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id qcom_ethqos_match[] = {
-	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_por},
+	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_data},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, qcom_ethqos_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index e0212d2fc2a1..70d41783329d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -241,6 +241,8 @@ static int socfpga_set_phy_mode_common(int phymode, u32 *val)
 	switch (phymode) {
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		*val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII;
 		break;
 	case PHY_INTERFACE_MODE_MII:
@@ -289,16 +291,19 @@ static int socfpga_gen5_set_phy_mode(struct socfpga_dwmac *dwmac)
 	    phymode == PHY_INTERFACE_MODE_MII ||
 	    phymode == PHY_INTERFACE_MODE_GMII ||
 	    phymode == PHY_INTERFACE_MODE_SGMII) {
-		ctrl |= SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2);
 		regmap_read(sys_mgr_base_addr, SYSMGR_FPGAGRP_MODULE_REG,
 			    &module);
 		module |= (SYSMGR_FPGAGRP_MODULE_EMAC << (reg_shift / 2));
 		regmap_write(sys_mgr_base_addr, SYSMGR_FPGAGRP_MODULE_REG,
 			     module);
-	} else {
-		ctrl &= ~(SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2));
 	}
 
+	if (dwmac->f2h_ptp_ref_clk)
+		ctrl |= SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2);
+	else
+		ctrl &= ~(SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK <<
+			  (reg_shift / 2));
+
 	regmap_write(sys_mgr_base_addr, reg_offset, ctrl);
 
 	/* Deassert reset for the phy configuration to be sampled by
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 7d40760e9ba8..0e1ca2cba3c7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -150,6 +150,8 @@ static int sun7i_gmac_probe(struct platform_device *pdev)
 	plat_dat->init = sun7i_gmac_init;
 	plat_dat->exit = sun7i_gmac_exit;
 	plat_dat->fix_mac_speed = sun7i_fix_speed;
+	plat_dat->tx_fifo_size = 4096;
+	plat_dat->rx_fifo_size = 16384;
 
 	ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv);
 	if (ret)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index 494c859b4ade..67ba67ed0cb9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -624,7 +624,7 @@ int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
 		total_offset += offset;
 	}
 
-	total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000;
+	total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000ULL;
 	total_ctr += total_offset;
 
 	ctr_low = do_div(total_ctr, 1000000000);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index fcf080243a0f..d291612eeafb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -27,12 +27,16 @@ static void config_sub_second_increment(void __iomem *ioaddr,
 	unsigned long data;
 	u32 reg_value;
 
-	/* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second
-	 *	formula = (1/ptp_clock) * 1000000000
-	 * where ptp_clock is 50MHz if fine method is used to update system
+	/* For GMAC3.x, 4.x versions, in "fine adjustement mode" set sub-second
+	 * increment to twice the number of nanoseconds of a clock cycle.
+	 * The calculation of the default_addend value by the caller will set it
+	 * to mid-range = 2^31 when the remainder of this division is zero,
+	 * which will make the accumulator overflow once every 2 ptp_clock
+	 * cycles, adding twice the number of nanoseconds of a clock cycle :
+	 * 2000000000ULL / ptp_clock.
 	 */
 	if (value & PTP_TCR_TSCFUPDT)
-		data = (1000000000ULL / 50000000);
+		data = (2000000000ULL / ptp_clock);
 	else
 		data = (1000000000ULL / ptp_clock);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e6898fd5223f..7e9cbfd23530 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -630,7 +630,8 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
-			ts_event_en = PTP_TCR_TSEVNTENA;
+			if (priv->synopsys_id != DWMAC_CORE_5_10)
+				ts_event_en = PTP_TCR_TSEVNTENA;
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
 			ptp_over_ethernet = PTP_TCR_TSIPENA;
@@ -4060,7 +4061,7 @@ static int stmmac_set_features(struct net_device *netdev,
 /**
  *  stmmac_interrupt - main ISR
  *  @irq: interrupt number.
- *  @dev_id: to pass the net device pointer.
+ *  @dev_id: to pass the net device pointer (must be valid).
  *  Description: this is the main driver interrupt service routine.
  *  It can call:
  *  o DMA service routine (to manage incoming frame reception and transmission
@@ -4084,11 +4085,6 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	if (priv->irq_wake)
 		pm_wakeup_event(priv->device, 0);
 
-	if (unlikely(!dev)) {
-		netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
-		return IRQ_NONE;
-	}
-
 	/* Check if adapter is up */
 	if (test_bit(STMMAC_DOWN, &priv->state))
 		return IRQ_HANDLED;
@@ -4986,12 +4982,22 @@ int stmmac_dvr_probe(struct device *device,
 		goto error_netdev_register;
 	}
 
+	if (priv->plat->serdes_powerup) {
+		ret = priv->plat->serdes_powerup(ndev,
+						 priv->plat->bsp_priv);
+
+		if (ret < 0)
+			goto error_serdes_powerup;
+	}
+
 #ifdef CONFIG_DEBUG_FS
 	stmmac_init_fs(ndev);
 #endif
 
 	return ret;
 
+error_serdes_powerup:
+	unregister_netdev(ndev);
 error_netdev_register:
 	phylink_destroy(priv->phylink);
 error_phy_setup:
@@ -5029,6 +5035,9 @@ int stmmac_dvr_remove(struct device *dev)
 
 	stmmac_stop_all_dma(priv);
 
+	if (priv->plat->serdes_powerdown)
+		priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv);
+
 	stmmac_mac_set(priv, priv->ioaddr, false);
 	netif_carrier_off(ndev);
 	unregister_netdev(ndev);
@@ -5081,6 +5090,9 @@ int stmmac_suspend(struct device *dev)
 	/* Stop TX/RX DMA */
 	stmmac_stop_all_dma(priv);
 
+	if (priv->plat->serdes_powerdown)
+		priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv);
+
 	/* Enable Power down mode by programming the PMT regs */
 	if (device_may_wakeup(priv->device)) {
 		stmmac_pmt(priv, priv->hw, priv->wolopts);
@@ -5143,6 +5155,7 @@ int stmmac_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	int ret;
 
 	if (!netif_running(ndev))
 		return 0;
@@ -5170,7 +5183,13 @@ int stmmac_resume(struct device *dev)
 			stmmac_mdio_reset(priv->mii);
 	}
 
-	netif_device_attach(ndev);
+	if (priv->plat->serdes_powerup) {
+		ret = priv->plat->serdes_powerup(ndev,
+						 priv->plat->bsp_priv);
+
+		if (ret < 0)
+			return ret;
+	}
 
 	mutex_lock(&priv->lock);
 
@@ -5198,6 +5217,8 @@ int stmmac_resume(struct device *dev)
 
 	phylink_mac_change(priv->phylink, true);
 
+	netif_device_attach(ndev);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(stmmac_resume);
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index e6d1aa882fa5..f1c8615ab6f0 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -4963,7 +4963,7 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 					  cas_cacheline_size)) {
 			dev_err(&pdev->dev, "Could not set PCI cache "
 			       "line size\n");
-			goto err_write_cacheline;
+			goto err_out_free_res;
 		}
 	}
 #endif
@@ -5136,7 +5136,6 @@ err_out_iounmap:
 err_out_free_res:
 	pci_release_regions(pdev);
 
-err_write_cacheline:
 	/* Try to restore it in case the error occurred after we
 	 * set it.
 	 */
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 89cec778cf2d..62f809b67469 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -49,6 +49,7 @@ config TI_CPSW_PHY_SEL
 config TI_CPSW
 	tristate "TI CPSW Switch Support"
 	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
+	depends on TI_CPTS || !TI_CPTS
 	select TI_DAVINCI_MDIO
 	select MFD_SYSCON
 	select PAGE_POOL
@@ -64,6 +65,7 @@ config TI_CPSW_SWITCHDEV
 	tristate "TI CPSW Switch Support with switchdev"
 	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
 	depends on NET_SWITCHDEV
+	depends on TI_CPTS || !TI_CPTS
 	select PAGE_POOL
 	select TI_DAVINCI_MDIO
 	select MFD_SYSCON
@@ -77,24 +79,16 @@ config TI_CPSW_SWITCHDEV
 	  will be called cpsw_new.
 
 config TI_CPTS
-	bool "TI Common Platform Time Sync (CPTS) Support"
-	depends on TI_CPSW || TI_KEYSTONE_NETCP || TI_CPSW_SWITCHDEV || COMPILE_TEST
+	tristate "TI Common Platform Time Sync (CPTS) Support"
+	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
 	depends on COMMON_CLK
-	depends on POSIX_TIMERS
+	depends on PTP_1588_CLOCK
 	---help---
 	  This driver supports the Common Platform Time Sync unit of
 	  the CPSW Ethernet Switch and Keystone 2 1g/10g Switch Subsystem.
 	  The unit can time stamp PTP UDP/IPv4 and Layer 2 packets, and the
 	  driver offers a PTP Hardware Clock.
 
-config TI_CPTS_MOD
-	tristate
-	depends on TI_CPTS
-	default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y || TI_CPSW_SWITCHDEV=y
-	select NET_PTP_CLASSIFY
-	imply PTP_1588_CLOCK
-	default m
-
 config TI_K3_AM65_CPSW_NUSS
 	tristate "TI K3 AM654x/J721E CPSW Ethernet driver"
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
@@ -115,6 +109,7 @@ config TI_KEYSTONE_NETCP
 	select TI_DAVINCI_MDIO
 	depends on OF
 	depends on KEYSTONE_NAVIGATOR_DMA && KEYSTONE_NAVIGATOR_QMSS
+	depends on TI_CPTS || !TI_CPTS
 	---help---
 	  This driver supports TI's Keystone NETCP Core.
 
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 53792190e9c2..cb26a9d21869 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_TI_DAVINCI_EMAC) += ti_davinci_emac.o
 ti_davinci_emac-y := davinci_emac.o davinci_cpdma.o
 obj-$(CONFIG_TI_DAVINCI_MDIO) += davinci_mdio.o
 obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o
-obj-$(CONFIG_TI_CPTS_MOD) += cpts.o
+obj-$(CONFIG_TI_CPTS) += cpts.o
 obj-$(CONFIG_TI_CPSW) += ti_cpsw.o
 ti_cpsw-y := cpsw.o davinci_cpdma.o cpsw_ale.o cpsw_priv.o cpsw_sl.o cpsw_ethtool.o
 obj-$(CONFIG_TI_CPSW_SWITCHDEV) += ti_cpsw_new.o
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index f71c15c39492..88f52a2f85b3 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1372,7 +1372,7 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common)
 err:
 	i = devm_add_action(dev, am65_cpsw_nuss_free_tx_chns, common);
 	if (i) {
-		dev_err(dev, "failed to add free_tx_chns action %d", i);
+		dev_err(dev, "Failed to add free_tx_chns action %d\n", i);
 		return i;
 	}
 
@@ -1481,7 +1481,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 err:
 	i = devm_add_action(dev, am65_cpsw_nuss_free_rx_chns, common);
 	if (i) {
-		dev_err(dev, "failed to add free_rx_chns action %d", i);
+		dev_err(dev, "Failed to add free_rx_chns action %d\n", i);
 		return i;
 	}
 
@@ -1691,7 +1691,7 @@ static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common)
 	ret = devm_add_action_or_reset(dev, am65_cpsw_pcpu_stats_free,
 				       ndev_priv->stats);
 	if (ret) {
-		dev_err(dev, "failed to add percpu stat free action %d", ret);
+		dev_err(dev, "Failed to add percpu stat free action %d\n", ret);
 		return ret;
 	}
 
@@ -1719,7 +1719,8 @@ static int am65_cpsw_nuss_ndev_add_napi_2g(struct am65_cpsw_common *common)
 
 		ret = devm_request_irq(dev, tx_chn->irq,
 				       am65_cpsw_nuss_tx_irq,
-				       0, tx_chn->tx_chn_name, tx_chn);
+				       IRQF_TRIGGER_HIGH,
+				       tx_chn->tx_chn_name, tx_chn);
 		if (ret) {
 			dev_err(dev, "failure requesting tx%u irq %u, %d\n",
 				tx_chn->id, tx_chn->irq, ret);
@@ -1744,7 +1745,7 @@ static int am65_cpsw_nuss_ndev_reg_2g(struct am65_cpsw_common *common)
 
 	ret = devm_request_irq(dev, common->rx_chns.irq,
 			       am65_cpsw_nuss_rx_irq,
-			       0, dev_name(dev), common);
+			       IRQF_TRIGGER_HIGH, dev_name(dev), common);
 	if (ret) {
 		dev_err(dev, "failure requesting rx irq %u, %d\n",
 			common->rx_chns.irq, ret);
@@ -1894,8 +1895,9 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	ale_params.nu_switch_ale = true;
 
 	common->ale = cpsw_ale_create(&ale_params);
-	if (!common->ale) {
+	if (IS_ERR(common->ale)) {
 		dev_err(dev, "error initializing ale engine\n");
+		ret = PTR_ERR(common->ale);
 		goto err_of_clear;
 	}
 
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index c2c5bf87da01..ffeb8633e530 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1753,11 +1753,15 @@ static int cpsw_suspend(struct device *dev)
 	struct cpsw_common *cpsw = dev_get_drvdata(dev);
 	int i;
 
+	rtnl_lock();
+
 	for (i = 0; i < cpsw->data.slaves; i++)
 		if (cpsw->slaves[i].ndev)
 			if (netif_running(cpsw->slaves[i].ndev))
 				cpsw_ndo_stop(cpsw->slaves[i].ndev);
 
+	rtnl_unlock();
+
 	/* Select sleep pin state */
 	pinctrl_pm_select_sleep_state(dev);
 
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 0374e6936091..8dc6be11b2ff 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -955,7 +955,7 @@ struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params)
 
 	ale = devm_kzalloc(params->dev, sizeof(*ale), GFP_KERNEL);
 	if (!ale)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	ale->p0_untag_vid_mask =
 		devm_kmalloc_array(params->dev, BITS_TO_LONGS(VLAN_N_VID),
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 97a058ca60ac..d0b6c418a870 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -490,9 +490,9 @@ int cpsw_init_common(struct cpsw_common *cpsw, void __iomem *ss_regs,
 	ale_params.ale_ports		= CPSW_ALE_PORTS_NUM;
 
 	cpsw->ale = cpsw_ale_create(&ale_params);
-	if (!cpsw->ale) {
+	if (IS_ERR(cpsw->ale)) {
 		dev_err(dev, "error initializing ale engine\n");
-		return -ENODEV;
+		return PTR_ERR(cpsw->ale);
 	}
 
 	dma_params.dev		= dev;
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index fb36115e9c51..fdbae734acce 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -3704,9 +3704,9 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 		ale_params.nu_switch_ale = true;
 	}
 	gbe_dev->ale = cpsw_ale_create(&ale_params);
-	if (!gbe_dev->ale) {
+	if (IS_ERR(gbe_dev->ale)) {
 		dev_err(gbe_dev->dev, "error initializing ale engine\n");
-		ret = -ENODEV;
+		ret = PTR_ERR(gbe_dev->ale);
 		goto free_sec_ports;
 	} else {
 		dev_dbg(gbe_dev->dev, "Created a gbe ale engine\n");
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index b50c3ec3495b..6bcda20ed7e7 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -643,7 +643,7 @@ static int tc_mii_probe(struct net_device *dev)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
 	}
-	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_andnot(phydev->supported, phydev->supported, mask);
 	linkmode_copy(phydev->advertising, phydev->supported);
 
 	lp->link = 0;
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 269596c15133..2e5202923510 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -1387,6 +1387,8 @@ static int ixp4xx_eth_probe(struct platform_device *pdev)
 		return -ENODEV;
 	regs_phys = res->start;
 	port->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(port->regs))
+		return PTR_ERR(port->regs);
 
 	switch (port->id) {
 	case IXP4XX_ETH_NPEA:
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 09f279c0182b..6b461be1820b 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1207,7 +1207,7 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
 		enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]);
 
 		if (df < 0 || df > GENEVE_DF_MAX) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_DF],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF],
 					    "Invalid DF attribute");
 			return -EINVAL;
 		}
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 672cd2caf2fb..21640a035d7d 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1169,11 +1169,11 @@ out_unlock:
 static struct genl_family gtp_genl_family;
 
 static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
-			      u32 type, struct pdp_ctx *pctx)
+			      int flags, u32 type, struct pdp_ctx *pctx)
 {
 	void *genlh;
 
-	genlh = genlmsg_put(skb, snd_portid, snd_seq, &gtp_genl_family, 0,
+	genlh = genlmsg_put(skb, snd_portid, snd_seq, &gtp_genl_family, flags,
 			    type);
 	if (genlh == NULL)
 		goto nlmsg_failure;
@@ -1227,8 +1227,8 @@ static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock;
 	}
 
-	err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid,
-				 info->snd_seq, info->nlhdr->nlmsg_type, pctx);
+	err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid, info->snd_seq,
+				 0, info->nlhdr->nlmsg_type, pctx);
 	if (err < 0)
 		goto err_unlock_free;
 
@@ -1271,6 +1271,7 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb,
 				    gtp_genl_fill_info(skb,
 					    NETLINK_CB(cb->skb).portid,
 					    cb->nlh->nlmsg_seq,
+					    NLM_F_MULTI,
 					    cb->nlh->nlmsg_type, pctx)) {
 					cb->args[0] = i;
 					cb->args[1] = j;
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index fbea6f232819..e2ad3c2e8df5 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -127,7 +127,8 @@ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev)
 {
 	struct bpqdev *bpq;
 
-	list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list) {
+	list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list,
+				lockdep_rtnl_is_held()) {
 		if (bpq->ethdev == dev)
 			return bpq->axdev;
 	}
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index d8e86bdbfba1..ebcfbae05690 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -707,7 +707,8 @@ no_memory:
 	goto drop;
 }
 
-static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t netvsc_start_xmit(struct sk_buff *skb,
+				     struct net_device *ndev)
 {
 	return netvsc_xmit(skb, ndev, false);
 }
diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c
index 845478a19a4f..8d9ca1c335e8 100644
--- a/drivers/net/ipa/gsi.c
+++ b/drivers/net/ipa/gsi.c
@@ -1041,6 +1041,7 @@ static void gsi_isr_gp_int1(struct gsi *gsi)
 
 	complete(&gsi->completion);
 }
+
 /* Inter-EE interrupt handler */
 static void gsi_isr_glob_ee(struct gsi *gsi)
 {
@@ -1391,6 +1392,7 @@ static int gsi_channel_poll(struct napi_struct *napi, int budget)
 	while (count < budget) {
 		struct gsi_trans *trans;
 
+		count++;
 		trans = gsi_channel_poll_one(channel);
 		if (!trans)
 			break;
@@ -1493,6 +1495,12 @@ static int gsi_generic_command(struct gsi *gsi, u32 channel_id,
 	struct completion *completion = &gsi->completion;
 	u32 val;
 
+	/* First zero the result code field */
+	val = ioread32(gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET);
+	val &= ~GENERIC_EE_RESULT_FMASK;
+	iowrite32(val, gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET);
+
+	/* Now issue the command */
 	val = u32_encode_bits(opcode, GENERIC_OPCODE_FMASK);
 	val |= u32_encode_bits(channel_id, GENERIC_CHID_FMASK);
 	val |= u32_encode_bits(GSI_EE_MODEM, GENERIC_EE_FMASK);
@@ -1798,9 +1806,9 @@ static int gsi_channel_init_one(struct gsi *gsi,
 
 	/* Worst case we need an event for every outstanding TRE */
 	if (data->channel.tre_count > data->channel.event_count) {
-		dev_warn(gsi->dev, "channel %u limited to %u TREs\n",
-			data->channel_id, data->channel.tre_count);
 		tre_count = data->channel.event_count;
+		dev_warn(gsi->dev, "channel %u limited to %u TREs\n",
+			 data->channel_id, tre_count);
 	} else {
 		tre_count = data->channel.tre_count;
 	}
diff --git a/drivers/net/ipa/gsi_reg.h b/drivers/net/ipa/gsi_reg.h
index 7613b9cc7cf6..acc9e744c67d 100644
--- a/drivers/net/ipa/gsi_reg.h
+++ b/drivers/net/ipa/gsi_reg.h
@@ -410,6 +410,8 @@
 #define INTER_EE_RESULT_FMASK		GENMASK(2, 0)
 #define GENERIC_EE_RESULT_FMASK		GENMASK(7, 5)
 #define GENERIC_EE_SUCCESS_FVAL			1
+#define GENERIC_EE_INCORRECT_DIRECTION_FVAL	3
+#define GENERIC_EE_INCORRECT_CHANNEL_FVAL	5
 #define GENERIC_EE_NO_RESOURCES_FVAL		7
 #define USB_MAX_PACKET_FMASK		GENMASK(15, 15)	/* 0: HS; 1: SS */
 #define MHI_BASE_CHANNEL_FMASK		GENMASK(31, 24)
diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c
index 2fd21d75367d..bdbfeed359db 100644
--- a/drivers/net/ipa/gsi_trans.c
+++ b/drivers/net/ipa/gsi_trans.c
@@ -399,13 +399,14 @@ void gsi_trans_cmd_add(struct gsi_trans *trans, void *buf, u32 size,
 	/* assert(which < trans->tre_count); */
 
 	/* Set the page information for the buffer.  We also need to fill in
-	 * the DMA address for the buffer (something dma_map_sg() normally
-	 * does).
+	 * the DMA address and length for the buffer (something dma_map_sg()
+	 * normally does).
 	 */
 	sg = &trans->sgl[which];
 
 	sg_set_buf(sg, buf, size);
 	sg_dma_address(sg) = addr;
+	sg_dma_len(sg) = sg->length;
 
 	info = &trans->info[which];
 	info->opcode = opcode;
diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c
index d226b858742d..cee417181f98 100644
--- a/drivers/net/ipa/ipa_cmd.c
+++ b/drivers/net/ipa/ipa_cmd.c
@@ -628,23 +628,15 @@ static void ipa_cmd_transfer_add(struct gsi_trans *trans, u16 size)
 
 void ipa_cmd_tag_process_add(struct gsi_trans *trans)
 {
-	ipa_cmd_register_write_add(trans, 0, 0, 0, true);
-#if 1
-	/* Reference these functions to avoid a compile error */
-	(void)ipa_cmd_ip_packet_init_add;
-	(void)ipa_cmd_ip_tag_status_add;
-	(void) ipa_cmd_transfer_add;
-#else
 	struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi);
-	struct gsi_endpoint *endpoint;
+	struct ipa_endpoint *endpoint;
 
 	endpoint = ipa->name_map[IPA_ENDPOINT_AP_LAN_RX];
-	ipa_cmd_ip_packet_init_add(trans, endpoint->endpoint_id);
 
+	ipa_cmd_register_write_add(trans, 0, 0, 0, true);
+	ipa_cmd_ip_packet_init_add(trans, endpoint->endpoint_id);
 	ipa_cmd_ip_tag_status_add(trans, 0xcba987654321);
-
 	ipa_cmd_transfer_add(trans, 4);
-#endif
 }
 
 /* Returns the number of commands required for the tag process */
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index 6de03be28784..a21534f1462f 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -1283,7 +1283,7 @@ static int ipa_endpoint_stop_rx_dma(struct ipa *ipa)
  */
 int ipa_endpoint_stop(struct ipa_endpoint *endpoint)
 {
-	u32 retries = endpoint->toward_ipa ? 0 : IPA_ENDPOINT_STOP_RX_RETRIES;
+	u32 retries = IPA_ENDPOINT_STOP_RX_RETRIES;
 	int ret;
 
 	do {
@@ -1291,12 +1291,9 @@ int ipa_endpoint_stop(struct ipa_endpoint *endpoint)
 		struct gsi *gsi = &ipa->gsi;
 
 		ret = gsi_channel_stop(gsi, endpoint->channel_id);
-		if (ret != -EAGAIN)
+		if (ret != -EAGAIN || endpoint->toward_ipa)
 			break;
 
-		if (endpoint->toward_ipa)
-			continue;
-
 		/* For IPA v3.5.1, send a DMA read task and check again */
 		if (ipa->version == IPA_VERSION_3_5_1) {
 			ret = ipa_endpoint_stop_rx_dma(ipa);
diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c
index 55c9329a4b1d..ed10818dd99f 100644
--- a/drivers/net/ipa/ipa_modem.c
+++ b/drivers/net/ipa/ipa_modem.c
@@ -297,14 +297,13 @@ static void ipa_modem_crashed(struct ipa *ipa)
 
 	ret = ipa_endpoint_modem_exception_reset_all(ipa);
 	if (ret)
-		dev_err(dev, "error %d resetting exception endpoint",
-			ret);
+		dev_err(dev, "error %d resetting exception endpoint\n", ret);
 
 	ipa_endpoint_modem_pause_all(ipa, false);
 
 	ret = ipa_modem_stop(ipa);
 	if (ret)
-		dev_err(dev, "error %d stopping modem", ret);
+		dev_err(dev, "error %d stopping modem\n", ret);
 
 	/* Now prepare for the next modem boot */
 	ret = ipa_mem_zero_modem(ipa);
diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c
index 4d33aa7ebfbb..a5f7a79a1923 100644
--- a/drivers/net/ipa/ipa_smp2p.c
+++ b/drivers/net/ipa/ipa_smp2p.c
@@ -53,7 +53,7 @@
  * @clock_on:		Whether IPA clock is on
  * @notified:		Whether modem has been notified of clock state
  * @disabled:		Whether setup ready interrupt handling is disabled
- * @mutex mutex:	Motex protecting ready interrupt/shutdown interlock
+ * @mutex:		Mutex protecting ready-interrupt/shutdown interlock
  * @panic_notifier:	Panic notifier structure
 */
 struct ipa_smp2p {
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 0d580d81d910..d0d31cb99180 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1305,7 +1305,8 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len)
 	struct crypto_aead *tfm;
 	int ret;
 
-	tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
+	/* Pick a sync gcm(aes) cipher to ensure order is preserved. */
+	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
 
 	if (IS_ERR(tfm))
 		return tfm;
@@ -2640,11 +2641,12 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info)
 	if (ret)
 		goto rollback;
 
-	rtnl_unlock();
 	/* Force features update, since they are different for SW MACSec and
 	 * HW offloading cases.
 	 */
 	netdev_update_features(dev);
+
+	rtnl_unlock();
 	return 0;
 
 rollback:
@@ -3809,7 +3811,7 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[],
 			     struct netlink_ext_ack *extack)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
-	struct macsec_tx_sa tx_sc;
+	struct macsec_tx_sc tx_sc;
 	struct macsec_secy secy;
 	int ret;
 
@@ -4002,11 +4004,11 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 			  struct netlink_ext_ack *extack)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
+	rx_handler_func_t *rx_handler;
+	u8 icv_len = DEFAULT_ICV_LEN;
 	struct net_device *real_dev;
-	int err;
+	int err, mtu;
 	sci_t sci;
-	u8 icv_len = DEFAULT_ICV_LEN;
-	rx_handler_func_t *rx_handler;
 
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
@@ -4033,7 +4035,11 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 
 	if (data && data[IFLA_MACSEC_ICV_LEN])
 		icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]);
-	dev->mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
+	mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
+	if (mtu < 0)
+		dev->mtu = 0;
+	else
+		dev->mtu = mtu;
 
 	rx_handler = rtnl_dereference(real_dev->rx_handler);
 	if (rx_handler && rx_handler != macsec_handle_frame)
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index e7289d67268f..0482adc9916b 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1704,7 +1704,7 @@ static int macvlan_device_event(struct notifier_block *unused,
 						struct macvlan_dev,
 						list);
 
-		if (macvlan_sync_address(vlan->dev, dev->dev_addr))
+		if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr))
 			return NOTIFY_BAD;
 
 		break;
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 68668a22b9dd..dc3ff0e20944 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -858,8 +858,7 @@ nsim_dev_devlink_trap_policer_counter_get(struct devlink *devlink,
 		return -EINVAL;
 
 	cnt = &nsim_dev->trap_data->trap_policers_cnt_arr[policer->id - 1];
-	*p_drops = *cnt;
-	*cnt += jiffies % 64;
+	*p_drops = (*cnt)++;
 
 	return 0;
 }
diff --git a/drivers/net/phy/bcm84881.c b/drivers/net/phy/bcm84881.c
index 3840d2adbbb9..9717a1626f3f 100644
--- a/drivers/net/phy/bcm84881.c
+++ b/drivers/net/phy/bcm84881.c
@@ -155,9 +155,6 @@ static int bcm84881_read_status(struct phy_device *phydev)
 	if (phydev->autoneg == AUTONEG_ENABLE && !phydev->autoneg_complete)
 		phydev->link = false;
 
-	if (!phydev->link)
-		return 0;
-
 	linkmode_zero(phydev->lp_advertising);
 	phydev->speed = SPEED_UNKNOWN;
 	phydev->duplex = DUPLEX_UNKNOWN;
@@ -165,6 +162,9 @@ static int bcm84881_read_status(struct phy_device *phydev)
 	phydev->asym_pause = 0;
 	phydev->mdix = 0;
 
+	if (!phydev->link)
+		return 0;
+
 	if (phydev->autoneg_complete) {
 		val = genphy_c45_read_lpa(phydev);
 		if (val < 0)
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index ae4873f2f86e..d14d91b759b7 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -225,8 +225,12 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev)
 	else
 		val |= BCM54XX_SHD_SCR3_DLLAPD_DIS;
 
-	if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY)
-		val |= BCM54XX_SHD_SCR3_TRDDAPD;
+	if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) {
+		if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54810)
+			val |= BCM54810_SHD_SCR3_TRDDAPD;
+		else
+			val |= BCM54XX_SHD_SCR3_TRDDAPD;
+	}
 
 	if (orig != val)
 		bcm_phy_write_shadow(phydev, BCM54XX_SHD_SCR3, val);
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 415c27310982..ecbd5e0d685c 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1120,7 +1120,7 @@ static struct dp83640_clock *dp83640_clock_get_bus(struct mii_bus *bus)
 		goto out;
 	}
 	dp83640_clock_init(clock, bus);
-	list_add_tail(&phyter_clocks, &clock->list);
+	list_add_tail(&clock->list, &phyter_clocks);
 out:
 	mutex_unlock(&phyter_clocks_lock);
 
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index fe9aa3ad52a7..1dd19d0cb269 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -137,19 +137,18 @@ static int dp83822_set_wol(struct phy_device *phydev,
 			value &= ~DP83822_WOL_SECURE_ON;
 		}
 
-		value |= (DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL |
-			  DP83822_WOL_CLR_INDICATION);
-		phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG,
-			      value);
+		/* Clear any pending WoL interrupt */
+		phy_read(phydev, MII_DP83822_MISR2);
+
+		value |= DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL |
+			 DP83822_WOL_CLR_INDICATION;
+
+		return phy_write_mmd(phydev, DP83822_DEVADDR,
+				     MII_DP83822_WOL_CFG, value);
 	} else {
-		value = phy_read_mmd(phydev, DP83822_DEVADDR,
-				     MII_DP83822_WOL_CFG);
-		value &= ~DP83822_WOL_EN;
-		phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG,
-			      value);
+		return phy_clear_bits_mmd(phydev, DP83822_DEVADDR,
+					  MII_DP83822_WOL_CFG, DP83822_WOL_EN);
 	}
-
-	return 0;
 }
 
 static void dp83822_get_wol(struct phy_device *phydev,
@@ -258,12 +257,11 @@ static int dp83822_config_intr(struct phy_device *phydev)
 
 static int dp83822_config_init(struct phy_device *phydev)
 {
-	int value;
-
-	value = DP83822_WOL_MAGIC_EN | DP83822_WOL_SECURE_ON | DP83822_WOL_EN;
+	int value = DP83822_WOL_EN | DP83822_WOL_MAGIC_EN |
+		    DP83822_WOL_SECURE_ON;
 
-	return phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG,
-	      value);
+	return phy_clear_bits_mmd(phydev, DP83822_DEVADDR,
+				  MII_DP83822_WOL_CFG, value);
 }
 
 static int dp83822_phy_reset(struct phy_device *phydev)
diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c
index 06f08832ebcd..d73725312c7c 100644
--- a/drivers/net/phy/dp83tc811.c
+++ b/drivers/net/phy/dp83tc811.c
@@ -139,16 +139,19 @@ static int dp83811_set_wol(struct phy_device *phydev,
 			value &= ~DP83811_WOL_SECURE_ON;
 		}
 
-		value |= (DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL |
-			  DP83811_WOL_CLR_INDICATION);
-		phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
-			      value);
+		/* Clear any pending WoL interrupt */
+		phy_read(phydev, MII_DP83811_INT_STAT1);
+
+		value |= DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL |
+			 DP83811_WOL_CLR_INDICATION;
+
+		return phy_write_mmd(phydev, DP83811_DEVADDR,
+				     MII_DP83811_WOL_CFG, value);
 	} else {
-		phy_clear_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
-				   DP83811_WOL_EN);
+		return phy_clear_bits_mmd(phydev, DP83811_DEVADDR,
+					  MII_DP83811_WOL_CFG, DP83811_WOL_EN);
 	}
 
-	return 0;
 }
 
 static void dp83811_get_wol(struct phy_device *phydev,
@@ -292,8 +295,8 @@ static int dp83811_config_init(struct phy_device *phydev)
 
 	value = DP83811_WOL_MAGIC_EN | DP83811_WOL_SECURE_ON | DP83811_WOL_EN;
 
-	return phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
-	      value);
+	return phy_clear_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
+				  value);
 }
 
 static int dp83811_phy_reset(struct phy_device *phydev)
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 4714ca0e0d4b..7fc8e10c5f33 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1263,6 +1263,30 @@ static int marvell_read_status_page_an(struct phy_device *phydev,
 	int lpa;
 	int err;
 
+	if (!(status & MII_M1011_PHY_STATUS_RESOLVED)) {
+		phydev->link = 0;
+		return 0;
+	}
+
+	if (status & MII_M1011_PHY_STATUS_FULLDUPLEX)
+		phydev->duplex = DUPLEX_FULL;
+	else
+		phydev->duplex = DUPLEX_HALF;
+
+	switch (status & MII_M1011_PHY_STATUS_SPD_MASK) {
+	case MII_M1011_PHY_STATUS_1000:
+		phydev->speed = SPEED_1000;
+		break;
+
+	case MII_M1011_PHY_STATUS_100:
+		phydev->speed = SPEED_100;
+		break;
+
+	default:
+		phydev->speed = SPEED_10;
+		break;
+	}
+
 	if (!fiber) {
 		err = genphy_read_lpa(phydev);
 		if (err < 0)
@@ -1291,28 +1315,6 @@ static int marvell_read_status_page_an(struct phy_device *phydev,
 		}
 	}
 
-	if (!(status & MII_M1011_PHY_STATUS_RESOLVED))
-		return 0;
-
-	if (status & MII_M1011_PHY_STATUS_FULLDUPLEX)
-		phydev->duplex = DUPLEX_FULL;
-	else
-		phydev->duplex = DUPLEX_HALF;
-
-	switch (status & MII_M1011_PHY_STATUS_SPD_MASK) {
-	case MII_M1011_PHY_STATUS_1000:
-		phydev->speed = SPEED_1000;
-		break;
-
-	case MII_M1011_PHY_STATUS_100:
-		phydev->speed = SPEED_100;
-		break;
-
-	default:
-		phydev->speed = SPEED_10;
-		break;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 7621badae64d..1f1a01c98e44 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -33,6 +33,8 @@
 #define MV_PHY_ALASKA_NBT_QUIRK_REV	(MARVELL_PHY_ID_88X3310 | 0xa)
 
 enum {
+	MV_PMA_FW_VER0		= 0xc011,
+	MV_PMA_FW_VER1		= 0xc012,
 	MV_PMA_BOOT		= 0xc050,
 	MV_PMA_BOOT_FATAL	= BIT(0),
 
@@ -64,6 +66,9 @@ enum {
 	MV_PCS_CSSR1_SPD2_2500	= 0x0004,
 	MV_PCS_CSSR1_SPD2_10000	= 0x0000,
 
+	/* Temperature read register (88E2110 only) */
+	MV_PCS_TEMP		= 0x8042,
+
 	/* These registers appear at 0x800X and 0xa00X - the 0xa00X control
 	 * registers appear to set themselves to the 0x800X when AN is
 	 * restarted, but status registers appear readable from either.
@@ -73,7 +78,9 @@ enum {
 
 	/* Vendor2 MMD registers */
 	MV_V2_PORT_CTRL		= 0xf001,
-	MV_V2_PORT_CTRL_PWRDOWN = 0x0800,
+	MV_V2_PORT_CTRL_SWRST	= BIT(15),
+	MV_V2_PORT_CTRL_PWRDOWN = BIT(11),
+	/* Temperature control/read registers (88X3310 only) */
 	MV_V2_TEMP_CTRL		= 0xf08a,
 	MV_V2_TEMP_CTRL_MASK	= 0xc000,
 	MV_V2_TEMP_CTRL_SAMPLE	= 0x0000,
@@ -83,6 +90,8 @@ enum {
 };
 
 struct mv3310_priv {
+	u32 firmware_ver;
+
 	struct device *hwmon_dev;
 	char *hwmon_name;
 };
@@ -99,6 +108,24 @@ static umode_t mv3310_hwmon_is_visible(const void *data,
 	return 0;
 }
 
+static int mv3310_hwmon_read_temp_reg(struct phy_device *phydev)
+{
+	return phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP);
+}
+
+static int mv2110_hwmon_read_temp_reg(struct phy_device *phydev)
+{
+	return phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_TEMP);
+}
+
+static int mv10g_hwmon_read_temp_reg(struct phy_device *phydev)
+{
+	if (phydev->drv->phy_id == MARVELL_PHY_ID_88X3310)
+		return mv3310_hwmon_read_temp_reg(phydev);
+	else /* MARVELL_PHY_ID_88E2110 */
+		return mv2110_hwmon_read_temp_reg(phydev);
+}
+
 static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 			     u32 attr, int channel, long *value)
 {
@@ -111,7 +138,7 @@ static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 	}
 
 	if (type == hwmon_temp && attr == hwmon_temp_input) {
-		temp = phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP);
+		temp = mv10g_hwmon_read_temp_reg(phydev);
 		if (temp < 0)
 			return temp;
 
@@ -164,6 +191,9 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable)
 	u16 val;
 	int ret;
 
+	if (phydev->drv->phy_id != MARVELL_PHY_ID_88X3310)
+		return 0;
+
 	ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP,
 			    MV_V2_TEMP_UNKNOWN);
 	if (ret < 0)
@@ -235,8 +265,18 @@ static int mv3310_power_down(struct phy_device *phydev)
 
 static int mv3310_power_up(struct phy_device *phydev)
 {
-	return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, MV_V2_PORT_CTRL,
-				  MV_V2_PORT_CTRL_PWRDOWN);
+	struct mv3310_priv *priv = dev_get_drvdata(&phydev->mdio.dev);
+	int ret;
+
+	ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, MV_V2_PORT_CTRL,
+				 MV_V2_PORT_CTRL_PWRDOWN);
+
+	if (phydev->drv->phy_id != MARVELL_PHY_ID_88X3310 ||
+	    priv->firmware_ver < 0x00030000)
+		return ret;
+
+	return phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MV_V2_PORT_CTRL,
+				MV_V2_PORT_CTRL_SWRST);
 }
 
 static int mv3310_reset(struct phy_device *phydev, u32 unit)
@@ -355,6 +395,22 @@ static int mv3310_probe(struct phy_device *phydev)
 
 	dev_set_drvdata(&phydev->mdio.dev, priv);
 
+	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MV_PMA_FW_VER0);
+	if (ret < 0)
+		return ret;
+
+	priv->firmware_ver = ret << 16;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MV_PMA_FW_VER1);
+	if (ret < 0)
+		return ret;
+
+	priv->firmware_ver |= ret;
+
+	phydev_info(phydev, "Firmware version %u.%u.%u.%u\n",
+		    priv->firmware_ver >> 24, (priv->firmware_ver >> 16) & 255,
+		    (priv->firmware_ver >> 8) & 255, priv->firmware_ver & 255);
+
 	/* Powering down the port when not in use saves about 600mW */
 	ret = mv3310_power_down(phydev);
 	if (ret)
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 522760c8bca6..7a4eb3f2cb74 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -464,7 +464,7 @@ static struct class mdio_bus_class = {
 
 /**
  * mdio_find_bus - Given the name of a mdiobus, find the mii_bus.
- * @mdio_bus_np: Pointer to the mii_bus.
+ * @mdio_name: The name of a mdiobus.
  *
  * Returns a reference to the mii_bus, or NULL if none found.  The
  * embedded struct device will have its reference count incremented,
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 05d20343b816..3a4d83fa52dc 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1204,7 +1204,7 @@ static struct phy_driver ksphy_driver[] = {
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz9131_config_init,
-	.read_status	= ksz9031_read_status,
+	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
 	.get_sset_count = kszphy_get_sset_count,
diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c
index 001def4509c2..fed3e395f18e 100644
--- a/drivers/net/phy/microchip_t1.c
+++ b/drivers/net/phy/microchip_t1.c
@@ -3,9 +3,21 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/delay.h>
 #include <linux/mii.h>
 #include <linux/phy.h>
 
+/* External Register Control Register */
+#define LAN87XX_EXT_REG_CTL                     (0x14)
+#define LAN87XX_EXT_REG_CTL_RD_CTL              (0x1000)
+#define LAN87XX_EXT_REG_CTL_WR_CTL              (0x0800)
+
+/* External Register Read Data Register */
+#define LAN87XX_EXT_REG_RD_DATA                 (0x15)
+
+/* External Register Write Data Register */
+#define LAN87XX_EXT_REG_WR_DATA                 (0x16)
+
 /* Interrupt Source Register */
 #define LAN87XX_INTERRUPT_SOURCE                (0x18)
 
@@ -14,9 +26,160 @@
 #define LAN87XX_MASK_LINK_UP                    (0x0004)
 #define LAN87XX_MASK_LINK_DOWN                  (0x0002)
 
+/* phyaccess nested types */
+#define	PHYACC_ATTR_MODE_READ		0
+#define	PHYACC_ATTR_MODE_WRITE		1
+#define	PHYACC_ATTR_MODE_MODIFY		2
+
+#define	PHYACC_ATTR_BANK_SMI		0
+#define	PHYACC_ATTR_BANK_MISC		1
+#define	PHYACC_ATTR_BANK_PCS		2
+#define	PHYACC_ATTR_BANK_AFE		3
+#define	PHYACC_ATTR_BANK_MAX		7
+
 #define DRIVER_AUTHOR	"Nisar Sayed <nisar.sayed@microchip.com>"
 #define DRIVER_DESC	"Microchip LAN87XX T1 PHY driver"
 
+struct access_ereg_val {
+	u8  mode;
+	u8  bank;
+	u8  offset;
+	u16 val;
+	u16 mask;
+};
+
+static int access_ereg(struct phy_device *phydev, u8 mode, u8 bank,
+		       u8 offset, u16 val)
+{
+	u16 ereg = 0;
+	int rc = 0;
+
+	if (mode > PHYACC_ATTR_MODE_WRITE || bank > PHYACC_ATTR_BANK_MAX)
+		return -EINVAL;
+
+	if (bank == PHYACC_ATTR_BANK_SMI) {
+		if (mode == PHYACC_ATTR_MODE_WRITE)
+			rc = phy_write(phydev, offset, val);
+		else
+			rc = phy_read(phydev, offset);
+		return rc;
+	}
+
+	if (mode == PHYACC_ATTR_MODE_WRITE) {
+		ereg = LAN87XX_EXT_REG_CTL_WR_CTL;
+		rc = phy_write(phydev, LAN87XX_EXT_REG_WR_DATA, val);
+		if (rc < 0)
+			return rc;
+	} else {
+		ereg = LAN87XX_EXT_REG_CTL_RD_CTL;
+	}
+
+	ereg |= (bank << 8) | offset;
+
+	rc = phy_write(phydev, LAN87XX_EXT_REG_CTL, ereg);
+	if (rc < 0)
+		return rc;
+
+	if (mode == PHYACC_ATTR_MODE_READ)
+		rc = phy_read(phydev, LAN87XX_EXT_REG_RD_DATA);
+
+	return rc;
+}
+
+static int access_ereg_modify_changed(struct phy_device *phydev,
+				      u8 bank, u8 offset, u16 val, u16 mask)
+{
+	int new = 0, rc = 0;
+
+	if (bank > PHYACC_ATTR_BANK_MAX)
+		return -EINVAL;
+
+	rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ, bank, offset, val);
+	if (rc < 0)
+		return rc;
+
+	new = val | (rc & (mask ^ 0xFFFF));
+	rc = access_ereg(phydev, PHYACC_ATTR_MODE_WRITE, bank, offset, new);
+
+	return rc;
+}
+
+static int lan87xx_phy_init(struct phy_device *phydev)
+{
+	static const struct access_ereg_val init[] = {
+		/* TX Amplitude = 5 */
+		{PHYACC_ATTR_MODE_MODIFY, PHYACC_ATTR_BANK_AFE, 0x0B,
+		 0x000A, 0x001E},
+		/* Clear SMI interrupts */
+		{PHYACC_ATTR_MODE_READ, PHYACC_ATTR_BANK_SMI, 0x18,
+		 0, 0},
+		/* Clear MISC interrupts */
+		{PHYACC_ATTR_MODE_READ, PHYACC_ATTR_BANK_MISC, 0x08,
+		 0, 0},
+		/* Turn on TC10 Ring Oscillator (ROSC) */
+		{PHYACC_ATTR_MODE_MODIFY, PHYACC_ATTR_BANK_MISC, 0x20,
+		 0x0020, 0x0020},
+		/* WUR Detect Length to 1.2uS, LPC Detect Length to 1.09uS */
+		{PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_PCS, 0x20,
+		 0x283C, 0},
+		/* Wake_In Debounce Length to 39uS, Wake_Out Length to 79uS */
+		{PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_MISC, 0x21,
+		 0x274F, 0},
+		/* Enable Auto Wake Forward to Wake_Out, ROSC on, Sleep,
+		 * and Wake_In to wake PHY
+		 */
+		{PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_MISC, 0x20,
+		 0x80A7, 0},
+		/* Enable WUP Auto Fwd, Enable Wake on MDI, Wakeup Debouncer
+		 * to 128 uS
+		 */
+		{PHYACC_ATTR_MODE_WRITE, PHYACC_ATTR_BANK_MISC, 0x24,
+		 0xF110, 0},
+		/* Enable HW Init */
+		{PHYACC_ATTR_MODE_MODIFY, PHYACC_ATTR_BANK_SMI, 0x1A,
+		 0x0100, 0x0100},
+	};
+	int rc, i;
+
+	/* Start manual initialization procedures in Managed Mode */
+	rc = access_ereg_modify_changed(phydev, PHYACC_ATTR_BANK_SMI,
+					0x1a, 0x0000, 0x0100);
+	if (rc < 0)
+		return rc;
+
+	/* Soft Reset the SMI block */
+	rc = access_ereg_modify_changed(phydev, PHYACC_ATTR_BANK_SMI,
+					0x00, 0x8000, 0x8000);
+	if (rc < 0)
+		return rc;
+
+	/* Check to see if the self-clearing bit is cleared */
+	usleep_range(1000, 2000);
+	rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ,
+			 PHYACC_ATTR_BANK_SMI, 0x00, 0);
+	if (rc < 0)
+		return rc;
+	if ((rc & 0x8000) != 0)
+		return -ETIMEDOUT;
+
+	/* PHY Initialization */
+	for (i = 0; i < ARRAY_SIZE(init); i++) {
+		if (init[i].mode == PHYACC_ATTR_MODE_MODIFY) {
+			rc = access_ereg_modify_changed(phydev, init[i].bank,
+							init[i].offset,
+							init[i].val,
+							init[i].mask);
+		} else {
+			rc = access_ereg(phydev, init[i].mode, init[i].bank,
+					 init[i].offset, init[i].val);
+		}
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
 static int lan87xx_phy_config_intr(struct phy_device *phydev)
 {
 	int rc, val = 0;
@@ -40,6 +203,13 @@ static int lan87xx_phy_ack_interrupt(struct phy_device *phydev)
 	return rc < 0 ? rc : 0;
 }
 
+static int lan87xx_config_init(struct phy_device *phydev)
+{
+	int rc = lan87xx_phy_init(phydev);
+
+	return rc < 0 ? rc : 0;
+}
+
 static struct phy_driver microchip_t1_phy_driver[] = {
 	{
 		.phy_id         = 0x0007c150,
@@ -48,6 +218,7 @@ static struct phy_driver microchip_t1_phy_driver[] = {
 
 		.features       = PHY_BASIC_T1_FEATURES,
 
+		.config_init	= lan87xx_config_init,
 		.config_aneg    = genphy_config_aneg,
 
 		.ack_interrupt  = lan87xx_phy_ack_interrupt,
diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h
index 030bf8b600df..414e3b31bb1f 100644
--- a/drivers/net/phy/mscc/mscc.h
+++ b/drivers/net/phy/mscc/mscc.h
@@ -354,6 +354,8 @@ struct vsc8531_private {
 	u64 *stats;
 	int nstats;
 	bool pkg_init;
+	/* PHY address within the package. */
+	u8 addr;
 	/* For multiple port PHYs; the MDIO address of the base PHY in the
 	 * package.
 	 */
diff --git a/drivers/net/phy/mscc/mscc_mac.h b/drivers/net/phy/mscc/mscc_mac.h
index fcb5ba5e5d03..59b6837c60b3 100644
--- a/drivers/net/phy/mscc/mscc_mac.h
+++ b/drivers/net/phy/mscc/mscc_mac.h
@@ -152,8 +152,8 @@
 #define MSCC_MAC_PAUSE_CFG_STATE_PAUSE_STATE			BIT(0)
 #define MSCC_MAC_PAUSE_CFG_STATE_MAC_TX_PAUSE_GEN		BIT(4)
 
-#define MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL			0x2
-#define MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE(x)	(x)
-#define MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE_M	GENMASK(2, 0)
+#define MSCC_PROC_IP_1588_TOP_CFG_STAT_MODE_CTL			0x2
+#define MSCC_PROC_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE(x)	(x)
+#define MSCC_PROC_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE_M	GENMASK(2, 0)
 
 #endif /* _MSCC_PHY_LINE_MAC_H_ */
diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c
index e99e2cd72a0c..b4d3dc4068e2 100644
--- a/drivers/net/phy/mscc/mscc_macsec.c
+++ b/drivers/net/phy/mscc/mscc_macsec.c
@@ -316,6 +316,8 @@ static void vsc8584_macsec_mac_init(struct phy_device *phydev,
 /* Must be called with mdio_lock taken */
 static int __vsc8584_macsec_init(struct phy_device *phydev)
 {
+	struct vsc8531_private *priv = phydev->priv;
+	enum macsec_bank proc_bank;
 	u32 val;
 
 	vsc8584_macsec_block_init(phydev, MACSEC_INGR);
@@ -351,12 +353,14 @@ static int __vsc8584_macsec_init(struct phy_device *phydev)
 	val |= MSCC_FCBUF_ENA_CFG_TX_ENA | MSCC_FCBUF_ENA_CFG_RX_ENA;
 	vsc8584_macsec_phy_write(phydev, FC_BUFFER, MSCC_FCBUF_ENA_CFG, val);
 
-	val = vsc8584_macsec_phy_read(phydev, IP_1588,
-				      MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL);
-	val &= ~MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE_M;
-	val |= MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE(4);
-	vsc8584_macsec_phy_write(phydev, IP_1588,
-				 MSCC_PROC_0_IP_1588_TOP_CFG_STAT_MODE_CTL, val);
+	proc_bank = (priv->addr < 2) ? PROC_0 : PROC_2;
+
+	val = vsc8584_macsec_phy_read(phydev, proc_bank,
+				      MSCC_PROC_IP_1588_TOP_CFG_STAT_MODE_CTL);
+	val &= ~MSCC_PROC_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE_M;
+	val |= MSCC_PROC_IP_1588_TOP_CFG_STAT_MODE_CTL_PROTOCOL_MODE(4);
+	vsc8584_macsec_phy_write(phydev, proc_bank,
+				 MSCC_PROC_IP_1588_TOP_CFG_STAT_MODE_CTL, val);
 
 	return 0;
 }
diff --git a/drivers/net/phy/mscc/mscc_macsec.h b/drivers/net/phy/mscc/mscc_macsec.h
index d0783944d106..d751f2946b79 100644
--- a/drivers/net/phy/mscc/mscc_macsec.h
+++ b/drivers/net/phy/mscc/mscc_macsec.h
@@ -64,7 +64,8 @@ enum macsec_bank {
 	FC_BUFFER   = 0x04,
 	HOST_MAC    = 0x05,
 	LINE_MAC    = 0x06,
-	IP_1588     = 0x0e,
+	PROC_0      = 0x0e,
+	PROC_2      = 0x0f,
 	MACSEC_INGR = 0x38,
 	MACSEC_EGR  = 0x3c,
 };
diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c
index acddef79f4e8..c8aa6d905d8e 100644
--- a/drivers/net/phy/mscc/mscc_main.c
+++ b/drivers/net/phy/mscc/mscc_main.c
@@ -1347,6 +1347,8 @@ static int vsc8584_config_init(struct phy_device *phydev)
 	else
 		vsc8531->base_addr = phydev->mdio.addr - addr;
 
+	vsc8531->addr = addr;
+
 	/* Some parts of the init sequence are identical for every PHY in the
 	 * package. Some parts are modifying the GPIO register bank which is a
 	 * set of registers that are affecting all PHYs, a few resetting the
@@ -1771,6 +1773,8 @@ static int vsc8514_config_init(struct phy_device *phydev)
 	else
 		vsc8531->base_addr = phydev->mdio.addr - addr;
 
+	vsc8531->addr = addr;
+
 	/* Some parts of the init sequence are identical for every PHY in the
 	 * package. Some parts are modifying the GPIO register bank which is a
 	 * set of registers that are affecting all PHYs, a few resetting the
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 72c69a9c8a98..20ca6418f7bc 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1132,9 +1132,11 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 		/* Restart autonegotiation so the new modes get sent to the
 		 * link partner.
 		 */
-		ret = phy_restart_aneg(phydev);
-		if (ret < 0)
-			return ret;
+		if (phydev->autoneg == AUTONEG_ENABLE) {
+			ret = phy_restart_aneg(phydev);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index ac2784192472..697c74deb222 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1233,7 +1233,7 @@ int phy_sfp_probe(struct phy_device *phydev,
 		  const struct sfp_upstream_ops *ops)
 {
 	struct sfp_bus *bus;
-	int ret;
+	int ret = 0;
 
 	if (phydev->mdio.dev.fwnode) {
 		bus = sfp_bus_find_fwnode(phydev->mdio.dev.fwnode);
@@ -1245,7 +1245,7 @@ int phy_sfp_probe(struct phy_device *phydev,
 		ret = sfp_bus_add_upstream(bus, phydev, ops);
 		sfp_bus_put(bus);
 	}
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(phy_sfp_probe);
 
diff --git a/drivers/net/phy/swphy.c b/drivers/net/phy/swphy.c
index 53c214a22b95..59f1ba4d49bc 100644
--- a/drivers/net/phy/swphy.c
+++ b/drivers/net/phy/swphy.c
@@ -2,7 +2,7 @@
 /*
  * Software PHY emulation
  *
- * Code taken from fixed_phy.c by Russell King <rmk+kernel@arm.linux.org.uk>
+ * Code taken from fixed_phy.c by Russell King.
  *
  * Author: Vitaly Bordug <vbordug@ru.mvista.com>
  *         Anton Vorontsov <avorontsov@ru.mvista.com>
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index d760a36db28c..beedaad08255 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -490,6 +490,9 @@ static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb)
 		goto out;
 
+	if (skb->pkt_type != PACKET_HOST)
+		goto abort;
+
 	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
 		goto abort;
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 4004f98e50d9..04845a4017f9 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -468,6 +468,9 @@ static const struct team_mode *team_mode_get(const char *kind)
 	struct team_mode_item *mitem;
 	const struct team_mode *mode = NULL;
 
+	if (!try_module_get(THIS_MODULE))
+		return NULL;
+
 	spin_lock(&mode_list_lock);
 	mitem = __find_mode(kind);
 	if (!mitem) {
@@ -483,6 +486,7 @@ static const struct team_mode *team_mode_get(const char *kind)
 	}
 
 	spin_unlock(&mode_list_lock);
+	module_put(THIS_MODULE);
 	return mode;
 }
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 07476c6510f2..44889eba1dbc 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1888,6 +1888,7 @@ drop:
 
 	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb);
+	skb_record_rx_queue(skb, tfile->queue_index);
 
 	if (skb_xdp) {
 		struct bpf_prog *xdp_prog;
@@ -2459,6 +2460,7 @@ build:
 	skb->protocol = eth_type_trans(skb, tun->dev);
 	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb);
+	skb_record_rx_queue(skb, tfile->queue_index);
 
 	if (skb_xdp) {
 		err = do_xdp_generic(xdp_prog, skb);
@@ -2470,7 +2472,6 @@ build:
 	    !tfile->detached)
 		rxhash = __skb_get_hash_symmetric(skb);
 
-	skb_record_rx_queue(skb, tfile->queue_index);
 	netif_receive_skb(skb);
 
 	/* No need for get_cpu_ptr() here since this function is
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 0cdb2ce47645..a657943c9f01 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -815,14 +815,21 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
-/* Microsoft Surface 3 dock (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
 	.driver_info = 0,
 },
 
-	/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153B) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x0927, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
+/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, 0x0601, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 417e42c9fd03..bb8c34d746ab 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2659,7 +2659,7 @@ static struct hso_device *hso_create_bulk_serial_device(
 	if (!
 	    (serial->out_endp =
 	     hso_get_ep(interface, USB_ENDPOINT_XFER_BULK, USB_DIR_OUT))) {
-		dev_err(&interface->dev, "Failed to find BULK IN ep\n");
+		dev_err(&interface->dev, "Failed to find BULK OUT ep\n");
 		goto exit2;
 	}
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6c738a271257..4a2c7355be63 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1324,6 +1324,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
@@ -1359,6 +1360,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81cc, 8)},	/* Dell Wireless 5816e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e preproduction config */
 	{QMI_FIXED_INTF(0x413c, 0x81e0, 0)},	/* Dell Wireless 5821e with eSIM support*/
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 8f8d9883d363..c8c873a613b6 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -6880,6 +6880,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3062)},
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 11f722460513..ce07f52d89e7 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1243,9 +1243,11 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 			break;
 	} while (rq->vq->num_free);
 	if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) {
-		u64_stats_update_begin(&rq->stats.syncp);
+		unsigned long flags;
+
+		flags = u64_stats_update_begin_irqsave(&rq->stats.syncp);
 		rq->stats.kicks++;
-		u64_stats_update_end(&rq->stats.syncp);
+		u64_stats_update_end_irqrestore(&rq->stats.syncp, flags);
 	}
 
 	return !oom;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 66e00ddc0d42..56f8aab46f89 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -188,8 +188,8 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 	fl6.flowi6_proto = iph->nexthdr;
 	fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
 
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst == dst_null)
+	dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL);
+	if (IS_ERR(dst) || dst == dst_null)
 		goto err;
 
 	skb_dst_drop(skb);
@@ -474,7 +474,8 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
 	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
 		return skb;
 
-	if (qdisc_tx_is_default(vrf_dev))
+	if (qdisc_tx_is_default(vrf_dev) ||
+	    IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
 		return vrf_ip6_out_direct(vrf_dev, sk, skb);
 
 	return vrf_ip6_out_redirect(vrf_dev, skb);
@@ -686,7 +687,8 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 	    ipv4_is_lbcast(ip_hdr(skb)->daddr))
 		return skb;
 
-	if (qdisc_tx_is_default(vrf_dev))
+	if (qdisc_tx_is_default(vrf_dev) ||
+	    IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
 		return vrf_ip_out_direct(vrf_dev, sk, skb);
 
 	return vrf_ip_out_redirect(vrf_dev, skb);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 45308b3350cf..a5b415fed11e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3144,7 +3144,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		u32 id = nla_get_u32(data[IFLA_VXLAN_ID]);
 
 		if (id >= VXLAN_N_VID) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID],
 					    "VXLAN ID must be lower than 16777216");
 			return -ERANGE;
 		}
@@ -3155,7 +3155,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 			= nla_data(data[IFLA_VXLAN_PORT_RANGE]);
 
 		if (ntohs(p->high) < ntohs(p->low)) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE],
 					    "Invalid source port range");
 			return -EINVAL;
 		}
@@ -3165,7 +3165,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]);
 
 		if (df < 0 || df > VXLAN_DF_MAX) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_DF],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF],
 					    "Invalid DF attribute");
 			return -EINVAL;
 		}
diff --git a/drivers/net/wimax/i2400m/usb-fw.c b/drivers/net/wimax/i2400m/usb-fw.c
index 529ebca1e9e1..1f7709d24f35 100644
--- a/drivers/net/wimax/i2400m/usb-fw.c
+++ b/drivers/net/wimax/i2400m/usb-fw.c
@@ -354,6 +354,7 @@ out:
 		usb_autopm_put_interface(i2400mu->usb_iface);
 	d_fnend(8, dev, "(i2400m %p ack %p size %zu) = %ld\n",
 		i2400m, ack, ack_size, (long) result);
+	usb_put_urb(&notif_urb);
 	return result;
 
 error_exceeded:
diff --git a/drivers/net/wireguard/messages.h b/drivers/net/wireguard/messages.h
index b8a7b9ce32ba..208da72673fc 100644
--- a/drivers/net/wireguard/messages.h
+++ b/drivers/net/wireguard/messages.h
@@ -32,7 +32,7 @@ enum cookie_values {
 };
 
 enum counter_values {
-	COUNTER_BITS_TOTAL = 2048,
+	COUNTER_BITS_TOTAL = 8192,
 	COUNTER_REDUNDANT_BITS = BITS_PER_LONG,
 	COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS
 };
diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c
index 708dc61c974f..626433690abb 100644
--- a/drivers/net/wireguard/noise.c
+++ b/drivers/net/wireguard/noise.c
@@ -104,6 +104,7 @@ static struct noise_keypair *keypair_create(struct wg_peer *peer)
 
 	if (unlikely(!keypair))
 		return NULL;
+	spin_lock_init(&keypair->receiving_counter.lock);
 	keypair->internal_id = atomic64_inc_return(&keypair_counter);
 	keypair->entry.type = INDEX_HASHTABLE_KEYPAIR;
 	keypair->entry.peer = peer;
@@ -358,25 +359,16 @@ out:
 	memzero_explicit(output, BLAKE2S_HASH_SIZE + 1);
 }
 
-static void symmetric_key_init(struct noise_symmetric_key *key)
-{
-	spin_lock_init(&key->counter.receive.lock);
-	atomic64_set(&key->counter.counter, 0);
-	memset(key->counter.receive.backtrack, 0,
-	       sizeof(key->counter.receive.backtrack));
-	key->birthdate = ktime_get_coarse_boottime_ns();
-	key->is_valid = true;
-}
-
 static void derive_keys(struct noise_symmetric_key *first_dst,
 			struct noise_symmetric_key *second_dst,
 			const u8 chaining_key[NOISE_HASH_LEN])
 {
+	u64 birthdate = ktime_get_coarse_boottime_ns();
 	kdf(first_dst->key, second_dst->key, NULL, NULL,
 	    NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0,
 	    chaining_key);
-	symmetric_key_init(first_dst);
-	symmetric_key_init(second_dst);
+	first_dst->birthdate = second_dst->birthdate = birthdate;
+	first_dst->is_valid = second_dst->is_valid = true;
 }
 
 static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN],
@@ -715,6 +707,7 @@ wg_noise_handshake_consume_response(struct message_handshake_response *src,
 	u8 e[NOISE_PUBLIC_KEY_LEN];
 	u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN];
 	u8 static_private[NOISE_PUBLIC_KEY_LEN];
+	u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN];
 
 	down_read(&wg->static_identity.lock);
 
@@ -733,6 +726,8 @@ wg_noise_handshake_consume_response(struct message_handshake_response *src,
 	memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN);
 	memcpy(ephemeral_private, handshake->ephemeral_private,
 	       NOISE_PUBLIC_KEY_LEN);
+	memcpy(preshared_key, handshake->preshared_key,
+	       NOISE_SYMMETRIC_KEY_LEN);
 	up_read(&handshake->lock);
 
 	if (state != HANDSHAKE_CREATED_INITIATION)
@@ -750,7 +745,7 @@ wg_noise_handshake_consume_response(struct message_handshake_response *src,
 		goto fail;
 
 	/* psk */
-	mix_psk(chaining_key, hash, key, handshake->preshared_key);
+	mix_psk(chaining_key, hash, key, preshared_key);
 
 	/* {} */
 	if (!message_decrypt(NULL, src->encrypted_nothing,
@@ -783,6 +778,7 @@ out:
 	memzero_explicit(chaining_key, NOISE_HASH_LEN);
 	memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN);
 	memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN);
+	memzero_explicit(preshared_key, NOISE_SYMMETRIC_KEY_LEN);
 	up_read(&wg->static_identity.lock);
 	return ret_peer;
 }
diff --git a/drivers/net/wireguard/noise.h b/drivers/net/wireguard/noise.h
index f532d59d3f19..c527253dba80 100644
--- a/drivers/net/wireguard/noise.h
+++ b/drivers/net/wireguard/noise.h
@@ -15,18 +15,14 @@
 #include <linux/mutex.h>
 #include <linux/kref.h>
 
-union noise_counter {
-	struct {
-		u64 counter;
-		unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
-		spinlock_t lock;
-	} receive;
-	atomic64_t counter;
+struct noise_replay_counter {
+	u64 counter;
+	spinlock_t lock;
+	unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
 };
 
 struct noise_symmetric_key {
 	u8 key[NOISE_SYMMETRIC_KEY_LEN];
-	union noise_counter counter;
 	u64 birthdate;
 	bool is_valid;
 };
@@ -34,7 +30,9 @@ struct noise_symmetric_key {
 struct noise_keypair {
 	struct index_hashtable_entry entry;
 	struct noise_symmetric_key sending;
+	atomic64_t sending_counter;
 	struct noise_symmetric_key receiving;
+	struct noise_replay_counter receiving_counter;
 	__le32 remote_index;
 	bool i_am_the_initiator;
 	struct kref refcount;
diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c
index 5c964fcb994e..71b8e80b58e1 100644
--- a/drivers/net/wireguard/queueing.c
+++ b/drivers/net/wireguard/queueing.c
@@ -35,8 +35,10 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
 		if (multicore) {
 			queue->worker = wg_packet_percpu_multicore_worker_alloc(
 				function, queue);
-			if (!queue->worker)
+			if (!queue->worker) {
+				ptr_ring_cleanup(&queue->ring, NULL);
 				return -ENOMEM;
+			}
 		} else {
 			INIT_WORK(&queue->work, function);
 		}
diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h
index 3432232afe06..c58df439dbbe 100644
--- a/drivers/net/wireguard/queueing.h
+++ b/drivers/net/wireguard/queueing.h
@@ -87,12 +87,20 @@ static inline bool wg_check_packet_protocol(struct sk_buff *skb)
 	return real_protocol && skb->protocol == real_protocol;
 }
 
-static inline void wg_reset_packet(struct sk_buff *skb)
+static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating)
 {
+	u8 l4_hash = skb->l4_hash;
+	u8 sw_hash = skb->sw_hash;
+	u32 hash = skb->hash;
 	skb_scrub_packet(skb, true);
 	memset(&skb->headers_start, 0,
 	       offsetof(struct sk_buff, headers_end) -
 		       offsetof(struct sk_buff, headers_start));
+	if (encapsulating) {
+		skb->l4_hash = l4_hash;
+		skb->sw_hash = sw_hash;
+		skb->hash = hash;
+	}
 	skb->queue_mapping = 0;
 	skb->nohdr = 0;
 	skb->peeked = 0;
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index da3b782ab7d3..91438144e4f7 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -226,40 +226,39 @@ void wg_packet_handshake_receive_worker(struct work_struct *work)
 static void keep_key_fresh(struct wg_peer *peer)
 {
 	struct noise_keypair *keypair;
-	bool send = false;
+	bool send;
 
 	if (peer->sent_lastminute_handshake)
 		return;
 
 	rcu_read_lock_bh();
 	keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
-	if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
-	    keypair->i_am_the_initiator &&
-	    unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
-			REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT)))
-		send = true;
+	send = keypair && READ_ONCE(keypair->sending.is_valid) &&
+	       keypair->i_am_the_initiator &&
+	       wg_birthdate_has_expired(keypair->sending.birthdate,
+			REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT);
 	rcu_read_unlock_bh();
 
-	if (send) {
+	if (unlikely(send)) {
 		peer->sent_lastminute_handshake = true;
 		wg_packet_send_queued_handshake_initiation(peer, false);
 	}
 }
 
-static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
+static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair)
 {
 	struct scatterlist sg[MAX_SKB_FRAGS + 8];
 	struct sk_buff *trailer;
 	unsigned int offset;
 	int num_frags;
 
-	if (unlikely(!key))
+	if (unlikely(!keypair))
 		return false;
 
-	if (unlikely(!READ_ONCE(key->is_valid) ||
-		  wg_birthdate_has_expired(key->birthdate, REJECT_AFTER_TIME) ||
-		  key->counter.receive.counter >= REJECT_AFTER_MESSAGES)) {
-		WRITE_ONCE(key->is_valid, false);
+	if (unlikely(!READ_ONCE(keypair->receiving.is_valid) ||
+		  wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) ||
+		  keypair->receiving_counter.counter >= REJECT_AFTER_MESSAGES)) {
+		WRITE_ONCE(keypair->receiving.is_valid, false);
 		return false;
 	}
 
@@ -284,7 +283,7 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
 
 	if (!chacha20poly1305_decrypt_sg_inplace(sg, skb->len, NULL, 0,
 					         PACKET_CB(skb)->nonce,
-						 key->key))
+						 keypair->receiving.key))
 		return false;
 
 	/* Another ugly situation of pushing and pulling the header so as to
@@ -299,41 +298,41 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
 }
 
 /* This is RFC6479, a replay detection bitmap algorithm that avoids bitshifts */
-static bool counter_validate(union noise_counter *counter, u64 their_counter)
+static bool counter_validate(struct noise_replay_counter *counter, u64 their_counter)
 {
 	unsigned long index, index_current, top, i;
 	bool ret = false;
 
-	spin_lock_bh(&counter->receive.lock);
+	spin_lock_bh(&counter->lock);
 
-	if (unlikely(counter->receive.counter >= REJECT_AFTER_MESSAGES + 1 ||
+	if (unlikely(counter->counter >= REJECT_AFTER_MESSAGES + 1 ||
 		     their_counter >= REJECT_AFTER_MESSAGES))
 		goto out;
 
 	++their_counter;
 
 	if (unlikely((COUNTER_WINDOW_SIZE + their_counter) <
-		     counter->receive.counter))
+		     counter->counter))
 		goto out;
 
 	index = their_counter >> ilog2(BITS_PER_LONG);
 
-	if (likely(their_counter > counter->receive.counter)) {
-		index_current = counter->receive.counter >> ilog2(BITS_PER_LONG);
+	if (likely(their_counter > counter->counter)) {
+		index_current = counter->counter >> ilog2(BITS_PER_LONG);
 		top = min_t(unsigned long, index - index_current,
 			    COUNTER_BITS_TOTAL / BITS_PER_LONG);
 		for (i = 1; i <= top; ++i)
-			counter->receive.backtrack[(i + index_current) &
+			counter->backtrack[(i + index_current) &
 				((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0;
-		counter->receive.counter = their_counter;
+		counter->counter = their_counter;
 	}
 
 	index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1;
 	ret = !test_and_set_bit(their_counter & (BITS_PER_LONG - 1),
-				&counter->receive.backtrack[index]);
+				&counter->backtrack[index]);
 
 out:
-	spin_unlock_bh(&counter->receive.lock);
+	spin_unlock_bh(&counter->lock);
 	return ret;
 }
 
@@ -393,13 +392,11 @@ static void wg_packet_consume_data_done(struct wg_peer *peer,
 		len = ntohs(ip_hdr(skb)->tot_len);
 		if (unlikely(len < sizeof(struct iphdr)))
 			goto dishonest_packet_size;
-		if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
-			IP_ECN_set_ce(ip_hdr(skb));
+		INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ip_hdr(skb)->tos);
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
 		len = ntohs(ipv6_hdr(skb)->payload_len) +
 		      sizeof(struct ipv6hdr);
-		if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
-			IP6_ECN_set_ce(skb, ipv6_hdr(skb));
+		INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ipv6_get_dsfield(ipv6_hdr(skb)));
 	} else {
 		goto dishonest_packet_type;
 	}
@@ -475,19 +472,19 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget)
 		if (unlikely(state != PACKET_STATE_CRYPTED))
 			goto next;
 
-		if (unlikely(!counter_validate(&keypair->receiving.counter,
+		if (unlikely(!counter_validate(&keypair->receiving_counter,
 					       PACKET_CB(skb)->nonce))) {
 			net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n",
 					    peer->device->dev->name,
 					    PACKET_CB(skb)->nonce,
-					    keypair->receiving.counter.receive.counter);
+					    keypair->receiving_counter.counter);
 			goto next;
 		}
 
 		if (unlikely(wg_socket_endpoint_from_skb(&endpoint, skb)))
 			goto next;
 
-		wg_reset_packet(skb);
+		wg_reset_packet(skb, false);
 		wg_packet_consume_data_done(peer, skb, &endpoint);
 		free = false;
 
@@ -514,10 +511,12 @@ void wg_packet_decrypt_worker(struct work_struct *work)
 	struct sk_buff *skb;
 
 	while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) {
-		enum packet_state state = likely(decrypt_packet(skb,
-				&PACKET_CB(skb)->keypair->receiving)) ?
+		enum packet_state state =
+			likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ?
 				PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
 		wg_queue_enqueue_per_peer_napi(skb, state);
+		if (need_resched())
+			cond_resched();
 	}
 }
 
diff --git a/drivers/net/wireguard/selftest/counter.c b/drivers/net/wireguard/selftest/counter.c
index f4fbb9072ed7..ec3c156bf91b 100644
--- a/drivers/net/wireguard/selftest/counter.c
+++ b/drivers/net/wireguard/selftest/counter.c
@@ -6,18 +6,24 @@
 #ifdef DEBUG
 bool __init wg_packet_counter_selftest(void)
 {
+	struct noise_replay_counter *counter;
 	unsigned int test_num = 0, i;
-	union noise_counter counter;
 	bool success = true;
 
-#define T_INIT do {                                               \
-		memset(&counter, 0, sizeof(union noise_counter)); \
-		spin_lock_init(&counter.receive.lock);            \
+	counter = kmalloc(sizeof(*counter), GFP_KERNEL);
+	if (unlikely(!counter)) {
+		pr_err("nonce counter self-test malloc: FAIL\n");
+		return false;
+	}
+
+#define T_INIT do {                                    \
+		memset(counter, 0, sizeof(*counter));  \
+		spin_lock_init(&counter->lock);        \
 	} while (0)
 #define T_LIM (COUNTER_WINDOW_SIZE + 1)
 #define T(n, v) do {                                                  \
 		++test_num;                                           \
-		if (counter_validate(&counter, n) != (v)) {           \
+		if (counter_validate(counter, n) != (v)) {            \
 			pr_err("nonce counter self-test %u: FAIL\n",  \
 			       test_num);                             \
 			success = false;                              \
@@ -99,6 +105,7 @@ bool __init wg_packet_counter_selftest(void)
 
 	if (success)
 		pr_info("nonce counter self-tests: pass\n");
+	kfree(counter);
 	return success;
 }
 #endif
diff --git a/drivers/net/wireguard/selftest/ratelimiter.c b/drivers/net/wireguard/selftest/ratelimiter.c
index bcd6462e4540..007cd4457c5f 100644
--- a/drivers/net/wireguard/selftest/ratelimiter.c
+++ b/drivers/net/wireguard/selftest/ratelimiter.c
@@ -120,9 +120,9 @@ bool __init wg_ratelimiter_selftest(void)
 	enum { TRIALS_BEFORE_GIVING_UP = 5000 };
 	bool success = false;
 	int test = 0, trials;
-	struct sk_buff *skb4, *skb6;
+	struct sk_buff *skb4, *skb6 = NULL;
 	struct iphdr *hdr4;
-	struct ipv6hdr *hdr6;
+	struct ipv6hdr *hdr6 = NULL;
 
 	if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN))
 		return true;
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index 7348c10cbae3..f74b9341ab0f 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -124,20 +124,17 @@ void wg_packet_send_handshake_cookie(struct wg_device *wg,
 static void keep_key_fresh(struct wg_peer *peer)
 {
 	struct noise_keypair *keypair;
-	bool send = false;
+	bool send;
 
 	rcu_read_lock_bh();
 	keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
-	if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
-	    (unlikely(atomic64_read(&keypair->sending.counter.counter) >
-		      REKEY_AFTER_MESSAGES) ||
-	     (keypair->i_am_the_initiator &&
-	      unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
-						REKEY_AFTER_TIME)))))
-		send = true;
+	send = keypair && READ_ONCE(keypair->sending.is_valid) &&
+	       (atomic64_read(&keypair->sending_counter) > REKEY_AFTER_MESSAGES ||
+		(keypair->i_am_the_initiator &&
+		 wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME)));
 	rcu_read_unlock_bh();
 
-	if (send)
+	if (unlikely(send))
 		wg_packet_send_queued_handshake_initiation(peer, false);
 }
 
@@ -170,6 +167,11 @@ static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair)
 	struct sk_buff *trailer;
 	int num_frags;
 
+	/* Force hash calculation before encryption so that flow analysis is
+	 * consistent over the inner packet.
+	 */
+	skb_get_hash(skb);
+
 	/* Calculate lengths. */
 	padding_len = calculate_skb_padding(skb);
 	trailer_len = padding_len + noise_encrypted_len(0);
@@ -281,6 +283,8 @@ void wg_packet_tx_worker(struct work_struct *work)
 
 		wg_noise_keypair_put(keypair, false);
 		wg_peer_put(peer);
+		if (need_resched())
+			cond_resched();
 	}
 }
 
@@ -296,7 +300,7 @@ void wg_packet_encrypt_worker(struct work_struct *work)
 		skb_list_walk_safe(first, skb, next) {
 			if (likely(encrypt_packet(skb,
 					PACKET_CB(first)->keypair))) {
-				wg_reset_packet(skb);
+				wg_reset_packet(skb, true);
 			} else {
 				state = PACKET_STATE_DEAD;
 				break;
@@ -304,7 +308,8 @@ void wg_packet_encrypt_worker(struct work_struct *work)
 		}
 		wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
 					  state);
-
+		if (need_resched())
+			cond_resched();
 	}
 }
 
@@ -344,7 +349,6 @@ void wg_packet_purge_staged_packets(struct wg_peer *peer)
 
 void wg_packet_send_staged_packets(struct wg_peer *peer)
 {
-	struct noise_symmetric_key *key;
 	struct noise_keypair *keypair;
 	struct sk_buff_head packets;
 	struct sk_buff *skb;
@@ -364,10 +368,9 @@ void wg_packet_send_staged_packets(struct wg_peer *peer)
 	rcu_read_unlock_bh();
 	if (unlikely(!keypair))
 		goto out_nokey;
-	key = &keypair->sending;
-	if (unlikely(!READ_ONCE(key->is_valid)))
+	if (unlikely(!READ_ONCE(keypair->sending.is_valid)))
 		goto out_nokey;
-	if (unlikely(wg_birthdate_has_expired(key->birthdate,
+	if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
 					      REJECT_AFTER_TIME)))
 		goto out_invalid;
 
@@ -382,7 +385,7 @@ void wg_packet_send_staged_packets(struct wg_peer *peer)
 		 */
 		PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb);
 		PACKET_CB(skb)->nonce =
-				atomic64_inc_return(&key->counter.counter) - 1;
+				atomic64_inc_return(&keypair->sending_counter) - 1;
 		if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES))
 			goto out_invalid;
 	}
@@ -394,7 +397,7 @@ void wg_packet_send_staged_packets(struct wg_peer *peer)
 	return;
 
 out_invalid:
-	WRITE_ONCE(key->is_valid, false);
+	WRITE_ONCE(keypair->sending.is_valid, false);
 out_nokey:
 	wg_noise_keypair_put(keypair, false);
 
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index b0d6541582d3..f9018027fc13 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -76,12 +76,6 @@ static int send4(struct wg_device *wg, struct sk_buff *skb,
 			net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
 					    wg->dev->name, &endpoint->addr, ret);
 			goto err;
-		} else if (unlikely(rt->dst.dev == skb->dev)) {
-			ip_rt_put(rt);
-			ret = -ELOOP;
-			net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
-					    wg->dev->name, &endpoint->addr);
-			goto err;
 		}
 		if (cache)
 			dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
@@ -149,12 +143,6 @@ static int send6(struct wg_device *wg, struct sk_buff *skb,
 			net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
 					    wg->dev->name, &endpoint->addr, ret);
 			goto err;
-		} else if (unlikely(dst->dev == skb->dev)) {
-			dst_release(dst);
-			ret = -ELOOP;
-			net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
-					    wg->dev->name, &endpoint->addr);
-			goto err;
 		}
 		if (cache)
 			dst_cache_set_ip6(cache, dst, &fl.saddr);
diff --git a/drivers/net/wireless/ath/ath11k/thermal.h b/drivers/net/wireless/ath/ath11k/thermal.h
index 459b8d49c184..f9af55f3682d 100644
--- a/drivers/net/wireless/ath/ath11k/thermal.h
+++ b/drivers/net/wireless/ath/ath11k/thermal.h
@@ -36,12 +36,13 @@ static inline int ath11k_thermal_register(struct ath11k_base *sc)
 	return 0;
 }
 
-static inline void ath11k_thermal_unregister(struct ath11k *ar)
+static inline void ath11k_thermal_unregister(struct ath11k_base *sc)
 {
 }
 
 static inline int ath11k_thermal_set_throttling(struct ath11k *ar, u32 throttle_state)
 {
+	return 0;
 }
 
 static inline void ath11k_thermal_event_temperature(struct ath11k *ar,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index 23627c953a5e..436f501be937 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -729,9 +729,18 @@ static int brcmf_net_mon_stop(struct net_device *ndev)
 	return err;
 }
 
+static netdev_tx_t brcmf_net_mon_start_xmit(struct sk_buff *skb,
+					    struct net_device *ndev)
+{
+	dev_kfree_skb_any(skb);
+
+	return NETDEV_TX_OK;
+}
+
 static const struct net_device_ops brcmf_netdev_ops_mon = {
 	.ndo_open = brcmf_net_mon_open,
 	.ndo_stop = brcmf_net_mon_stop,
+	.ndo_start_xmit = brcmf_net_mon_start_xmit,
 };
 
 int brcmf_net_mon_attach(struct brcmf_if *ifp)
diff --git a/drivers/net/wireless/intel/iwlegacy/3945-rs.c b/drivers/net/wireless/intel/iwlegacy/3945-rs.c
index 6209f85a71dd..0af9e997c9f6 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-rs.c
@@ -374,7 +374,7 @@ out:
 }
 
 static void *
-il3945_rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+il3945_rs_alloc(struct ieee80211_hw *hw)
 {
 	return hw->priv;
 }
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
index 7c6e2c863497..0a02d8aca320 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
@@ -2474,7 +2474,7 @@ il4965_rs_fill_link_cmd(struct il_priv *il, struct il_lq_sta *lq_sta,
 }
 
 static void *
-il4965_rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+il4965_rs_alloc(struct ieee80211_hw *hw)
 {
 	return hw->priv;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
index 226165db7dfd..dac809df7f1d 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c
@@ -3019,7 +3019,7 @@ static void rs_fill_link_cmd(struct iwl_priv *priv,
 			cpu_to_le16(priv->lib->bt_params->agg_time_limit);
 }
 
-static void *rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+static void *rs_alloc(struct ieee80211_hw *hw)
 {
 	return hw->priv;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index ba2aff3af0fe..e3a33388be70 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -296,9 +296,14 @@ int iwl_sar_select_profile(struct iwl_fw_runtime *fwrt,
 		if (!prof->enabled) {
 			IWL_DEBUG_RADIO(fwrt, "SAR profile %d is disabled.\n",
 					profs[i]);
-			/* if one of the profiles is disabled, we fail all */
-			return -ENOENT;
+			/*
+			 * if one of the profiles is disabled, we
+			 * ignore all of them and return 1 to
+			 * differentiate disabled from other failures.
+			 */
+			return 1;
 		}
+
 		IWL_DEBUG_INFO(fwrt,
 			       "SAR EWRD: chain %d profile index %d\n",
 			       i, profs[i]);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
index 73196cbc7fbe..75d958bab0e3 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/txq.h
@@ -8,7 +8,7 @@
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2019 Intel Corporation
+ * Copyright(c) 2019 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2019 Intel Corporation
+ * Copyright(c) 2019 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -99,7 +99,7 @@ enum iwl_mvm_dqa_txq {
 	IWL_MVM_DQA_MAX_MGMT_QUEUE = 8,
 	IWL_MVM_DQA_AP_PROBE_RESP_QUEUE = 9,
 	IWL_MVM_DQA_MIN_DATA_QUEUE = 10,
-	IWL_MVM_DQA_MAX_DATA_QUEUE = 31,
+	IWL_MVM_DQA_MAX_DATA_QUEUE = 30,
 };
 
 enum iwl_mvm_tx_fifo {
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index ff52e69c1c80..eeb750bdbda1 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1467,7 +1467,7 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 				kmemdup(pieces->dbg_conf_tlv[i],
 					pieces->dbg_conf_tlv_len[i],
 					GFP_KERNEL);
-			if (!pieces->dbg_conf_tlv[i])
+			if (!drv->fw.dbg.conf_tlv[i])
 				goto out_free_fw;
 		}
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 9e9810d2b262..ccf0bc16465d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -532,8 +532,7 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = {
 					IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
 					IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8,
 				.mac_cap_info[2] =
-					IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP |
-					IEEE80211_HE_MAC_CAP2_ACK_EN,
+					IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP,
 				.mac_cap_info[3] =
 					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
 					IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2,
@@ -617,8 +616,7 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = {
 					IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
 					IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8,
 				.mac_cap_info[2] =
-					IEEE80211_HE_MAC_CAP2_BSR |
-					IEEE80211_HE_MAC_CAP2_ACK_EN,
+					IEEE80211_HE_MAC_CAP2_BSR,
 				.mac_cap_info[3] =
 					IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
 					IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index a4038f289ab3..e67c452fa92c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -727,6 +727,7 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 		struct iwl_dev_tx_power_cmd_v4 v4;
 	} cmd;
 
+	int ret;
 	u16 len = 0;
 
 	cmd.v5.v3.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS);
@@ -741,9 +742,14 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 		len = sizeof(cmd.v4.v3);
 
 
-	if (iwl_sar_select_profile(&mvm->fwrt, cmd.v5.v3.per_chain_restriction,
-				   prof_a, prof_b))
-		return -ENOENT;
+	ret = iwl_sar_select_profile(&mvm->fwrt,
+				     cmd.v5.v3.per_chain_restriction,
+				     prof_a, prof_b);
+
+	/* return on error or if the profile is disabled (positive number) */
+	if (ret)
+		return ret;
+
 	IWL_DEBUG_RADIO(mvm, "Sending REDUCE_TX_POWER_CMD per chain\n");
 	return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0, len, &cmd);
 }
@@ -1034,16 +1040,7 @@ static int iwl_mvm_sar_init(struct iwl_mvm *mvm)
 				"EWRD SAR BIOS table invalid or unavailable. (%d)\n",
 				ret);
 
-	ret = iwl_mvm_sar_select_profile(mvm, 1, 1);
-	/*
-	 * If we don't have profile 0 from BIOS, just skip it.  This
-	 * means that SAR Geo will not be enabled either, even if we
-	 * have other valid profiles.
-	 */
-	if (ret == -ENOENT)
-		return 1;
-
-	return ret;
+	return iwl_mvm_sar_select_profile(mvm, 1, 1);
 }
 
 static int iwl_mvm_load_rt_fw(struct iwl_mvm *mvm)
@@ -1272,7 +1269,7 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	ret = iwl_mvm_sar_init(mvm);
 	if (ret == 0) {
 		ret = iwl_mvm_sar_geo_init(mvm);
-	} else if (ret > 0 && !iwl_sar_get_wgds_table(&mvm->fwrt)) {
+	} else if (ret == -ENOENT && !iwl_sar_get_wgds_table(&mvm->fwrt)) {
 		/*
 		 * If basic SAR is not available, we check for WGDS,
 		 * which should *not* be available either.  If it is
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index c1aba2bf73cf..00e7fdbaeb7f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -3665,7 +3665,7 @@ static void rs_fill_lq_cmd(struct iwl_mvm *mvm,
 			cpu_to_le16(iwl_mvm_coex_agg_time_limit(mvm, sta));
 }
 
-static void *rs_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+static void *rs_alloc(struct ieee80211_hw *hw)
 {
 	return hw->priv;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index 5ee33c8ae9d2..77b8def26edb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -8,7 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -566,6 +566,7 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi,
 
 struct iwl_mvm_stat_data {
 	struct iwl_mvm *mvm;
+	__le32 flags;
 	__le32 mac_id;
 	u8 beacon_filter_average_energy;
 	void *general;
@@ -606,6 +607,13 @@ static void iwl_mvm_stat_iterator(void *_data, u8 *mac,
 			-general->beacon_average_energy[vif_id];
 	}
 
+	/* make sure that beacon statistics don't go backwards with TCM
+	 * request to clear statistics
+	 */
+	if (le32_to_cpu(data->flags) & IWL_STATISTICS_REPLY_FLG_CLEAR)
+		mvmvif->beacon_stats.accu_num_beacons +=
+			mvmvif->beacon_stats.num_beacons;
+
 	if (mvmvif->id != id)
 		return;
 
@@ -763,6 +771,7 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm,
 
 		flags = stats->flag;
 	}
+	data.flags = flags;
 
 	iwl_mvm_rx_stats_check_trigger(mvm, pkt);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 64ef3f3ba23b..56ae72debb96 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -722,6 +722,11 @@ static int iwl_mvm_find_free_queue(struct iwl_mvm *mvm, u8 sta_id,
 
 	lockdep_assert_held(&mvm->mutex);
 
+	if (WARN(maxq >= mvm->trans->trans_cfg->base_params->num_of_queues,
+		 "max queue %d >= num_of_queues (%d)", maxq,
+		 mvm->trans->trans_cfg->base_params->num_of_queues))
+		maxq = mvm->trans->trans_cfg->base_params->num_of_queues - 1;
+
 	/* This should not be hit with new TX path */
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
 		return -ENOSPC;
@@ -1164,9 +1169,9 @@ static int iwl_mvm_inactivity_check(struct iwl_mvm *mvm, u8 alloc_for_sta)
 						   inactive_tid_bitmap,
 						   &unshare_queues,
 						   &changetid_queues);
-		if (ret >= 0 && free_queue < 0) {
+		if (ret && free_queue < 0) {
 			queue_owner = sta;
-			free_queue = ret;
+			free_queue = i;
 		}
 		/* only unlock sta lock - we still need the queue info lock */
 		spin_unlock_bh(&mvmsta->lock);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
index 01f248ba8fec..9d5b1e51b50d 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
@@ -129,6 +129,18 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 	int cmdq_size = max_t(u32, IWL_CMD_QUEUE_SIZE,
 			      trans->cfg->min_txq_size);
 
+	switch (trans_pcie->rx_buf_size) {
+	case IWL_AMSDU_DEF:
+		return -EINVAL;
+	case IWL_AMSDU_2K:
+		break;
+	case IWL_AMSDU_4K:
+	case IWL_AMSDU_8K:
+	case IWL_AMSDU_12K:
+		control_flags |= IWL_PRPH_SCRATCH_RB_SIZE_4K;
+		break;
+	}
+
 	/* Allocate prph scratch */
 	prph_scratch = dma_alloc_coherent(trans->dev, sizeof(*prph_scratch),
 					  &trans_pcie->prph_scratch_dma_addr,
@@ -143,10 +155,8 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 		cpu_to_le16((u16)iwl_read32(trans, CSR_HW_REV));
 	prph_sc_ctrl->version.size = cpu_to_le16(sizeof(*prph_scratch) / 4);
 
-	control_flags = IWL_PRPH_SCRATCH_RB_SIZE_4K |
-			IWL_PRPH_SCRATCH_MTR_MODE |
-			(IWL_PRPH_MTR_FORMAT_256B &
-			 IWL_PRPH_SCRATCH_MTR_FORMAT);
+	control_flags |= IWL_PRPH_SCRATCH_MTR_MODE;
+	control_flags |= IWL_PRPH_MTR_FORMAT_256B & IWL_PRPH_SCRATCH_MTR_FORMAT;
 
 	/* initialize RX default queue */
 	prph_sc_ctrl->rbd_cfg.free_rbd_addr =
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 6744c0281ffb..29971c25dba4 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1092,6 +1092,10 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			iwl_trans->cfg = &iwl_ax101_cfg_quz_hr;
 		else if (iwl_trans->cfg == &iwl_ax201_cfg_qu_hr)
 			iwl_trans->cfg = &iwl_ax201_cfg_quz_hr;
+		else if (iwl_trans->cfg == &killer1650s_2ax_cfg_qu_b0_hr_b0)
+			iwl_trans->cfg = &iwl_ax1650s_cfg_quz_hr;
+		else if (iwl_trans->cfg == &killer1650i_2ax_cfg_qu_b0_hr_b0)
+			iwl_trans->cfg = &iwl_ax1650i_cfg_quz_hr;
 	}
 
 #endif
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 86fc00167817..9664dbc70ef1 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -1418,6 +1418,9 @@ void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue)
 
 	iwl_pcie_gen2_txq_unmap(trans, queue);
 
+	iwl_pcie_gen2_txq_free_memory(trans, trans_pcie->txq[queue]);
+	trans_pcie->txq[queue] = NULL;
+
 	IWL_DEBUG_TX_QUEUES(trans, "Deactivate queue %d\n", queue);
 }
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 7fe8207db6ae..0528d4cb4d37 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3669,9 +3669,9 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	}
 
 	if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
-		hwname = kasprintf(GFP_KERNEL, "%.*s",
-				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
-				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
+		hwname = kstrndup((char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				  nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				  GFP_KERNEL);
 		if (!hwname)
 			return -ENOMEM;
 		param.hwname = hwname;
@@ -3691,9 +3691,9 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	if (info->attrs[HWSIM_ATTR_RADIO_ID]) {
 		idx = nla_get_u32(info->attrs[HWSIM_ATTR_RADIO_ID]);
 	} else if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
-		hwname = kasprintf(GFP_KERNEL, "%.*s",
-				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
-				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
+		hwname = kstrndup((char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				  nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				  GFP_KERNEL);
 		if (!hwname)
 			return -ENOMEM;
 	} else
@@ -4068,7 +4068,7 @@ static void hwsim_virtio_rx_work(struct work_struct *work)
 	}
 	vq = hwsim_vqs[HWSIM_VQ_RX];
 	sg_init_one(sg, skb->head, skb_end_offset(skb));
-	err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_KERNEL);
+	err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_ATOMIC);
 	if (WARN(err, "virtqueue_add_inbuf returned %d\n", err))
 		nlmsg_free(skb);
 	else
diff --git a/drivers/net/wireless/realtek/rtlwifi/rc.c b/drivers/net/wireless/realtek/rtlwifi/rc.c
index 0c7d74902d33..4b5ea0ec9109 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rc.c
@@ -261,7 +261,7 @@ static void rtl_rate_update(void *ppriv,
 {
 }
 
-static void *rtl_rate_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+static void *rtl_rate_alloc(struct ieee80211_hw *hw)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	return rtlpriv;
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index e37c71495c0d..1af87eb2e53a 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -1338,22 +1338,17 @@ static void rtw_pci_phy_cfg(struct rtw_dev *rtwdev)
 	rtw_pci_link_cfg(rtwdev);
 }
 
-#ifdef CONFIG_PM
-static int rtw_pci_suspend(struct device *dev)
+static int __maybe_unused rtw_pci_suspend(struct device *dev)
 {
 	return 0;
 }
 
-static int rtw_pci_resume(struct device *dev)
+static int __maybe_unused rtw_pci_resume(struct device *dev)
 {
 	return 0;
 }
 
 static SIMPLE_DEV_PM_OPS(rtw_pm_ops, rtw_pci_suspend, rtw_pci_resume);
-#define RTW_PM_OPS (&rtw_pm_ops)
-#else
-#define RTW_PM_OPS NULL
-#endif
 
 static int rtw_pci_claim(struct rtw_dev *rtwdev, struct pci_dev *pdev)
 {
@@ -1582,7 +1577,7 @@ static struct pci_driver rtw_pci_driver = {
 	.id_table = rtw_pci_id_table,
 	.probe = rtw_pci_probe,
 	.remove = rtw_pci_remove,
-	.driver.pm = RTW_PM_OPS,
+	.driver.pm = &rtw_pm_ops,
 };
 module_pci_driver(rtw_pci_driver);
 
diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c
index de613c623a2c..69857f080704 100644
--- a/drivers/nfc/s3fwrn5/firmware.c
+++ b/drivers/nfc/s3fwrn5/firmware.c
@@ -434,15 +434,7 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info)
 		goto out;
 	}
 
-	{
-		SHASH_DESC_ON_STACK(desc, tfm);
-
-		desc->tfm = tfm;
-
-		ret = crypto_shash_digest(desc, fw->image, image_size,
-					  hash_data);
-		shash_desc_zero(desc);
-	}
+	ret = crypto_shash_tfm_digest(tfm, fw->image, image_size, hash_data);
 
 	crypto_free_shash(tfm);
 	if (ret) {
diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c
index a1d69f9b2d4a..0b9ca6d20ffa 100644
--- a/drivers/nfc/st21nfca/dep.c
+++ b/drivers/nfc/st21nfca/dep.c
@@ -173,8 +173,10 @@ static int st21nfca_tm_send_atr_res(struct nfc_hci_dev *hdev,
 		memcpy(atr_res->gbi, atr_req->gbi, gb_len);
 		r = nfc_set_remote_general_bytes(hdev->ndev, atr_res->gbi,
 						  gb_len);
-		if (r < 0)
+		if (r < 0) {
+			kfree_skb(skb);
 			return r;
+		}
 	}
 
 	info->dep_info.curr_nfc_dep_pni = 0;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 91c1bd659947..f3c037f5a9ba 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1110,7 +1110,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		  * Don't treat an error as fatal, as we potentially already
 		  * have a NGUID or EUI-64.
 		  */
-		if (status > 0)
+		if (status > 0 && !(status & NVME_SC_DNR))
 			status = 0;
 		goto free_data;
 	}
@@ -3642,6 +3642,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	return;
  out_put_disk:
+	/* prevent double queue cleanup */
+	ns->disk->queue = NULL;
 	put_disk(ns->disk);
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4e79e412b276..cc46e250fcac 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -973,9 +973,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 
 static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
 {
-	if (++nvmeq->cq_head == nvmeq->q_depth) {
+	u16 tmp = nvmeq->cq_head + 1;
+
+	if (tmp == nvmeq->q_depth) {
 		nvmeq->cq_head = 0;
 		nvmeq->cq_phase ^= 1;
+	} else {
+		nvmeq->cq_head = tmp;
 	}
 }
 
@@ -985,6 +989,11 @@ static inline int nvme_process_cq(struct nvme_queue *nvmeq)
 
 	while (nvme_cqe_pending(nvmeq)) {
 		found++;
+		/*
+		 * load-load control dependency between phase and the rest of
+		 * the cqe requires a full read memory barrier
+		 */
+		dma_rmb();
 		nvme_handle_cqe(nvmeq, nvmeq->cq_head);
 		nvme_update_cq_head(nvmeq);
 	}
@@ -1373,16 +1382,19 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown)
 
 /*
  * Called only on a device that has been disabled and after all other threads
- * that can check this device's completion queues have synced. This is the
- * last chance for the driver to see a natural completion before
- * nvme_cancel_request() terminates all incomplete requests.
+ * that can check this device's completion queues have synced, except
+ * nvme_poll(). This is the last chance for the driver to see a natural
+ * completion before nvme_cancel_request() terminates all incomplete requests.
  */
 static void nvme_reap_pending_cqes(struct nvme_dev *dev)
 {
 	int i;
 
-	for (i = dev->ctrl.queue_count - 1; i > 0; i--)
+	for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
+		spin_lock(&dev->queues[i].cq_poll_lock);
 		nvme_process_cq(&dev->queues[i]);
+		spin_unlock(&dev->queues[i].cq_poll_lock);
+	}
 }
 
 static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index c9219fddf44b..50bbe0edf538 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -261,6 +261,8 @@ static struct property *dup_and_fixup_symbol_prop(
 
 	of_property_set_flag(new_prop, OF_DYNAMIC);
 
+	kfree(target_path);
+
 	return new_prop;
 
 err_free_new_prop:
diff --git a/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts b/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts
index c190da54f175..6327d1ffb963 100644
--- a/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts
+++ b/drivers/of/unittest-data/overlay_bad_add_dup_prop.dts
@@ -3,22 +3,37 @@
 /plugin/;
 
 /*
- * &electric_1/motor-1 and &spin_ctrl_1 are the same node:
- *   /testcase-data-2/substation@100/motor-1
+ * &electric_1/motor-1/electric and &spin_ctrl_1/electric are the same node:
+ *   /testcase-data-2/substation@100/motor-1/electric
  *
  * Thus the property "rpm_avail" in each fragment will
  * result in an attempt to update the same property twice.
  * This will result in an error and the overlay apply
  * will fail.
+ *
+ * The previous version of this test did not include the extra
+ * level of node 'electric'.  That resulted in the 'rpm_avail'
+ * property being located in the pre-existing node 'motor-1'.
+ * Modifying a property results in a WARNING that a memory leak
+ * will occur if the overlay is removed.  Since the overlay apply
+ * fails, the memory leak does actually occur, and kmemleak will
+ * further report the memory leak if CONFIG_DEBUG_KMEMLEAK is
+ * enabled.  Adding the overlay node 'electric' avoids the
+ * memory leak and thus people who use kmemleak will not
+ * have to debug this non-problem again.
  */
 
 &electric_1 {
 
 	motor-1 {
-		rpm_avail = < 100 >;
+		electric {
+			rpm_avail = < 100 >;
+		};
 	};
 };
 
 &spin_ctrl_1 {
-		rpm_avail = < 100 200 >;
+		electric {
+			rpm_avail = < 100 200 >;
+		};
 };
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 7e27670c3616..398de04fd19c 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -861,6 +861,10 @@ static void __init of_unittest_changeset(void)
 	unittest(!of_changeset_revert(&chgset), "revert failed\n");
 
 	of_changeset_destroy(&chgset);
+
+	of_node_put(n1);
+	of_node_put(n2);
+	of_node_put(n21);
 #endif
 }
 
@@ -1243,10 +1247,13 @@ static void __init of_unittest_platform_populate(void)
 
 	of_platform_populate(np, match, NULL, &test_bus->dev);
 	for_each_child_of_node(np, child) {
-		for_each_child_of_node(child, grandchild)
-			unittest(of_find_device_by_node(grandchild),
+		for_each_child_of_node(child, grandchild) {
+			pdev = of_find_device_by_node(grandchild);
+			unittest(pdev,
 				 "Could not create device for node '%pOFn'\n",
 				 grandchild);
+			of_dev_put(pdev);
+		}
 	}
 
 	of_platform_depopulate(&test_bus->dev);
@@ -3087,8 +3094,11 @@ static __init void of_unittest_overlay_high_level(void)
 				goto err_unlock;
 			}
 			if (__of_add_property(of_symbols, new_prop)) {
+				kfree(new_prop->name);
+				kfree(new_prop->value);
+				kfree(new_prop);
 				/* "name" auto-generated by unflatten */
-				if (!strcmp(new_prop->name, "name"))
+				if (!strcmp(prop->name, "name"))
 					continue;
 				unittest(0, "duplicate property '%s' in overlay_base node __symbols__",
 					 prop->name);
@@ -3171,21 +3181,21 @@ static __init void of_unittest_overlay_high_level(void)
 		   "OF: overlay: ERROR: multiple fragments add and/or delete node /testcase-data-2/substation@100/motor-1/controller");
 
 	EXPECT_BEGIN(KERN_ERR,
-		     "OF: overlay: WARNING: memory leak will occur if overlay removed, property: /testcase-data-2/substation@100/motor-1/rpm_avail");
+		     "OF: overlay: ERROR: multiple fragments add and/or delete node /testcase-data-2/substation@100/motor-1/electric");
 	EXPECT_BEGIN(KERN_ERR,
-		     "OF: overlay: WARNING: memory leak will occur if overlay removed, property: /testcase-data-2/substation@100/motor-1/rpm_avail");
+		     "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/electric/rpm_avail");
 	EXPECT_BEGIN(KERN_ERR,
-		     "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/rpm_avail");
+		     "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/electric/name");
 
 	unittest(overlay_data_apply("overlay_bad_add_dup_prop", NULL),
 		 "Adding overlay 'overlay_bad_add_dup_prop' failed\n");
 
 	EXPECT_END(KERN_ERR,
-		   "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/rpm_avail");
+		     "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/electric/name");
 	EXPECT_END(KERN_ERR,
-		   "OF: overlay: WARNING: memory leak will occur if overlay removed, property: /testcase-data-2/substation@100/motor-1/rpm_avail");
+		     "OF: overlay: ERROR: multiple fragments add, update, and/or delete property /testcase-data-2/substation@100/motor-1/electric/rpm_avail");
 	EXPECT_END(KERN_ERR,
-		   "OF: overlay: WARNING: memory leak will occur if overlay removed, property: /testcase-data-2/substation@100/motor-1/rpm_avail");
+		     "OF: overlay: ERROR: multiple fragments add and/or delete node /testcase-data-2/substation@100/motor-1/electric");
 
 	unittest(overlay_data_apply("overlay_bad_phandle", NULL),
 		 "Adding overlay 'overlay_bad_phandle' failed\n");
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index ba43e6a3dc0a..e4f01e7771a2 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -819,6 +819,8 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	if (unlikely(!target_freq)) {
 		if (opp_table->required_opp_tables) {
 			ret = _set_required_opps(dev, opp_table, NULL);
+		} else if (!_get_opp_count(opp_table)) {
+			return 0;
 		} else {
 			dev_err(dev, "target frequency can't be 0\n");
 			ret = -EINVAL;
@@ -849,6 +851,18 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		goto put_opp_table;
 	}
 
+	/*
+	 * For IO devices which require an OPP on some platforms/SoCs
+	 * while just needing to scale the clock on some others
+	 * we look for empty OPP tables with just a clock handle and
+	 * scale only the clk. This makes dev_pm_opp_set_rate()
+	 * equivalent to a clk_set_rate()
+	 */
+	if (!_get_opp_count(opp_table)) {
+		ret = _generic_set_opp_clk_only(dev, clk, freq);
+		goto put_opp_table;
+	}
+
 	temp_freq = old_freq;
 	old_opp = _find_freq_ceil(opp_table, &temp_freq);
 	if (IS_ERR(old_opp)) {
diff --git a/drivers/oprofile/event_buffer.c b/drivers/oprofile/event_buffer.c
index 12ea4a4ad607..6c9edc8bbc95 100644
--- a/drivers/oprofile/event_buffer.c
+++ b/drivers/oprofile/event_buffer.c
@@ -113,7 +113,7 @@ static int event_buffer_open(struct inode *inode, struct file *file)
 {
 	int err = -EPERM;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EPERM;
 
 	if (test_and_set_bit_lock(0, &buffer_opened))
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 28c9a2409c50..ca9ed5774eb1 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -5567,3 +5567,10 @@ static void pci_fixup_no_d0_pme(struct pci_dev *dev)
 	dev->pme_support &= ~(PCI_PM_CAP_PME_D0 >> PCI_PM_CAP_PME_SHIFT);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x2142, pci_fixup_no_d0_pme);
+
+static void apex_pci_fixup_class(struct pci_dev *pdev)
+{
+	pdev->class = (PCI_CLASS_SYSTEM_OTHER << 8) | pdev->class;
+}
+DECLARE_PCI_FIXUP_CLASS_HEADER(0x1ac1, 0x089a,
+			       PCI_CLASS_NOT_DEFINED, 8, apex_pci_fixup_class);
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index 09ae8a970880..a9261cf48293 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -79,13 +79,6 @@ config FSL_IMX8_DDR_PMU
 	  can give information about memory throughput and other related
 	  events.
 
-config HISI_PMU
-       bool "HiSilicon SoC PMU"
-       depends on ARM64 && ACPI
-       help
-         Support for HiSilicon SoC uncore performance monitoring
-         unit (PMU), such as: L3C, HHA and DDRC.
-
 config QCOM_L2_PMU
 	bool "Qualcomm Technologies L2-cache PMU"
 	depends on ARCH_QCOM && ARM64 && ACPI
@@ -129,4 +122,6 @@ config ARM_SPE_PMU
 	  Extension, which provides periodic sampling of operations in
 	  the CPU pipeline and reports this via the perf AUX interface.
 
+source "drivers/perf/hisilicon/Kconfig"
+
 endmenu
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index 70968c8c09d7..518d0603e24f 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -690,10 +690,8 @@ static int dsu_pmu_device_probe(struct platform_device *pdev)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_warn(&pdev->dev, "Failed to find IRQ\n");
+	if (irq < 0)
 		return -EINVAL;
-	}
 
 	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_%d",
 				PMUNAME, atomic_inc_return(&pmu_idx));
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index f01a57e5a5f3..48e28ef93a70 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -814,7 +814,7 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 	if (err) {
 		dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
 			err, &res_0->start);
-		return err;
+		goto out_clear_affinity;
 	}
 
 	err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
@@ -833,6 +833,8 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 
 out_unregister:
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+out_clear_affinity:
+	irq_set_affinity_hint(smmu_pmu->irq, NULL);
 	return err;
 }
 
@@ -842,6 +844,7 @@ static int smmu_pmu_remove(struct platform_device *pdev)
 
 	perf_pmu_unregister(&smmu_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+	irq_set_affinity_hint(smmu_pmu->irq, NULL);
 
 	return 0;
 }
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index b72c04852599..d80f48798bce 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -274,7 +274,7 @@ static u64 arm_spe_event_to_pmscr(struct perf_event *event)
 	if (!attr->exclude_kernel)
 		reg |= BIT(SYS_PMSCR_EL1_E1SPE_SHIFT);
 
-	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && capable(CAP_SYS_ADMIN))
+	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && perfmon_capable())
 		reg |= BIT(SYS_PMSCR_EL1_CX_SHIFT);
 
 	return reg;
@@ -700,7 +700,7 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
 		return -EOPNOTSUPP;
 
 	reg = arm_spe_event_to_pmscr(event);
-	if (!capable(CAP_SYS_ADMIN) &&
+	if (!perfmon_capable() &&
 	    (reg & (BIT(SYS_PMSCR_EL1_PA_SHIFT) |
 		    BIT(SYS_PMSCR_EL1_CX_SHIFT) |
 		    BIT(SYS_PMSCR_EL1_PCT_SHIFT))))
@@ -1133,10 +1133,8 @@ static int arm_spe_pmu_irq_probe(struct arm_spe_pmu *spe_pmu)
 	struct platform_device *pdev = spe_pmu->pdev;
 	int irq = platform_get_irq(pdev, 0);
 
-	if (irq < 0) {
-		dev_err(&pdev->dev, "failed to get IRQ (%d)\n", irq);
+	if (irq < 0)
 		return -ENXIO;
-	}
 
 	if (!irq_is_percpu(irq)) {
 		dev_err(&pdev->dev, "expected PPI but got SPI (%d)\n", irq);
diff --git a/drivers/perf/hisilicon/Kconfig b/drivers/perf/hisilicon/Kconfig
new file mode 100644
index 000000000000..c5d1b7019fff
--- /dev/null
+++ b/drivers/perf/hisilicon/Kconfig
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config HISI_PMU
+	tristate "HiSilicon SoC PMU drivers"
+	depends on ARM64 && ACPI
+	  help
+	  Support for HiSilicon SoC L3 Cache performance monitor, Hydra Home
+	  Agent performance monitor and DDR Controller performance monitor.
diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile
index c3a96ec2bf66..e8377061845f 100644
--- a/drivers/perf/hisilicon/Makefile
+++ b/drivers/perf/hisilicon/Makefile
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o
+obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \
+			  hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o
diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index 453f1c6a16ca..15713faaa07e 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -394,8 +394,9 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 	ret = perf_pmu_register(&ddrc_pmu->pmu, name, -1);
 	if (ret) {
 		dev_err(ddrc_pmu->dev, "DDRC PMU register failed!\n");
-		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
-					    &ddrc_pmu->node);
+		cpuhp_state_remove_instance_nocalls(
+			CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, &ddrc_pmu->node);
+		irq_set_affinity_hint(ddrc_pmu->irq, NULL);
 	}
 
 	return ret;
@@ -406,8 +407,9 @@ static int hisi_ddrc_pmu_remove(struct platform_device *pdev)
 	struct hisi_pmu *ddrc_pmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&ddrc_pmu->pmu);
-	cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
-				    &ddrc_pmu->node);
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
+					    &ddrc_pmu->node);
+	irq_set_affinity_hint(ddrc_pmu->irq, NULL);
 
 	return 0;
 }
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index 6a1dd72d8abb..dcc5600788a9 100644
--- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
@@ -283,7 +283,7 @@ static struct attribute *hisi_hha_pmu_events_attr[] = {
 	HISI_PMU_EVENT_ATTR(rx_wbip,		0x05),
 	HISI_PMU_EVENT_ATTR(rx_wtistash,	0x11),
 	HISI_PMU_EVENT_ATTR(rd_ddr_64b,		0x1c),
-	HISI_PMU_EVENT_ATTR(wr_dr_64b,		0x1d),
+	HISI_PMU_EVENT_ATTR(wr_ddr_64b,		0x1d),
 	HISI_PMU_EVENT_ATTR(rd_ddr_128b,	0x1e),
 	HISI_PMU_EVENT_ATTR(wr_ddr_128b,	0x1f),
 	HISI_PMU_EVENT_ATTR(spill_num,		0x20),
@@ -406,8 +406,9 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev)
 	ret = perf_pmu_register(&hha_pmu->pmu, name, -1);
 	if (ret) {
 		dev_err(hha_pmu->dev, "HHA PMU register failed!\n");
-		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
-					    &hha_pmu->node);
+		cpuhp_state_remove_instance_nocalls(
+			CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, &hha_pmu->node);
+		irq_set_affinity_hint(hha_pmu->irq, NULL);
 	}
 
 	return ret;
@@ -418,8 +419,9 @@ static int hisi_hha_pmu_remove(struct platform_device *pdev)
 	struct hisi_pmu *hha_pmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&hha_pmu->pmu);
-	cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
-				    &hha_pmu->node);
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
+					    &hha_pmu->node);
+	irq_set_affinity_hint(hha_pmu->irq, NULL);
 
 	return 0;
 }
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index 1151e99b241c..8dd1278bec04 100644
--- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
@@ -396,8 +396,9 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev)
 	ret = perf_pmu_register(&l3c_pmu->pmu, name, -1);
 	if (ret) {
 		dev_err(l3c_pmu->dev, "L3C PMU register failed!\n");
-		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
-					    &l3c_pmu->node);
+		cpuhp_state_remove_instance_nocalls(
+			CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, &l3c_pmu->node);
+		irq_set_affinity_hint(l3c_pmu->irq, NULL);
 	}
 
 	return ret;
@@ -408,8 +409,9 @@ static int hisi_l3c_pmu_remove(struct platform_device *pdev)
 	struct hisi_pmu *l3c_pmu = platform_get_drvdata(pdev);
 
 	perf_pmu_unregister(&l3c_pmu->pmu);
-	cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
-				    &l3c_pmu->node);
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
+					    &l3c_pmu->node);
+	irq_set_affinity_hint(l3c_pmu->irq, NULL);
 
 	return 0;
 }
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 584de8f807cc..97aff877a4e7 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -35,6 +35,7 @@ ssize_t hisi_format_sysfs_show(struct device *dev,
 
 	return sprintf(buf, "%s\n", (char *)eattr->var);
 }
+EXPORT_SYMBOL_GPL(hisi_format_sysfs_show);
 
 /*
  * PMU event attributes
@@ -48,6 +49,7 @@ ssize_t hisi_event_sysfs_show(struct device *dev,
 
 	return sprintf(page, "config=0x%lx\n", (unsigned long)eattr->var);
 }
+EXPORT_SYMBOL_GPL(hisi_event_sysfs_show);
 
 /*
  * sysfs cpumask attributes. For uncore PMU, we only have a single CPU to show
@@ -59,6 +61,7 @@ ssize_t hisi_cpumask_sysfs_show(struct device *dev,
 
 	return sprintf(buf, "%d\n", hisi_pmu->on_cpu);
 }
+EXPORT_SYMBOL_GPL(hisi_cpumask_sysfs_show);
 
 static bool hisi_validate_event_group(struct perf_event *event)
 {
@@ -97,6 +100,7 @@ int hisi_uncore_pmu_counter_valid(struct hisi_pmu *hisi_pmu, int idx)
 {
 	return idx >= 0 && idx < hisi_pmu->num_counters;
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_counter_valid);
 
 int hisi_uncore_pmu_get_event_idx(struct perf_event *event)
 {
@@ -113,6 +117,7 @@ int hisi_uncore_pmu_get_event_idx(struct perf_event *event)
 
 	return idx;
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_get_event_idx);
 
 static void hisi_uncore_pmu_clear_event_idx(struct hisi_pmu *hisi_pmu, int idx)
 {
@@ -173,6 +178,7 @@ int hisi_uncore_pmu_event_init(struct perf_event *event)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_event_init);
 
 /*
  * Set the counter to count the event that we're interested in,
@@ -220,6 +226,7 @@ void hisi_uncore_pmu_set_event_period(struct perf_event *event)
 	/* Write start value to the hardware event counter */
 	hisi_pmu->ops->write_counter(hisi_pmu, hwc, val);
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_set_event_period);
 
 void hisi_uncore_pmu_event_update(struct perf_event *event)
 {
@@ -240,6 +247,7 @@ void hisi_uncore_pmu_event_update(struct perf_event *event)
 		HISI_MAX_PERIOD(hisi_pmu->counter_bits);
 	local64_add(delta, &event->count);
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_event_update);
 
 void hisi_uncore_pmu_start(struct perf_event *event, int flags)
 {
@@ -262,6 +270,7 @@ void hisi_uncore_pmu_start(struct perf_event *event, int flags)
 	hisi_uncore_pmu_enable_event(event);
 	perf_event_update_userpage(event);
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_start);
 
 void hisi_uncore_pmu_stop(struct perf_event *event, int flags)
 {
@@ -278,6 +287,7 @@ void hisi_uncore_pmu_stop(struct perf_event *event, int flags)
 	hisi_uncore_pmu_event_update(event);
 	hwc->state |= PERF_HES_UPTODATE;
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_stop);
 
 int hisi_uncore_pmu_add(struct perf_event *event, int flags)
 {
@@ -300,6 +310,7 @@ int hisi_uncore_pmu_add(struct perf_event *event, int flags)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_add);
 
 void hisi_uncore_pmu_del(struct perf_event *event, int flags)
 {
@@ -311,12 +322,14 @@ void hisi_uncore_pmu_del(struct perf_event *event, int flags)
 	perf_event_update_userpage(event);
 	hisi_pmu->pmu_events.hw_events[hwc->idx] = NULL;
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_del);
 
 void hisi_uncore_pmu_read(struct perf_event *event)
 {
 	/* Read hardware counter and update the perf counter statistics */
 	hisi_uncore_pmu_event_update(event);
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_read);
 
 void hisi_uncore_pmu_enable(struct pmu *pmu)
 {
@@ -329,6 +342,7 @@ void hisi_uncore_pmu_enable(struct pmu *pmu)
 
 	hisi_pmu->ops->start_counters(hisi_pmu);
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_enable);
 
 void hisi_uncore_pmu_disable(struct pmu *pmu)
 {
@@ -336,6 +350,7 @@ void hisi_uncore_pmu_disable(struct pmu *pmu)
 
 	hisi_pmu->ops->stop_counters(hisi_pmu);
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_disable);
 
 
 /*
@@ -414,10 +429,11 @@ int hisi_uncore_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
 	hisi_pmu->on_cpu = cpu;
 
 	/* Overflow interrupt also should use the same CPU */
-	WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(cpu)));
+	WARN_ON(irq_set_affinity_hint(hisi_pmu->irq, cpumask_of(cpu)));
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_online_cpu);
 
 int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
@@ -446,7 +462,10 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	perf_pmu_migrate_context(&hisi_pmu->pmu, cpu, target);
 	/* Use this CPU for event counting */
 	hisi_pmu->on_cpu = target;
-	WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(target)));
+	WARN_ON(irq_set_affinity_hint(hisi_pmu->irq, cpumask_of(target)));
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_offline_cpu);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c
index 3708d43b7508..393011a05b48 100644
--- a/drivers/phy/qualcomm/phy-qcom-qusb2.c
+++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c
@@ -816,6 +816,13 @@ static const struct of_device_id qusb2_phy_of_match_table[] = {
 		.compatible	= "qcom,msm8998-qusb2-phy",
 		.data		= &msm8998_phy_cfg,
 	}, {
+		/*
+		 * Deprecated. Only here to support legacy device
+		 * trees that didn't include "qcom,qusb2-v2-phy"
+		 */
+		.compatible	= "qcom,sdm845-qusb2-phy",
+		.data		= &qusb2_v2_phy_cfg,
+	}, {
 		.compatible	= "qcom,qusb2-v2-phy",
 		.data		= &qusb2_v2_phy_cfg,
 	},
diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c
index d998e65c89c8..a52a9bf13b75 100644
--- a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c
+++ b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c
@@ -160,18 +160,11 @@ static int qcom_snps_hsphy_power_on(struct phy *phy)
 	ret = regulator_bulk_enable(VREG_NUM, priv->vregs);
 	if (ret)
 		return ret;
-	ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks);
-	if (ret)
-		goto err_disable_regulator;
+
 	qcom_snps_hsphy_disable_hv_interrupts(priv);
 	qcom_snps_hsphy_exit_retention(priv);
 
 	return 0;
-
-err_disable_regulator:
-	regulator_bulk_disable(VREG_NUM, priv->vregs);
-
-	return ret;
 }
 
 static int qcom_snps_hsphy_power_off(struct phy *phy)
@@ -180,7 +173,6 @@ static int qcom_snps_hsphy_power_off(struct phy *phy)
 
 	qcom_snps_hsphy_enter_retention(priv);
 	qcom_snps_hsphy_enable_hv_interrupts(priv);
-	clk_bulk_disable_unprepare(priv->num_clks, priv->clks);
 	regulator_bulk_disable(VREG_NUM, priv->vregs);
 
 	return 0;
@@ -266,21 +258,39 @@ static int qcom_snps_hsphy_init(struct phy *phy)
 	struct hsphy_priv *priv = phy_get_drvdata(phy);
 	int ret;
 
-	ret = qcom_snps_hsphy_reset(priv);
+	ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks);
 	if (ret)
 		return ret;
 
+	ret = qcom_snps_hsphy_reset(priv);
+	if (ret)
+		goto disable_clocks;
+
 	qcom_snps_hsphy_init_sequence(priv);
 
 	ret = qcom_snps_hsphy_por_reset(priv);
 	if (ret)
-		return ret;
+		goto disable_clocks;
+
+	return 0;
+
+disable_clocks:
+	clk_bulk_disable_unprepare(priv->num_clks, priv->clks);
+	return ret;
+}
+
+static int qcom_snps_hsphy_exit(struct phy *phy)
+{
+	struct hsphy_priv *priv = phy_get_drvdata(phy);
+
+	clk_bulk_disable_unprepare(priv->num_clks, priv->clks);
 
 	return 0;
 }
 
 static const struct phy_ops qcom_snps_hsphy_ops = {
 	.init = qcom_snps_hsphy_init,
+	.exit = qcom_snps_hsphy_exit,
 	.power_on = qcom_snps_hsphy_power_on,
 	.power_off = qcom_snps_hsphy_power_off,
 	.set_mode = qcom_snps_hsphy_set_mode,
diff --git a/drivers/phy/tegra/Kconfig b/drivers/phy/tegra/Kconfig
index a208aca4ba7b..c591c958f1eb 100644
--- a/drivers/phy/tegra/Kconfig
+++ b/drivers/phy/tegra/Kconfig
@@ -1,7 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config PHY_TEGRA_XUSB
 	tristate "NVIDIA Tegra XUSB pad controller driver"
-	depends on ARCH_TEGRA
+	depends on ARCH_TEGRA && USB_SUPPORT
+	select USB_COMMON
 	select USB_CONN_GPIO
 	select USB_PHY
 	help
diff --git a/drivers/pinctrl/actions/pinctrl-s700.c b/drivers/pinctrl/actions/pinctrl-s700.c
index 47a4ccd9fed4..f579a6593f37 100644
--- a/drivers/pinctrl/actions/pinctrl-s700.c
+++ b/drivers/pinctrl/actions/pinctrl-s700.c
@@ -1435,7 +1435,7 @@ static const char * const sd2_groups[] = {
 static const char * const i2c0_groups[] = {
 	"uart0_rx_mfp",
 	"uart0_tx_mfp",
-	"i2c0_mfp_mfp",
+	"i2c0_mfp",
 };
 
 static const char * const i2c1_groups[] = {
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index b409642f168d..9b821c9cbd16 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -1286,6 +1286,7 @@ static const struct gpio_chip byt_gpio_chip = {
 	.direction_output	= byt_gpio_direction_output,
 	.get			= byt_gpio_get,
 	.set			= byt_gpio_set,
+	.set_config		= gpiochip_generic_config,
 	.dbg_show		= byt_gpio_dbg_show,
 };
 
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 4c74fdde576d..1093a6105d40 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1479,11 +1479,15 @@ static void chv_gpio_irq_handler(struct irq_desc *desc)
 	struct chv_pinctrl *pctrl = gpiochip_get_data(gc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned long pending;
+	unsigned long flags;
 	u32 intr_line;
 
 	chained_irq_enter(chip, desc);
 
+	raw_spin_lock_irqsave(&chv_lock, flags);
 	pending = readl(pctrl->regs + CHV_INTSTAT);
+	raw_spin_unlock_irqrestore(&chv_lock, flags);
+
 	for_each_set_bit(intr_line, &pending, pctrl->community->nirqs) {
 		unsigned int irq, offset;
 
diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index 330c8f077b73..4d7a86a5a37b 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -15,17 +15,18 @@
 
 #include "pinctrl-intel.h"
 
-#define SPT_PAD_OWN	0x020
-#define SPT_PADCFGLOCK	0x0a0
-#define SPT_HOSTSW_OWN	0x0d0
-#define SPT_GPI_IS	0x100
-#define SPT_GPI_IE	0x120
+#define SPT_PAD_OWN		0x020
+#define SPT_H_PADCFGLOCK	0x090
+#define SPT_LP_PADCFGLOCK	0x0a0
+#define SPT_HOSTSW_OWN		0x0d0
+#define SPT_GPI_IS		0x100
+#define SPT_GPI_IE		0x120
 
 #define SPT_COMMUNITY(b, s, e)				\
 	{						\
 		.barno = (b),				\
 		.padown_offset = SPT_PAD_OWN,		\
-		.padcfglock_offset = SPT_PADCFGLOCK,	\
+		.padcfglock_offset = SPT_LP_PADCFGLOCK,	\
 		.hostown_offset = SPT_HOSTSW_OWN,	\
 		.is_offset = SPT_GPI_IS,		\
 		.ie_offset = SPT_GPI_IE,		\
@@ -47,7 +48,7 @@
 	{						\
 		.barno = (b),				\
 		.padown_offset = SPT_PAD_OWN,		\
-		.padcfglock_offset = SPT_PADCFGLOCK,	\
+		.padcfglock_offset = SPT_H_PADCFGLOCK,	\
 		.hostown_offset = SPT_HOSTSW_OWN,	\
 		.is_offset = SPT_GPI_IS,		\
 		.ie_offset = SPT_GPI_IE,		\
diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c
index 3853ec3a2a8e..ee305f140400 100644
--- a/drivers/pinctrl/mediatek/pinctrl-paris.c
+++ b/drivers/pinctrl/mediatek/pinctrl-paris.c
@@ -164,8 +164,6 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev,
 	case MTK_PIN_CONFIG_PU_ADV:
 	case MTK_PIN_CONFIG_PD_ADV:
 		if (hw->soc->adv_pull_get) {
-			bool pullup;
-
 			pullup = param == MTK_PIN_CONFIG_PU_ADV;
 			err = hw->soc->adv_pull_get(hw, desc, pullup, &ret);
 		} else
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 9a398a211d30..85858c1d56d0 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -697,7 +697,7 @@ static void msm_gpio_update_dual_edge_pos(struct msm_pinctrl *pctrl,
 
 		pol = msm_readl_intr_cfg(pctrl, g);
 		pol ^= BIT(g->intr_polarity_bit);
-		msm_writel_intr_cfg(val, pctrl, g);
+		msm_writel_intr_cfg(pol, pctrl, g);
 
 		val2 = msm_readl_io(pctrl, g) & BIT(g->in_bit);
 		intstat = msm_readl_intr_status(pctrl, g);
@@ -1034,6 +1034,29 @@ static void msm_gpio_irq_relres(struct irq_data *d)
 	module_put(gc->owner);
 }
 
+static int msm_gpio_irq_set_affinity(struct irq_data *d,
+				const struct cpumask *dest, bool force)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+
+	if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs))
+		return irq_chip_set_affinity_parent(d, dest, force);
+
+	return 0;
+}
+
+static int msm_gpio_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+
+	if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs))
+		return irq_chip_set_vcpu_affinity_parent(d, vcpu_info);
+
+	return 0;
+}
+
 static void msm_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
@@ -1132,6 +1155,8 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
 	pctrl->irq_chip.irq_set_wake = msm_gpio_irq_set_wake;
 	pctrl->irq_chip.irq_request_resources = msm_gpio_irq_reqres;
 	pctrl->irq_chip.irq_release_resources = msm_gpio_irq_relres;
+	pctrl->irq_chip.irq_set_affinity = msm_gpio_irq_set_affinity;
+	pctrl->irq_chip.irq_set_vcpu_affinity = msm_gpio_irq_set_vcpu_affinity;
 
 	np = of_parse_phandle(pctrl->dev->of_node, "wakeup-parent", 0);
 	if (np) {
diff --git a/drivers/platform/chrome/chromeos_pstore.c b/drivers/platform/chrome/chromeos_pstore.c
index d13770785fb5..fa51153688b4 100644
--- a/drivers/platform/chrome/chromeos_pstore.c
+++ b/drivers/platform/chrome/chromeos_pstore.c
@@ -57,7 +57,7 @@ static struct ramoops_platform_data chromeos_ramoops_data = {
 	.record_size	= 0x40000,
 	.console_size	= 0x20000,
 	.ftrace_size	= 0x20000,
-	.dump_oops	= 1,
+	.max_reason	= KMSG_DUMP_OOPS,
 };
 
 static struct platform_device chromeos_ramoops = {
diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c
index b7f2c00db5e1..9c4af76a9956 100644
--- a/drivers/platform/chrome/cros_ec_sensorhub.c
+++ b/drivers/platform/chrome/cros_ec_sensorhub.c
@@ -52,28 +52,15 @@ static int cros_ec_sensorhub_register(struct device *dev,
 	int sensor_type[MOTIONSENSE_TYPE_MAX] = { 0 };
 	struct cros_ec_command *msg = sensorhub->msg;
 	struct cros_ec_dev *ec = sensorhub->ec;
-	int ret, i, sensor_num;
+	int ret, i;
 	char *name;
 
-	sensor_num = cros_ec_get_sensor_count(ec);
-	if (sensor_num < 0) {
-		dev_err(dev,
-			"Unable to retrieve sensor information (err:%d)\n",
-			sensor_num);
-		return sensor_num;
-	}
-
-	sensorhub->sensor_num = sensor_num;
-	if (sensor_num == 0) {
-		dev_err(dev, "Zero sensors reported.\n");
-		return -EINVAL;
-	}
 
 	msg->version = 1;
 	msg->insize = sizeof(struct ec_response_motion_sense);
 	msg->outsize = sizeof(struct ec_params_motion_sense);
 
-	for (i = 0; i < sensor_num; i++) {
+	for (i = 0; i < sensorhub->sensor_num; i++) {
 		sensorhub->params->cmd = MOTIONSENSE_CMD_INFO;
 		sensorhub->params->info.sensor_num = i;
 
@@ -140,8 +127,7 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev)
 	struct cros_ec_dev *ec = dev_get_drvdata(dev->parent);
 	struct cros_ec_sensorhub *data;
 	struct cros_ec_command *msg;
-	int ret;
-	int i;
+	int ret, i, sensor_num;
 
 	msg = devm_kzalloc(dev, sizeof(struct cros_ec_command) +
 			   max((u16)sizeof(struct ec_params_motion_sense),
@@ -166,10 +152,52 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev)
 	dev_set_drvdata(dev, data);
 
 	/* Check whether this EC is a sensor hub. */
-	if (cros_ec_check_features(data->ec, EC_FEATURE_MOTION_SENSE)) {
+	if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE)) {
+		sensor_num = cros_ec_get_sensor_count(ec);
+		if (sensor_num < 0) {
+			dev_err(dev,
+				"Unable to retrieve sensor information (err:%d)\n",
+				sensor_num);
+			return sensor_num;
+		}
+		if (sensor_num == 0) {
+			dev_err(dev, "Zero sensors reported.\n");
+			return -EINVAL;
+		}
+		data->sensor_num = sensor_num;
+
+		/*
+		 * Prepare the ring handler before enumering the
+		 * sensors.
+		 */
+		if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) {
+			ret = cros_ec_sensorhub_ring_allocate(data);
+			if (ret)
+				return ret;
+		}
+
+		/* Enumerate the sensors.*/
 		ret = cros_ec_sensorhub_register(dev, data);
 		if (ret)
 			return ret;
+
+		/*
+		 * When the EC does not have a FIFO, the sensors will query
+		 * their data themselves via sysfs or a software trigger.
+		 */
+		if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) {
+			ret = cros_ec_sensorhub_ring_add(data);
+			if (ret)
+				return ret;
+			/*
+			 * The msg and its data is not under the control of the
+			 * ring handler.
+			 */
+			return devm_add_action_or_reset(dev,
+					cros_ec_sensorhub_ring_remove,
+					data);
+		}
+
 	} else {
 		/*
 		 * If the device has sensors but does not claim to
@@ -184,22 +212,6 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev)
 		}
 	}
 
-	/*
-	 * If the EC does not have a FIFO, the sensors will query their data
-	 * themselves via sysfs or a software trigger.
-	 */
-	if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) {
-		ret = cros_ec_sensorhub_ring_add(data);
-		if (ret)
-			return ret;
-		/*
-		 * The msg and its data is not under the control of the ring
-		 * handler.
-		 */
-		return devm_add_action_or_reset(dev,
-						cros_ec_sensorhub_ring_remove,
-						data);
-	}
 
 	return 0;
 }
diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c
index 230e6cf3da2f..24e48d96ed76 100644
--- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c
+++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c
@@ -40,7 +40,7 @@ cros_sensorhub_send_sample(struct cros_ec_sensorhub *sensorhub,
 	int id = sample->sensor_id;
 	struct iio_dev *indio_dev;
 
-	if (id > sensorhub->sensor_num)
+	if (id >= sensorhub->sensor_num)
 		return -EINVAL;
 
 	cb = sensorhub->push_data[id].push_data_cb;
@@ -820,7 +820,7 @@ static void cros_ec_sensorhub_ring_handler(struct cros_ec_sensorhub *sensorhub)
 	if (fifo_info->count > sensorhub->fifo_size ||
 	    fifo_info->size != sensorhub->fifo_size) {
 		dev_warn(sensorhub->dev,
-			 "Mismatch EC data: count %d, size %d - expected %d",
+			 "Mismatch EC data: count %d, size %d - expected %d\n",
 			 fifo_info->count, fifo_info->size,
 			 sensorhub->fifo_size);
 		goto error;
@@ -851,14 +851,14 @@ static void cros_ec_sensorhub_ring_handler(struct cros_ec_sensorhub *sensorhub)
 		}
 		if (number_data > fifo_info->count - i) {
 			dev_warn(sensorhub->dev,
-				 "Invalid EC data: too many entry received: %d, expected %d",
+				 "Invalid EC data: too many entry received: %d, expected %d\n",
 				 number_data, fifo_info->count - i);
 			break;
 		}
 		if (out + number_data >
 		    sensorhub->ring + fifo_info->count) {
 			dev_warn(sensorhub->dev,
-				 "Too many samples: %d (%zd data) to %d entries for expected %d entries",
+				 "Too many samples: %d (%zd data) to %d entries for expected %d entries\n",
 				 i, out - sensorhub->ring, i + number_data,
 				 fifo_info->count);
 			break;
@@ -957,17 +957,15 @@ static int cros_ec_sensorhub_event(struct notifier_block *nb,
 }
 
 /**
- * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC
- *				  supports it.
+ * cros_ec_sensorhub_ring_allocate() - Prepare the FIFO functionality if the EC
+ *				       supports it.
  *
  * @sensorhub : Sensor Hub object.
  *
  * Return: 0 on success.
  */
-int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub)
+int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub)
 {
-	struct cros_ec_dev *ec = sensorhub->ec;
-	int ret;
 	int fifo_info_length =
 		sizeof(struct ec_response_motion_sense_fifo_info) +
 		sizeof(u16) * sensorhub->sensor_num;
@@ -978,6 +976,49 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub)
 	if (!sensorhub->fifo_info)
 		return -ENOMEM;
 
+	/*
+	 * Allocate the callback area based on the number of sensors.
+	 * Add one for the sensor ring.
+	 */
+	sensorhub->push_data = devm_kcalloc(sensorhub->dev,
+			sensorhub->sensor_num,
+			sizeof(*sensorhub->push_data),
+			GFP_KERNEL);
+	if (!sensorhub->push_data)
+		return -ENOMEM;
+
+	sensorhub->tight_timestamps = cros_ec_check_features(
+			sensorhub->ec,
+			EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS);
+
+	if (sensorhub->tight_timestamps) {
+		sensorhub->batch_state = devm_kcalloc(sensorhub->dev,
+				sensorhub->sensor_num,
+				sizeof(*sensorhub->batch_state),
+				GFP_KERNEL);
+		if (!sensorhub->batch_state)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC
+ *				  supports it.
+ *
+ * @sensorhub : Sensor Hub object.
+ *
+ * Return: 0 on success.
+ */
+int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub)
+{
+	struct cros_ec_dev *ec = sensorhub->ec;
+	int ret;
+	int fifo_info_length =
+		sizeof(struct ec_response_motion_sense_fifo_info) +
+		sizeof(u16) * sensorhub->sensor_num;
+
 	/* Retrieve FIFO information */
 	sensorhub->msg->version = 2;
 	sensorhub->params->cmd = MOTIONSENSE_CMD_FIFO_INFO;
@@ -998,31 +1039,9 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub)
 	if (!sensorhub->ring)
 		return -ENOMEM;
 
-	/*
-	 * Allocate the callback area based on the number of sensors.
-	 */
-	sensorhub->push_data = devm_kcalloc(
-			sensorhub->dev, sensorhub->sensor_num,
-			sizeof(*sensorhub->push_data),
-			GFP_KERNEL);
-	if (!sensorhub->push_data)
-		return -ENOMEM;
-
 	sensorhub->fifo_timestamp[CROS_EC_SENSOR_LAST_TS] =
 		cros_ec_get_time_ns();
 
-	sensorhub->tight_timestamps = cros_ec_check_features(
-			ec, EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS);
-
-	if (sensorhub->tight_timestamps) {
-		sensorhub->batch_state = devm_kcalloc(sensorhub->dev,
-				sensorhub->sensor_num,
-				sizeof(*sensorhub->batch_state),
-				GFP_KERNEL);
-		if (!sensorhub->batch_state)
-			return -ENOMEM;
-	}
-
 	/* Register the notifier that will act as a top half interrupt. */
 	sensorhub->notifier.notifier_call = cros_ec_sensorhub_event;
 	ret = blocking_notifier_chain_register(&ec->ec_dev->event_notifier,
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 6f12747a359a..c4404d9c1de4 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -515,9 +515,33 @@ static struct asus_wmi_driver asus_nb_wmi_driver = {
 	.detect_quirks = asus_nb_wmi_quirks,
 };
 
+static const struct dmi_system_id asus_nb_wmi_blacklist[] __initconst = {
+	{
+		/*
+		 * asus-nb-wm adds no functionality. The T100TA has a detachable
+		 * USB kbd, so no hotkeys and it has no WMI rfkill; and loading
+		 * asus-nb-wm causes the camera LED to turn and _stay_ on.
+		 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"),
+		},
+	},
+	{
+		/* The Asus T200TA has the same issue as the T100TA */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T200TA"),
+		},
+	},
+	{} /* Terminating entry */
+};
 
 static int __init asus_nb_wmi_init(void)
 {
+	if (dmi_check_system(asus_nb_wmi_blacklist))
+		return -ENODEV;
+
 	return asus_wmi_register_driver(&asus_nb_wmi_driver);
 }
 
diff --git a/drivers/platform/x86/intel-uncore-frequency.c b/drivers/platform/x86/intel-uncore-frequency.c
index b96d172eb2c1..12d5ab7e1f5d 100644
--- a/drivers/platform/x86/intel-uncore-frequency.c
+++ b/drivers/platform/x86/intel-uncore-frequency.c
@@ -53,7 +53,7 @@ static int uncore_max_entries __read_mostly;
 /* Storage for uncore data for all instances */
 static struct uncore_data *uncore_instances;
 /* Root of the all uncore sysfs kobjs */
-struct kobject *uncore_root_kobj;
+static struct kobject *uncore_root_kobj;
 /* Stores the CPU mask of the target CPUs to use during uncore read/write */
 static cpumask_t uncore_cpu_mask;
 /* CPU online callback register instance */
diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c
index d2a5d4c36715..7c8bdab078cf 100644
--- a/drivers/platform/x86/intel_pmc_core.c
+++ b/drivers/platform/x86/intel_pmc_core.c
@@ -255,7 +255,7 @@ static const struct pmc_bit_map *ext_cnp_pfear_map[] = {
 };
 
 static const struct pmc_bit_map icl_pfear_map[] = {
-	/* Ice Lake generation onwards only */
+	/* Ice Lake and Jasper Lake generation onwards only */
 	{"RES_65",		BIT(0)},
 	{"RES_66",		BIT(1)},
 	{"RES_67",		BIT(2)},
@@ -274,7 +274,7 @@ static const struct pmc_bit_map *ext_icl_pfear_map[] = {
 };
 
 static const struct pmc_bit_map tgl_pfear_map[] = {
-	/* Tiger Lake, Elkhart Lake and Jasper Lake generation onwards only */
+	/* Tiger Lake and Elkhart Lake generation onwards only */
 	{"PSF9",		BIT(0)},
 	{"RES_66",		BIT(1)},
 	{"RES_67",		BIT(2)},
@@ -692,7 +692,6 @@ static void pmc_core_lpm_display(struct pmc_dev *pmcdev, struct device *dev,
 	kfree(lpm_regs);
 }
 
-#if IS_ENABLED(CONFIG_DEBUG_FS)
 static bool slps0_dbg_latch;
 
 static inline u8 pmc_core_reg_read_byte(struct pmc_dev *pmcdev, int offset)
@@ -1133,15 +1132,6 @@ static void pmc_core_dbgfs_register(struct pmc_dev *pmcdev)
 				    &pmc_core_substate_l_sts_regs_fops);
 	}
 }
-#else
-static inline void pmc_core_dbgfs_register(struct pmc_dev *pmcdev)
-{
-}
-
-static inline void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
-{
-}
-#endif /* CONFIG_DEBUG_FS */
 
 static const struct x86_cpu_id intel_pmc_core_ids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&spt_reg_map),
@@ -1156,7 +1146,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&tgl_reg_map),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&tgl_reg_map),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	&tgl_reg_map),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	&tgl_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	&icl_reg_map),
 	{}
 };
 
@@ -1260,13 +1250,11 @@ static int pmc_core_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-
 static bool warn_on_s0ix_failures;
 module_param(warn_on_s0ix_failures, bool, 0644);
 MODULE_PARM_DESC(warn_on_s0ix_failures, "Check and warn for S0ix failures");
 
-static int pmc_core_suspend(struct device *dev)
+static __maybe_unused int pmc_core_suspend(struct device *dev)
 {
 	struct pmc_dev *pmcdev = dev_get_drvdata(dev);
 
@@ -1318,7 +1306,7 @@ static inline bool pmc_core_is_s0ix_failed(struct pmc_dev *pmcdev)
 	return false;
 }
 
-static int pmc_core_resume(struct device *dev)
+static __maybe_unused int pmc_core_resume(struct device *dev)
 {
 	struct pmc_dev *pmcdev = dev_get_drvdata(dev);
 	const struct pmc_bit_map **maps = pmcdev->map->lpm_sts;
@@ -1348,8 +1336,6 @@ static int pmc_core_resume(struct device *dev)
 	return 0;
 }
 
-#endif
-
 static const struct dev_pm_ops pmc_core_pm_ops = {
 	SET_LATE_SYSTEM_SLEEP_PM_OPS(pmc_core_suspend, pmc_core_resume)
 };
diff --git a/drivers/platform/x86/intel_pmc_core.h b/drivers/platform/x86/intel_pmc_core.h
index 0d50b2402abe..5eae55d80226 100644
--- a/drivers/platform/x86/intel_pmc_core.h
+++ b/drivers/platform/x86/intel_pmc_core.h
@@ -282,9 +282,7 @@ struct pmc_dev {
 	u32 base_addr;
 	void __iomem *regbase;
 	const struct pmc_reg_map *map;
-#if IS_ENABLED(CONFIG_DEBUG_FS)
 	struct dentry *dbgfs_dir;
-#endif /* CONFIG_DEBUG_FS */
 	int pmc_xram_read_bit;
 	struct mutex lock; /* generic mutex lock for PMC Core */
 
diff --git a/drivers/platform/x86/surface3_power.c b/drivers/platform/x86/surface3_power.c
index 946ac2dc08ae..cc4f9cba6856 100644
--- a/drivers/platform/x86/surface3_power.c
+++ b/drivers/platform/x86/surface3_power.c
@@ -522,8 +522,8 @@ static int mshw0011_probe(struct i2c_client *client)
 	strlcpy(board_info.type, "MSHW0011-bat0", I2C_NAME_SIZE);
 
 	bat0 = i2c_acpi_new_device(dev, 1, &board_info);
-	if (!bat0)
-		return -ENOMEM;
+	if (IS_ERR(bat0))
+		return PTR_ERR(bat0);
 
 	data->bat0 = bat0;
 	i2c_set_clientdata(bat0, data);
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 8eaadbaf8ffa..0f704484ae1d 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -9548,7 +9548,7 @@ static ssize_t tpacpi_battery_store(int what,
 		if (!battery_info.batteries[battery].start_support)
 			return -ENODEV;
 		/* valid values are [0, 99] */
-		if (value < 0 || value > 99)
+		if (value > 99)
 			return -EINVAL;
 		if (value > battery_info.batteries[battery].charge_stop)
 			return -EINVAL;
diff --git a/drivers/platform/x86/xiaomi-wmi.c b/drivers/platform/x86/xiaomi-wmi.c
index 601cbb282f54..54a2546bb93b 100644
--- a/drivers/platform/x86/xiaomi-wmi.c
+++ b/drivers/platform/x86/xiaomi-wmi.c
@@ -23,7 +23,7 @@ struct xiaomi_wmi {
 	unsigned int key_code;
 };
 
-int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context)
+static int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context)
 {
 	struct xiaomi_wmi *data;
 
@@ -48,7 +48,7 @@ int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context)
 	return input_register_device(data->input_dev);
 }
 
-void xiaomi_wmi_notify(struct wmi_device *wdev, union acpi_object *dummy)
+static void xiaomi_wmi_notify(struct wmi_device *wdev, union acpi_object *dummy)
 {
 	struct xiaomi_wmi *data;
 
diff --git a/drivers/power/supply/bd70528-charger.c b/drivers/power/supply/bd70528-charger.c
index b8e1ec106627..3b820110ecfa 100644
--- a/drivers/power/supply/bd70528-charger.c
+++ b/drivers/power/supply/bd70528-charger.c
@@ -335,14 +335,14 @@ static int bd70528_get_present(struct bd70528_psy *bdpsy, int *val)
 	return 0;
 }
 
-struct linear_range {
+struct bd70528_linear_range {
 	int min;
 	int step;
 	int vals;
 	int low_sel;
 };
 
-static const struct linear_range current_limit_ranges[] = {
+static const struct bd70528_linear_range current_limit_ranges[] = {
 	{
 		.min = 5,
 		.step = 1,
@@ -374,7 +374,7 @@ static const struct linear_range current_limit_ranges[] = {
  * voltage for low temperatures. The driver currently only reads
  * the charge current at room temperature. We do set both though.
  */
-static const struct linear_range warm_charge_curr[] = {
+static const struct bd70528_linear_range warm_charge_curr[] = {
 	{
 		.min = 10,
 		.step = 10,
@@ -398,7 +398,7 @@ static const struct linear_range warm_charge_curr[] = {
 #define MAX_WARM_CHG_CURR_SEL 0x1f
 #define MIN_CHG_CURR_SEL 0x0
 
-static int find_value_for_selector_low(const struct linear_range *r,
+static int find_value_for_selector_low(const struct bd70528_linear_range *r,
 				       int selectors, unsigned int sel,
 				       unsigned int *val)
 {
@@ -420,7 +420,7 @@ static int find_value_for_selector_low(const struct linear_range *r,
  * I guess it is enough if we use voltage/current which is closest (below)
  * the requested?
  */
-static int find_selector_for_value_low(const struct linear_range *r,
+static int find_selector_for_value_low(const struct bd70528_linear_range *r,
 				       int selectors, unsigned int val,
 				       unsigned int *sel, bool *found)
 {
diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c
index dfda54cbd866..52d77db39829 100644
--- a/drivers/ptp/ptp_ines.c
+++ b/drivers/ptp/ptp_ines.c
@@ -400,8 +400,8 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 	ines_write32(port, ts_stat_rx, ts_stat_rx);
 	ines_write32(port, ts_stat_tx, ts_stat_tx);
 
-	port->rxts_enabled = ts_stat_rx == TS_ENABLE ? true : false;
-	port->txts_enabled = ts_stat_tx == TS_ENABLE ? true : false;
+	port->rxts_enabled = ts_stat_rx == TS_ENABLE;
+	port->txts_enabled = ts_stat_tx == TS_ENABLE;
 
 	spin_unlock_irqrestore(&port->lock, flags);
 
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 8155f59ece38..10af330153b5 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -877,6 +877,11 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
 				rmcd_error("pinned %ld out of %ld pages",
 					   pinned, nr_pages);
 			ret = -EFAULT;
+			/*
+			 * Set nr_pages up to mean "how many pages to unpin, in
+			 * the error handler:
+			 */
+			nr_pages = pinned;
 			goto err_pg;
 		}
 
diff --git a/drivers/regulator/88pg86x.c b/drivers/regulator/88pg86x.c
index d5ef55c81185..71cfa2c5de5e 100644
--- a/drivers/regulator/88pg86x.c
+++ b/drivers/regulator/88pg86x.c
@@ -11,13 +11,13 @@ static const struct regulator_ops pg86x_ops = {
 	.list_voltage = regulator_list_voltage_linear_range,
 };
 
-static const struct regulator_linear_range pg86x_buck1_ranges[] = {
+static const struct linear_range pg86x_buck1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(      0,  0, 10,     0),
 	REGULATOR_LINEAR_RANGE(1000000, 11, 34, 25000),
 	REGULATOR_LINEAR_RANGE(1600000, 35, 47, 50000),
 };
 
-static const struct regulator_linear_range pg86x_buck2_ranges[] = {
+static const struct linear_range pg86x_buck2_ranges[] = {
 	REGULATOR_LINEAR_RANGE(      0,  0, 15,     0),
 	REGULATOR_LINEAR_RANGE(1000000, 16, 39, 25000),
 	REGULATOR_LINEAR_RANGE(1600000, 40, 52, 50000),
diff --git a/drivers/regulator/88pm800-regulator.c b/drivers/regulator/88pm800-regulator.c
index 69ae25886181..d08ee81ed1ac 100644
--- a/drivers/regulator/88pm800-regulator.c
+++ b/drivers/regulator/88pm800-regulator.c
@@ -134,13 +134,13 @@ struct pm800_regulator_info {
 }
 
 /* Ranges are sorted in ascending order. */
-static const struct regulator_linear_range buck1_volt_range[] = {
+static const struct linear_range buck1_volt_range[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 0x4f, 12500),
 	REGULATOR_LINEAR_RANGE(1600000, 0x50, 0x54, 50000),
 };
 
 /* BUCK 2~5 have same ranges. */
-static const struct regulator_linear_range buck2_5_volt_range[] = {
+static const struct linear_range buck2_5_volt_range[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 0x4f, 12500),
 	REGULATOR_LINEAR_RANGE(1600000, 0x50, 0x72, 50000),
 };
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index f4b72cb098ef..8f677f5d79b4 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menuconfig REGULATOR
 	bool "Voltage and Current Regulator Support"
+	select LINEAR_RANGES
 	help
 	  Generic Voltage and Current Regulator support.
 
@@ -585,6 +586,16 @@ config REGULATOR_MAX77802
 	  Exynos5420/Exynos5800 SoCs to control various voltages.
 	  It includes support for control of voltage and ramp speed.
 
+config REGULATOR_MAX77826
+	tristate "Maxim 77826 regulator"
+	depends on I2C
+	select REGMAP_I2C
+	help
+	  This driver controls a Maxim 77826 regulator via I2C bus.
+	  The regulator include 15 LDOs, BUCK and BUCK BOOST regulator.
+	  It includes support for control of output voltage. This
+	  regulator is found on the Samsung Galaxy S5 (klte) smartphone.
+
 config REGULATOR_MC13XXX_CORE
 	tristate
 
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 6610ee001d9a..e8f163371071 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -74,6 +74,7 @@ obj-$(CONFIG_REGULATOR_MAX8998) += max8998.o
 obj-$(CONFIG_REGULATOR_MAX77686) += max77686-regulator.o
 obj-$(CONFIG_REGULATOR_MAX77693) += max77693-regulator.o
 obj-$(CONFIG_REGULATOR_MAX77802) += max77802-regulator.o
+obj-$(CONFIG_REGULATOR_MAX77826) += max77826-regulator.o
 obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o
 obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o
 obj-$(CONFIG_REGULATOR_MC13XXX_CORE) +=  mc13xxx-regulator-core.o
diff --git a/drivers/regulator/ab8500.c b/drivers/regulator/ab8500.c
index f60e1b26c2d2..716ca5bb178e 100644
--- a/drivers/regulator/ab8500.c
+++ b/drivers/regulator/ab8500.c
@@ -139,17 +139,6 @@ static const unsigned int ldo_vintcore_voltages[] = {
 	1350000,
 };
 
-static const unsigned int ldo_sdio_voltages[] = {
-	1160000,
-	1050000,
-	1100000,
-	1500000,
-	1800000,
-	2200000,
-	2910000,
-	3050000,
-};
-
 static const unsigned int fixed_1200000_voltage[] = {
 	1200000,
 };
@@ -166,10 +155,6 @@ static const unsigned int fixed_2050000_voltage[] = {
 	2050000,
 };
 
-static const unsigned int fixed_3300000_voltage[] = {
-	3300000,
-};
-
 static const unsigned int ldo_vana_voltages[] = {
 	1050000,
 	1075000,
@@ -192,13 +177,6 @@ static const unsigned int ldo_vaudio_voltages[] = {
 	2600000,	/* Duplicated in Vaudio and IsoUicc Control register. */
 };
 
-static const unsigned int ldo_vdmic_voltages[] = {
-	1800000,
-	1900000,
-	2000000,
-	2850000,
-};
-
 static DEFINE_MUTEX(shared_mode_mutex);
 static struct ab8500_shared_mode ldo_anamic1_shared;
 static struct ab8500_shared_mode ldo_anamic2_shared;
diff --git a/drivers/regulator/act8865-regulator.c b/drivers/regulator/act8865-regulator.c
index 0fa97f934df4..19b9742c9ecc 100644
--- a/drivers/regulator/act8865-regulator.c
+++ b/drivers/regulator/act8865-regulator.c
@@ -220,13 +220,13 @@ static const struct regmap_config act8865_regmap_config = {
 	.val_bits = 8,
 };
 
-static const struct regulator_linear_range act8865_voltage_ranges[] = {
+static const struct linear_range act8865_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 23, 25000),
 	REGULATOR_LINEAR_RANGE(1200000, 24, 47, 50000),
 	REGULATOR_LINEAR_RANGE(2400000, 48, 63, 100000),
 };
 
-static const struct regulator_linear_range act8600_sudcdc_voltage_ranges[] = {
+static const struct linear_range act8600_sudcdc_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(3000000, 0, 63, 0),
 	REGULATOR_LINEAR_RANGE(3000000, 64, 159, 100000),
 	REGULATOR_LINEAR_RANGE(12600000, 160, 191, 200000),
diff --git a/drivers/regulator/act8945a-regulator.c b/drivers/regulator/act8945a-regulator.c
index d2f804dbc785..6a62f946ccae 100644
--- a/drivers/regulator/act8945a-regulator.c
+++ b/drivers/regulator/act8945a-regulator.c
@@ -73,7 +73,7 @@ struct act8945a_pmic {
 	u32 op_mode[ACT8945A_ID_MAX];
 };
 
-static const struct regulator_linear_range act8945a_voltage_ranges[] = {
+static const struct linear_range act8945a_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 23, 25000),
 	REGULATOR_LINEAR_RANGE(1200000, 24, 47, 50000),
 	REGULATOR_LINEAR_RANGE(2400000, 48, 63, 100000),
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index 1a3d7b720f5e..ade0bef4569d 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -87,7 +87,7 @@ static const struct regulator_ops arizona_ldo1_hc_ops = {
 	.set_bypass = regulator_set_bypass_regmap,
 };
 
-static const struct regulator_linear_range arizona_ldo1_hc_ranges[] = {
+static const struct linear_range arizona_ldo1_hc_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0, 0x6, 50000),
 	REGULATOR_LINEAR_RANGE(1800000, 0x7, 0x7, 0),
 };
diff --git a/drivers/regulator/arizona-micsupp.c b/drivers/regulator/arizona-micsupp.c
index ae1a5de3e57d..f6cfd3f6f0dd 100644
--- a/drivers/regulator/arizona-micsupp.c
+++ b/drivers/regulator/arizona-micsupp.c
@@ -125,7 +125,7 @@ static const struct regulator_ops arizona_micsupp_ops = {
 	.set_bypass = arizona_micsupp_set_bypass,
 };
 
-static const struct regulator_linear_range arizona_micsupp_ranges[] = {
+static const struct linear_range arizona_micsupp_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1700000, 0,    0x1e, 50000),
 	REGULATOR_LINEAR_RANGE(3300000, 0x1f, 0x1f, 0),
 };
@@ -152,7 +152,7 @@ static const struct regulator_desc arizona_micsupp = {
 	.owner = THIS_MODULE,
 };
 
-static const struct regulator_linear_range arizona_micsupp_ext_ranges[] = {
+static const struct linear_range arizona_micsupp_ext_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000,  0,    0x14, 25000),
 	REGULATOR_LINEAR_RANGE(1500000, 0x15, 0x27, 100000),
 };
diff --git a/drivers/regulator/as3711-regulator.c b/drivers/regulator/as3711-regulator.c
index ece88103f2fd..b6b9206969ae 100644
--- a/drivers/regulator/as3711-regulator.c
+++ b/drivers/regulator/as3711-regulator.c
@@ -103,18 +103,18 @@ static const struct regulator_ops as3711_dldo_ops = {
 	.map_voltage		= regulator_map_voltage_linear_range,
 };
 
-static const struct regulator_linear_range as3711_sd_ranges[] = {
+static const struct linear_range as3711_sd_ranges[] = {
 	REGULATOR_LINEAR_RANGE(612500, 0x1, 0x40, 12500),
 	REGULATOR_LINEAR_RANGE(1425000, 0x41, 0x70, 25000),
 	REGULATOR_LINEAR_RANGE(2650000, 0x71, 0x7f, 50000),
 };
 
-static const struct regulator_linear_range as3711_aldo_ranges[] = {
+static const struct linear_range as3711_aldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1200000, 0, 0xf, 50000),
 	REGULATOR_LINEAR_RANGE(1800000, 0x10, 0x1f, 100000),
 };
 
-static const struct regulator_linear_range as3711_dldo_ranges[] = {
+static const struct linear_range as3711_dldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0, 0x10, 50000),
 	REGULATOR_LINEAR_RANGE(1750000, 0x20, 0x3f, 50000),
 };
diff --git a/drivers/regulator/as3722-regulator.c b/drivers/regulator/as3722-regulator.c
index bd5d0bacb08d..33ca197860b3 100644
--- a/drivers/regulator/as3722-regulator.c
+++ b/drivers/regulator/as3722-regulator.c
@@ -389,7 +389,7 @@ static const struct regulator_ops as3722_ldo6_extcntrl_ops = {
 	.set_bypass = regulator_set_bypass_regmap,
 };
 
-static const struct regulator_linear_range as3722_ldo_ranges[] = {
+static const struct linear_range as3722_ldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE(0, 0x00, 0x00, 0),
 	REGULATOR_LINEAR_RANGE(825000, 0x01, 0x24, 25000),
 	REGULATOR_LINEAR_RANGE(1725000, 0x40, 0x7F, 25000),
@@ -487,7 +487,7 @@ static bool as3722_sd0_is_low_voltage(struct as3722_regulators *as3722_regs)
 	return false;
 }
 
-static const struct regulator_linear_range as3722_sd2345_ranges[] = {
+static const struct linear_range as3722_sd2345_ranges[] = {
 	REGULATOR_LINEAR_RANGE(0, 0x00, 0x00, 0),
 	REGULATOR_LINEAR_RANGE(612500, 0x01, 0x40, 12500),
 	REGULATOR_LINEAR_RANGE(1425000, 0x41, 0x70, 25000),
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index 1e6eb5b1f8d8..fbc95cadaf53 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -510,7 +510,7 @@ static const struct regulator_ops axp20x_ops_sw = {
 	.is_enabled		= regulator_is_enabled_regmap,
 };
 
-static const struct regulator_linear_range axp20x_ldo4_ranges[] = {
+static const struct linear_range axp20x_ldo4_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1250000,
 			       AXP20X_LDO4_V_OUT_1250mV_START,
 			       AXP20X_LDO4_V_OUT_1250mV_END,
@@ -638,7 +638,7 @@ static const struct regulator_desc axp22x_drivevbus_regulator = {
 };
 
 /* DCDC ranges shared with AXP813 */
-static const struct regulator_linear_range axp803_dcdc234_ranges[] = {
+static const struct linear_range axp803_dcdc234_ranges[] = {
 	REGULATOR_LINEAR_RANGE(500000,
 			       AXP803_DCDC234_500mV_START,
 			       AXP803_DCDC234_500mV_END,
@@ -649,7 +649,7 @@ static const struct regulator_linear_range axp803_dcdc234_ranges[] = {
 			       20000),
 };
 
-static const struct regulator_linear_range axp803_dcdc5_ranges[] = {
+static const struct linear_range axp803_dcdc5_ranges[] = {
 	REGULATOR_LINEAR_RANGE(800000,
 			       AXP803_DCDC5_800mV_START,
 			       AXP803_DCDC5_800mV_END,
@@ -660,7 +660,7 @@ static const struct regulator_linear_range axp803_dcdc5_ranges[] = {
 			       20000),
 };
 
-static const struct regulator_linear_range axp803_dcdc6_ranges[] = {
+static const struct linear_range axp803_dcdc6_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000,
 			       AXP803_DCDC6_600mV_START,
 			       AXP803_DCDC6_600mV_END,
@@ -672,7 +672,7 @@ static const struct regulator_linear_range axp803_dcdc6_ranges[] = {
 };
 
 /* AXP806's CLDO2 and AXP809's DLDO1 share the same range */
-static const struct regulator_linear_range axp803_dldo2_ranges[] = {
+static const struct linear_range axp803_dldo2_ranges[] = {
 	REGULATOR_LINEAR_RANGE(700000,
 			       AXP803_DLDO2_700mV_START,
 			       AXP803_DLDO2_700mV_END,
@@ -758,7 +758,7 @@ static const struct regulator_desc axp803_regulators[] = {
 	AXP_DESC_FIXED(AXP803, RTC_LDO, "rtc-ldo", "ips", 3000),
 };
 
-static const struct regulator_linear_range axp806_dcdca_ranges[] = {
+static const struct linear_range axp806_dcdca_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000,
 			       AXP806_DCDCA_600mV_START,
 			       AXP806_DCDCA_600mV_END,
@@ -769,7 +769,7 @@ static const struct regulator_linear_range axp806_dcdca_ranges[] = {
 			       20000),
 };
 
-static const struct regulator_linear_range axp806_dcdcd_ranges[] = {
+static const struct linear_range axp806_dcdcd_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000,
 			       AXP806_DCDCD_600mV_START,
 			       AXP806_DCDCD_600mV_END,
@@ -834,7 +834,7 @@ static const struct regulator_desc axp806_regulators[] = {
 		    AXP806_PWR_OUT_CTRL2, AXP806_PWR_OUT_SW_MASK),
 };
 
-static const struct regulator_linear_range axp809_dcdc4_ranges[] = {
+static const struct linear_range axp809_dcdc4_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000,
 			       AXP809_DCDC4_600mV_START,
 			       AXP809_DCDC4_600mV_END,
diff --git a/drivers/regulator/bcm590xx-regulator.c b/drivers/regulator/bcm590xx-regulator.c
index 8c98c3f07660..65e23fc5f9c3 100644
--- a/drivers/regulator/bcm590xx-regulator.c
+++ b/drivers/regulator/bcm590xx-regulator.c
@@ -116,14 +116,14 @@ static const unsigned int ldo_vbus[] = {
 };
 
 /* DCDC group CSR: supported voltages in microvolts */
-static const struct regulator_linear_range dcdc_csr_ranges[] = {
+static const struct linear_range dcdc_csr_ranges[] = {
 	REGULATOR_LINEAR_RANGE(860000, 2, 50, 10000),
 	REGULATOR_LINEAR_RANGE(1360000, 51, 55, 20000),
 	REGULATOR_LINEAR_RANGE(900000, 56, 63, 0),
 };
 
 /* DCDC group IOSR1: supported voltages in microvolts */
-static const struct regulator_linear_range dcdc_iosr1_ranges[] = {
+static const struct linear_range dcdc_iosr1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(860000, 2, 51, 10000),
 	REGULATOR_LINEAR_RANGE(1500000, 52, 52, 0),
 	REGULATOR_LINEAR_RANGE(1800000, 53, 53, 0),
@@ -131,7 +131,7 @@ static const struct regulator_linear_range dcdc_iosr1_ranges[] = {
 };
 
 /* DCDC group SDSR1: supported voltages in microvolts */
-static const struct regulator_linear_range dcdc_sdsr1_ranges[] = {
+static const struct linear_range dcdc_sdsr1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(860000, 2, 50, 10000),
 	REGULATOR_LINEAR_RANGE(1340000, 51, 51, 0),
 	REGULATOR_LINEAR_RANGE(900000, 52, 63, 0),
@@ -143,7 +143,7 @@ struct bcm590xx_info {
 	u8 n_voltages;
 	const unsigned int *volt_table;
 	u8 n_linear_ranges;
-	const struct regulator_linear_range *linear_ranges;
+	const struct linear_range *linear_ranges;
 };
 
 #define BCM590XX_REG_TABLE(_name, _table) \
diff --git a/drivers/regulator/bd70528-regulator.c b/drivers/regulator/bd70528-regulator.c
index 5bf8a2dc5fe7..d44adf7e875a 100644
--- a/drivers/regulator/bd70528-regulator.c
+++ b/drivers/regulator/bd70528-regulator.c
@@ -20,22 +20,22 @@
 #define BUCK_RAMPRATE_125MV 1
 #define BUCK_RAMP_MAX 250
 
-static const struct regulator_linear_range bd70528_buck1_volts[] = {
+static const struct linear_range bd70528_buck1_volts[] = {
 	REGULATOR_LINEAR_RANGE(1200000, 0x00, 0x1, 600000),
 	REGULATOR_LINEAR_RANGE(2750000, 0x2, 0xf, 50000),
 };
-static const struct regulator_linear_range bd70528_buck2_volts[] = {
+static const struct linear_range bd70528_buck2_volts[] = {
 	REGULATOR_LINEAR_RANGE(1200000, 0x00, 0x1, 300000),
 	REGULATOR_LINEAR_RANGE(1550000, 0x2, 0xd, 50000),
 	REGULATOR_LINEAR_RANGE(3000000, 0xe, 0xf, 300000),
 };
-static const struct regulator_linear_range bd70528_buck3_volts[] = {
+static const struct linear_range bd70528_buck3_volts[] = {
 	REGULATOR_LINEAR_RANGE(800000, 0x00, 0xd, 50000),
 	REGULATOR_LINEAR_RANGE(1800000, 0xe, 0xf, 0),
 };
 
 /* All LDOs have same voltage ranges */
-static const struct regulator_linear_range bd70528_ldo_volts[] = {
+static const struct linear_range bd70528_ldo_volts[] = {
 	REGULATOR_LINEAR_RANGE(1650000, 0x0, 0x07, 50000),
 	REGULATOR_LINEAR_RANGE(2100000, 0x8, 0x0f, 100000),
 	REGULATOR_LINEAR_RANGE(2850000, 0x10, 0x19, 50000),
diff --git a/drivers/regulator/bd71828-regulator.c b/drivers/regulator/bd71828-regulator.c
index b2fa17be4988..85c0b9000963 100644
--- a/drivers/regulator/bd71828-regulator.c
+++ b/drivers/regulator/bd71828-regulator.c
@@ -65,27 +65,27 @@ static const struct reg_init buck7_inits[] = {
 	},
 };
 
-static const struct regulator_linear_range bd71828_buck1267_volts[] = {
+static const struct linear_range bd71828_buck1267_volts[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0x00, 0xef, 6250),
 	REGULATOR_LINEAR_RANGE(2000000, 0xf0, 0xff, 0),
 };
 
-static const struct regulator_linear_range bd71828_buck3_volts[] = {
+static const struct linear_range bd71828_buck3_volts[] = {
 	REGULATOR_LINEAR_RANGE(1200000, 0x00, 0x0f, 50000),
 	REGULATOR_LINEAR_RANGE(2000000, 0x10, 0x1f, 0),
 };
 
-static const struct regulator_linear_range bd71828_buck4_volts[] = {
+static const struct linear_range bd71828_buck4_volts[] = {
 	REGULATOR_LINEAR_RANGE(1000000, 0x00, 0x1f, 25000),
 	REGULATOR_LINEAR_RANGE(1800000, 0x20, 0x3f, 0),
 };
 
-static const struct regulator_linear_range bd71828_buck5_volts[] = {
+static const struct linear_range bd71828_buck5_volts[] = {
 	REGULATOR_LINEAR_RANGE(2500000, 0x00, 0x0f, 50000),
 	REGULATOR_LINEAR_RANGE(3300000, 0x10, 0x1f, 0),
 };
 
-static const struct regulator_linear_range bd71828_ldo_volts[] = {
+static const struct linear_range bd71828_ldo_volts[] = {
 	REGULATOR_LINEAR_RANGE(800000, 0x00, 0x31, 50000),
 	REGULATOR_LINEAR_RANGE(3300000, 0x32, 0x3f, 0),
 };
diff --git a/drivers/regulator/bd718x7-regulator.c b/drivers/regulator/bd718x7-regulator.c
index cf3872837abc..7b311389f925 100644
--- a/drivers/regulator/bd718x7-regulator.c
+++ b/drivers/regulator/bd718x7-regulator.c
@@ -55,12 +55,20 @@ static int bd718xx_buck1234_set_ramp_delay(struct regulator_dev *rdev,
 				  BUCK_RAMPRATE_MASK, ramp_value << 6);
 }
 
-/* Bucks 1 to 4 support DVS. PWM mode is used when voltage is changed.
+/*
+ * On BD71837 (not on BD71847, BD71850, ...)
+ * Bucks 1 to 4 support DVS. PWM mode is used when voltage is changed.
  * Bucks 5 to 8 and LDOs can use PFM and must be disabled when voltage
  * is changed. Hence we return -EBUSY for these if voltage is changed
  * when BUCK/LDO is enabled.
+ *
+ * On BD71847, BD71850, ... The LDO voltage can be changed when LDO is
+ * enabled. But if voltage is increased the LDO power-good monitoring
+ * must be disabled for the duration of changing + 1mS to ensure voltage
+ * has reached the higher level before HW does next under voltage detection
+ * cycle.
  */
-static int bd718xx_set_voltage_sel_restricted(struct regulator_dev *rdev,
+static int bd71837_set_voltage_sel_restricted(struct regulator_dev *rdev,
 						    unsigned int sel)
 {
 	if (regulator_is_enabled_regmap(rdev))
@@ -69,9 +77,124 @@ static int bd718xx_set_voltage_sel_restricted(struct regulator_dev *rdev,
 	return regulator_set_voltage_sel_regmap(rdev, sel);
 }
 
+static void voltage_change_done(struct regulator_dev *rdev, unsigned int sel,
+				unsigned int *mask)
+{
+	int ret;
+
+	if (*mask) {
+		/*
+		 * Let's allow scheduling as we use I2C anyways. We just need to
+		 * guarantee minimum of 1ms sleep - it shouldn't matter if we
+		 * exceed it due to the scheduling.
+		 */
+		msleep(1);
+		/*
+		 * Note for next hacker. The PWRGOOD should not be masked on
+		 * BD71847 so we will just unconditionally enable detection
+		 * when voltage is set.
+		 * If someone want's to disable PWRGOOD he must implement
+		 * caching and restoring the old value here. I am not
+		 * aware of such use-cases so for the sake of the simplicity
+		 * we just always enable PWRGOOD here.
+		 */
+		ret = regmap_update_bits(rdev->regmap, BD718XX_REG_MVRFLTMASK2,
+					 *mask, 0);
+		if (ret)
+			dev_err(&rdev->dev,
+				"Failed to re-enable voltage monitoring (%d)\n",
+				ret);
+	}
+}
+
+static int voltage_change_prepare(struct regulator_dev *rdev, unsigned int sel,
+				  unsigned int *mask)
+{
+	int ret;
+
+	*mask = 0;
+	if (regulator_is_enabled_regmap(rdev)) {
+		int now, new;
+
+		now = rdev->desc->ops->get_voltage_sel(rdev);
+		if (now < 0)
+			return now;
+
+		now = rdev->desc->ops->list_voltage(rdev, now);
+		if (now < 0)
+			return now;
+
+		new = rdev->desc->ops->list_voltage(rdev, sel);
+		if (new < 0)
+			return new;
+
+		/*
+		 * If we increase LDO voltage when LDO is enabled we need to
+		 * disable the power-good detection until voltage has reached
+		 * the new level. According to HW colleagues the maximum time
+		 * it takes is 1000us. I assume that on systems with light load
+		 * this might be less - and we could probably use DT to give
+		 * system specific delay value if performance matters.
+		 *
+		 * Well, knowing we use I2C here and can add scheduling delays
+		 * I don't think it is worth the hassle and I just add fixed
+		 * 1ms sleep here (and allow scheduling). If this turns out to
+		 * be a problem we can change it to delay and make the delay
+		 * time configurable.
+		 */
+		if (new > now) {
+			int ldo_offset = rdev->desc->id - BD718XX_LDO1;
+
+			*mask = BD718XX_LDO1_VRMON80 << ldo_offset;
+			ret = regmap_update_bits(rdev->regmap,
+						 BD718XX_REG_MVRFLTMASK2,
+						 *mask, *mask);
+			if (ret) {
+				dev_err(&rdev->dev,
+					"Failed to stop voltage monitoring\n");
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int bd718xx_set_voltage_sel_restricted(struct regulator_dev *rdev,
+						    unsigned int sel)
+{
+	int ret;
+	int mask;
+
+	ret = voltage_change_prepare(rdev, sel, &mask);
+	if (ret)
+		return ret;
+
+	ret = regulator_set_voltage_sel_regmap(rdev, sel);
+	voltage_change_done(rdev, sel, &mask);
+
+	return ret;
+}
+
 static int bd718xx_set_voltage_sel_pickable_restricted(
 		struct regulator_dev *rdev, unsigned int sel)
 {
+	int ret;
+	int mask;
+
+	ret = voltage_change_prepare(rdev, sel, &mask);
+	if (ret)
+		return ret;
+
+	ret = regulator_set_voltage_sel_pickable_regmap(rdev, sel);
+	voltage_change_done(rdev, sel, &mask);
+
+	return ret;
+}
+
+static int bd71837_set_voltage_sel_pickable_restricted(
+		struct regulator_dev *rdev, unsigned int sel)
+{
 	if (regulator_is_enabled_regmap(rdev))
 		return -EBUSY;
 
@@ -85,6 +208,16 @@ static const struct regulator_ops bd718xx_pickable_range_ldo_ops = {
 	.list_voltage = regulator_list_voltage_pickable_linear_range,
 	.set_voltage_sel = bd718xx_set_voltage_sel_pickable_restricted,
 	.get_voltage_sel = regulator_get_voltage_sel_pickable_regmap,
+
+};
+
+static const struct regulator_ops bd71837_pickable_range_ldo_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_pickable_linear_range,
+	.set_voltage_sel = bd71837_set_voltage_sel_pickable_restricted,
+	.get_voltage_sel = regulator_get_voltage_sel_pickable_regmap,
 };
 
 static const struct regulator_ops bd718xx_pickable_range_buck_ops = {
@@ -92,11 +225,30 @@ static const struct regulator_ops bd718xx_pickable_range_buck_ops = {
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
 	.list_voltage = regulator_list_voltage_pickable_linear_range,
-	.set_voltage_sel = bd718xx_set_voltage_sel_pickable_restricted,
+	.set_voltage_sel = regulator_set_voltage_sel_pickable_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_pickable_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+};
+
+static const struct regulator_ops bd71837_pickable_range_buck_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_pickable_linear_range,
+	.set_voltage_sel = bd71837_set_voltage_sel_pickable_restricted,
 	.get_voltage_sel = regulator_get_voltage_sel_pickable_regmap,
 	.set_voltage_time_sel = regulator_set_voltage_time_sel,
 };
 
+static const struct regulator_ops bd71837_ldo_regulator_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_linear_range,
+	.set_voltage_sel = bd71837_set_voltage_sel_restricted,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+};
+
 static const struct regulator_ops bd718xx_ldo_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
@@ -106,6 +258,15 @@ static const struct regulator_ops bd718xx_ldo_regulator_ops = {
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 };
 
+static const struct regulator_ops bd71837_ldo_regulator_nolinear_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_table,
+	.set_voltage_sel = bd71837_set_voltage_sel_restricted,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+};
+
 static const struct regulator_ops bd718xx_ldo_regulator_nolinear_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
@@ -120,7 +281,17 @@ static const struct regulator_ops bd718xx_buck_regulator_ops = {
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
 	.list_voltage = regulator_list_voltage_linear_range,
-	.set_voltage_sel = bd718xx_set_voltage_sel_restricted,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+};
+
+static const struct regulator_ops bd71837_buck_regulator_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_linear_range,
+	.set_voltage_sel = bd71837_set_voltage_sel_restricted,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_time_sel = regulator_set_voltage_time_sel,
 };
@@ -131,6 +302,17 @@ static const struct regulator_ops bd718xx_buck_regulator_nolinear_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
 	.list_voltage = regulator_list_voltage_table,
 	.map_voltage = regulator_map_voltage_ascend,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+};
+
+static const struct regulator_ops bd71837_buck_regulator_nolinear_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_table,
+	.map_voltage = regulator_map_voltage_ascend,
 	.set_voltage_sel = bd718xx_set_voltage_sel_restricted,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_time_sel = regulator_set_voltage_time_sel,
@@ -152,7 +334,7 @@ static const struct regulator_ops bd718xx_dvs_buck_regulator_ops = {
  * BD71847 BUCK1/2
  * 0.70 to 1.30V (10mV step)
  */
-static const struct regulator_linear_range bd718xx_dvs_buck_volts[] = {
+static const struct linear_range bd718xx_dvs_buck_volts[] = {
 	REGULATOR_LINEAR_RANGE(700000, 0x00, 0x3C, 10000),
 	REGULATOR_LINEAR_RANGE(1300000, 0x3D, 0x3F, 0),
 };
@@ -163,7 +345,7 @@ static const struct regulator_linear_range bd718xx_dvs_buck_volts[] = {
  * and
  * 0.675 to 1.325 (range 1)
  */
-static const struct regulator_linear_range bd71837_buck5_volts[] = {
+static const struct linear_range bd71837_buck5_volts[] = {
 	/* Ranges when VOLT_SEL bit is 0 */
 	REGULATOR_LINEAR_RANGE(700000, 0x00, 0x03, 100000),
 	REGULATOR_LINEAR_RANGE(1050000, 0x04, 0x05, 50000),
@@ -185,7 +367,7 @@ static const unsigned int bd71837_buck5_volt_range_sel[] = {
 /*
  * BD71847 BUCK3
  */
-static const struct regulator_linear_range bd71847_buck3_volts[] = {
+static const struct linear_range bd71847_buck3_volts[] = {
 	/* Ranges when VOLT_SEL bits are 00 */
 	REGULATOR_LINEAR_RANGE(700000, 0x00, 0x03, 100000),
 	REGULATOR_LINEAR_RANGE(1050000, 0x04, 0x05, 50000),
@@ -202,7 +384,7 @@ static const unsigned int bd71847_buck3_volt_range_sel[] = {
 	0x0, 0x0, 0x0, 0x40, 0x80, 0x80, 0x80
 };
 
-static const struct regulator_linear_range bd71847_buck4_volts[] = {
+static const struct linear_range bd71847_buck4_volts[] = {
 	REGULATOR_LINEAR_RANGE(3000000, 0x00, 0x03, 100000),
 	REGULATOR_LINEAR_RANGE(2600000, 0x00, 0x03, 100000),
 };
@@ -213,7 +395,7 @@ static const unsigned int bd71847_buck4_volt_range_sel[] = { 0x0, 0x40 };
  * BUCK6
  * 3.0V to 3.3V (step 100mV)
  */
-static const struct regulator_linear_range bd71837_buck6_volts[] = {
+static const struct linear_range bd71837_buck6_volts[] = {
 	REGULATOR_LINEAR_RANGE(3000000, 0x00, 0x03, 100000),
 };
 
@@ -237,7 +419,7 @@ static const unsigned int bd718xx_3rd_nodvs_buck_volts[] = {
  * BUCK8
  * 0.8V to 1.40V (step 10mV)
  */
-static const struct regulator_linear_range bd718xx_4th_nodvs_buck_volts[] = {
+static const struct linear_range bd718xx_4th_nodvs_buck_volts[] = {
 	REGULATOR_LINEAR_RANGE(800000, 0x00, 0x3C, 10000),
 };
 
@@ -245,7 +427,7 @@ static const struct regulator_linear_range bd718xx_4th_nodvs_buck_volts[] = {
  * LDO1
  * 3.0 to 3.3V (100mV step)
  */
-static const struct regulator_linear_range bd718xx_ldo1_volts[] = {
+static const struct linear_range bd718xx_ldo1_volts[] = {
 	REGULATOR_LINEAR_RANGE(3000000, 0x00, 0x03, 100000),
 	REGULATOR_LINEAR_RANGE(1600000, 0x00, 0x03, 100000),
 };
@@ -264,7 +446,7 @@ static const unsigned int ldo_2_volts[] = {
  * LDO3
  * 1.8 to 3.3V (100mV step)
  */
-static const struct regulator_linear_range bd718xx_ldo3_volts[] = {
+static const struct linear_range bd718xx_ldo3_volts[] = {
 	REGULATOR_LINEAR_RANGE(1800000, 0x00, 0x0F, 100000),
 };
 
@@ -272,7 +454,7 @@ static const struct regulator_linear_range bd718xx_ldo3_volts[] = {
  * LDO4
  * 0.9 to 1.8V (100mV step)
  */
-static const struct regulator_linear_range bd718xx_ldo4_volts[] = {
+static const struct linear_range bd718xx_ldo4_volts[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0x00, 0x09, 100000),
 };
 
@@ -280,7 +462,7 @@ static const struct regulator_linear_range bd718xx_ldo4_volts[] = {
  * LDO5 for BD71837
  * 1.8 to 3.3V (100mV step)
  */
-static const struct regulator_linear_range bd71837_ldo5_volts[] = {
+static const struct linear_range bd71837_ldo5_volts[] = {
 	REGULATOR_LINEAR_RANGE(1800000, 0x00, 0x0F, 100000),
 };
 
@@ -288,7 +470,7 @@ static const struct regulator_linear_range bd71837_ldo5_volts[] = {
  * LDO5 for BD71837
  * 1.8 to 3.3V (100mV step)
  */
-static const struct regulator_linear_range bd71847_ldo5_volts[] = {
+static const struct linear_range bd71847_ldo5_volts[] = {
 	REGULATOR_LINEAR_RANGE(1800000, 0x00, 0x0F, 100000),
 	REGULATOR_LINEAR_RANGE(800000, 0x00, 0x0F, 100000),
 };
@@ -299,7 +481,7 @@ static const unsigned int bd71847_ldo5_volt_range_sel[] = { 0x0, 0x20 };
  * LDO6
  * 0.9 to 1.8V (100mV step)
  */
-static const struct regulator_linear_range bd718xx_ldo6_volts[] = {
+static const struct linear_range bd718xx_ldo6_volts[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0x00, 0x09, 100000),
 };
 
@@ -307,7 +489,7 @@ static const struct regulator_linear_range bd718xx_ldo6_volts[] = {
  * LDO7
  * 1.8 to 3.3V (100mV step)
  */
-static const struct regulator_linear_range bd71837_ldo7_volts[] = {
+static const struct linear_range bd71837_ldo7_volts[] = {
 	REGULATOR_LINEAR_RANGE(1800000, 0x00, 0x0F, 100000),
 };
 
@@ -805,7 +987,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("BUCK5"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_BUCK5,
-			.ops = &bd718xx_pickable_range_buck_ops,
+			.ops = &bd71837_pickable_range_buck_ops,
 			.type = REGULATOR_VOLTAGE,
 			.n_voltages = BD71837_BUCK5_VOLTAGE_NUM,
 			.linear_ranges = bd71837_buck5_volts,
@@ -832,7 +1014,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("BUCK6"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_BUCK6,
-			.ops = &bd718xx_buck_regulator_ops,
+			.ops = &bd71837_buck_regulator_ops,
 			.type = REGULATOR_VOLTAGE,
 			.n_voltages = BD71837_BUCK6_VOLTAGE_NUM,
 			.linear_ranges = bd71837_buck6_volts,
@@ -856,7 +1038,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("BUCK7"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_BUCK7,
-			.ops = &bd718xx_buck_regulator_nolinear_ops,
+			.ops = &bd71837_buck_regulator_nolinear_ops,
 			.type = REGULATOR_VOLTAGE,
 			.volt_table = &bd718xx_3rd_nodvs_buck_volts[0],
 			.n_voltages = ARRAY_SIZE(bd718xx_3rd_nodvs_buck_volts),
@@ -878,7 +1060,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("BUCK8"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_BUCK8,
-			.ops = &bd718xx_buck_regulator_ops,
+			.ops = &bd71837_buck_regulator_ops,
 			.type = REGULATOR_VOLTAGE,
 			.n_voltages = BD718XX_4TH_NODVS_BUCK_VOLTAGE_NUM,
 			.linear_ranges = bd718xx_4th_nodvs_buck_volts,
@@ -902,7 +1084,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("LDO1"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_LDO1,
-			.ops = &bd718xx_pickable_range_ldo_ops,
+			.ops = &bd71837_pickable_range_ldo_ops,
 			.type = REGULATOR_VOLTAGE,
 			.n_voltages = BD718XX_LDO1_VOLTAGE_NUM,
 			.linear_ranges = bd718xx_ldo1_volts,
@@ -928,7 +1110,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("LDO2"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_LDO2,
-			.ops = &bd718xx_ldo_regulator_nolinear_ops,
+			.ops = &bd71837_ldo_regulator_nolinear_ops,
 			.type = REGULATOR_VOLTAGE,
 			.volt_table = &ldo_2_volts[0],
 			.vsel_reg = BD718XX_REG_LDO2_VOLT,
@@ -950,7 +1132,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("LDO3"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_LDO3,
-			.ops = &bd718xx_ldo_regulator_ops,
+			.ops = &bd71837_ldo_regulator_ops,
 			.type = REGULATOR_VOLTAGE,
 			.n_voltages = BD718XX_LDO3_VOLTAGE_NUM,
 			.linear_ranges = bd718xx_ldo3_volts,
@@ -973,7 +1155,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("LDO4"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_LDO4,
-			.ops = &bd718xx_ldo_regulator_ops,
+			.ops = &bd71837_ldo_regulator_ops,
 			.type = REGULATOR_VOLTAGE,
 			.n_voltages = BD718XX_LDO4_VOLTAGE_NUM,
 			.linear_ranges = bd718xx_ldo4_volts,
@@ -996,7 +1178,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("LDO5"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_LDO5,
-			.ops = &bd718xx_ldo_regulator_ops,
+			.ops = &bd71837_ldo_regulator_ops,
 			.type = REGULATOR_VOLTAGE,
 			.n_voltages = BD71837_LDO5_VOLTAGE_NUM,
 			.linear_ranges = bd71837_ldo5_volts,
@@ -1023,7 +1205,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("LDO6"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_LDO6,
-			.ops = &bd718xx_ldo_regulator_ops,
+			.ops = &bd71837_ldo_regulator_ops,
 			.type = REGULATOR_VOLTAGE,
 			.n_voltages = BD718XX_LDO6_VOLTAGE_NUM,
 			.linear_ranges = bd718xx_ldo6_volts,
@@ -1050,7 +1232,7 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.of_match = of_match_ptr("LDO7"),
 			.regulators_node = of_match_ptr("regulators"),
 			.id = BD718XX_LDO7,
-			.ops = &bd718xx_ldo_regulator_ops,
+			.ops = &bd71837_ldo_regulator_ops,
 			.type = REGULATOR_VOLTAGE,
 			.n_voltages = BD71837_LDO7_VOLTAGE_NUM,
 			.linear_ranges = bd71837_ldo7_volts,
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index c340505150b6..03154f5b939f 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -3642,36 +3642,19 @@ finish:
 	return done;
 }
 
-static int regulator_balance_voltage(struct regulator_dev *rdev,
-				     suspend_state_t state)
+int regulator_do_balance_voltage(struct regulator_dev *rdev,
+				 suspend_state_t state, bool skip_coupled)
 {
 	struct regulator_dev **c_rdevs;
 	struct regulator_dev *best_rdev;
 	struct coupling_desc *c_desc = &rdev->coupling_desc;
-	struct regulator_coupler *coupler = c_desc->coupler;
 	int i, ret, n_coupled, best_min_uV, best_max_uV, best_c_rdev;
 	unsigned int delta, best_delta;
 	unsigned long c_rdev_done = 0;
 	bool best_c_rdev_done;
 
 	c_rdevs = c_desc->coupled_rdevs;
-	n_coupled = c_desc->n_coupled;
-
-	/*
-	 * If system is in a state other than PM_SUSPEND_ON, don't check
-	 * other coupled regulators.
-	 */
-	if (state != PM_SUSPEND_ON)
-		n_coupled = 1;
-
-	if (c_desc->n_resolved < n_coupled) {
-		rdev_err(rdev, "Not all coupled regulators registered\n");
-		return -EPERM;
-	}
-
-	/* Invoke custom balancer for customized couplers */
-	if (coupler && coupler->balance_voltage)
-		return coupler->balance_voltage(coupler, rdev, state);
+	n_coupled = skip_coupled ? 1 : c_desc->n_coupled;
 
 	/*
 	 * Find the best possible voltage change on each loop. Leave the loop
@@ -3742,6 +3725,32 @@ out:
 	return ret;
 }
 
+static int regulator_balance_voltage(struct regulator_dev *rdev,
+				     suspend_state_t state)
+{
+	struct coupling_desc *c_desc = &rdev->coupling_desc;
+	struct regulator_coupler *coupler = c_desc->coupler;
+	bool skip_coupled = false;
+
+	/*
+	 * If system is in a state other than PM_SUSPEND_ON, don't check
+	 * other coupled regulators.
+	 */
+	if (state != PM_SUSPEND_ON)
+		skip_coupled = true;
+
+	if (c_desc->n_resolved < c_desc->n_coupled) {
+		rdev_err(rdev, "Not all coupled regulators registered\n");
+		return -EPERM;
+	}
+
+	/* Invoke custom balancer for customized couplers */
+	if (coupler && coupler->balance_voltage)
+		return coupler->balance_voltage(coupler, rdev, state);
+
+	return regulator_do_balance_voltage(rdev, state, skip_coupled);
+}
+
 /**
  * regulator_set_voltage - set regulator output voltage
  * @regulator: regulator source
@@ -4312,6 +4321,7 @@ EXPORT_SYMBOL_GPL(regulator_set_load);
 int regulator_allow_bypass(struct regulator *regulator, bool enable)
 {
 	struct regulator_dev *rdev = regulator->rdev;
+	const char *name = rdev_get_name(rdev);
 	int ret = 0;
 
 	if (!rdev->desc->ops->set_bypass)
@@ -4326,18 +4336,26 @@ int regulator_allow_bypass(struct regulator *regulator, bool enable)
 		rdev->bypass_count++;
 
 		if (rdev->bypass_count == rdev->open_count) {
+			trace_regulator_bypass_enable(name);
+
 			ret = rdev->desc->ops->set_bypass(rdev, enable);
 			if (ret != 0)
 				rdev->bypass_count--;
+			else
+				trace_regulator_bypass_enable_complete(name);
 		}
 
 	} else if (!enable && regulator->bypass) {
 		rdev->bypass_count--;
 
 		if (rdev->bypass_count != rdev->open_count) {
+			trace_regulator_bypass_disable(name);
+
 			ret = rdev->desc->ops->set_bypass(rdev, enable);
 			if (ret != 0)
 				rdev->bypass_count++;
+			else
+				trace_regulator_bypass_disable_complete(name);
 		}
 	}
 
@@ -5496,6 +5514,7 @@ static void regulator_summary_show_subtree(struct seq_file *s,
 		seq_printf(s, "%*s%-*s ",
 			   (level + 1) * 3 + 1, "",
 			   30 - (level + 1) * 3,
+			   consumer->supply_name ? consumer->supply_name :
 			   consumer->dev ? dev_name(consumer->dev) : "deviceless");
 
 		switch (rdev->desc->type) {
@@ -5754,10 +5773,6 @@ static DECLARE_DELAYED_WORK(regulator_init_complete_work,
 
 static int __init regulator_init_complete(void)
 {
-	int delay = driver_deferred_probe_timeout;
-
-	if (delay < 0)
-		delay = 0;
 	/*
 	 * Since DT doesn't provide an idiomatic mechanism for
 	 * enabling full constraints and since it's much more natural
@@ -5768,17 +5783,18 @@ static int __init regulator_init_complete(void)
 		has_full_constraints = true;
 
 	/*
-	 * If driver_deferred_probe_timeout is set, we punt
-	 * completion for that many seconds since systems like
-	 * distros will load many drivers from userspace so consumers
-	 * might not always be ready yet, this is particularly an
-	 * issue with laptops where this might bounce the display off
-	 * then on.  Ideally we'd get a notification from userspace
-	 * when this happens but we don't so just wait a bit and hope
-	 * we waited long enough.  It'd be better if we'd only do
-	 * this on systems that need it.
+	 * We punt completion for an arbitrary amount of time since
+	 * systems like distros will load many drivers from userspace
+	 * so consumers might not always be ready yet, this is
+	 * particularly an issue with laptops where this might bounce
+	 * the display off then on.  Ideally we'd get a notification
+	 * from userspace when this happens but we don't so just wait
+	 * a bit and hope we waited long enough.  It'd be better if
+	 * we'd only do this on systems that need it, and a kernel
+	 * command line option might be useful.
 	 */
-	schedule_delayed_work(&regulator_init_complete_work, delay * HZ);
+	schedule_delayed_work(&regulator_init_complete_work,
+			      msecs_to_jiffies(30000));
 
 	return 0;
 }
diff --git a/drivers/regulator/da903x.c b/drivers/regulator/da903x.c
index 5493c3a86426..770e694824ac 100644
--- a/drivers/regulator/da903x.c
+++ b/drivers/regulator/da903x.c
@@ -248,7 +248,7 @@ static int da9034_set_dvc_voltage_sel(struct regulator_dev *rdev,
 	return ret;
 }
 
-static const struct regulator_linear_range da9034_ldo12_ranges[] = {
+static const struct linear_range da9034_ldo12_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1700000, 0, 7, 50000),
 	REGULATOR_LINEAR_RANGE(2700000, 8, 15, 50000),
 };
diff --git a/drivers/regulator/db8500-prcmu.c b/drivers/regulator/db8500-prcmu.c
index 88a2dcb9fe8a..0ce6ec4933af 100644
--- a/drivers/regulator/db8500-prcmu.c
+++ b/drivers/regulator/db8500-prcmu.c
@@ -181,7 +181,7 @@ static int db8500_regulator_switch_disable(struct regulator_dev *rdev)
 		goto out;
 	}
 
-	info->is_enabled = 0;
+	info->is_enabled = false;
 out:
 	return ret;
 }
diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c
index bb16c465426e..e970e9d2f8be 100644
--- a/drivers/regulator/helpers.c
+++ b/drivers/regulator/helpers.c
@@ -131,10 +131,11 @@ int regulator_get_voltage_sel_pickable_regmap(struct regulator_dev *rdev)
 	unsigned int r_val;
 	int range;
 	unsigned int val;
-	int ret, i;
-	unsigned int voltages_in_range = 0;
+	int ret;
+	unsigned int voltages = 0;
+	const struct linear_range *r = rdev->desc->linear_ranges;
 
-	if (!rdev->desc->linear_ranges)
+	if (!r)
 		return -EINVAL;
 
 	ret = regmap_read(rdev->regmap, rdev->desc->vsel_reg, &val);
@@ -152,11 +153,9 @@ int regulator_get_voltage_sel_pickable_regmap(struct regulator_dev *rdev)
 	if (range < 0)
 		return -EINVAL;
 
-	for (i = 0; i < range; i++)
-		voltages_in_range += (rdev->desc->linear_ranges[i].max_sel -
-				     rdev->desc->linear_ranges[i].min_sel) + 1;
+	voltages = linear_range_values_in_range_array(r, range);
 
-	return val + voltages_in_range;
+	return val + voltages;
 }
 EXPORT_SYMBOL_GPL(regulator_get_voltage_sel_pickable_regmap);
 
@@ -179,8 +178,11 @@ int regulator_set_voltage_sel_pickable_regmap(struct regulator_dev *rdev,
 	unsigned int voltages_in_range = 0;
 
 	for (i = 0; i < rdev->desc->n_linear_ranges; i++) {
-		voltages_in_range = (rdev->desc->linear_ranges[i].max_sel -
-				     rdev->desc->linear_ranges[i].min_sel) + 1;
+		const struct linear_range *r;
+
+		r = &rdev->desc->linear_ranges[i];
+		voltages_in_range = linear_range_values_in_range(r);
+
 		if (sel < voltages_in_range)
 			break;
 		sel -= voltages_in_range;
@@ -405,8 +407,10 @@ EXPORT_SYMBOL_GPL(regulator_map_voltage_linear);
 int regulator_map_voltage_linear_range(struct regulator_dev *rdev,
 				       int min_uV, int max_uV)
 {
-	const struct regulator_linear_range *range;
+	const struct linear_range *range;
 	int ret = -EINVAL;
+	unsigned int sel;
+	bool found;
 	int voltage, i;
 
 	if (!rdev->desc->n_linear_ranges) {
@@ -415,35 +419,19 @@ int regulator_map_voltage_linear_range(struct regulator_dev *rdev,
 	}
 
 	for (i = 0; i < rdev->desc->n_linear_ranges; i++) {
-		int linear_max_uV;
-
 		range = &rdev->desc->linear_ranges[i];
-		linear_max_uV = range->min_uV +
-			(range->max_sel - range->min_sel) * range->uV_step;
 
-		if (!(min_uV <= linear_max_uV && max_uV >= range->min_uV))
+		ret = linear_range_get_selector_high(range, min_uV, &sel,
+						     &found);
+		if (ret)
 			continue;
-
-		if (min_uV <= range->min_uV)
-			min_uV = range->min_uV;
-
-		/* range->uV_step == 0 means fixed voltage range */
-		if (range->uV_step == 0) {
-			ret = 0;
-		} else {
-			ret = DIV_ROUND_UP(min_uV - range->min_uV,
-					   range->uV_step);
-			if (ret < 0)
-				return ret;
-		}
-
-		ret += range->min_sel;
+		ret = sel;
 
 		/*
 		 * Map back into a voltage to verify we're still in bounds.
 		 * If we are not, then continue checking rest of the ranges.
 		 */
-		voltage = rdev->desc->ops->list_voltage(rdev, ret);
+		voltage = rdev->desc->ops->list_voltage(rdev, sel);
 		if (voltage >= min_uV && voltage <= max_uV)
 			break;
 	}
@@ -468,7 +456,7 @@ EXPORT_SYMBOL_GPL(regulator_map_voltage_linear_range);
 int regulator_map_voltage_pickable_linear_range(struct regulator_dev *rdev,
 						int min_uV, int max_uV)
 {
-	const struct regulator_linear_range *range;
+	const struct linear_range *range;
 	int ret = -EINVAL;
 	int voltage, i;
 	unsigned int selector = 0;
@@ -480,30 +468,25 @@ int regulator_map_voltage_pickable_linear_range(struct regulator_dev *rdev,
 
 	for (i = 0; i < rdev->desc->n_linear_ranges; i++) {
 		int linear_max_uV;
+		bool found;
+		unsigned int sel;
 
 		range = &rdev->desc->linear_ranges[i];
-		linear_max_uV = range->min_uV +
-			(range->max_sel - range->min_sel) * range->uV_step;
+		linear_max_uV = linear_range_get_max_value(range);
 
-		if (!(min_uV <= linear_max_uV && max_uV >= range->min_uV)) {
-			selector += (range->max_sel - range->min_sel + 1);
+		if (!(min_uV <= linear_max_uV && max_uV >= range->min)) {
+			selector += linear_range_values_in_range(range);
 			continue;
 		}
 
-		if (min_uV <= range->min_uV)
-			min_uV = range->min_uV;
-
-		/* range->uV_step == 0 means fixed voltage range */
-		if (range->uV_step == 0) {
-			ret = 0;
-		} else {
-			ret = DIV_ROUND_UP(min_uV - range->min_uV,
-					   range->uV_step);
-			if (ret < 0)
-				return ret;
+		ret = linear_range_get_selector_high(range, min_uV, &sel,
+						     &found);
+		if (ret) {
+			selector += linear_range_values_in_range(range);
+			continue;
 		}
 
-		ret += selector;
+		ret = selector + sel;
 
 		voltage = rdev->desc->ops->list_voltage(rdev, ret);
 
@@ -513,7 +496,7 @@ int regulator_map_voltage_pickable_linear_range(struct regulator_dev *rdev,
 		 * exit but retry until we have checked all ranges.
 		 */
 		if (voltage < min_uV || voltage > max_uV)
-			selector += (range->max_sel - range->min_sel + 1);
+			selector += linear_range_values_in_range(range);
 		else
 			break;
 	}
@@ -561,7 +544,7 @@ EXPORT_SYMBOL_GPL(regulator_list_voltage_linear);
 int regulator_list_voltage_pickable_linear_range(struct regulator_dev *rdev,
 						 unsigned int selector)
 {
-	const struct regulator_linear_range *range;
+	const struct linear_range *range;
 	int i;
 	unsigned int all_sels = 0;
 
@@ -571,18 +554,28 @@ int regulator_list_voltage_pickable_linear_range(struct regulator_dev *rdev,
 	}
 
 	for (i = 0; i < rdev->desc->n_linear_ranges; i++) {
-		unsigned int sels_in_range;
+		unsigned int sel_indexes;
 
 		range = &rdev->desc->linear_ranges[i];
 
-		sels_in_range = range->max_sel - range->min_sel;
+		sel_indexes = linear_range_values_in_range(range) - 1;
 
-		if (all_sels + sels_in_range >= selector) {
+		if (all_sels + sel_indexes >= selector) {
 			selector -= all_sels;
-			return range->min_uV + (range->uV_step * selector);
+			/*
+			 * As we see here, pickable ranges work only as
+			 * long as the first selector for each pickable
+			 * range is 0, and the each subsequent range for
+			 * this 'pick' follow immediately at next unused
+			 * selector (Eg. there is no gaps between ranges).
+			 * I think this is fine but it probably should be
+			 * documented. OTOH, whole pickable range stuff
+			 * might benefit from some documentation
+			 */
+			return range->min + (range->step * selector);
 		}
 
-		all_sels += (sels_in_range + 1);
+		all_sels += (sel_indexes + 1);
 	}
 
 	return -EINVAL;
@@ -604,27 +597,18 @@ EXPORT_SYMBOL_GPL(regulator_list_voltage_pickable_linear_range);
 int regulator_desc_list_voltage_linear_range(const struct regulator_desc *desc,
 					     unsigned int selector)
 {
-	const struct regulator_linear_range *range;
-	int i;
-
-	if (!desc->n_linear_ranges) {
-		BUG_ON(!desc->n_linear_ranges);
-		return -EINVAL;
-	}
-
-	for (i = 0; i < desc->n_linear_ranges; i++) {
-		range = &desc->linear_ranges[i];
-
-		if (!(selector >= range->min_sel &&
-		      selector <= range->max_sel))
-			continue;
+	unsigned int val;
+	int ret;
 
-		selector -= range->min_sel;
+	BUG_ON(!desc->n_linear_ranges);
 
-		return range->min_uV + (range->uV_step * selector);
-	}
+	ret = linear_range_get_value_array(desc->linear_ranges,
+					   desc->n_linear_ranges, selector,
+					   &val);
+	if (ret)
+		return ret;
 
-	return -EINVAL;
+	return val;
 }
 EXPORT_SYMBOL_GPL(regulator_desc_list_voltage_linear_range);
 
diff --git a/drivers/regulator/hi6421-regulator.c b/drivers/regulator/hi6421-regulator.c
index 5ac3d7c29725..66219d8dfc1a 100644
--- a/drivers/regulator/hi6421-regulator.c
+++ b/drivers/regulator/hi6421-regulator.c
@@ -87,7 +87,7 @@ static const unsigned int ldo_8_voltages[] = {
 };
 
 /* Ranges are sorted in ascending order. */
-static const struct regulator_linear_range ldo_audio_volt_range[] = {
+static const struct linear_range ldo_audio_volt_range[] = {
 	REGULATOR_LINEAR_RANGE(2800000, 0, 3, 50000),
 	REGULATOR_LINEAR_RANGE(3000000, 4, 7, 100000),
 };
@@ -195,7 +195,7 @@ static const struct regulator_ops hi6421_buck345_ops;
  * _id - LDO id name string
  * _match - of match name string
  * n_volt - number of votages available
- * volt_ranges - array of regulator_linear_range
+ * volt_ranges - array of linear_range
  * vstep - voltage increase in each linear step in uV
  * vreg - voltage select register
  * vmask - voltage select mask
diff --git a/drivers/regulator/lochnagar-regulator.c b/drivers/regulator/lochnagar-regulator.c
index 9b05e03ba830..5ea3e4141684 100644
--- a/drivers/regulator/lochnagar-regulator.c
+++ b/drivers/regulator/lochnagar-regulator.c
@@ -36,7 +36,7 @@ static const struct regulator_ops lochnagar_micvdd_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 };
 
-static const struct regulator_linear_range lochnagar_micvdd_ranges[] = {
+static const struct linear_range lochnagar_micvdd_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1000000, 0,    0xC, 50000),
 	REGULATOR_LINEAR_RANGE(1700000, 0xD, 0x1F, 100000),
 };
@@ -97,7 +97,7 @@ static const struct regulator_ops lochnagar_vddcore_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 };
 
-static const struct regulator_linear_range lochnagar_vddcore_ranges[] = {
+static const struct linear_range lochnagar_vddcore_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0x8, 0x41, 12500),
 };
 
diff --git a/drivers/regulator/lp873x-regulator.c b/drivers/regulator/lp873x-regulator.c
index b55de293ca7a..fe049b67e7d5 100644
--- a/drivers/regulator/lp873x-regulator.c
+++ b/drivers/regulator/lp873x-regulator.c
@@ -54,14 +54,14 @@ struct lp873x_regulator {
 
 static const struct lp873x_regulator regulators[];
 
-static const struct regulator_linear_range buck0_buck1_ranges[] = {
+static const struct linear_range buck0_buck1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(0, 0x0, 0x13, 0),
 	REGULATOR_LINEAR_RANGE(700000, 0x14, 0x17, 10000),
 	REGULATOR_LINEAR_RANGE(735000, 0x18, 0x9d, 5000),
 	REGULATOR_LINEAR_RANGE(1420000, 0x9e, 0xff, 20000),
 };
 
-static const struct regulator_linear_range ldo0_ldo1_ranges[] = {
+static const struct linear_range ldo0_ldo1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(800000, 0x0, 0x19, 100000),
 };
 
diff --git a/drivers/regulator/lp87565-regulator.c b/drivers/regulator/lp87565-regulator.c
index 4ae12ac1f4c6..5d525dacf959 100644
--- a/drivers/regulator/lp87565-regulator.c
+++ b/drivers/regulator/lp87565-regulator.c
@@ -46,7 +46,7 @@ struct lp87565_regulator {
 
 static const struct lp87565_regulator regulators[];
 
-static const struct regulator_linear_range buck0_1_2_3_ranges[] = {
+static const struct linear_range buck0_1_2_3_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0xA, 0x17, 10000),
 	REGULATOR_LINEAR_RANGE(735000, 0x18, 0x9d, 5000),
 	REGULATOR_LINEAR_RANGE(1420000, 0x9e, 0xff, 20000),
diff --git a/drivers/regulator/lp8788-buck.c b/drivers/regulator/lp8788-buck.c
index 222502a29658..74b7b496b12d 100644
--- a/drivers/regulator/lp8788-buck.c
+++ b/drivers/regulator/lp8788-buck.c
@@ -92,7 +92,7 @@ struct lp8788_buck {
 };
 
 /* BUCK 1 ~ 4 voltage ranges */
-static const struct regulator_linear_range buck_volt_ranges[] = {
+static const struct linear_range buck_volt_ranges[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0, 0, 0),
 	REGULATOR_LINEAR_RANGE(800000, 1, 25, 50000),
 };
diff --git a/drivers/regulator/max77650-regulator.c b/drivers/regulator/max77650-regulator.c
index ac89a412f665..ca08f94a368d 100644
--- a/drivers/regulator/max77650-regulator.c
+++ b/drivers/regulator/max77650-regulator.c
@@ -49,7 +49,7 @@ static const unsigned int max77651_sbb1_volt_range_sel[] = {
 	0x0, 0x1, 0x2, 0x3
 };
 
-static const struct regulator_linear_range max77651_sbb1_volt_ranges[] = {
+static const struct linear_range max77651_sbb1_volt_ranges[] = {
 	/* range index 0 */
 	REGULATOR_LINEAR_RANGE(2400000, 0x00, 0x0f, 50000),
 	/* range index 1 */
diff --git a/drivers/regulator/max77826-regulator.c b/drivers/regulator/max77826-regulator.c
new file mode 100644
index 000000000000..502ab6afc814
--- /dev/null
+++ b/drivers/regulator/max77826-regulator.c
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+//
+// max77826-regulator.c  - regulator driver for Maxim MAX77826
+//
+// Author: Iskren Chernev <iskren.chernev@gmail.com>
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/of_regulator.h>
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+
+enum max77826_registers {
+	MAX77826_REG_INT_SRC = 0x00,
+	MAX77826_REG_SYS_INT,
+	MAX77826_REG_INT1,
+	MAX77826_REG_INT2,
+	MAX77826_REG_BB_INT,
+	MAX77826_REG_INT_SRC_M,
+	MAX77826_REG_TOPSYS_INT_M,
+	MAX77826_REG_INT1_M,
+	MAX77826_REG_INT2_M,
+	MAX77826_REG_BB_INT_M,
+	MAX77826_REG_TOPSYS_STAT,
+	MAX77826_REG_STAT1,
+	MAX77826_REG_STAT2,
+	MAX77826_REG_BB_STAT,
+	/* 0x0E - 0x0F: Reserved */
+	MAX77826_REG_LDO_OPMD1 = 0x10,
+	MAX77826_REG_LDO_OPMD2,
+	MAX77826_REG_LDO_OPMD3,
+	MAX77826_REG_LDO_OPMD4,
+	MAX77826_REG_B_BB_OPMD,
+	/* 0x15 - 0x1F: Reserved */
+	MAX77826_REG_LDO1_CFG = 0x20,
+	MAX77826_REG_LDO2_CFG,
+	MAX77826_REG_LDO3_CFG,
+	MAX77826_REG_LDO4_CFG,
+	MAX77826_REG_LDO5_CFG,
+	MAX77826_REG_LDO6_CFG,
+	MAX77826_REG_LDO7_CFG,
+	MAX77826_REG_LDO8_CFG,
+	MAX77826_REG_LDO9_CFG,
+	MAX77826_REG_LDO10_CFG,
+	MAX77826_REG_LDO11_CFG,
+	MAX77826_REG_LDO12_CFG,
+	MAX77826_REG_LDO13_CFG,
+	MAX77826_REG_LDO14_CFG,
+	MAX77826_REG_LDO15_CFG,
+	/* 0x2F: Reserved */
+	MAX77826_REG_BUCK_CFG = 0x30,
+	MAX77826_REG_BUCK_VOUT,
+	MAX77826_REG_BB_CFG,
+	MAX77826_REG_BB_VOUT,
+	/* 0x34 - 0x3F: Reserved */
+	MAX77826_REG_BUCK_SS_FREQ = 0x40,
+	MAX77826_REG_UVLO_FALL,
+	/* 0x42 - 0xCE: Reserved */
+	MAX77826_REG_DEVICE_ID = 0xCF,
+};
+
+enum max77826_regulators {
+	MAX77826_LDO1 = 0,
+	MAX77826_LDO2,
+	MAX77826_LDO3,
+	MAX77826_LDO4,
+	MAX77826_LDO5,
+	MAX77826_LDO6,
+	MAX77826_LDO7,
+	MAX77826_LDO8,
+	MAX77826_LDO9,
+	MAX77826_LDO10,
+	MAX77826_LDO11,
+	MAX77826_LDO12,
+	MAX77826_LDO13,
+	MAX77826_LDO14,
+	MAX77826_LDO15,
+	MAX77826_BUCK,
+	MAX77826_BUCKBOOST,
+	MAX77826_MAX_REGULATORS,
+};
+
+#define MAX77826_MASK_LDO		0x7f
+#define MAX77826_MASK_BUCK		0xff
+#define MAX77826_MASK_BUCKBOOST		0x7f
+#define MAX77826_BUCK_RAMP_DELAY	12500
+
+/* values in mV */
+/* for LDO1-3 */
+#define MAX77826_NMOS_LDO_VOLT_MIN	600000
+#define MAX77826_NMOS_LDO_VOLT_MAX	2187500
+#define MAX77826_NMOS_LDO_VOLT_STEP	12500
+
+/* for LDO4-15 */
+#define MAX77826_PMOS_LDO_VOLT_MIN	800000
+#define MAX77826_PMOS_LDO_VOLT_MAX	3975000
+#define MAX77826_PMOS_LDO_VOLT_STEP	25000
+
+/* for BUCK */
+#define MAX77826_BUCK_VOLT_MIN		500000
+#define MAX77826_BUCK_VOLT_MAX		1800000
+#define MAX77826_BUCK_VOLT_STEP		6250
+
+/* for BUCKBOOST */
+#define MAX77826_BUCKBOOST_VOLT_MIN	2600000
+#define MAX77826_BUCKBOOST_VOLT_MAX	4187500
+#define MAX77826_BUCKBOOST_VOLT_STEP	12500
+#define MAX77826_VOLT_RANGE(_type)					\
+	((MAX77826_ ## _type ## _VOLT_MAX -				\
+	  MAX77826_ ## _type ## _VOLT_MIN) /				\
+	 MAX77826_ ## _type ## _VOLT_STEP + 1)
+
+#define MAX77826_LDO(_id, _type)					\
+	[MAX77826_LDO ## _id] = {					\
+		.id = MAX77826_LDO ## _id,				\
+		.name = "LDO"#_id,					\
+		.of_match = of_match_ptr("LDO"#_id),			\
+		.regulators_node = "regulators",			\
+		.ops = &max77826_most_ops,				\
+		.min_uV = MAX77826_ ## _type ## _LDO_VOLT_MIN,		\
+		.uV_step = MAX77826_ ## _type ## _LDO_VOLT_STEP,	\
+		.n_voltages = MAX77826_VOLT_RANGE(_type ## _LDO),	\
+		.enable_reg = MAX77826_REG_LDO_OPMD1 + (_id - 1) / 4,	\
+		.enable_mask = BIT(((_id - 1) % 4) * 2 + 1),		\
+		.vsel_reg = MAX77826_REG_LDO1_CFG + (_id - 1),		\
+		.vsel_mask = MAX77826_MASK_LDO,				\
+		.owner = THIS_MODULE,					\
+	}
+
+#define MAX77826_BUCK(_idx, _id, _ops)					\
+	[MAX77826_ ## _id] = {						\
+		.id = MAX77826_ ## _id,					\
+		.name = #_id,						\
+		.of_match = of_match_ptr(#_id),				\
+		.regulators_node = "regulators",			\
+		.ops = &_ops,						\
+		.min_uV =  MAX77826_ ## _id ## _VOLT_MIN,		\
+		.uV_step = MAX77826_ ## _id ## _VOLT_STEP,		\
+		.n_voltages = MAX77826_VOLT_RANGE(_id),			\
+		.enable_reg = MAX77826_REG_B_BB_OPMD,			\
+		.enable_mask = BIT(_idx * 2 + 1),			\
+		.vsel_reg = MAX77826_REG_BUCK_VOUT + _idx * 2,		\
+		.vsel_mask = MAX77826_MASK_ ## _id,			\
+		.owner = THIS_MODULE,					\
+	}
+
+
+
+struct max77826_regulator_info {
+	struct regmap *regmap;
+	struct regulator_desc *rdesc;
+};
+
+static const struct regmap_config max77826_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = MAX77826_REG_DEVICE_ID,
+};
+
+static int max77826_set_voltage_time_sel(struct regulator_dev *,
+				unsigned int old_selector,
+				unsigned int new_selector);
+
+static const struct regulator_ops max77826_most_ops = {
+	.enable			= regulator_enable_regmap,
+	.disable		= regulator_disable_regmap,
+	.is_enabled		= regulator_is_enabled_regmap,
+	.list_voltage		= regulator_list_voltage_linear,
+	.map_voltage		= regulator_map_voltage_linear,
+	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
+	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
+};
+
+static const struct regulator_ops max77826_buck_ops = {
+	.enable			= regulator_enable_regmap,
+	.disable		= regulator_disable_regmap,
+	.is_enabled		= regulator_is_enabled_regmap,
+	.list_voltage		= regulator_list_voltage_linear,
+	.map_voltage		= regulator_map_voltage_linear,
+	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
+	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
+	.set_voltage_time_sel	= max77826_set_voltage_time_sel,
+};
+
+static struct regulator_desc max77826_regulators_desc[] = {
+	MAX77826_LDO(1, NMOS),
+	MAX77826_LDO(2, NMOS),
+	MAX77826_LDO(3, NMOS),
+	MAX77826_LDO(4, PMOS),
+	MAX77826_LDO(5, PMOS),
+	MAX77826_LDO(6, PMOS),
+	MAX77826_LDO(7, PMOS),
+	MAX77826_LDO(8, PMOS),
+	MAX77826_LDO(9, PMOS),
+	MAX77826_LDO(10, PMOS),
+	MAX77826_LDO(11, PMOS),
+	MAX77826_LDO(12, PMOS),
+	MAX77826_LDO(13, PMOS),
+	MAX77826_LDO(14, PMOS),
+	MAX77826_LDO(15, PMOS),
+	MAX77826_BUCK(0, BUCK, max77826_buck_ops),
+	MAX77826_BUCK(1, BUCKBOOST, max77826_most_ops),
+};
+
+static int max77826_set_voltage_time_sel(struct regulator_dev *rdev,
+				unsigned int old_selector,
+				unsigned int new_selector)
+{
+	if (new_selector > old_selector) {
+		return DIV_ROUND_UP(MAX77826_BUCK_VOLT_STEP *
+				(new_selector - old_selector),
+				MAX77826_BUCK_RAMP_DELAY);
+	}
+
+	return 0;
+}
+
+static int max77826_read_device_id(struct regmap *regmap, struct device *dev)
+{
+	unsigned int device_id;
+	int res;
+
+	res = regmap_read(regmap, MAX77826_REG_DEVICE_ID, &device_id);
+	if (!res)
+		dev_dbg(dev, "DEVICE_ID: 0x%x\n", device_id);
+
+	return res;
+}
+
+static int max77826_i2c_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct max77826_regulator_info *info;
+	struct regulator_config config = {};
+	struct regulator_dev *rdev;
+	struct regmap *regmap;
+	int i;
+
+	info = devm_kzalloc(dev, sizeof(struct max77826_regulator_info),
+				GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->rdesc = max77826_regulators_desc;
+	regmap = devm_regmap_init_i2c(client, &max77826_regmap_config);
+	if (IS_ERR(regmap)) {
+		dev_err(dev, "Failed to allocate regmap!\n");
+		return PTR_ERR(regmap);
+	}
+
+	info->regmap = regmap;
+	i2c_set_clientdata(client, info);
+
+	config.dev = dev;
+	config.regmap = regmap;
+	config.driver_data = info;
+
+	for (i = 0; i < MAX77826_MAX_REGULATORS; i++) {
+		rdev = devm_regulator_register(dev,
+					       &max77826_regulators_desc[i],
+					       &config);
+		if (IS_ERR(rdev)) {
+			dev_err(dev, "Failed to register regulator!\n");
+			return PTR_ERR(rdev);
+		}
+	}
+
+	return max77826_read_device_id(regmap, dev);
+}
+
+static const struct of_device_id max77826_of_match[] = {
+	{ .compatible = "maxim,max77826" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, max77826_of_match);
+
+static const struct i2c_device_id max77826_id[] = {
+	{ "max77826-regulator" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, max77826_id);
+
+static struct i2c_driver max77826_regulator_driver = {
+	.driver = {
+		.name = "max77826",
+		.of_match_table = of_match_ptr(max77826_of_match),
+	},
+	.probe_new = max77826_i2c_probe,
+	.id_table = max77826_id,
+};
+module_i2c_driver(max77826_regulator_driver);
+
+MODULE_AUTHOR("Iskren Chernev <iskren.chernev@gmail.com>");
+MODULE_DESCRIPTION("MAX77826 PMIC regulator driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c
index 60599c3bb845..340413bba0c5 100644
--- a/drivers/regulator/max8998.c
+++ b/drivers/regulator/max8998.c
@@ -33,6 +33,10 @@ struct max8998_data {
 	unsigned int		buck2_idx;
 };
 
+static const unsigned int charger_current_table[] = {
+	90000, 380000, 475000, 550000, 570000, 600000, 700000, 800000,
+};
+
 static int max8998_get_enable_register(struct regulator_dev *rdev,
 					int *reg, int *shift)
 {
@@ -63,6 +67,10 @@ static int max8998_get_enable_register(struct regulator_dev *rdev,
 		*reg = MAX8998_REG_CHGR2;
 		*shift = 7 - (ldo - MAX8998_ESAFEOUT1);
 		break;
+	case MAX8998_CHARGER:
+		*reg = MAX8998_REG_CHGR2;
+		*shift = 0;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -88,6 +96,11 @@ static int max8998_ldo_is_enabled(struct regulator_dev *rdev)
 	return val & (1 << shift);
 }
 
+static int max8998_ldo_is_enabled_inverted(struct regulator_dev *rdev)
+{
+	return (!max8998_ldo_is_enabled(rdev));
+}
+
 static int max8998_ldo_enable(struct regulator_dev *rdev)
 {
 	struct max8998_data *max8998 = rdev_get_drvdata(rdev);
@@ -358,6 +371,74 @@ static int max8998_set_voltage_buck_time_sel(struct regulator_dev *rdev,
 	return 0;
 }
 
+static int max8998_set_current_limit(struct regulator_dev *rdev,
+				     int min_uA, int max_uA)
+{
+	struct max8998_data *max8998 = rdev_get_drvdata(rdev);
+	struct i2c_client *i2c = max8998->iodev->i2c;
+	unsigned int n_currents = rdev->desc->n_current_limits;
+	int i, sel = -1;
+
+	if (n_currents == 0)
+		return -EINVAL;
+
+	if (rdev->desc->curr_table) {
+		const unsigned int *curr_table = rdev->desc->curr_table;
+		bool ascend = curr_table[n_currents - 1] > curr_table[0];
+
+		/* search for closest to maximum */
+		if (ascend) {
+			for (i = n_currents - 1; i >= 0; i--) {
+				if (min_uA <= curr_table[i] &&
+				    curr_table[i] <= max_uA) {
+					sel = i;
+					break;
+				}
+			}
+		} else {
+			for (i = 0; i < n_currents; i++) {
+				if (min_uA <= curr_table[i] &&
+				    curr_table[i] <= max_uA) {
+					sel = i;
+					break;
+				}
+			}
+		}
+	}
+
+	if (sel < 0)
+		return -EINVAL;
+
+	sel <<= ffs(rdev->desc->csel_mask) - 1;
+
+	return max8998_update_reg(i2c, rdev->desc->csel_reg,
+				  sel, rdev->desc->csel_mask);
+}
+
+int max8998_get_current_limit(struct regulator_dev *rdev)
+{
+	struct max8998_data *max8998 = rdev_get_drvdata(rdev);
+	struct i2c_client *i2c = max8998->iodev->i2c;
+	u8 val;
+	int ret;
+
+	ret = max8998_read_reg(i2c, rdev->desc->csel_reg, &val);
+	if (ret != 0)
+		return ret;
+
+	val &= rdev->desc->csel_mask;
+	val >>= ffs(rdev->desc->csel_mask) - 1;
+
+	if (rdev->desc->curr_table) {
+		if (val >= rdev->desc->n_current_limits)
+			return -EINVAL;
+
+		return rdev->desc->curr_table[val];
+	}
+
+	return -EINVAL;
+}
+
 static const struct regulator_ops max8998_ldo_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
@@ -379,6 +460,15 @@ static const struct regulator_ops max8998_buck_ops = {
 	.set_voltage_time_sel	= max8998_set_voltage_buck_time_sel,
 };
 
+static const struct regulator_ops max8998_charger_ops = {
+	.set_current_limit	= max8998_set_current_limit,
+	.get_current_limit	= max8998_get_current_limit,
+	.is_enabled		= max8998_ldo_is_enabled_inverted,
+	/* Swapped as register is inverted */
+	.enable			= max8998_ldo_disable,
+	.disable		= max8998_ldo_enable,
+};
+
 static const struct regulator_ops max8998_others_ops = {
 	.is_enabled		= max8998_ldo_is_enabled,
 	.enable			= max8998_ldo_enable,
@@ -397,6 +487,19 @@ static const struct regulator_ops max8998_others_ops = {
 		.owner = THIS_MODULE, \
 	}
 
+#define MAX8998_CURRENT_REG(_name, _ops, _table, _reg, _mask) \
+	{ \
+		.name = #_name, \
+		.id = MAX8998_##_name, \
+		.ops = _ops, \
+		.curr_table = _table, \
+		.n_current_limits = ARRAY_SIZE(_table), \
+		.csel_reg = _reg, \
+		.csel_mask = _mask, \
+		.type = REGULATOR_CURRENT, \
+		.owner = THIS_MODULE, \
+	}
+
 #define MAX8998_OTHERS_REG(_name, _id) \
 	{ \
 		.name = #_name, \
@@ -432,6 +535,8 @@ static const struct regulator_desc regulators[] = {
 	MAX8998_OTHERS_REG(ENVICHG, MAX8998_ENVICHG),
 	MAX8998_OTHERS_REG(ESAFEOUT1, MAX8998_ESAFEOUT1),
 	MAX8998_OTHERS_REG(ESAFEOUT2, MAX8998_ESAFEOUT2),
+	MAX8998_CURRENT_REG(CHARGER, &max8998_charger_ops,
+			    charger_current_table, MAX8998_REG_CHGR1, 0x7),
 };
 
 static int max8998_pmic_dt_parse_dvs_gpio(struct max8998_dev *iodev,
diff --git a/drivers/regulator/mcp16502.c b/drivers/regulator/mcp16502.c
index e5a02711cb46..6d0ad74935b3 100644
--- a/drivers/regulator/mcp16502.c
+++ b/drivers/regulator/mcp16502.c
@@ -391,11 +391,11 @@ static const struct of_device_id mcp16502_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, mcp16502_ids);
 
-static const struct regulator_linear_range b1l12_ranges[] = {
+static const struct linear_range b1l12_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1200000, VDD_LOW_SEL, VDD_HIGH_SEL, 50000),
 };
 
-static const struct regulator_linear_range b234_ranges[] = {
+static const struct linear_range b234_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000, VDD_LOW_SEL, VDD_HIGH_SEL, 25000),
 };
 
diff --git a/drivers/regulator/mp8859.c b/drivers/regulator/mp8859.c
index 6ed987648188..f2300714d5a9 100644
--- a/drivers/regulator/mp8859.c
+++ b/drivers/regulator/mp8859.c
@@ -73,7 +73,7 @@ static int mp8859_get_voltage_sel(struct regulator_dev *rdev)
 	return val;
 }
 
-static const struct regulator_linear_range mp8859_dcdc_ranges[] = {
+static const struct linear_range mp8859_dcdc_ranges[] = {
 	REGULATOR_LINEAR_RANGE(0, VOL_MIN_IDX, VOL_MAX_IDX, 10000),
 };
 
diff --git a/drivers/regulator/mt6323-regulator.c b/drivers/regulator/mt6323-regulator.c
index 893ea190788a..ff9016170db3 100644
--- a/drivers/regulator/mt6323-regulator.c
+++ b/drivers/regulator/mt6323-regulator.c
@@ -102,15 +102,15 @@ struct mt6323_regulator_info {
 	.modeset_mask = _modeset_mask,					\
 }
 
-static const struct regulator_linear_range buck_volt_range1[] = {
+static const struct linear_range buck_volt_range1[] = {
 	REGULATOR_LINEAR_RANGE(700000, 0, 0x7f, 6250),
 };
 
-static const struct regulator_linear_range buck_volt_range2[] = {
+static const struct linear_range buck_volt_range2[] = {
 	REGULATOR_LINEAR_RANGE(1400000, 0, 0x7f, 12500),
 };
 
-static const struct regulator_linear_range buck_volt_range3[] = {
+static const struct linear_range buck_volt_range3[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0, 0x3f, 50000),
 };
 
diff --git a/drivers/regulator/mt6358-regulator.c b/drivers/regulator/mt6358-regulator.c
index ba42682e06f3..13cb6ac9a892 100644
--- a/drivers/regulator/mt6358-regulator.c
+++ b/drivers/regulator/mt6358-regulator.c
@@ -137,19 +137,19 @@ struct mt6358_regulator_info {
 	.qi = BIT(15),							\
 }
 
-static const struct regulator_linear_range buck_volt_range1[] = {
+static const struct linear_range buck_volt_range1[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0, 0x7f, 6250),
 };
 
-static const struct regulator_linear_range buck_volt_range2[] = {
+static const struct linear_range buck_volt_range2[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0, 0x7f, 12500),
 };
 
-static const struct regulator_linear_range buck_volt_range3[] = {
+static const struct linear_range buck_volt_range3[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0, 0x3f, 50000),
 };
 
-static const struct regulator_linear_range buck_volt_range4[] = {
+static const struct linear_range buck_volt_range4[] = {
 	REGULATOR_LINEAR_RANGE(1000000, 0, 0x7f, 12500),
 };
 
diff --git a/drivers/regulator/mt6380-regulator.c b/drivers/regulator/mt6380-regulator.c
index b6aed090b5e0..9efd8710a6f3 100644
--- a/drivers/regulator/mt6380-regulator.c
+++ b/drivers/regulator/mt6380-regulator.c
@@ -152,15 +152,15 @@ struct mt6380_regulator_info {
 	.modeset_mask = _modeset_mask,					\
 }
 
-static const struct regulator_linear_range buck_volt_range1[] = {
+static const struct linear_range buck_volt_range1[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 0xfe, 6250),
 };
 
-static const struct regulator_linear_range buck_volt_range2[] = {
+static const struct linear_range buck_volt_range2[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 0xfe, 6250),
 };
 
-static const struct regulator_linear_range buck_volt_range3[] = {
+static const struct linear_range buck_volt_range3[] = {
 	REGULATOR_LINEAR_RANGE(1200000, 0, 0x3c, 25000),
 };
 
diff --git a/drivers/regulator/mt6397-regulator.c b/drivers/regulator/mt6397-regulator.c
index fd9ed864a0c1..269c2a6028e8 100644
--- a/drivers/regulator/mt6397-regulator.c
+++ b/drivers/regulator/mt6397-regulator.c
@@ -102,15 +102,15 @@ struct mt6397_regulator_info {
 	.qi = BIT(15),							\
 }
 
-static const struct regulator_linear_range buck_volt_range1[] = {
+static const struct linear_range buck_volt_range1[] = {
 	REGULATOR_LINEAR_RANGE(700000, 0, 0x7f, 6250),
 };
 
-static const struct regulator_linear_range buck_volt_range2[] = {
+static const struct linear_range buck_volt_range2[] = {
 	REGULATOR_LINEAR_RANGE(800000, 0, 0x7f, 6250),
 };
 
-static const struct regulator_linear_range buck_volt_range3[] = {
+static const struct linear_range buck_volt_range3[] = {
 	REGULATOR_LINEAR_RANGE(1500000, 0, 0x1f, 20000),
 };
 
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index 31325912d311..337dd614695e 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -22,14 +22,14 @@
 #include <linux/of_platform.h>
 #include <linux/regulator/of_regulator.h>
 
-static const struct regulator_linear_range smps_low_ranges[] = {
+static const struct linear_range smps_low_ranges[] = {
 	REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(500000, 0x1, 0x6, 0),
 	REGULATOR_LINEAR_RANGE(510000, 0x7, 0x79, 10000),
 	REGULATOR_LINEAR_RANGE(1650000, 0x7A, 0x7f, 0),
 };
 
-static const struct regulator_linear_range smps_high_ranges[] = {
+static const struct linear_range smps_high_ranges[] = {
 	REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(1000000, 0x1, 0x6, 0),
 	REGULATOR_LINEAR_RANGE(1020000, 0x7, 0x79, 20000),
diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
index c86ad40015ce..79bdc129cb50 100644
--- a/drivers/regulator/qcom-rpmh-regulator.c
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -86,7 +86,7 @@ enum rpmh_regulator_type {
 struct rpmh_vreg_hw_data {
 	enum rpmh_regulator_type		regulator_type;
 	const struct regulator_ops		*ops;
-	const struct regulator_linear_range	voltage_range;
+	const struct linear_range	voltage_range;
 	int					n_voltages;
 	int					hpm_min_load_uA;
 	const int				*pmic_mode_map;
@@ -832,11 +832,11 @@ static const struct rpmh_vreg_init_data pm8150_vreg_data[] = {
 	RPMH_VREG("ldo10",  "ldo%s10", &pmic5_pldo,      "vdd-l2-l10"),
 	RPMH_VREG("ldo11",  "ldo%s11", &pmic5_nldo,      "vdd-l1-l8-l11"),
 	RPMH_VREG("ldo12",  "ldo%s12", &pmic5_pldo_lv,   "vdd-l7-l12-l14-l15"),
-	RPMH_VREG("ldo13",  "ldo%s13", &pmic5_pldo,      "vdd-l13-l6-l17"),
+	RPMH_VREG("ldo13",  "ldo%s13", &pmic5_pldo,      "vdd-l13-l16-l17"),
 	RPMH_VREG("ldo14",  "ldo%s14", &pmic5_pldo_lv,   "vdd-l7-l12-l14-l15"),
 	RPMH_VREG("ldo15",  "ldo%s15", &pmic5_pldo_lv,   "vdd-l7-l12-l14-l15"),
-	RPMH_VREG("ldo16",  "ldo%s16", &pmic5_pldo,      "vdd-l13-l6-l17"),
-	RPMH_VREG("ldo17",  "ldo%s17", &pmic5_pldo,      "vdd-l13-l6-l17"),
+	RPMH_VREG("ldo16",  "ldo%s16", &pmic5_pldo,      "vdd-l13-l16-l17"),
+	RPMH_VREG("ldo17",  "ldo%s17", &pmic5_pldo,      "vdd-l13-l16-l17"),
 	RPMH_VREG("ldo18",  "ldo%s18", &pmic5_nldo,      "vdd-l3-l4-l5-l18"),
 	{},
 };
@@ -857,7 +857,7 @@ static const struct rpmh_vreg_init_data pm8150l_vreg_data[] = {
 	RPMH_VREG("ldo5",   "ldo%s5",  &pmic5_pldo,      "vdd-l4-l5-l6"),
 	RPMH_VREG("ldo6",   "ldo%s6",  &pmic5_pldo,      "vdd-l4-l5-l6"),
 	RPMH_VREG("ldo7",   "ldo%s7",  &pmic5_pldo,      "vdd-l7-l11"),
-	RPMH_VREG("ldo8",   "ldo%s8",  &pmic5_pldo_lv,   "vdd-l1-l8-l11"),
+	RPMH_VREG("ldo8",   "ldo%s8",  &pmic5_pldo_lv,   "vdd-l1-l8"),
 	RPMH_VREG("ldo9",   "ldo%s9",  &pmic5_pldo,      "vdd-l9-l10"),
 	RPMH_VREG("ldo10",  "ldo%s10", &pmic5_pldo,      "vdd-l9-l10"),
 	RPMH_VREG("ldo11",  "ldo%s11", &pmic5_pldo,      "vdd-l7-l11"),
diff --git a/drivers/regulator/qcom_rpm-regulator.c b/drivers/regulator/qcom_rpm-regulator.c
index 7fc97f23fcf4..0066f850f15d 100644
--- a/drivers/regulator/qcom_rpm-regulator.c
+++ b/drivers/regulator/qcom_rpm-regulator.c
@@ -148,41 +148,41 @@ static const struct rpm_reg_parts rpm8960_ncp_parts = {
 /*
  * Physically available PMIC regulator voltage ranges
  */
-static const struct regulator_linear_range pldo_ranges[] = {
+static const struct linear_range pldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE( 750000,   0,  59, 12500),
 	REGULATOR_LINEAR_RANGE(1500000,  60, 123, 25000),
 	REGULATOR_LINEAR_RANGE(3100000, 124, 160, 50000),
 };
 
-static const struct regulator_linear_range nldo_ranges[] = {
+static const struct linear_range nldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE( 750000,   0,  63, 12500),
 };
 
-static const struct regulator_linear_range nldo1200_ranges[] = {
+static const struct linear_range nldo1200_ranges[] = {
 	REGULATOR_LINEAR_RANGE( 375000,   0,  59,  6250),
 	REGULATOR_LINEAR_RANGE( 750000,  60, 123, 12500),
 };
 
-static const struct regulator_linear_range smps_ranges[] = {
+static const struct linear_range smps_ranges[] = {
 	REGULATOR_LINEAR_RANGE( 375000,   0,  29, 12500),
 	REGULATOR_LINEAR_RANGE( 750000,  30,  89, 12500),
 	REGULATOR_LINEAR_RANGE(1500000,  90, 153, 25000),
 };
 
-static const struct regulator_linear_range ftsmps_ranges[] = {
+static const struct linear_range ftsmps_ranges[] = {
 	REGULATOR_LINEAR_RANGE( 350000,   0,   6, 50000),
 	REGULATOR_LINEAR_RANGE( 700000,   7,  63, 12500),
 	REGULATOR_LINEAR_RANGE(1500000,  64, 100, 50000),
 };
 
-static const struct regulator_linear_range smb208_ranges[] = {
+static const struct linear_range smb208_ranges[] = {
 	REGULATOR_LINEAR_RANGE( 375000,   0,  29, 12500),
 	REGULATOR_LINEAR_RANGE( 750000,  30,  89, 12500),
 	REGULATOR_LINEAR_RANGE(1500000,  90, 153, 25000),
 	REGULATOR_LINEAR_RANGE(3100000, 154, 234, 25000),
 };
 
-static const struct regulator_linear_range ncp_ranges[] = {
+static const struct linear_range ncp_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1500000,   0,  31, 50000),
 };
 
@@ -604,16 +604,6 @@ static const struct qcom_rpm_reg pm8921_smps = {
 	.supports_force_mode_bypass = false,
 };
 
-static const struct qcom_rpm_reg pm8921_ftsmps = {
-	.desc.linear_ranges = ftsmps_ranges,
-	.desc.n_linear_ranges = ARRAY_SIZE(ftsmps_ranges),
-	.desc.n_voltages = 101,
-	.desc.ops = &uV_ops,
-	.parts = &rpm8960_smps_parts,
-	.supports_force_mode_auto = true,
-	.supports_force_mode_bypass = false,
-};
-
 static const struct qcom_rpm_reg pm8921_ncp = {
 	.desc.linear_ranges = ncp_ranges,
 	.desc.n_linear_ranges = ARRAY_SIZE(ncp_ranges),
diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index fdde4195cefb..53a64d856926 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -199,7 +199,7 @@ static const struct regulator_ops rpm_bob_ops = {
 };
 
 static const struct regulator_desc pma8084_hfsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(375000,  0,  95, 12500),
 		REGULATOR_LINEAR_RANGE(1550000, 96, 158, 25000),
 	},
@@ -209,7 +209,7 @@ static const struct regulator_desc pma8084_hfsmps = {
 };
 
 static const struct regulator_desc pma8084_ftsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(350000,  0, 184, 5000),
 		REGULATOR_LINEAR_RANGE(1280000, 185, 261, 10000),
 	},
@@ -219,7 +219,7 @@ static const struct regulator_desc pma8084_ftsmps = {
 };
 
 static const struct regulator_desc pma8084_pldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE( 750000,  0,  63, 12500),
 		REGULATOR_LINEAR_RANGE(1550000, 64, 126, 25000),
 		REGULATOR_LINEAR_RANGE(3100000, 127, 163, 50000),
@@ -230,7 +230,7 @@ static const struct regulator_desc pma8084_pldo = {
 };
 
 static const struct regulator_desc pma8084_nldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(750000, 0, 63, 12500),
 	},
 	.n_linear_ranges = 1,
@@ -243,7 +243,7 @@ static const struct regulator_desc pma8084_switch = {
 };
 
 static const struct regulator_desc pm8x41_hfsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE( 375000,  0,  95, 12500),
 		REGULATOR_LINEAR_RANGE(1575000, 96, 158, 25000),
 	},
@@ -253,7 +253,7 @@ static const struct regulator_desc pm8x41_hfsmps = {
 };
 
 static const struct regulator_desc pm8841_ftsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(350000,  0, 184, 5000),
 		REGULATOR_LINEAR_RANGE(1280000, 185, 261, 10000),
 	},
@@ -263,7 +263,7 @@ static const struct regulator_desc pm8841_ftsmps = {
 };
 
 static const struct regulator_desc pm8941_boost = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(4000000, 0, 30, 50000),
 	},
 	.n_linear_ranges = 1,
@@ -272,7 +272,7 @@ static const struct regulator_desc pm8941_boost = {
 };
 
 static const struct regulator_desc pm8941_pldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE( 750000,  0,  63, 12500),
 		REGULATOR_LINEAR_RANGE(1550000, 64, 126, 25000),
 		REGULATOR_LINEAR_RANGE(3100000, 127, 163, 50000),
@@ -283,7 +283,7 @@ static const struct regulator_desc pm8941_pldo = {
 };
 
 static const struct regulator_desc pm8941_nldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(750000, 0, 63, 12500),
 	},
 	.n_linear_ranges = 1,
@@ -302,7 +302,7 @@ static const struct regulator_desc pm8941_switch = {
 };
 
 static const struct regulator_desc pm8916_pldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(750000, 0, 208, 12500),
 	},
 	.n_linear_ranges = 1,
@@ -311,7 +311,7 @@ static const struct regulator_desc pm8916_pldo = {
 };
 
 static const struct regulator_desc pm8916_nldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(375000, 0, 93, 12500),
 	},
 	.n_linear_ranges = 1,
@@ -320,7 +320,7 @@ static const struct regulator_desc pm8916_nldo = {
 };
 
 static const struct regulator_desc pm8916_buck_lvo_smps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(375000, 0, 95, 12500),
 		REGULATOR_LINEAR_RANGE(750000, 96, 127, 25000),
 	},
@@ -330,7 +330,7 @@ static const struct regulator_desc pm8916_buck_lvo_smps = {
 };
 
 static const struct regulator_desc pm8916_buck_hvo_smps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(1550000, 0, 31, 25000),
 	},
 	.n_linear_ranges = 1,
@@ -339,7 +339,7 @@ static const struct regulator_desc pm8916_buck_hvo_smps = {
 };
 
 static const struct regulator_desc pm8950_hfsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(375000, 0, 95, 12500),
 		REGULATOR_LINEAR_RANGE(1550000, 96, 127, 25000),
 	},
@@ -349,7 +349,7 @@ static const struct regulator_desc pm8950_hfsmps = {
 };
 
 static const struct regulator_desc pm8950_ftsmps2p5 = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(80000, 0, 255, 5000),
 		REGULATOR_LINEAR_RANGE(160000, 256, 460, 10000),
 	},
@@ -359,7 +359,7 @@ static const struct regulator_desc pm8950_ftsmps2p5 = {
 };
 
 static const struct regulator_desc pm8950_ult_nldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(375000, 0, 202, 12500),
 	},
 	.n_linear_ranges = 1,
@@ -368,7 +368,7 @@ static const struct regulator_desc pm8950_ult_nldo = {
 };
 
 static const struct regulator_desc pm8950_ult_pldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(1750000, 0, 127, 12500),
 	},
 	.n_linear_ranges = 1,
@@ -377,7 +377,7 @@ static const struct regulator_desc pm8950_ult_pldo = {
 };
 
 static const struct regulator_desc pm8950_pldo_lv = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(1500000, 0, 16, 25000),
 	},
 	.n_linear_ranges = 1,
@@ -386,7 +386,7 @@ static const struct regulator_desc pm8950_pldo_lv = {
 };
 
 static const struct regulator_desc pm8950_pldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(975000, 0, 164, 12500),
 	},
 	.n_linear_ranges = 1,
@@ -396,7 +396,7 @@ static const struct regulator_desc pm8950_pldo = {
 
 
 static const struct regulator_desc pm8994_hfsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE( 375000,  0,  95, 12500),
 		REGULATOR_LINEAR_RANGE(1550000, 96, 158, 25000),
 	},
@@ -406,7 +406,7 @@ static const struct regulator_desc pm8994_hfsmps = {
 };
 
 static const struct regulator_desc pm8994_ftsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(350000,  0, 199, 5000),
 		REGULATOR_LINEAR_RANGE(700000, 200, 349, 10000),
 	},
@@ -416,7 +416,7 @@ static const struct regulator_desc pm8994_ftsmps = {
 };
 
 static const struct regulator_desc pm8994_nldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(750000, 0, 63, 12500),
 	},
 	.n_linear_ranges = 1,
@@ -425,7 +425,7 @@ static const struct regulator_desc pm8994_nldo = {
 };
 
 static const struct regulator_desc pm8994_pldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE( 750000,  0,  63, 12500),
 		REGULATOR_LINEAR_RANGE(1550000, 64, 126, 25000),
 		REGULATOR_LINEAR_RANGE(3100000, 127, 163, 50000),
@@ -446,7 +446,7 @@ static const struct regulator_desc pm8994_lnldo = {
 };
 
 static const struct regulator_desc pmi8994_ftsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(350000,  0, 199, 5000),
 		REGULATOR_LINEAR_RANGE(700000, 200, 349, 10000),
 	},
@@ -456,7 +456,7 @@ static const struct regulator_desc pmi8994_ftsmps = {
 };
 
 static const struct regulator_desc pmi8994_hfsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(350000,  0,  80, 12500),
 		REGULATOR_LINEAR_RANGE(700000, 81, 141, 25000),
 	},
@@ -466,7 +466,7 @@ static const struct regulator_desc pmi8994_hfsmps = {
 };
 
 static const struct regulator_desc pmi8994_bby = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(3000000, 0, 44, 50000),
 	},
 	.n_linear_ranges = 1,
@@ -475,7 +475,7 @@ static const struct regulator_desc pmi8994_bby = {
 };
 
 static const struct regulator_desc pmi8994_boost = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(4000000, 0, 30, 50000),
 	},
 	.n_linear_ranges = 1,
@@ -484,7 +484,7 @@ static const struct regulator_desc pmi8994_boost = {
 };
 
 static const struct regulator_desc pm8998_ftsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(320000, 0, 258, 4000),
 	},
 	.n_linear_ranges = 1,
@@ -493,7 +493,7 @@ static const struct regulator_desc pm8998_ftsmps = {
 };
 
 static const struct regulator_desc pm8998_hfsmps = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
 	},
 	.n_linear_ranges = 1,
@@ -502,7 +502,7 @@ static const struct regulator_desc pm8998_hfsmps = {
 };
 
 static const struct regulator_desc pm8998_nldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(312000, 0, 127, 8000),
 	},
 	.n_linear_ranges = 1,
@@ -511,7 +511,7 @@ static const struct regulator_desc pm8998_nldo = {
 };
 
 static const struct regulator_desc pm8998_pldo = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(1664000, 0, 255, 8000),
 	},
 	.n_linear_ranges = 1,
@@ -520,7 +520,7 @@ static const struct regulator_desc pm8998_pldo = {
 };
 
 static const struct regulator_desc pm8998_pldo_lv = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(1256000, 0, 127, 8000),
 	},
 	.n_linear_ranges = 1,
@@ -533,7 +533,7 @@ static const struct regulator_desc pm8998_switch = {
 };
 
 static const struct regulator_desc pmi8998_bob = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(1824000, 0, 83, 32000),
 	},
 	.n_linear_ranges = 1,
@@ -542,7 +542,7 @@ static const struct regulator_desc pmi8998_bob = {
 };
 
 static const struct regulator_desc pms405_hfsmps3 = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
 	},
 	.n_linear_ranges = 1,
@@ -551,7 +551,7 @@ static const struct regulator_desc pms405_hfsmps3 = {
 };
 
 static const struct regulator_desc pms405_nldo300 = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(312000, 0, 127, 8000),
 	},
 	.n_linear_ranges = 1,
@@ -560,7 +560,7 @@ static const struct regulator_desc pms405_nldo300 = {
 };
 
 static const struct regulator_desc pms405_nldo1200 = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(312000, 0, 127, 8000),
 	},
 	.n_linear_ranges = 1,
@@ -569,7 +569,7 @@ static const struct regulator_desc pms405_nldo1200 = {
 };
 
 static const struct regulator_desc pms405_pldo50 = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(1664000, 0, 128, 16000),
 	},
 	.n_linear_ranges = 1,
@@ -578,7 +578,7 @@ static const struct regulator_desc pms405_pldo50 = {
 };
 
 static const struct regulator_desc pms405_pldo150 = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(1664000, 0, 128, 16000),
 	},
 	.n_linear_ranges = 1,
@@ -587,7 +587,7 @@ static const struct regulator_desc pms405_pldo150 = {
 };
 
 static const struct regulator_desc pms405_pldo600 = {
-	.linear_ranges = (struct regulator_linear_range[]) {
+	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(1256000, 0, 98, 8000),
 	},
 	.n_linear_ranges = 1,
diff --git a/drivers/regulator/rk808-regulator.c b/drivers/regulator/rk808-regulator.c
index 31f79fda3238..e926c1a85846 100644
--- a/drivers/regulator/rk808-regulator.c
+++ b/drivers/regulator/rk808-regulator.c
@@ -165,14 +165,14 @@ static const int rk808_buck_config_regs[] = {
 	RK808_BUCK4_CONFIG_REG,
 };
 
-static const struct regulator_linear_range rk808_ldo3_voltage_ranges[] = {
+static const struct linear_range rk808_ldo3_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(800000, 0, 13, 100000),
 	REGULATOR_LINEAR_RANGE(2500000, 15, 15, 0),
 };
 
 #define RK809_BUCK5_SEL_CNT		(8)
 
-static const struct regulator_linear_range rk809_buck5_voltage_ranges[] = {
+static const struct linear_range rk809_buck5_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1500000, 0, 0, 0),
 	REGULATOR_LINEAR_RANGE(1800000, 1, 3, 200000),
 	REGULATOR_LINEAR_RANGE(2800000, 4, 5, 200000),
@@ -201,14 +201,14 @@ static const struct regulator_linear_range rk809_buck5_voltage_ranges[] = {
 #define RK817_BUCK1_SEL_CNT (RK817_BUCK1_SEL0 + RK817_BUCK1_SEL1 + 1)
 #define RK817_BUCK3_SEL_CNT (RK817_BUCK1_SEL0 + RK817_BUCK3_SEL1 + 1)
 
-static const struct regulator_linear_range rk817_buck1_voltage_ranges[] = {
+static const struct linear_range rk817_buck1_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(RK817_BUCK1_MIN0, 0,
 			       RK817_BUCK1_SEL0, RK817_BUCK1_STP0),
 	REGULATOR_LINEAR_RANGE(RK817_BUCK1_MIN1, RK817_BUCK1_SEL0 + 1,
 			       RK817_BUCK1_SEL_CNT, RK817_BUCK1_STP1),
 };
 
-static const struct regulator_linear_range rk817_buck3_voltage_ranges[] = {
+static const struct linear_range rk817_buck3_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(RK817_BUCK1_MIN0, 0,
 			       RK817_BUCK1_SEL0, RK817_BUCK1_STP0),
 	REGULATOR_LINEAR_RANGE(RK817_BUCK1_MIN1, RK817_BUCK1_SEL0 + 1,
@@ -665,7 +665,7 @@ static const struct regulator_ops rk808_switch_ops = {
 	.set_suspend_disable	= rk808_set_suspend_disable,
 };
 
-static const struct regulator_linear_range rk805_buck_1_2_voltage_ranges[] = {
+static const struct linear_range rk805_buck_1_2_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(712500, 0, 59, 12500),
 	REGULATOR_LINEAR_RANGE(1800000, 60, 62, 200000),
 	REGULATOR_LINEAR_RANGE(2300000, 63, 63, 0),
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index 23d288278957..33cf84bce05a 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -749,37 +749,37 @@ static const struct regulator_ops s2mps15_reg_buck_ops = {
 }
 
 /* voltage range for s2mps15 LDO 3, 5, 15, 16, 18, 20, 23 and 27 */
-static const struct regulator_linear_range s2mps15_ldo_voltage_ranges1[] = {
+static const struct linear_range s2mps15_ldo_voltage_ranges1[] = {
 	REGULATOR_LINEAR_RANGE(1000000, 0xc, 0x38, 25000),
 };
 
 /* voltage range for s2mps15 LDO 2, 6, 14, 17, 19, 21, 24 and 25 */
-static const struct regulator_linear_range s2mps15_ldo_voltage_ranges2[] = {
+static const struct linear_range s2mps15_ldo_voltage_ranges2[] = {
 	REGULATOR_LINEAR_RANGE(1800000, 0x0, 0x3f, 25000),
 };
 
 /* voltage range for s2mps15 LDO 4, 11, 12, 13, 22 and 26 */
-static const struct regulator_linear_range s2mps15_ldo_voltage_ranges3[] = {
+static const struct linear_range s2mps15_ldo_voltage_ranges3[] = {
 	REGULATOR_LINEAR_RANGE(700000, 0x0, 0x34, 12500),
 };
 
 /* voltage range for s2mps15 LDO 7, 8, 9 and 10 */
-static const struct regulator_linear_range s2mps15_ldo_voltage_ranges4[] = {
+static const struct linear_range s2mps15_ldo_voltage_ranges4[] = {
 	REGULATOR_LINEAR_RANGE(700000, 0x10, 0x20, 25000),
 };
 
 /* voltage range for s2mps15 LDO 1 */
-static const struct regulator_linear_range s2mps15_ldo_voltage_ranges5[] = {
+static const struct linear_range s2mps15_ldo_voltage_ranges5[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0x0, 0x20, 12500),
 };
 
 /* voltage range for s2mps15 BUCK 1, 2, 3, 4, 5, 6 and 7 */
-static const struct regulator_linear_range s2mps15_buck_voltage_ranges1[] = {
+static const struct linear_range s2mps15_buck_voltage_ranges1[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0x20, 0xc0, 6250),
 };
 
 /* voltage range for s2mps15 BUCK 8, 9 and 10 */
-static const struct regulator_linear_range s2mps15_buck_voltage_ranges2[] = {
+static const struct linear_range s2mps15_buck_voltage_ranges2[] = {
 	REGULATOR_LINEAR_RANGE(1000000, 0x20, 0x78, 12500),
 };
 
diff --git a/drivers/regulator/sky81452-regulator.c b/drivers/regulator/sky81452-regulator.c
index 177dede82a61..37658affe072 100644
--- a/drivers/regulator/sky81452-regulator.c
+++ b/drivers/regulator/sky81452-regulator.c
@@ -32,7 +32,7 @@ static const struct regulator_ops sky81452_reg_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
 };
 
-static const struct regulator_linear_range sky81452_reg_ranges[] = {
+static const struct linear_range sky81452_reg_ranges[] = {
 	REGULATOR_LINEAR_RANGE(4500000, 0, 14, 250000),
 	REGULATOR_LINEAR_RANGE(9000000, 15, 31, 1000000),
 };
diff --git a/drivers/regulator/stpmic1_regulator.c b/drivers/regulator/stpmic1_regulator.c
index f3d7d007ecbb..adc9973d1b2f 100644
--- a/drivers/regulator/stpmic1_regulator.c
+++ b/drivers/regulator/stpmic1_regulator.c
@@ -57,13 +57,13 @@ enum {
 /* Ramp delay worst case is (2250uV/uS) */
 #define PMIC_RAMP_DELAY 2200
 
-static const struct regulator_linear_range buck1_ranges[] = {
+static const struct linear_range buck1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(725000, 0, 4, 0),
 	REGULATOR_LINEAR_RANGE(725000, 5, 36, 25000),
 	REGULATOR_LINEAR_RANGE(1500000, 37, 63, 0),
 };
 
-static const struct regulator_linear_range buck2_ranges[] = {
+static const struct linear_range buck2_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1000000, 0, 17, 0),
 	REGULATOR_LINEAR_RANGE(1050000, 18, 19, 0),
 	REGULATOR_LINEAR_RANGE(1100000, 20, 21, 0),
@@ -77,7 +77,7 @@ static const struct regulator_linear_range buck2_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1500000, 36, 63, 0),
 };
 
-static const struct regulator_linear_range buck3_ranges[] = {
+static const struct linear_range buck3_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1000000, 0, 19, 0),
 	REGULATOR_LINEAR_RANGE(1100000, 20, 23, 0),
 	REGULATOR_LINEAR_RANGE(1200000, 24, 27, 0),
@@ -87,7 +87,7 @@ static const struct regulator_linear_range buck3_ranges[] = {
 	REGULATOR_LINEAR_RANGE(3400000, 56, 63, 0),
 };
 
-static const struct regulator_linear_range buck4_ranges[] = {
+static const struct linear_range buck4_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 27, 25000),
 	REGULATOR_LINEAR_RANGE(1300000, 28, 29, 0),
 	REGULATOR_LINEAR_RANGE(1350000, 30, 31, 0),
@@ -97,19 +97,19 @@ static const struct regulator_linear_range buck4_ranges[] = {
 	REGULATOR_LINEAR_RANGE(3900000, 61, 63, 0),
 };
 
-static const struct regulator_linear_range ldo1_ranges[] = {
+static const struct linear_range ldo1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1700000, 0, 7, 0),
 	REGULATOR_LINEAR_RANGE(1700000, 8, 24, 100000),
 	REGULATOR_LINEAR_RANGE(3300000, 25, 31, 0),
 };
 
-static const struct regulator_linear_range ldo2_ranges[] = {
+static const struct linear_range ldo2_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1700000, 0, 7, 0),
 	REGULATOR_LINEAR_RANGE(1700000, 8, 24, 100000),
 	REGULATOR_LINEAR_RANGE(3300000, 25, 30, 0),
 };
 
-static const struct regulator_linear_range ldo3_ranges[] = {
+static const struct linear_range ldo3_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1700000, 0, 7, 0),
 	REGULATOR_LINEAR_RANGE(1700000, 8, 24, 100000),
 	REGULATOR_LINEAR_RANGE(3300000, 25, 30, 0),
@@ -117,13 +117,13 @@ static const struct regulator_linear_range ldo3_ranges[] = {
 	REGULATOR_LINEAR_RANGE(500000, 31, 31, 0),
 };
 
-static const struct regulator_linear_range ldo5_ranges[] = {
+static const struct linear_range ldo5_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1700000, 0, 7, 0),
 	REGULATOR_LINEAR_RANGE(1700000, 8, 30, 100000),
 	REGULATOR_LINEAR_RANGE(3900000, 31, 31, 0),
 };
 
-static const struct regulator_linear_range ldo6_ranges[] = {
+static const struct linear_range ldo6_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0, 24, 100000),
 	REGULATOR_LINEAR_RANGE(3300000, 25, 31, 0),
 };
diff --git a/drivers/regulator/tps65086-regulator.c b/drivers/regulator/tps65086-regulator.c
index 5a5e9b5bf4be..9910e949373c 100644
--- a/drivers/regulator/tps65086-regulator.c
+++ b/drivers/regulator/tps65086-regulator.c
@@ -71,23 +71,23 @@ struct tps65086_regulator {
 	unsigned int decay_mask;
 };
 
-static const struct regulator_linear_range tps65086_10mv_ranges[] = {
+static const struct linear_range tps65086_10mv_ranges[] = {
 	REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(410000, 0x1, 0x7F, 10000),
 };
 
-static const struct regulator_linear_range tps65086_buck126_25mv_ranges[] = {
+static const struct linear_range tps65086_buck126_25mv_ranges[] = {
 	REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(1000000, 0x1, 0x18, 0),
 	REGULATOR_LINEAR_RANGE(1025000, 0x19, 0x7F, 25000),
 };
 
-static const struct regulator_linear_range tps65086_buck345_25mv_ranges[] = {
+static const struct linear_range tps65086_buck345_25mv_ranges[] = {
 	REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(425000, 0x1, 0x7F, 25000),
 };
 
-static const struct regulator_linear_range tps65086_ldoa1_ranges[] = {
+static const struct linear_range tps65086_ldoa1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1350000, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(1500000, 0x1, 0x7, 100000),
 	REGULATOR_LINEAR_RANGE(2300000, 0x8, 0xB, 100000),
@@ -95,7 +95,7 @@ static const struct regulator_linear_range tps65086_ldoa1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(3300000, 0xE, 0xE, 0),
 };
 
-static const struct regulator_linear_range tps65086_ldoa23_ranges[] = {
+static const struct linear_range tps65086_ldoa23_ranges[] = {
 	REGULATOR_LINEAR_RANGE(700000, 0x0, 0xD, 50000),
 	REGULATOR_LINEAR_RANGE(1400000, 0xE, 0xF, 100000),
 };
diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index 67ba78da77ec..d27dbbafcf72 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -56,14 +56,14 @@ static const unsigned int LDO1_VSEL_table[] = {
 	2800000, 3000000, 3100000, 3300000,
 };
 
-static const struct regulator_linear_range tps65217_uv1_ranges[] = {
+static const struct linear_range tps65217_uv1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0, 24, 25000),
 	REGULATOR_LINEAR_RANGE(1550000, 25, 52, 50000),
 	REGULATOR_LINEAR_RANGE(3000000, 53, 55, 100000),
 	REGULATOR_LINEAR_RANGE(3300000, 56, 63, 0),
 };
 
-static const struct regulator_linear_range tps65217_uv2_ranges[] = {
+static const struct linear_range tps65217_uv2_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1500000, 0, 8, 50000),
 	REGULATOR_LINEAR_RANGE(2000000, 9, 13, 100000),
 	REGULATOR_LINEAR_RANGE(2450000, 14, 31, 50000),
diff --git a/drivers/regulator/tps65218-regulator.c b/drivers/regulator/tps65218-regulator.c
index b72035610013..05d13f807918 100644
--- a/drivers/regulator/tps65218-regulator.c
+++ b/drivers/regulator/tps65218-regulator.c
@@ -56,17 +56,17 @@
 		.bypass_mask	= _sm,				\
 	}							\
 
-static const struct regulator_linear_range dcdc1_dcdc2_ranges[] = {
+static const struct linear_range dcdc1_dcdc2_ranges[] = {
 	REGULATOR_LINEAR_RANGE(850000, 0x0, 0x32, 10000),
 	REGULATOR_LINEAR_RANGE(1375000, 0x33, 0x3f, 25000),
 };
 
-static const struct regulator_linear_range ldo1_dcdc3_ranges[] = {
+static const struct linear_range ldo1_dcdc3_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0x0, 0x1a, 25000),
 	REGULATOR_LINEAR_RANGE(1600000, 0x1b, 0x3f, 50000),
 };
 
-static const struct regulator_linear_range dcdc4_ranges[] = {
+static const struct linear_range dcdc4_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1175000, 0x0, 0xf, 25000),
 	REGULATOR_LINEAR_RANGE(1600000, 0x10, 0x34, 50000),
 };
diff --git a/drivers/regulator/tps65912-regulator.c b/drivers/regulator/tps65912-regulator.c
index 276faeddc370..15c79931ea89 100644
--- a/drivers/regulator/tps65912-regulator.c
+++ b/drivers/regulator/tps65912-regulator.c
@@ -46,11 +46,11 @@ enum tps65912_regulators { DCDC1, DCDC2, DCDC3, DCDC4, LDO1, LDO2, LDO3,
 		.n_linear_ranges	= ARRAY_SIZE(_lr),		\
 	}
 
-static const struct regulator_linear_range tps65912_dcdc_ranges[] = {
+static const struct linear_range tps65912_dcdc_ranges[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0x0, 0x3f, 50000),
 };
 
-static const struct regulator_linear_range tps65912_ldo_ranges[] = {
+static const struct linear_range tps65912_ldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE(800000, 0x0, 0x20, 25000),
 	REGULATOR_LINEAR_RANGE(1650000, 0x21, 0x3c, 50000),
 	REGULATOR_LINEAR_RANGE(3100000, 0x3d, 0x3f, 100000),
diff --git a/drivers/regulator/tps80031-regulator.c b/drivers/regulator/tps80031-regulator.c
index 85a6a8ca8c1b..a29e65230132 100644
--- a/drivers/regulator/tps80031-regulator.c
+++ b/drivers/regulator/tps80031-regulator.c
@@ -271,7 +271,7 @@ static int tps80031_vbus_is_enabled(struct regulator_dev *rdev)
 {
 	struct tps80031_regulator *ri = rdev_get_drvdata(rdev);
 	struct device *parent = to_tps80031_dev(rdev);
-	int ret = -EIO;
+	int ret;
 	uint8_t ctrl1 = 0;
 	uint8_t ctrl3 = 0;
 
@@ -322,7 +322,7 @@ static int tps80031_vbus_disable(struct regulator_dev *rdev)
 {
 	struct tps80031_regulator *ri = rdev_get_drvdata(rdev);
 	struct device *parent = to_tps80031_dev(rdev);
-	int ret = 0;
+	int ret;
 
 	if (ri->config_flags & TPS80031_VBUS_DISCHRG_EN_PDN) {
 		ret = tps80031_write(parent, TPS80031_SLAVE_ID2,
@@ -530,7 +530,8 @@ static int tps80031_regulator_config(struct device *parent,
 	case TPS80031_REGULATOR_LDOUSB:
 		if (ri->config_flags & (TPS80031_USBLDO_INPUT_VSYS |
 			TPS80031_USBLDO_INPUT_PMID)) {
-			unsigned val = 0;
+			unsigned val;
+
 			if (ri->config_flags & TPS80031_USBLDO_INPUT_VSYS)
 				val = MISC2_LDOUSB_IN_VSYS;
 			else
diff --git a/drivers/regulator/twl-regulator.c b/drivers/regulator/twl-regulator.c
index 866b4dd01da9..4a51cfea45ac 100644
--- a/drivers/regulator/twl-regulator.c
+++ b/drivers/regulator/twl-regulator.c
@@ -360,12 +360,12 @@ static const u16 VINTANA2_VSEL_table[] = {
 };
 
 /* 600mV to 1450mV in 12.5 mV steps */
-static const struct regulator_linear_range VDD1_ranges[] = {
+static const struct linear_range VDD1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 68, 12500)
 };
 
 /* 600mV to 1450mV in 12.5 mV steps, everything above = 1500mV */
-static const struct regulator_linear_range VDD2_ranges[] = {
+static const struct linear_range VDD2_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 68, 12500),
 	REGULATOR_LINEAR_RANGE(1500000, 69, 69, 12500)
 };
diff --git a/drivers/regulator/twl6030-regulator.c b/drivers/regulator/twl6030-regulator.c
index b8100c3cedad..f7db250a7583 100644
--- a/drivers/regulator/twl6030-regulator.c
+++ b/drivers/regulator/twl6030-regulator.c
@@ -495,7 +495,7 @@ static const struct regulator_ops twlsmps_ops = {
 };
 
 /*----------------------------------------------------------------------*/
-static const struct regulator_linear_range twl6030ldo_linear_range[] = {
+static const struct linear_range twl6030ldo_linear_range[] = {
 	REGULATOR_LINEAR_RANGE(0, 0, 0, 0),
 	REGULATOR_LINEAR_RANGE(1000000, 1, 24, 100000),
 	REGULATOR_LINEAR_RANGE(2750000, 31, 31, 0),
diff --git a/drivers/regulator/wm831x-dcdc.c b/drivers/regulator/wm831x-dcdc.c
index 018dbbd96771..ad2203d11a88 100644
--- a/drivers/regulator/wm831x-dcdc.c
+++ b/drivers/regulator/wm831x-dcdc.c
@@ -204,7 +204,7 @@ static irqreturn_t wm831x_dcdc_oc_irq(int irq, void *data)
  * BUCKV specifics
  */
 
-static const struct regulator_linear_range wm831x_buckv_ranges[] = {
+static const struct linear_range wm831x_buckv_ranges[] = {
 	REGULATOR_LINEAR_RANGE(600000, 0, 0x7, 0),
 	REGULATOR_LINEAR_RANGE(600000, 0x8, 0x68, 12500),
 };
diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c
index 56754686c982..7b6cf4810cb7 100644
--- a/drivers/regulator/wm831x-ldo.c
+++ b/drivers/regulator/wm831x-ldo.c
@@ -59,7 +59,7 @@ static irqreturn_t wm831x_ldo_uv_irq(int irq, void *data)
  * General purpose LDOs
  */
 
-static const struct regulator_linear_range wm831x_gp_ldo_ranges[] = {
+static const struct linear_range wm831x_gp_ldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0, 14, 50000),
 	REGULATOR_LINEAR_RANGE(1700000, 15, 31, 100000),
 };
@@ -312,7 +312,7 @@ static struct platform_driver wm831x_gp_ldo_driver = {
  * Analogue LDOs
  */
 
-static const struct regulator_linear_range wm831x_aldo_ranges[] = {
+static const struct linear_range wm831x_aldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1000000, 0, 12, 50000),
 	REGULATOR_LINEAR_RANGE(1700000, 13, 31, 100000),
 };
diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c
index 56d6168a888d..ae5f0e7fce8b 100644
--- a/drivers/regulator/wm8350-regulator.c
+++ b/drivers/regulator/wm8350-regulator.c
@@ -470,7 +470,7 @@ static int wm8350_dcdc_set_suspend_mode(struct regulator_dev *rdev,
 	return 0;
 }
 
-static const struct regulator_linear_range wm8350_ldo_ranges[] = {
+static const struct linear_range wm8350_ldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0, 15, 50000),
 	REGULATOR_LINEAR_RANGE(1800000, 16, 31, 100000),
 };
diff --git a/drivers/regulator/wm8400-regulator.c b/drivers/regulator/wm8400-regulator.c
index 6f331b51e479..4cb1fbb59722 100644
--- a/drivers/regulator/wm8400-regulator.c
+++ b/drivers/regulator/wm8400-regulator.c
@@ -13,7 +13,7 @@
 #include <linux/regulator/driver.h>
 #include <linux/mfd/wm8400-private.h>
 
-static const struct regulator_linear_range wm8400_ldo_ranges[] = {
+static const struct linear_range wm8400_ldo_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0, 14, 50000),
 	REGULATOR_LINEAR_RANGE(1700000, 15, 31, 100000),
 };
diff --git a/drivers/remoteproc/mtk_common.h b/drivers/remoteproc/mtk_common.h
index deb20096146a..0066c83636d0 100644
--- a/drivers/remoteproc/mtk_common.h
+++ b/drivers/remoteproc/mtk_common.h
@@ -68,7 +68,7 @@ struct mtk_scp {
 	wait_queue_head_t ack_wq;
 
 	void __iomem *cpu_addr;
-	phys_addr_t phys_addr;
+	dma_addr_t dma_addr;
 	size_t dram_size;
 
 	struct rproc_subdev *rpmsg_subdev;
diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
index ea3743e7e794..2bead57c9cf9 100644
--- a/drivers/remoteproc/mtk_scp.c
+++ b/drivers/remoteproc/mtk_scp.c
@@ -330,7 +330,7 @@ static void *scp_da_to_va(struct rproc *rproc, u64 da, size_t len)
 		if (offset >= 0 && (offset + len) < scp->sram_size)
 			return (void __force *)scp->sram_base + offset;
 	} else {
-		offset = da - scp->phys_addr;
+		offset = da - scp->dma_addr;
 		if (offset >= 0 && (offset + len) < scp->dram_size)
 			return (void __force *)scp->cpu_addr + offset;
 	}
@@ -451,7 +451,7 @@ static int scp_map_memory_region(struct mtk_scp *scp)
 	/* Reserved SCP code size */
 	scp->dram_size = MAX_CODE_SIZE;
 	scp->cpu_addr = dma_alloc_coherent(scp->dev, scp->dram_size,
-					   &scp->phys_addr, GFP_KERNEL);
+					   &scp->dma_addr, GFP_KERNEL);
 	if (!scp->cpu_addr)
 		return -ENOMEM;
 
@@ -461,7 +461,7 @@ static int scp_map_memory_region(struct mtk_scp *scp)
 static void scp_unmap_memory_region(struct mtk_scp *scp)
 {
 	dma_free_coherent(scp->dev, scp->dram_size, scp->cpu_addr,
-			  scp->phys_addr);
+			  scp->dma_addr);
 	of_reserved_mem_device_release(scp->dev);
 }
 
diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index ce49c3236ff7..5475d4f808a8 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -367,7 +367,7 @@ unroll_pd_votes:
 	}
 
 	return ret;
-};
+}
 
 static void q6v5_pds_disable(struct q6v5 *qproc, struct device **pds,
 			     size_t pd_count)
@@ -1527,7 +1527,7 @@ unroll_attach:
 		dev_pm_domain_detach(devs[i], false);
 
 	return ret;
-};
+}
 
 static void q6v5_pds_detach(struct q6v5 *qproc, struct device **pds,
 			    size_t pd_count)
@@ -1675,7 +1675,7 @@ static int q6v5_probe(struct platform_device *pdev)
 	ret = of_property_read_string_index(pdev->dev.of_node, "firmware-name",
 					    1, &qproc->hexagon_mdt_image);
 	if (ret < 0 && ret != -EINVAL)
-		return ret;
+		goto free_rproc;
 
 	platform_set_drvdata(pdev, qproc);
 
@@ -1766,17 +1766,23 @@ static int q6v5_probe(struct platform_device *pdev)
 	qproc->sysmon = qcom_add_sysmon_subdev(rproc, "modem", 0x12);
 	if (IS_ERR(qproc->sysmon)) {
 		ret = PTR_ERR(qproc->sysmon);
-		goto detach_proxy_pds;
+		goto remove_subdevs;
 	}
 
 	ret = rproc_add(rproc);
 	if (ret)
-		goto detach_proxy_pds;
+		goto remove_sysmon_subdev;
 
 	return 0;
 
-detach_proxy_pds:
+remove_sysmon_subdev:
+	qcom_remove_sysmon_subdev(qproc->sysmon);
+remove_subdevs:
 	qcom_remove_ipa_notify_subdev(qproc->rproc, &qproc->ipa_notify_subdev);
+	qcom_remove_ssr_subdev(rproc, &qproc->ssr_subdev);
+	qcom_remove_smd_subdev(rproc, &qproc->smd_subdev);
+	qcom_remove_glink_subdev(rproc, &qproc->glink_subdev);
+detach_proxy_pds:
 	q6v5_pds_detach(qproc, qproc->proxy_pds, qproc->proxy_pd_count);
 detach_active_pds:
 	q6v5_pds_detach(qproc, qproc->active_pds, qproc->active_pd_count);
@@ -1789,19 +1795,20 @@ free_rproc:
 static int q6v5_remove(struct platform_device *pdev)
 {
 	struct q6v5 *qproc = platform_get_drvdata(pdev);
+	struct rproc *rproc = qproc->rproc;
 
-	rproc_del(qproc->rproc);
+	rproc_del(rproc);
 
 	qcom_remove_sysmon_subdev(qproc->sysmon);
-	qcom_remove_ipa_notify_subdev(qproc->rproc, &qproc->ipa_notify_subdev);
-	qcom_remove_glink_subdev(qproc->rproc, &qproc->glink_subdev);
-	qcom_remove_smd_subdev(qproc->rproc, &qproc->smd_subdev);
-	qcom_remove_ssr_subdev(qproc->rproc, &qproc->ssr_subdev);
+	qcom_remove_ipa_notify_subdev(rproc, &qproc->ipa_notify_subdev);
+	qcom_remove_ssr_subdev(rproc, &qproc->ssr_subdev);
+	qcom_remove_smd_subdev(rproc, &qproc->smd_subdev);
+	qcom_remove_glink_subdev(rproc, &qproc->glink_subdev);
 
-	q6v5_pds_detach(qproc, qproc->active_pds, qproc->active_pd_count);
 	q6v5_pds_detach(qproc, qproc->proxy_pds, qproc->proxy_pd_count);
+	q6v5_pds_detach(qproc, qproc->active_pds, qproc->active_pd_count);
 
-	rproc_free(qproc->rproc);
+	rproc_free(rproc);
 
 	return 0;
 }
diff --git a/drivers/remoteproc/remoteproc_sysfs.c b/drivers/remoteproc/remoteproc_sysfs.c
index 7f8536b73295..52b871327b55 100644
--- a/drivers/remoteproc/remoteproc_sysfs.c
+++ b/drivers/remoteproc/remoteproc_sysfs.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/remoteproc.h>
+#include <linux/slab.h>
 
 #include "remoteproc_internal.h"
 
diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c
index 6a66dbf2df40..0bdd56f02f18 100644
--- a/drivers/remoteproc/stm32_rproc.c
+++ b/drivers/remoteproc/stm32_rproc.c
@@ -19,6 +19,7 @@
 #include <linux/regmap.h>
 #include <linux/remoteproc.h>
 #include <linux/reset.h>
+#include <linux/slab.h>
 #include <linux/workqueue.h>
 
 #include "remoteproc_internal.h"
diff --git a/drivers/rpmsg/mtk_rpmsg.c b/drivers/rpmsg/mtk_rpmsg.c
index 232aa4e40133..83f2b8804ee9 100644
--- a/drivers/rpmsg/mtk_rpmsg.c
+++ b/drivers/rpmsg/mtk_rpmsg.c
@@ -8,6 +8,7 @@
 #include <linux/platform_device.h>
 #include <linux/remoteproc.h>
 #include <linux/rpmsg/mtk_rpmsg.h>
+#include <linux/slab.h>
 #include <linux/workqueue.h>
 
 #include "rpmsg_internal.h"
diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig
index a8682f69effc..376f1efbbb86 100644
--- a/drivers/s390/block/Kconfig
+++ b/drivers/s390/block/Kconfig
@@ -26,7 +26,6 @@ config DASD
 	def_tristate y
 	prompt "Support for DASD devices"
 	depends on CCW && BLOCK
-	select IOSCHED_DEADLINE
 	help
 	  Enable this option if you want to access DASDs directly utilizing
 	  S/390s channel subsystem commands. This is necessary for running
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index c75112ee7b97..c7fade836d83 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -521,8 +521,10 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops,
 				   ISM_NR_DMBS);
-	if (!ism->smcd)
+	if (!ism->smcd) {
+		ret = -ENOMEM;
 		goto err_resource;
+	}
 
 	ism->smcd->priv = ism;
 	ret = ism_dev_init(ism);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index f7689461c242..569966bdc513 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -6717,17 +6717,17 @@ int qeth_stop(struct net_device *dev)
 		unsigned int i;
 
 		/* Quiesce the NAPI instances: */
-		qeth_for_each_output_queue(card, queue, i) {
+		qeth_for_each_output_queue(card, queue, i)
 			napi_disable(&queue->napi);
-			del_timer_sync(&queue->timer);
-		}
 
 		/* Stop .ndo_start_xmit, might still access queue->napi. */
 		netif_tx_disable(dev);
 
-		/* Queues may get re-allocated, so remove the NAPIs here. */
-		qeth_for_each_output_queue(card, queue, i)
+		qeth_for_each_output_queue(card, queue, i) {
+			del_timer_sync(&queue->timer);
+			/* Queues may get re-allocated, so remove the NAPIs. */
 			netif_napi_del(&queue->napi);
+		}
 	} else {
 		netif_tx_disable(dev);
 	}
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 17feff174f57..2017c43dac1b 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -127,7 +127,7 @@ config CHR_DEV_SG
 
 	  For scanners, look at SANE (<http://www.sane-project.org/>). For CD
 	  writer software look at Cdrtools
-	  (<http://cdrecord.berlios.de/private/cdrecord.html>)
+	  (<http://cdrtools.sourceforge.net/>)
 	  and for burning a "disk at once": CDRDAO
 	  (<http://cdrdao.sourceforge.net/>). Cdparanoia is a high
 	  quality digital reader of audio CDs (<http://www.xiph.org/paranoia/>).
diff --git a/drivers/scsi/hisi_sas/Kconfig b/drivers/scsi/hisi_sas/Kconfig
index 90a17452a50d..13ed9073fc72 100644
--- a/drivers/scsi/hisi_sas/Kconfig
+++ b/drivers/scsi/hisi_sas/Kconfig
@@ -6,6 +6,7 @@ config SCSI_HISI_SAS
 	select SCSI_SAS_LIBSAS
 	select BLK_DEV_INTEGRITY
 	depends on ATA
+	select SATA_HOST
 	help
 		This driver supports HiSilicon's SAS HBA, including support based
 		on platform device
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 7da9e060b270..635f6f9cffc4 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -3640,6 +3640,11 @@ static void ibmvfc_tgt_implicit_logout_and_del(struct ibmvfc_target *tgt)
 	struct ibmvfc_host *vhost = tgt->vhost;
 	struct ibmvfc_event *evt;
 
+	if (!vhost->logged_in) {
+		ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT);
+		return;
+	}
+
 	if (vhost->discovery_threads >= disc_threads)
 		return;
 
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 7f66a7783209..59f0f1030c54 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -2320,16 +2320,12 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 static int ibmvscsi_remove(struct vio_dev *vdev)
 {
 	struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev);
-	unsigned long flags;
 
 	srp_remove_host(hostdata->host);
 	scsi_remove_host(hostdata->host);
 
 	purge_requests(hostdata, DID_ERROR);
-
-	spin_lock_irqsave(hostdata->host->host_lock, flags);
 	release_event_pool(&hostdata->pool, hostdata);
-	spin_unlock_irqrestore(hostdata->host->host_lock, flags);
 
 	ibmvscsi_release_crq_queue(&hostdata->queue, hostdata,
 					max_events);
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 97cabd7e0014..2c9e5ac24692 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -1850,9 +1850,6 @@ qla2x00_port_speed_show(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 	}
 
-	ql_log(ql_log_info, vha, 0x70d6,
-	    "port speed:%d\n", ha->link_data_rate);
-
 	return scnprintf(buf, PAGE_SIZE, "%s\n", spd[ha->link_data_rate]);
 }
 
@@ -3031,11 +3028,11 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 	    test_bit(FCPORT_UPDATE_NEEDED, &vha->dpc_flags))
 		msleep(1000);
 
-	qla_nvme_delete(vha);
 
 	qla24xx_disable_vp(vha);
 	qla2x00_wait_for_sess_deletion(vha);
 
+	qla_nvme_delete(vha);
 	vha->flags.delete_progress = 1;
 
 	qlt_remove_target(ha, vha);
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index f301a8048b2f..bf1e98f11990 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -2539,7 +2539,6 @@ ql_dbg(uint level, scsi_qla_host_t *vha, uint id, const char *fmt, ...)
 {
 	va_list va;
 	struct va_format vaf;
-	char pbuf[64];
 
 	va_start(va, fmt);
 
@@ -2547,6 +2546,8 @@ ql_dbg(uint level, scsi_qla_host_t *vha, uint id, const char *fmt, ...)
 	vaf.va = &va;
 
 	if (!ql_mask_match(level)) {
+		char pbuf[64];
+
 		if (vha != NULL) {
 			const struct pci_dev *pdev = vha->hw->pdev;
 			/* <module-name> <msg-id>:<host> Message */
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 5b2deaa730bf..caa6b840e459 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -3611,8 +3611,6 @@ qla24xx_detect_sfp(scsi_qla_host_t *vha)
 			ha->lr_distance = LR_DISTANCE_5K;
 	}
 
-	if (!vha->flags.init_done)
-		rc = QLA_SUCCESS;
 out:
 	ql_dbg(ql_dbg_async, vha, 0x507b,
 	    "SFP detect: %s-Range SFP %s (nvr=%x ll=%x lr=%x lrd=%x).\n",
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 8d7a905f6247..8a78d395bbc8 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -87,7 +87,6 @@ qla24xx_process_abts(struct scsi_qla_host *vha, void *pkt)
 	}
 
 	/* terminate exchange */
-	memset(rsp_els, 0, sizeof(*rsp_els));
 	rsp_els->entry_type = ELS_IOCB_TYPE;
 	rsp_els->entry_count = 1;
 	rsp_els->nport_handle = ~0;
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 9fd83d1bffe0..d6c991bd1bde 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -3153,7 +3153,7 @@ qla24xx_abort_command(srb_t *sp)
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x108c,
 	    "Entered %s.\n", __func__);
 
-	if (vha->flags.qpairs_available && sp->qpair)
+	if (sp->qpair)
 		req = sp->qpair->req;
 	else
 		return QLA_FUNCTION_FAILED;
@@ -4894,8 +4894,6 @@ qla25xx_set_els_cmds_supported(scsi_qla_host_t *vha)
 		return QLA_MEMORY_ALLOC_FAILED;
 	}
 
-	memset(els_cmd_map, 0, ELS_CMD_MAP_SIZE);
-
 	els_cmd_map[index] |= 1 << bit;
 
 	mcp->mb[0] = MBC_SET_RNID_PARAMS;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index d190db5ea7d9..1d9a4866f9a7 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3732,6 +3732,13 @@ qla2x00_remove_one(struct pci_dev *pdev)
 	}
 	qla2x00_wait_for_hba_ready(base_vha);
 
+	/*
+	 * if UNLOADING flag is already set, then continue unload,
+	 * where it was set first.
+	 */
+	if (test_and_set_bit(UNLOADING, &base_vha->dpc_flags))
+		return;
+
 	if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha) ||
 	    IS_QLA28XX(ha)) {
 		if (ha->flags.fw_started)
@@ -3750,15 +3757,6 @@ qla2x00_remove_one(struct pci_dev *pdev)
 
 	qla2x00_wait_for_sess_deletion(base_vha);
 
-	/*
-	 * if UNLOAD flag is already set, then continue unload,
-	 * where it was set first.
-	 */
-	if (test_bit(UNLOADING, &base_vha->dpc_flags))
-		return;
-
-	set_bit(UNLOADING, &base_vha->dpc_flags);
-
 	qla_nvme_delete(base_vha);
 
 	dma_free_coherent(&ha->pdev->dev,
@@ -4864,6 +4862,9 @@ qla2x00_alloc_work(struct scsi_qla_host *vha, enum qla_work_type type)
 	struct qla_work_evt *e;
 	uint8_t bail;
 
+	if (test_bit(UNLOADING, &vha->dpc_flags))
+		return NULL;
+
 	QLA_VHA_MARK_BUSY(vha, bail);
 	if (bail)
 		return NULL;
@@ -6628,13 +6629,6 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 	struct pci_dev *pdev = ha->pdev;
 	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
 
-	/*
-	 * if UNLOAD flag is already set, then continue unload,
-	 * where it was set first.
-	 */
-	if (test_bit(UNLOADING, &base_vha->dpc_flags))
-		return;
-
 	ql_log(ql_log_warn, base_vha, 0x015b,
 	    "Disabling adapter.\n");
 
@@ -6645,9 +6639,14 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work)
 		return;
 	}
 
-	qla2x00_wait_for_sess_deletion(base_vha);
+	/*
+	 * if UNLOADING flag is already set, then continue unload,
+	 * where it was set first.
+	 */
+	if (test_and_set_bit(UNLOADING, &base_vha->dpc_flags))
+		return;
 
-	set_bit(UNLOADING, &base_vha->dpc_flags);
+	qla2x00_wait_for_sess_deletion(base_vha);
 
 	qla2x00_delete_all_vps(ha, base_vha);
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 47835c4b4ee0..06c260f6cdae 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2284,6 +2284,7 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state)
 		switch (oldstate) {
 		case SDEV_RUNNING:
 		case SDEV_CREATED_BLOCK:
+		case SDEV_QUIESCE:
 		case SDEV_OFFLINE:
 			break;
 		default:
diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c
index 3717eea37ecb..5f0ad8b32e3a 100644
--- a/drivers/scsi/scsi_pm.c
+++ b/drivers/scsi/scsi_pm.c
@@ -80,6 +80,10 @@ static int scsi_dev_type_resume(struct device *dev,
 	dev_dbg(dev, "scsi resume: %d\n", err);
 
 	if (err == 0) {
+		bool was_runtime_suspended;
+
+		was_runtime_suspended = pm_runtime_suspended(dev);
+
 		pm_runtime_disable(dev);
 		err = pm_runtime_set_active(dev);
 		pm_runtime_enable(dev);
@@ -93,8 +97,10 @@ static int scsi_dev_type_resume(struct device *dev,
 		 */
 		if (!err && scsi_is_sdev_device(dev)) {
 			struct scsi_device *sdev = to_scsi_device(dev);
-
-			blk_set_runtime_active(sdev->request_queue);
+			if (was_runtime_suspended)
+				blk_post_runtime_resume(sdev->request_queue, 0);
+			else
+				blk_set_runtime_active(sdev->request_queue);
 		}
 	}
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 4e6af592f018..20472aaaf630 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -685,8 +685,10 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	hp->flags = input_size;	/* structure abuse ... */
 	hp->pack_id = old_hdr.pack_id;
 	hp->usr_ptr = NULL;
-	if (copy_from_user(cmnd, buf, cmd_size))
+	if (copy_from_user(cmnd, buf, cmd_size)) {
+		sg_remove_request(sfp, srp);
 		return -EFAULT;
+	}
 	/*
 	 * SG_DXFER_TO_FROM_DEV is functionally equivalent to SG_DXFER_FROM_DEV,
 	 * but is is possible that the app intended SG_DXFER_TO_DEV, because there
@@ -793,8 +795,10 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp,
 			"sg_common_write:  scsi opcode=0x%02x, cmd_size=%d\n",
 			(int) cmnd[0], (int) hp->cmd_len));
 
-	if (hp->dxfer_len >= SZ_256M)
+	if (hp->dxfer_len >= SZ_256M) {
+		sg_remove_request(sfp, srp);
 		return -EINVAL;
+	}
 
 	k = sg_start_req(srp, cmnd);
 	if (k) {
diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c
index cd4f6410e8c2..bcdcd3e7d7f1 100644
--- a/drivers/soc/fsl/dpio/dpio-service.c
+++ b/drivers/soc/fsl/dpio/dpio-service.c
@@ -478,12 +478,18 @@ int dpaa2_io_service_enqueue_multiple_desc_fq(struct dpaa2_io *d,
 				const struct dpaa2_fd *fd,
 				int nb)
 {
-	int i;
-	struct qbman_eq_desc ed[32];
+	struct qbman_eq_desc *ed;
+	int i, ret;
+
+	ed = kcalloc(sizeof(struct qbman_eq_desc), 32, GFP_KERNEL);
+	if (!ed)
+		return -ENOMEM;
 
 	d = service_select(d);
-	if (!d)
-		return -ENODEV;
+	if (!d) {
+		ret = -ENODEV;
+		goto out;
+	}
 
 	for (i = 0; i < nb; i++) {
 		qbman_eq_desc_clear(&ed[i]);
@@ -491,7 +497,10 @@ int dpaa2_io_service_enqueue_multiple_desc_fq(struct dpaa2_io *d,
 		qbman_eq_desc_set_fq(&ed[i], fqid[i]);
 	}
 
-	return qbman_swp_enqueue_multiple_desc(d->swp, &ed[0], fd, nb);
+	ret = qbman_swp_enqueue_multiple_desc(d->swp, &ed[0], fd, nb);
+out:
+	kfree(ed);
+	return ret;
 }
 EXPORT_SYMBOL(dpaa2_io_service_enqueue_multiple_desc_fq);
 
diff --git a/drivers/soc/fsl/dpio/qbman-portal.c b/drivers/soc/fsl/dpio/qbman-portal.c
index d1f49caa5b13..804b8ba9bf5c 100644
--- a/drivers/soc/fsl/dpio/qbman-portal.c
+++ b/drivers/soc/fsl/dpio/qbman-portal.c
@@ -753,7 +753,7 @@ int qbman_swp_enqueue_multiple_mem_back(struct qbman_swp *s,
 	if (!s->eqcr.available) {
 		eqcr_ci = s->eqcr.ci;
 		p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI_MEMBACK;
-		s->eqcr.ci = __raw_readl(p) & full_mask;
+		s->eqcr.ci = *p & full_mask;
 		s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size,
 					eqcr_ci, s->eqcr.ci);
 		if (!s->eqcr.available) {
@@ -823,7 +823,6 @@ int qbman_swp_enqueue_multiple_desc_direct(struct qbman_swp *s,
 	const uint32_t *cl;
 	uint32_t eqcr_ci, eqcr_pi, half_mask, full_mask;
 	int i, num_enqueued = 0;
-	uint64_t addr_cena;
 
 	half_mask = (s->eqcr.pi_ci_mask>>1);
 	full_mask = s->eqcr.pi_ci_mask;
@@ -867,7 +866,6 @@ int qbman_swp_enqueue_multiple_desc_direct(struct qbman_swp *s,
 
 	/* Flush all the cacheline without load/store in between */
 	eqcr_pi = s->eqcr.pi;
-	addr_cena = (uint64_t)s->addr_cena;
 	for (i = 0; i < num_enqueued; i++)
 		eqcr_pi++;
 	s->eqcr.pi = eqcr_pi & full_mask;
@@ -901,7 +899,7 @@ int qbman_swp_enqueue_multiple_desc_mem_back(struct qbman_swp *s,
 	if (!s->eqcr.available) {
 		eqcr_ci = s->eqcr.ci;
 		p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI_MEMBACK;
-		s->eqcr.ci = __raw_readl(p) & full_mask;
+		s->eqcr.ci = *p & full_mask;
 		s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size,
 					eqcr_ci, s->eqcr.ci);
 		if (!s->eqcr.available)
diff --git a/drivers/soc/imx/Kconfig b/drivers/soc/imx/Kconfig
index 67aa94b2481b..d515d2cc20ed 100644
--- a/drivers/soc/imx/Kconfig
+++ b/drivers/soc/imx/Kconfig
@@ -21,6 +21,7 @@ config SOC_IMX8M
 	bool "i.MX8M SoC family support"
 	depends on ARCH_MXC || COMPILE_TEST
 	default ARCH_MXC && ARM64
+	select SOC_BUS
 	help
 	  If you say yes here you get support for the NXP i.MX8M family
 	  support, it will provide the SoC info like SoC family,
diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index db37144ae98c..87ee9f767b7a 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -351,7 +351,9 @@ int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb,
 		spin_unlock_irqrestore(&client->lock, flags);
 	}
 
-	mbox_send_message(client->chan, pkt);
+	err = mbox_send_message(client->chan, pkt);
+	if (err < 0)
+		return err;
 	/* We can send next packet immediately, so just call txdone. */
 	mbox_client_txdone(client->chan, 0);
 
diff --git a/drivers/soc/xilinx/Kconfig b/drivers/soc/xilinx/Kconfig
index 223f1f9d0922..646512d7276f 100644
--- a/drivers/soc/xilinx/Kconfig
+++ b/drivers/soc/xilinx/Kconfig
@@ -19,7 +19,7 @@ config XILINX_VCU
 
 config ZYNQMP_POWER
 	bool "Enable Xilinx Zynq MPSoC Power Management driver"
-	depends on PM && ARCH_ZYNQMP
+	depends on PM && ZYNQMP_FIRMWARE
 	default y
 	select MAILBOX
 	select ZYNQMP_IPI_MBOX
@@ -35,7 +35,7 @@ config ZYNQMP_POWER
 config ZYNQMP_PM_DOMAINS
 	bool "Enable Zynq MPSoC generic PM domains"
 	default y
-	depends on PM && ARCH_ZYNQMP && ZYNQMP_FIRMWARE
+	depends on PM && ZYNQMP_FIRMWARE
 	select PM_GENERIC_DOMAINS
 	help
 	  Say yes to enable device power management through PM domains
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 741b9140992a..8f1f8fca79e3 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -226,17 +226,20 @@ config SPI_DESIGNWARE
 	help
 	  general driver for SPI controller core from DesignWare
 
+if SPI_DESIGNWARE
+
+config SPI_DW_DMA
+	bool "DMA support for DW SPI controller"
+
 config SPI_DW_PCI
 	tristate "PCI interface driver for DW SPI core"
-	depends on SPI_DESIGNWARE && PCI
-
-config SPI_DW_MID_DMA
-	bool "DMA support for DW SPI controller on Intel MID platform"
-	depends on SPI_DW_PCI && DW_DMAC_PCI
+	depends on PCI
 
 config SPI_DW_MMIO
 	tristate "Memory-mapped io interface driver for DW SPI core"
-	depends on SPI_DESIGNWARE
+	depends on HAS_IOMEM
+
+endif
 
 config SPI_DLN2
        tristate "Diolan DLN-2 USB SPI adapter"
@@ -844,6 +847,7 @@ config SPI_TXX9
 config SPI_UNIPHIER
 	tristate "Socionext UniPhier SPI Controller"
 	depends on (ARCH_UNIPHIER || COMPILE_TEST) && OF
+	depends on HAS_IOMEM
 	help
 	  This enables a driver for the Socionext UniPhier SoC SCSSI SPI controller.
 
@@ -910,6 +914,12 @@ config SPI_ZYNQMP_GQSPI
 	help
 	  Enables Xilinx GQSPI controller driver for Zynq UltraScale+ MPSoC.
 
+config SPI_AMD
+	tristate "AMD SPI controller"
+	depends on SPI_MASTER || COMPILE_TEST
+	help
+	  Enables SPI controller driver for AMD SoC.
+
 #
 # Add new SPI master controllers in alphabetical order above this line
 #
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 28f601327f8c..d2e41d3d464a 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -36,9 +36,10 @@ obj-$(CONFIG_SPI_COLDFIRE_QSPI)		+= spi-coldfire-qspi.o
 obj-$(CONFIG_SPI_DAVINCI)		+= spi-davinci.o
 obj-$(CONFIG_SPI_DLN2)			+= spi-dln2.o
 obj-$(CONFIG_SPI_DESIGNWARE)		+= spi-dw.o
+spi-dw-y				:= spi-dw-core.o
+spi-dw-$(CONFIG_SPI_DW_DMA)		+= spi-dw-dma.o
 obj-$(CONFIG_SPI_DW_MMIO)		+= spi-dw-mmio.o
-obj-$(CONFIG_SPI_DW_PCI)		+= spi-dw-midpci.o
-spi-dw-midpci-objs			:= spi-dw-pci.o spi-dw-mid.o
+obj-$(CONFIG_SPI_DW_PCI)		+= spi-dw-pci.o
 obj-$(CONFIG_SPI_EFM32)			+= spi-efm32.o
 obj-$(CONFIG_SPI_EP93XX)		+= spi-ep93xx.o
 obj-$(CONFIG_SPI_FALCON)		+= spi-falcon.o
@@ -127,6 +128,7 @@ obj-$(CONFIG_SPI_XLP)			+= spi-xlp.o
 obj-$(CONFIG_SPI_XTENSA_XTFPGA)		+= spi-xtensa-xtfpga.o
 obj-$(CONFIG_SPI_ZYNQ_QSPI)		+= spi-zynq-qspi.o
 obj-$(CONFIG_SPI_ZYNQMP_GQSPI)		+= spi-zynqmp-gqspi.o
+obj-$(CONFIG_SPI_AMD)			+= spi-amd.o
 
 # SPI slave protocol handlers
 obj-$(CONFIG_SPI_SLAVE_TIME)		+= spi-slave-time.o
diff --git a/drivers/spi/spi-amd.c b/drivers/spi/spi-amd.c
new file mode 100644
index 000000000000..d0aacd4de1b9
--- /dev/null
+++ b/drivers/spi/spi-amd.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+//
+// AMD SPI controller driver
+//
+// Copyright (c) 2020, Advanced Micro Devices, Inc.
+//
+// Author: Sanjay R Mehta <sanju.mehta@amd.com>
+
+#include <linux/acpi.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/spi/spi.h>
+
+#define AMD_SPI_CTRL0_REG	0x00
+#define AMD_SPI_EXEC_CMD	BIT(16)
+#define AMD_SPI_FIFO_CLEAR	BIT(20)
+#define AMD_SPI_BUSY		BIT(31)
+
+#define AMD_SPI_OPCODE_MASK	0xFF
+
+#define AMD_SPI_ALT_CS_REG	0x1D
+#define AMD_SPI_ALT_CS_MASK	0x3
+
+#define AMD_SPI_FIFO_BASE	0x80
+#define AMD_SPI_TX_COUNT_REG	0x48
+#define AMD_SPI_RX_COUNT_REG	0x4B
+#define AMD_SPI_STATUS_REG	0x4C
+
+#define AMD_SPI_MEM_SIZE	200
+
+/* M_CMD OP codes for SPI */
+#define AMD_SPI_XFER_TX		1
+#define AMD_SPI_XFER_RX		2
+
+struct amd_spi {
+	void __iomem *io_remap_addr;
+	unsigned long io_base_addr;
+	u32 rom_addr;
+	u8 chip_select;
+};
+
+static inline u8 amd_spi_readreg8(struct spi_master *master, int idx)
+{
+	struct amd_spi *amd_spi = spi_master_get_devdata(master);
+
+	return ioread8((u8 __iomem *)amd_spi->io_remap_addr + idx);
+}
+
+static inline void amd_spi_writereg8(struct spi_master *master, int idx,
+				     u8 val)
+{
+	struct amd_spi *amd_spi = spi_master_get_devdata(master);
+
+	iowrite8(val, ((u8 __iomem *)amd_spi->io_remap_addr + idx));
+}
+
+static inline void amd_spi_setclear_reg8(struct spi_master *master, int idx,
+					 u8 set, u8 clear)
+{
+	u8 tmp = amd_spi_readreg8(master, idx);
+
+	tmp = (tmp & ~clear) | set;
+	amd_spi_writereg8(master, idx, tmp);
+}
+
+static inline u32 amd_spi_readreg32(struct spi_master *master, int idx)
+{
+	struct amd_spi *amd_spi = spi_master_get_devdata(master);
+
+	return ioread32((u8 __iomem *)amd_spi->io_remap_addr + idx);
+}
+
+static inline void amd_spi_writereg32(struct spi_master *master, int idx,
+				      u32 val)
+{
+	struct amd_spi *amd_spi = spi_master_get_devdata(master);
+
+	iowrite32(val, ((u8 __iomem *)amd_spi->io_remap_addr + idx));
+}
+
+static inline void amd_spi_setclear_reg32(struct spi_master *master, int idx,
+					  u32 set, u32 clear)
+{
+	u32 tmp = amd_spi_readreg32(master, idx);
+
+	tmp = (tmp & ~clear) | set;
+	amd_spi_writereg32(master, idx, tmp);
+}
+
+static void amd_spi_select_chip(struct spi_master *master)
+{
+	struct amd_spi *amd_spi = spi_master_get_devdata(master);
+	u8 chip_select = amd_spi->chip_select;
+
+	amd_spi_setclear_reg8(master, AMD_SPI_ALT_CS_REG, chip_select,
+			      AMD_SPI_ALT_CS_MASK);
+}
+
+static void amd_spi_clear_fifo_ptr(struct spi_master *master)
+{
+	amd_spi_setclear_reg32(master, AMD_SPI_CTRL0_REG, AMD_SPI_FIFO_CLEAR,
+			       AMD_SPI_FIFO_CLEAR);
+}
+
+static void amd_spi_set_opcode(struct spi_master *master, u8 cmd_opcode)
+{
+	amd_spi_setclear_reg32(master, AMD_SPI_CTRL0_REG, cmd_opcode,
+			       AMD_SPI_OPCODE_MASK);
+}
+
+static inline void amd_spi_set_rx_count(struct spi_master *master,
+					u8 rx_count)
+{
+	amd_spi_setclear_reg8(master, AMD_SPI_RX_COUNT_REG, rx_count, 0xff);
+}
+
+static inline void amd_spi_set_tx_count(struct spi_master *master,
+					u8 tx_count)
+{
+	amd_spi_setclear_reg8(master, AMD_SPI_TX_COUNT_REG, tx_count, 0xff);
+}
+
+static inline int amd_spi_busy_wait(struct amd_spi *amd_spi)
+{
+	bool spi_busy;
+	int timeout = 100000;
+
+	/* poll for SPI bus to become idle */
+	spi_busy = (ioread32((u8 __iomem *)amd_spi->io_remap_addr +
+		    AMD_SPI_CTRL0_REG) & AMD_SPI_BUSY) == AMD_SPI_BUSY;
+	while (spi_busy) {
+		usleep_range(10, 20);
+		if (timeout-- < 0)
+			return -ETIMEDOUT;
+
+		spi_busy = (ioread32((u8 __iomem *)amd_spi->io_remap_addr +
+			    AMD_SPI_CTRL0_REG) & AMD_SPI_BUSY) == AMD_SPI_BUSY;
+	}
+
+	return 0;
+}
+
+static void amd_spi_execute_opcode(struct spi_master *master)
+{
+	struct amd_spi *amd_spi = spi_master_get_devdata(master);
+
+	/* Set ExecuteOpCode bit in the CTRL0 register */
+	amd_spi_setclear_reg32(master, AMD_SPI_CTRL0_REG, AMD_SPI_EXEC_CMD,
+			       AMD_SPI_EXEC_CMD);
+
+	amd_spi_busy_wait(amd_spi);
+}
+
+static int amd_spi_master_setup(struct spi_device *spi)
+{
+	struct spi_master *master = spi->master;
+
+	amd_spi_clear_fifo_ptr(master);
+
+	return 0;
+}
+
+static inline int amd_spi_fifo_xfer(struct amd_spi *amd_spi,
+				    struct spi_master *master,
+				    struct spi_message *message)
+{
+	struct spi_transfer *xfer = NULL;
+	u8 cmd_opcode;
+	u8 *buf = NULL;
+	u32 m_cmd = 0;
+	u32 i = 0;
+	u32 tx_len = 0, rx_len = 0;
+
+	list_for_each_entry(xfer, &message->transfers,
+			    transfer_list) {
+		if (xfer->rx_buf)
+			m_cmd = AMD_SPI_XFER_RX;
+		if (xfer->tx_buf)
+			m_cmd = AMD_SPI_XFER_TX;
+
+		if (m_cmd & AMD_SPI_XFER_TX) {
+			buf = (u8 *)xfer->tx_buf;
+			tx_len = xfer->len - 1;
+			cmd_opcode = *(u8 *)xfer->tx_buf;
+			buf++;
+			amd_spi_set_opcode(master, cmd_opcode);
+
+			/* Write data into the FIFO. */
+			for (i = 0; i < tx_len; i++) {
+				iowrite8(buf[i],
+					 ((u8 __iomem *)amd_spi->io_remap_addr +
+					 AMD_SPI_FIFO_BASE + i));
+			}
+
+			amd_spi_set_tx_count(master, tx_len);
+			amd_spi_clear_fifo_ptr(master);
+			/* Execute command */
+			amd_spi_execute_opcode(master);
+		}
+		if (m_cmd & AMD_SPI_XFER_RX) {
+			/*
+			 * Store no. of bytes to be received from
+			 * FIFO
+			 */
+			rx_len = xfer->len;
+			buf = (u8 *)xfer->rx_buf;
+			amd_spi_set_rx_count(master, rx_len);
+			amd_spi_clear_fifo_ptr(master);
+			/* Execute command */
+			amd_spi_execute_opcode(master);
+			/* Read data from FIFO to receive buffer  */
+			for (i = 0; i < rx_len; i++)
+				buf[i] = amd_spi_readreg8(master,
+							  AMD_SPI_FIFO_BASE +
+							  tx_len + i);
+		}
+	}
+
+	/* Update statistics */
+	message->actual_length = tx_len + rx_len + 1;
+	/* complete the transaction */
+	message->status = 0;
+	spi_finalize_current_message(master);
+
+	return 0;
+}
+
+static int amd_spi_master_transfer(struct spi_master *master,
+				   struct spi_message *msg)
+{
+	struct amd_spi *amd_spi = spi_master_get_devdata(master);
+	struct spi_device *spi = msg->spi;
+
+	amd_spi->chip_select = spi->chip_select;
+	amd_spi_select_chip(master);
+
+	/*
+	 * Extract spi_transfers from the spi message and
+	 * program the controller.
+	 */
+	amd_spi_fifo_xfer(amd_spi, master, msg);
+
+	return 0;
+}
+
+static int amd_spi_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct spi_master *master;
+	struct amd_spi *amd_spi;
+	struct resource *res;
+	int err = 0;
+
+	/* Allocate storage for spi_master and driver private data */
+	master = spi_alloc_master(dev, sizeof(struct amd_spi));
+	if (!master) {
+		dev_err(dev, "Error allocating SPI master\n");
+		return -ENOMEM;
+	}
+
+	amd_spi = spi_master_get_devdata(master);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	amd_spi->io_remap_addr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(amd_spi->io_remap_addr)) {
+		err = PTR_ERR(amd_spi->io_remap_addr);
+		dev_err(dev, "error %d ioremap of SPI registers failed\n", err);
+		goto err_free_master;
+	}
+	dev_dbg(dev, "io_remap_address: %p\n", amd_spi->io_remap_addr);
+
+	/* Initialize the spi_master fields */
+	master->bus_num = 0;
+	master->num_chipselect = 4;
+	master->mode_bits = 0;
+	master->flags = SPI_MASTER_HALF_DUPLEX;
+	master->setup = amd_spi_master_setup;
+	master->transfer_one_message = amd_spi_master_transfer;
+
+	/* Register the controller with SPI framework */
+	err = devm_spi_register_master(dev, master);
+	if (err) {
+		dev_err(dev, "error %d registering SPI controller\n", err);
+		goto err_free_master;
+	}
+
+	return 0;
+
+err_free_master:
+	spi_master_put(master);
+
+	return err;
+}
+
+static const struct acpi_device_id spi_acpi_match[] = {
+	{ "AMDI0061", 0 },
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, spi_acpi_match);
+
+static struct platform_driver amd_spi_driver = {
+	.driver = {
+		.name = "amd_spi",
+		.acpi_match_table = ACPI_PTR(spi_acpi_match),
+	},
+	.probe = amd_spi_probe,
+};
+
+module_platform_driver(amd_spi_driver);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Sanjay Mehta <sanju.mehta@amd.com>");
+MODULE_DESCRIPTION("AMD SPI Master Controller Driver");
diff --git a/drivers/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c
index e450ee17787f..fcde419e480c 100644
--- a/drivers/spi/spi-armada-3700.c
+++ b/drivers/spi/spi-armada-3700.c
@@ -276,11 +276,11 @@ static int a3700_spi_fifo_flush(struct a3700_spi *a3700_spi)
 	return -ETIMEDOUT;
 }
 
-static int a3700_spi_init(struct a3700_spi *a3700_spi)
+static void a3700_spi_init(struct a3700_spi *a3700_spi)
 {
 	struct spi_master *master = a3700_spi->master;
 	u32 val;
-	int i, ret = 0;
+	int i;
 
 	/* Reset SPI unit */
 	val = spireg_read(a3700_spi, A3700_SPI_IF_CFG_REG);
@@ -311,8 +311,6 @@ static int a3700_spi_init(struct a3700_spi *a3700_spi)
 	/* Mask the interrupts and clear cause bits */
 	spireg_write(a3700_spi, A3700_SPI_INT_MASK_REG, 0);
 	spireg_write(a3700_spi, A3700_SPI_INT_STAT_REG, ~0U);
-
-	return ret;
 }
 
 static irqreturn_t a3700_spi_interrupt(int irq, void *dev_id)
@@ -886,9 +884,7 @@ static int a3700_spi_probe(struct platform_device *pdev)
 	master->min_speed_hz = DIV_ROUND_UP(clk_get_rate(spi->clk),
 						A3700_SPI_MAX_PRESCALE);
 
-	ret = a3700_spi_init(spi);
-	if (ret)
-		goto error_clk;
+	a3700_spi_init(spi);
 
 	ret = devm_request_irq(dev, spi->irq, a3700_spi_interrupt, 0,
 			       dev_name(dev), master);
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 013458cabe3c..57ee8c3b7972 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -706,6 +706,7 @@ static void atmel_spi_next_xfer_pio(struct spi_master *master,
 static int atmel_spi_next_xfer_dma_submit(struct spi_master *master,
 				struct spi_transfer *xfer,
 				u32 *plen)
+	__must_hold(&as->lock)
 {
 	struct atmel_spi	*as = spi_master_get_devdata(master);
 	struct dma_chan		*rxchan = master->dma_rx;
diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c
index eb9b78a90dcf..af86e6d6e16b 100644
--- a/drivers/spi/spi-axi-spi-engine.c
+++ b/drivers/spi/spi-axi-spi-engine.c
@@ -489,22 +489,6 @@ static int spi_engine_probe(struct platform_device *pdev)
 
 	spin_lock_init(&spi_engine->lock);
 
-	spi_engine->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(spi_engine->base)) {
-		ret = PTR_ERR(spi_engine->base);
-		goto err_put_master;
-	}
-
-	version = readl(spi_engine->base + SPI_ENGINE_REG_VERSION);
-	if (SPI_ENGINE_VERSION_MAJOR(version) != 1) {
-		dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%c\n",
-			SPI_ENGINE_VERSION_MAJOR(version),
-			SPI_ENGINE_VERSION_MINOR(version),
-			SPI_ENGINE_VERSION_PATCH(version));
-		ret = -ENODEV;
-		goto err_put_master;
-	}
-
 	spi_engine->clk = devm_clk_get(&pdev->dev, "s_axi_aclk");
 	if (IS_ERR(spi_engine->clk)) {
 		ret = PTR_ERR(spi_engine->clk);
@@ -525,6 +509,22 @@ static int spi_engine_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_clk_disable;
 
+	spi_engine->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(spi_engine->base)) {
+		ret = PTR_ERR(spi_engine->base);
+		goto err_ref_clk_disable;
+	}
+
+	version = readl(spi_engine->base + SPI_ENGINE_REG_VERSION);
+	if (SPI_ENGINE_VERSION_MAJOR(version) != 1) {
+		dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%c\n",
+			SPI_ENGINE_VERSION_MAJOR(version),
+			SPI_ENGINE_VERSION_MINOR(version),
+			SPI_ENGINE_VERSION_PATCH(version));
+		ret = -ENODEV;
+		goto err_ref_clk_disable;
+	}
+
 	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_RESET);
 	writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
 	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 23d295f36c80..681d09085175 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -91,6 +91,7 @@
 #define MSPI_MSPI_STATUS			0x020
 #define MSPI_CPTQP				0x024
 #define MSPI_SPCR3				0x028
+#define MSPI_REV				0x02c
 #define MSPI_TXRAM				0x040
 #define MSPI_RXRAM				0x0c0
 #define MSPI_CDRAM				0x140
@@ -106,14 +107,22 @@
 #define MSPI_SPCR2_SPE				BIT(6)
 #define MSPI_SPCR2_CONT_AFTER_CMD		BIT(7)
 
+#define MSPI_SPCR3_FASTBR			BIT(0)
+#define MSPI_SPCR3_FASTDT			BIT(1)
+#define MSPI_SPCR3_SYSCLKSEL_MASK		GENMASK(11, 10)
+#define MSPI_SPCR3_SYSCLKSEL_27			(MSPI_SPCR3_SYSCLKSEL_MASK & \
+						 ~(BIT(10) | BIT(11)))
+#define MSPI_SPCR3_SYSCLKSEL_108		(MSPI_SPCR3_SYSCLKSEL_MASK & \
+						 BIT(11))
+
 #define MSPI_MSPI_STATUS_SPIF			BIT(0)
 
 #define INTR_BASE_BIT_SHIFT			0x02
 #define INTR_COUNT				0x07
 
 #define NUM_CHIPSELECT				4
-#define QSPI_SPBR_MIN				8U
 #define QSPI_SPBR_MAX				255U
+#define MSPI_BASE_FREQ				27000000UL
 
 #define OPCODE_DIOR				0xBB
 #define OPCODE_QIOR				0xEB
@@ -217,6 +226,9 @@ struct bcm_qspi {
 	struct bcm_qspi_dev_id *dev_ids;
 	struct completion mspi_done;
 	struct completion bspi_done;
+	u8 mspi_maj_rev;
+	u8 mspi_min_rev;
+	bool mspi_spcr3_sysclk;
 };
 
 static inline bool has_bspi(struct bcm_qspi *qspi)
@@ -224,6 +236,36 @@ static inline bool has_bspi(struct bcm_qspi *qspi)
 	return qspi->bspi_mode;
 }
 
+/* hardware supports spcr3 and fast baud-rate  */
+static inline bool bcm_qspi_has_fastbr(struct bcm_qspi *qspi)
+{
+	if (!has_bspi(qspi) &&
+	    ((qspi->mspi_maj_rev >= 1) &&
+	     (qspi->mspi_min_rev >= 5)))
+		return true;
+
+	return false;
+}
+
+/* hardware supports sys clk 108Mhz  */
+static inline bool bcm_qspi_has_sysclk_108(struct bcm_qspi *qspi)
+{
+	if (!has_bspi(qspi) && (qspi->mspi_spcr3_sysclk ||
+	    ((qspi->mspi_maj_rev >= 1) &&
+	     (qspi->mspi_min_rev >= 6))))
+		return true;
+
+	return false;
+}
+
+static inline int bcm_qspi_spbr_min(struct bcm_qspi *qspi)
+{
+	if (bcm_qspi_has_fastbr(qspi))
+		return 1;
+	else
+		return 8;
+}
+
 /* Read qspi controller register*/
 static inline u32 bcm_qspi_read(struct bcm_qspi *qspi, enum base_type type,
 				unsigned int offset)
@@ -531,16 +573,39 @@ static void bcm_qspi_hw_set_parms(struct bcm_qspi *qspi,
 	if (xp->speed_hz)
 		spbr = qspi->base_clk / (2 * xp->speed_hz);
 
-	spcr = clamp_val(spbr, QSPI_SPBR_MIN, QSPI_SPBR_MAX);
+	spcr = clamp_val(spbr, bcm_qspi_spbr_min(qspi), QSPI_SPBR_MAX);
 	bcm_qspi_write(qspi, MSPI, MSPI_SPCR0_LSB, spcr);
 
-	spcr = MSPI_MASTER_BIT;
+	if (!qspi->mspi_maj_rev)
+		/* legacy controller */
+		spcr = MSPI_MASTER_BIT;
+	else
+		spcr = 0;
+
 	/* for 16 bit the data should be zero */
 	if (xp->bits_per_word != 16)
 		spcr |= xp->bits_per_word << 2;
 	spcr |= xp->mode & 3;
+
 	bcm_qspi_write(qspi, MSPI, MSPI_SPCR0_MSB, spcr);
 
+	if (bcm_qspi_has_fastbr(qspi)) {
+		spcr = 0;
+
+		/* enable fastbr */
+		spcr |=	MSPI_SPCR3_FASTBR;
+
+		if (bcm_qspi_has_sysclk_108(qspi)) {
+			/* SYSCLK_108 */
+			spcr |= MSPI_SPCR3_SYSCLKSEL_108;
+			qspi->base_clk = MSPI_BASE_FREQ * 4;
+			/* Change spbr as we changed sysclk */
+			bcm_qspi_write(qspi, MSPI, MSPI_SPCR0_LSB, 4);
+		}
+
+		bcm_qspi_write(qspi, MSPI, MSPI_SPCR3, spcr);
+	}
+
 	qspi->last_parms = *xp;
 }
 
@@ -612,19 +677,15 @@ static int update_qspi_trans_byte_count(struct bcm_qspi *qspi,
 		if (qt->trans->cs_change &&
 		    (flags & TRANS_STATUS_BREAK_CS_CHANGE))
 			ret |= TRANS_STATUS_BREAK_CS_CHANGE;
-		if (ret)
-			goto done;
 
-		dev_dbg(&qspi->pdev->dev, "advance msg exit\n");
 		if (bcm_qspi_mspi_transfer_is_last(qspi, qt))
-			ret = TRANS_STATUS_BREAK_EOM;
+			ret |= TRANS_STATUS_BREAK_EOM;
 		else
-			ret = TRANS_STATUS_BREAK_NO_BYTES;
+			ret |= TRANS_STATUS_BREAK_NO_BYTES;
 
 		qt->trans = NULL;
 	}
 
-done:
 	dev_dbg(&qspi->pdev->dev, "trans %p len %d byte %d ret %x\n",
 		qt->trans, qt->trans ? qt->trans->len : 0, qt->byte, ret);
 	return ret;
@@ -670,7 +731,7 @@ static void read_from_hw(struct bcm_qspi *qspi, int slots)
 			if (buf)
 				buf[tp.byte] = read_rxram_slot_u8(qspi, slot);
 			dev_dbg(&qspi->pdev->dev, "RD %02x\n",
-				buf ? buf[tp.byte] : 0xff);
+				buf ? buf[tp.byte] : 0x0);
 		} else {
 			u16 *buf = tp.trans->rx_buf;
 
@@ -678,7 +739,7 @@ static void read_from_hw(struct bcm_qspi *qspi, int slots)
 				buf[tp.byte / 2] = read_rxram_slot_u16(qspi,
 								      slot);
 			dev_dbg(&qspi->pdev->dev, "RD %04x\n",
-				buf ? buf[tp.byte] : 0xffff);
+				buf ? buf[tp.byte / 2] : 0x0);
 		}
 
 		update_qspi_trans_byte_count(qspi, &tp,
@@ -733,13 +794,13 @@ static int write_to_hw(struct bcm_qspi *qspi, struct spi_device *spi)
 	while (!tstatus && slot < MSPI_NUM_CDRAM) {
 		if (tp.trans->bits_per_word <= 8) {
 			const u8 *buf = tp.trans->tx_buf;
-			u8 val = buf ? buf[tp.byte] : 0xff;
+			u8 val = buf ? buf[tp.byte] : 0x00;
 
 			write_txram_slot_u8(qspi, slot, val);
 			dev_dbg(&qspi->pdev->dev, "WR %02x\n", val);
 		} else {
 			const u16 *buf = tp.trans->tx_buf;
-			u16 val = buf ? buf[tp.byte / 2] : 0xffff;
+			u16 val = buf ? buf[tp.byte / 2] : 0x0000;
 
 			write_txram_slot_u16(qspi, slot, val);
 			dev_dbg(&qspi->pdev->dev, "WR %04x\n", val);
@@ -771,7 +832,16 @@ static int write_to_hw(struct bcm_qspi *qspi, struct spi_device *spi)
 	bcm_qspi_write(qspi, MSPI, MSPI_NEWQP, 0);
 	bcm_qspi_write(qspi, MSPI, MSPI_ENDQP, slot - 1);
 
-	if (tstatus & TRANS_STATUS_BREAK_DESELECT) {
+	/*
+	 *  case 1) EOM =1, cs_change =0: SSb inactive
+	 *  case 2) EOM =1, cs_change =1: SSb stay active
+	 *  case 3) EOM =0, cs_change =0: SSb stay active
+	 *  case 4) EOM =0, cs_change =1: SSb inactive
+	 */
+	if (((tstatus & TRANS_STATUS_BREAK_DESELECT)
+	     == TRANS_STATUS_BREAK_CS_CHANGE) ||
+	    ((tstatus & TRANS_STATUS_BREAK_DESELECT)
+	     == TRANS_STATUS_BREAK_EOM)) {
 		mspi_cdram = read_cdram_slot(qspi, slot - 1) &
 			~MSPI_CDRAM_CONT_BIT;
 		write_cdram_slot(qspi, slot - 1, mspi_cdram);
@@ -1190,8 +1260,51 @@ static const struct spi_controller_mem_ops bcm_qspi_mem_ops = {
 	.exec_op = bcm_qspi_exec_mem_op,
 };
 
+struct bcm_qspi_data {
+	bool	has_mspi_rev;
+	bool	has_spcr3_sysclk;
+};
+
+static const struct bcm_qspi_data bcm_qspi_no_rev_data = {
+	.has_mspi_rev	= false,
+	.has_spcr3_sysclk = false,
+};
+
+static const struct bcm_qspi_data bcm_qspi_rev_data = {
+	.has_mspi_rev	= true,
+	.has_spcr3_sysclk = false,
+};
+
+static const struct bcm_qspi_data bcm_qspi_spcr3_data = {
+	.has_mspi_rev	= true,
+	.has_spcr3_sysclk = true,
+};
+
 static const struct of_device_id bcm_qspi_of_match[] = {
-	{ .compatible = "brcm,spi-bcm-qspi" },
+	{
+		.compatible = "brcm,spi-bcm7425-qspi",
+		.data = &bcm_qspi_no_rev_data,
+	},
+	{
+		.compatible = "brcm,spi-bcm7429-qspi",
+		.data = &bcm_qspi_no_rev_data,
+	},
+	{
+		.compatible = "brcm,spi-bcm7435-qspi",
+		.data = &bcm_qspi_no_rev_data,
+	},
+	{
+		.compatible = "brcm,spi-bcm-qspi",
+		.data = &bcm_qspi_rev_data,
+	},
+	{
+		.compatible = "brcm,spi-bcm7216-qspi",
+		.data = &bcm_qspi_spcr3_data,
+	},
+	{
+		.compatible = "brcm,spi-bcm7278-qspi",
+		.data = &bcm_qspi_spcr3_data,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, bcm_qspi_of_match);
@@ -1199,12 +1312,15 @@ MODULE_DEVICE_TABLE(of, bcm_qspi_of_match);
 int bcm_qspi_probe(struct platform_device *pdev,
 		   struct bcm_qspi_soc_intc *soc_intc)
 {
+	const struct of_device_id *of_id = NULL;
+	const struct bcm_qspi_data *data;
 	struct device *dev = &pdev->dev;
 	struct bcm_qspi *qspi;
 	struct spi_master *master;
 	struct resource *res;
 	int irq, ret = 0, num_ints = 0;
 	u32 val;
+	u32 rev = 0;
 	const char *name = NULL;
 	int num_irqs = ARRAY_SIZE(qspi_irq_tab);
 
@@ -1212,9 +1328,12 @@ int bcm_qspi_probe(struct platform_device *pdev,
 	if (!dev->of_node)
 		return -ENODEV;
 
-	if (!of_match_node(bcm_qspi_of_match, dev->of_node))
+	of_id = of_match_node(bcm_qspi_of_match, dev->of_node);
+	if (!of_id)
 		return -ENODEV;
 
+	data = of_id->data;
+
 	master = spi_alloc_master(dev, sizeof(struct bcm_qspi));
 	if (!master) {
 		dev_err(dev, "error allocating spi_master\n");
@@ -1222,6 +1341,11 @@ int bcm_qspi_probe(struct platform_device *pdev,
 	}
 
 	qspi = spi_master_get_devdata(master);
+
+	qspi->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(qspi->clk))
+		return PTR_ERR(qspi->clk);
+
 	qspi->pdev = pdev;
 	qspi->trans_pos.trans = NULL;
 	qspi->trans_pos.byte = 0;
@@ -1335,13 +1459,6 @@ int bcm_qspi_probe(struct platform_device *pdev,
 		qspi->soc_intc = NULL;
 	}
 
-	qspi->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(qspi->clk)) {
-		dev_warn(dev, "unable to get clock\n");
-		ret = PTR_ERR(qspi->clk);
-		goto qspi_probe_err;
-	}
-
 	ret = clk_prepare_enable(qspi->clk);
 	if (ret) {
 		dev_err(dev, "failed to prepare clock\n");
@@ -1349,7 +1466,19 @@ int bcm_qspi_probe(struct platform_device *pdev,
 	}
 
 	qspi->base_clk = clk_get_rate(qspi->clk);
-	qspi->max_speed_hz = qspi->base_clk / (QSPI_SPBR_MIN * 2);
+
+	if (data->has_mspi_rev) {
+		rev = bcm_qspi_read(qspi, MSPI, MSPI_REV);
+		/* some older revs do not have a MSPI_REV register */
+		if ((rev & 0xff) == 0xff)
+			rev = 0;
+	}
+
+	qspi->mspi_maj_rev = (rev >> 4) & 0xf;
+	qspi->mspi_min_rev = rev & 0xf;
+	qspi->mspi_spcr3_sysclk = data->has_spcr3_sysclk;
+
+	qspi->max_speed_hz = qspi->base_clk / (bcm_qspi_spbr_min(qspi) * 2);
 
 	bcm_qspi_hw_init(qspi);
 	init_completion(&qspi->mspi_done);
@@ -1406,7 +1535,7 @@ static int __maybe_unused bcm_qspi_suspend(struct device *dev)
 			bcm_qspi_read(qspi, BSPI, BSPI_STRAP_OVERRIDE_CTRL);
 
 	spi_master_suspend(qspi->master);
-	clk_disable(qspi->clk);
+	clk_disable_unprepare(qspi->clk);
 	bcm_qspi_hw_uninit(qspi);
 
 	return 0;
@@ -1424,7 +1553,7 @@ static int __maybe_unused bcm_qspi_resume(struct device *dev)
 		qspi->soc_intc->bcm_qspi_int_set(qspi->soc_intc, MSPI_DONE,
 						 true);
 
-	ret = clk_enable(qspi->clk);
+	ret = clk_prepare_enable(qspi->clk);
 	if (!ret)
 		spi_master_resume(qspi->master);
 
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 11c235879bb7..237bd306c268 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -191,12 +191,12 @@ static void bcm2835_debugfs_remove(struct bcm2835_spi *bs)
 }
 #endif /* CONFIG_DEBUG_FS */
 
-static inline u32 bcm2835_rd(struct bcm2835_spi *bs, unsigned reg)
+static inline u32 bcm2835_rd(struct bcm2835_spi *bs, unsigned int reg)
 {
 	return readl(bs->regs + reg);
 }
 
-static inline void bcm2835_wr(struct bcm2835_spi *bs, unsigned reg, u32 val)
+static inline void bcm2835_wr(struct bcm2835_spi *bs, unsigned int reg, u32 val)
 {
 	writel(val, bs->regs + reg);
 }
@@ -940,6 +940,7 @@ static int bcm2835_dma_init(struct spi_controller *ctlr, struct device *dev,
 	if (dma_mapping_error(ctlr->dma_tx->device->dev, bs->fill_tx_addr)) {
 		dev_err(dev, "cannot map zero page - not using DMA mode\n");
 		bs->fill_tx_addr = 0;
+		ret = -ENOMEM;
 		goto err_release;
 	}
 
@@ -949,6 +950,7 @@ static int bcm2835_dma_init(struct spi_controller *ctlr, struct device *dev,
 						     DMA_MEM_TO_DEV, 0);
 	if (!bs->fill_tx_desc) {
 		dev_err(dev, "cannot prepare fill_tx_desc - not using DMA mode\n");
+		ret = -ENOMEM;
 		goto err_release;
 	}
 
@@ -979,6 +981,7 @@ static int bcm2835_dma_init(struct spi_controller *ctlr, struct device *dev,
 	if (dma_mapping_error(ctlr->dma_rx->device->dev, bs->clear_rx_addr)) {
 		dev_err(dev, "cannot map clear_rx_cs - not using DMA mode\n");
 		bs->clear_rx_addr = 0;
+		ret = -ENOMEM;
 		goto err_release;
 	}
 
@@ -989,6 +992,7 @@ static int bcm2835_dma_init(struct spi_controller *ctlr, struct device *dev,
 					   DMA_MEM_TO_DEV, 0);
 		if (!bs->clear_rx_desc[i]) {
 			dev_err(dev, "cannot prepare clear_rx_desc - not using DMA mode\n");
+			ret = -ENOMEM;
 			goto err_release;
 		}
 
@@ -1347,7 +1351,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev)
 		goto out_dma_release;
 	}
 
-	err = devm_spi_register_controller(&pdev->dev, ctlr);
+	err = spi_register_controller(ctlr);
 	if (err) {
 		dev_err(&pdev->dev, "could not register SPI controller: %d\n",
 			err);
@@ -1374,17 +1378,28 @@ static int bcm2835_spi_remove(struct platform_device *pdev)
 
 	bcm2835_debugfs_remove(bs);
 
+	spi_unregister_controller(ctlr);
+
+	bcm2835_dma_release(ctlr, bs);
+
 	/* Clear FIFOs, and disable the HW block */
 	bcm2835_wr(bs, BCM2835_SPI_CS,
 		   BCM2835_SPI_CS_CLEAR_RX | BCM2835_SPI_CS_CLEAR_TX);
 
 	clk_disable_unprepare(bs->clk);
 
-	bcm2835_dma_release(ctlr, bs);
-
 	return 0;
 }
 
+static void bcm2835_spi_shutdown(struct platform_device *pdev)
+{
+	int ret;
+
+	ret = bcm2835_spi_remove(pdev);
+	if (ret)
+		dev_err(&pdev->dev, "failed to shutdown\n");
+}
+
 static const struct of_device_id bcm2835_spi_match[] = {
 	{ .compatible = "brcm,bcm2835-spi", },
 	{}
@@ -1398,6 +1413,7 @@ static struct platform_driver bcm2835_spi_driver = {
 	},
 	.probe		= bcm2835_spi_probe,
 	.remove		= bcm2835_spi_remove,
+	.shutdown	= bcm2835_spi_shutdown,
 };
 module_platform_driver(bcm2835_spi_driver);
 
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index a2162ff56a12..c331efd6e86b 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -569,7 +569,7 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev)
 		goto out_clk_disable;
 	}
 
-	err = devm_spi_register_master(&pdev->dev, master);
+	err = spi_register_master(master);
 	if (err) {
 		dev_err(&pdev->dev, "could not register SPI master: %d\n", err);
 		goto out_clk_disable;
@@ -593,6 +593,8 @@ static int bcm2835aux_spi_remove(struct platform_device *pdev)
 
 	bcm2835aux_debugfs_remove(bs);
 
+	spi_unregister_master(master);
+
 	bcm2835aux_spi_reset_hw(bs);
 
 	/* disable the HW block by releasing the clock */
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw-core.c
index 31e3f866d11a..323c66c5db50 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw-core.c
@@ -24,74 +24,34 @@ struct chip_data {
 	u8 tmode;		/* TR/TO/RO/EEPROM */
 	u8 type;		/* SPI/SSP/MicroWire */
 
-	u8 poll_mode;		/* 1 means use poll mode */
-
 	u16 clk_div;		/* baud rate divider */
 	u32 speed_hz;		/* baud rate */
-	void (*cs_control)(u32 command);
 };
 
 #ifdef CONFIG_DEBUG_FS
-#define SPI_REGS_BUFSIZE	1024
-static ssize_t dw_spi_show_regs(struct file *file, char __user *user_buf,
-		size_t count, loff_t *ppos)
-{
-	struct dw_spi *dws = file->private_data;
-	char *buf;
-	u32 len = 0;
-	ssize_t ret;
-
-	buf = kzalloc(SPI_REGS_BUFSIZE, GFP_KERNEL);
-	if (!buf)
-		return 0;
-
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"%s registers:\n", dev_name(&dws->master->dev));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"=================================\n");
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"CTRL0: \t\t0x%08x\n", dw_readl(dws, DW_SPI_CTRL0));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"CTRL1: \t\t0x%08x\n", dw_readl(dws, DW_SPI_CTRL1));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"SSIENR: \t0x%08x\n", dw_readl(dws, DW_SPI_SSIENR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"SER: \t\t0x%08x\n", dw_readl(dws, DW_SPI_SER));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"BAUDR: \t\t0x%08x\n", dw_readl(dws, DW_SPI_BAUDR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"TXFTLR: \t0x%08x\n", dw_readl(dws, DW_SPI_TXFLTR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"RXFTLR: \t0x%08x\n", dw_readl(dws, DW_SPI_RXFLTR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"TXFLR: \t\t0x%08x\n", dw_readl(dws, DW_SPI_TXFLR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"RXFLR: \t\t0x%08x\n", dw_readl(dws, DW_SPI_RXFLR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"SR: \t\t0x%08x\n", dw_readl(dws, DW_SPI_SR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"IMR: \t\t0x%08x\n", dw_readl(dws, DW_SPI_IMR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"ISR: \t\t0x%08x\n", dw_readl(dws, DW_SPI_ISR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"DMACR: \t\t0x%08x\n", dw_readl(dws, DW_SPI_DMACR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"DMATDLR: \t0x%08x\n", dw_readl(dws, DW_SPI_DMATDLR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"DMARDLR: \t0x%08x\n", dw_readl(dws, DW_SPI_DMARDLR));
-	len += scnprintf(buf + len, SPI_REGS_BUFSIZE - len,
-			"=================================\n");
-
-	ret = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-	return ret;
+
+#define DW_SPI_DBGFS_REG(_name, _off)	\
+{					\
+	.name = _name,			\
+	.offset = _off,			\
 }
 
-static const struct file_operations dw_spi_regs_ops = {
-	.owner		= THIS_MODULE,
-	.open		= simple_open,
-	.read		= dw_spi_show_regs,
-	.llseek		= default_llseek,
+static const struct debugfs_reg32 dw_spi_dbgfs_regs[] = {
+	DW_SPI_DBGFS_REG("CTRLR0", DW_SPI_CTRLR0),
+	DW_SPI_DBGFS_REG("CTRLR1", DW_SPI_CTRLR1),
+	DW_SPI_DBGFS_REG("SSIENR", DW_SPI_SSIENR),
+	DW_SPI_DBGFS_REG("SER", DW_SPI_SER),
+	DW_SPI_DBGFS_REG("BAUDR", DW_SPI_BAUDR),
+	DW_SPI_DBGFS_REG("TXFTLR", DW_SPI_TXFTLR),
+	DW_SPI_DBGFS_REG("RXFTLR", DW_SPI_RXFTLR),
+	DW_SPI_DBGFS_REG("TXFLR", DW_SPI_TXFLR),
+	DW_SPI_DBGFS_REG("RXFLR", DW_SPI_RXFLR),
+	DW_SPI_DBGFS_REG("SR", DW_SPI_SR),
+	DW_SPI_DBGFS_REG("IMR", DW_SPI_IMR),
+	DW_SPI_DBGFS_REG("ISR", DW_SPI_ISR),
+	DW_SPI_DBGFS_REG("DMACR", DW_SPI_DMACR),
+	DW_SPI_DBGFS_REG("DMATDLR", DW_SPI_DMATDLR),
+	DW_SPI_DBGFS_REG("DMARDLR", DW_SPI_DMARDLR),
 };
 
 static int dw_spi_debugfs_init(struct dw_spi *dws)
@@ -103,8 +63,11 @@ static int dw_spi_debugfs_init(struct dw_spi *dws)
 	if (!dws->debugfs)
 		return -ENOMEM;
 
-	debugfs_create_file("registers", S_IFREG | S_IRUGO,
-		dws->debugfs, (void *)dws, &dw_spi_regs_ops);
+	dws->regset.regs = dw_spi_dbgfs_regs;
+	dws->regset.nregs = ARRAY_SIZE(dw_spi_dbgfs_regs);
+	dws->regset.base = dws->regs;
+	debugfs_create_regset32("registers", 0400, dws->debugfs, &dws->regset);
+
 	return 0;
 }
 
@@ -127,13 +90,16 @@ static inline void dw_spi_debugfs_remove(struct dw_spi *dws)
 void dw_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	struct dw_spi *dws = spi_controller_get_devdata(spi->controller);
-	struct chip_data *chip = spi_get_ctldata(spi);
-
-	/* Chip select logic is inverted from spi_set_cs() */
-	if (chip && chip->cs_control)
-		chip->cs_control(!enable);
+	bool cs_high = !!(spi->mode & SPI_CS_HIGH);
 
-	if (!enable)
+	/*
+	 * DW SPI controller demands any native CS being set in order to
+	 * proceed with data transfer. So in order to activate the SPI
+	 * communications we must set a corresponding bit in the Slave
+	 * Enable register no matter whether the SPI core is configured to
+	 * support active-high or active-low CS level.
+	 */
+	if (cs_high == enable)
 		dw_writel(dws, DW_SPI_SER, BIT(spi->chip_select));
 	else if (dws->cs_override)
 		dw_writel(dws, DW_SPI_SER, 0);
@@ -265,17 +231,56 @@ static irqreturn_t dw_spi_irq(int irq, void *dev_id)
 	return dws->transfer_handler(dws);
 }
 
-/* Must be called inside pump_transfers() */
-static int poll_transfer(struct dw_spi *dws)
+/* Configure CTRLR0 for DW_apb_ssi */
+u32 dw_spi_update_cr0(struct spi_controller *master, struct spi_device *spi,
+		      struct spi_transfer *transfer)
 {
-	do {
-		dw_writer(dws);
-		dw_reader(dws);
-		cpu_relax();
-	} while (dws->rx_end > dws->rx);
+	struct chip_data *chip = spi_get_ctldata(spi);
+	u32 cr0;
 
-	return 0;
+	/* Default SPI mode is SCPOL = 0, SCPH = 0 */
+	cr0 = (transfer->bits_per_word - 1)
+		| (chip->type << SPI_FRF_OFFSET)
+		| ((((spi->mode & SPI_CPOL) ? 1 : 0) << SPI_SCOL_OFFSET) |
+		   (((spi->mode & SPI_CPHA) ? 1 : 0) << SPI_SCPH_OFFSET) |
+		   (((spi->mode & SPI_LOOP) ? 1 : 0) << SPI_SRL_OFFSET))
+		| (chip->tmode << SPI_TMOD_OFFSET);
+
+	return cr0;
+}
+EXPORT_SYMBOL_GPL(dw_spi_update_cr0);
+
+/* Configure CTRLR0 for DWC_ssi */
+u32 dw_spi_update_cr0_v1_01a(struct spi_controller *master,
+			     struct spi_device *spi,
+			     struct spi_transfer *transfer)
+{
+	struct chip_data *chip = spi_get_ctldata(spi);
+	u32 cr0;
+
+	/* CTRLR0[ 4: 0] Data Frame Size */
+	cr0 = (transfer->bits_per_word - 1);
+
+	/* CTRLR0[ 7: 6] Frame Format */
+	cr0 |= chip->type << DWC_SSI_CTRLR0_FRF_OFFSET;
+
+	/*
+	 * SPI mode (SCPOL|SCPH)
+	 * CTRLR0[ 8] Serial Clock Phase
+	 * CTRLR0[ 9] Serial Clock Polarity
+	 */
+	cr0 |= ((spi->mode & SPI_CPOL) ? 1 : 0) << DWC_SSI_CTRLR0_SCPOL_OFFSET;
+	cr0 |= ((spi->mode & SPI_CPHA) ? 1 : 0) << DWC_SSI_CTRLR0_SCPH_OFFSET;
+
+	/* CTRLR0[11:10] Transfer Mode */
+	cr0 |= chip->tmode << DWC_SSI_CTRLR0_TMOD_OFFSET;
+
+	/* CTRLR0[13] Shift Register Loop */
+	cr0 |= ((spi->mode & SPI_LOOP) ? 1 : 0) << DWC_SSI_CTRLR0_SRL_OFFSET;
+
+	return cr0;
 }
+EXPORT_SYMBOL_GPL(dw_spi_update_cr0_v1_01a);
 
 static int dw_spi_transfer_one(struct spi_controller *master,
 		struct spi_device *spi, struct spi_transfer *transfer)
@@ -313,34 +318,11 @@ static int dw_spi_transfer_one(struct spi_controller *master,
 		spi_set_clk(dws, chip->clk_div);
 	}
 
+	transfer->effective_speed_hz = dws->max_freq / chip->clk_div;
 	dws->n_bytes = DIV_ROUND_UP(transfer->bits_per_word, BITS_PER_BYTE);
-	dws->dma_width = DIV_ROUND_UP(transfer->bits_per_word, BITS_PER_BYTE);
-
-	/* Default SPI mode is SCPOL = 0, SCPH = 0 */
-	cr0 = (transfer->bits_per_word - 1)
-		| (chip->type << SPI_FRF_OFFSET)
-		| ((((spi->mode & SPI_CPOL) ? 1 : 0) << SPI_SCOL_OFFSET) |
-			(((spi->mode & SPI_CPHA) ? 1 : 0) << SPI_SCPH_OFFSET) |
-			(((spi->mode & SPI_LOOP) ? 1 : 0) << SPI_SRL_OFFSET))
-		| (chip->tmode << SPI_TMOD_OFFSET);
 
-	/*
-	 * Adjust transfer mode if necessary. Requires platform dependent
-	 * chipselect mechanism.
-	 */
-	if (chip->cs_control) {
-		if (dws->rx && dws->tx)
-			chip->tmode = SPI_TMOD_TR;
-		else if (dws->rx)
-			chip->tmode = SPI_TMOD_RO;
-		else
-			chip->tmode = SPI_TMOD_TO;
-
-		cr0 &= ~SPI_TMOD_MASK;
-		cr0 |= (chip->tmode << SPI_TMOD_OFFSET);
-	}
-
-	dw_writel(dws, DW_SPI_CTRL0, cr0);
+	cr0 = dws->update_cr0(master, spi, transfer);
+	dw_writel(dws, DW_SPI_CTRLR0, cr0);
 
 	/* Check if current transfer is a DMA transaction */
 	if (master->can_dma && master->can_dma(master, spi, transfer))
@@ -359,9 +341,9 @@ static int dw_spi_transfer_one(struct spi_controller *master,
 			spi_enable_chip(dws, 1);
 			return ret;
 		}
-	} else if (!chip->poll_mode) {
+	} else {
 		txlevel = min_t(u16, dws->fifo_len / 2, dws->len / dws->n_bytes);
-		dw_writel(dws, DW_SPI_TXFLTR, txlevel);
+		dw_writel(dws, DW_SPI_TXFTLR, txlevel);
 
 		/* Set the interrupt mask */
 		imask |= SPI_INT_TXEI | SPI_INT_TXOI |
@@ -373,14 +355,8 @@ static int dw_spi_transfer_one(struct spi_controller *master,
 
 	spi_enable_chip(dws, 1);
 
-	if (dws->dma_mapped) {
-		ret = dws->dma_ops->dma_transfer(dws, transfer);
-		if (ret < 0)
-			return ret;
-	}
-
-	if (chip->poll_mode)
-		return poll_transfer(dws);
+	if (dws->dma_mapped)
+		return dws->dma_ops->dma_transfer(dws, transfer);
 
 	return 1;
 }
@@ -399,7 +375,6 @@ static void dw_spi_handle_err(struct spi_controller *master,
 /* This may be called twice for each spi dev */
 static int dw_spi_setup(struct spi_device *spi)
 {
-	struct dw_spi_chip *chip_info = NULL;
 	struct chip_data *chip;
 
 	/* Only alloc on first setup */
@@ -411,21 +386,6 @@ static int dw_spi_setup(struct spi_device *spi)
 		spi_set_ctldata(spi, chip);
 	}
 
-	/*
-	 * Protocol drivers may change the chip settings, so...
-	 * if chip_info exists, use it
-	 */
-	chip_info = spi->controller_data;
-
-	/* chip_info doesn't always exist */
-	if (chip_info) {
-		if (chip_info->cs_control)
-			chip->cs_control = chip_info->cs_control;
-
-		chip->poll_mode = chip_info->poll_mode;
-		chip->type = chip_info->type;
-	}
-
 	chip->tmode = SPI_TMOD_TR;
 
 	return 0;
@@ -452,11 +412,11 @@ static void spi_hw_init(struct device *dev, struct dw_spi *dws)
 		u32 fifo;
 
 		for (fifo = 1; fifo < 256; fifo++) {
-			dw_writel(dws, DW_SPI_TXFLTR, fifo);
-			if (fifo != dw_readl(dws, DW_SPI_TXFLTR))
+			dw_writel(dws, DW_SPI_TXFTLR, fifo);
+			if (fifo != dw_readl(dws, DW_SPI_TXFTLR))
 				break;
 		}
-		dw_writel(dws, DW_SPI_TXFLTR, 0);
+		dw_writel(dws, DW_SPI_TXFTLR, 0);
 
 		dws->fifo_len = (fifo == 1) ? 0 : fifo;
 		dev_dbg(dev, "Detected FIFO size: %u bytes\n", dws->fifo_len);
@@ -481,7 +441,6 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 
 	dws->master = master;
 	dws->type = SSI_MOTO_SPI;
-	dws->dma_inited = 0;
 	dws->dma_addr = (dma_addr_t)(dws->paddr + DW_SPI_DR);
 	spin_lock_init(&dws->buf_lock);
 
@@ -517,16 +476,16 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	spi_hw_init(dev, dws);
 
 	if (dws->dma_ops && dws->dma_ops->dma_init) {
-		ret = dws->dma_ops->dma_init(dws);
+		ret = dws->dma_ops->dma_init(dev, dws);
 		if (ret) {
 			dev_warn(dev, "DMA init failed\n");
-			dws->dma_inited = 0;
 		} else {
 			master->can_dma = dws->dma_ops->can_dma;
+			master->flags |= SPI_CONTROLLER_MUST_TX;
 		}
 	}
 
-	ret = devm_spi_register_controller(dev, master);
+	ret = spi_register_controller(master);
 	if (ret) {
 		dev_err(&master->dev, "problem registering spi master\n");
 		goto err_dma_exit;
@@ -550,6 +509,8 @@ void dw_spi_remove_host(struct dw_spi *dws)
 {
 	dw_spi_debugfs_remove(dws);
 
+	spi_unregister_controller(dws->master);
+
 	if (dws->dma_ops && dws->dma_ops->dma_exit)
 		dws->dma_ops->dma_exit(dws);
 
diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c
new file mode 100644
index 000000000000..5986c520b196
--- /dev/null
+++ b/drivers/spi/spi-dw-dma.c
@@ -0,0 +1,480 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Special handling for DW DMA core
+ *
+ * Copyright (c) 2009, 2014 Intel Corporation.
+ */
+
+#include <linux/completion.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/irqreturn.h>
+#include <linux/jiffies.h>
+#include <linux/pci.h>
+#include <linux/platform_data/dma-dw.h>
+#include <linux/spi/spi.h>
+#include <linux/types.h>
+
+#include "spi-dw.h"
+
+#define WAIT_RETRIES	5
+#define RX_BUSY		0
+#define RX_BURST_LEVEL	16
+#define TX_BUSY		1
+#define TX_BURST_LEVEL	16
+
+static bool dw_spi_dma_chan_filter(struct dma_chan *chan, void *param)
+{
+	struct dw_dma_slave *s = param;
+
+	if (s->dma_dev != chan->device->dev)
+		return false;
+
+	chan->private = s;
+	return true;
+}
+
+static void dw_spi_dma_maxburst_init(struct dw_spi *dws)
+{
+	struct dma_slave_caps caps;
+	u32 max_burst, def_burst;
+	int ret;
+
+	def_burst = dws->fifo_len / 2;
+
+	ret = dma_get_slave_caps(dws->rxchan, &caps);
+	if (!ret && caps.max_burst)
+		max_burst = caps.max_burst;
+	else
+		max_burst = RX_BURST_LEVEL;
+
+	dws->rxburst = min(max_burst, def_burst);
+
+	ret = dma_get_slave_caps(dws->txchan, &caps);
+	if (!ret && caps.max_burst)
+		max_burst = caps.max_burst;
+	else
+		max_burst = TX_BURST_LEVEL;
+
+	dws->txburst = min(max_burst, def_burst);
+}
+
+static int dw_spi_dma_init_mfld(struct device *dev, struct dw_spi *dws)
+{
+	struct dw_dma_slave dma_tx = { .dst_id = 1 }, *tx = &dma_tx;
+	struct dw_dma_slave dma_rx = { .src_id = 0 }, *rx = &dma_rx;
+	struct pci_dev *dma_dev;
+	dma_cap_mask_t mask;
+
+	/*
+	 * Get pci device for DMA controller, currently it could only
+	 * be the DMA controller of Medfield
+	 */
+	dma_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x0827, NULL);
+	if (!dma_dev)
+		return -ENODEV;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	/* 1. Init rx channel */
+	rx->dma_dev = &dma_dev->dev;
+	dws->rxchan = dma_request_channel(mask, dw_spi_dma_chan_filter, rx);
+	if (!dws->rxchan)
+		goto err_exit;
+
+	/* 2. Init tx channel */
+	tx->dma_dev = &dma_dev->dev;
+	dws->txchan = dma_request_channel(mask, dw_spi_dma_chan_filter, tx);
+	if (!dws->txchan)
+		goto free_rxchan;
+
+	dws->master->dma_rx = dws->rxchan;
+	dws->master->dma_tx = dws->txchan;
+
+	init_completion(&dws->dma_completion);
+
+	dw_spi_dma_maxburst_init(dws);
+
+	return 0;
+
+free_rxchan:
+	dma_release_channel(dws->rxchan);
+	dws->rxchan = NULL;
+err_exit:
+	return -EBUSY;
+}
+
+static int dw_spi_dma_init_generic(struct device *dev, struct dw_spi *dws)
+{
+	dws->rxchan = dma_request_slave_channel(dev, "rx");
+	if (!dws->rxchan)
+		return -ENODEV;
+
+	dws->txchan = dma_request_slave_channel(dev, "tx");
+	if (!dws->txchan) {
+		dma_release_channel(dws->rxchan);
+		dws->rxchan = NULL;
+		return -ENODEV;
+	}
+
+	dws->master->dma_rx = dws->rxchan;
+	dws->master->dma_tx = dws->txchan;
+
+	init_completion(&dws->dma_completion);
+
+	dw_spi_dma_maxburst_init(dws);
+
+	return 0;
+}
+
+static void dw_spi_dma_exit(struct dw_spi *dws)
+{
+	if (dws->txchan) {
+		dmaengine_terminate_sync(dws->txchan);
+		dma_release_channel(dws->txchan);
+	}
+
+	if (dws->rxchan) {
+		dmaengine_terminate_sync(dws->rxchan);
+		dma_release_channel(dws->rxchan);
+	}
+
+	dw_writel(dws, DW_SPI_DMACR, 0);
+}
+
+static irqreturn_t dw_spi_dma_transfer_handler(struct dw_spi *dws)
+{
+	u16 irq_status = dw_readl(dws, DW_SPI_ISR);
+
+	if (!irq_status)
+		return IRQ_NONE;
+
+	dw_readl(dws, DW_SPI_ICR);
+	spi_reset_chip(dws);
+
+	dev_err(&dws->master->dev, "%s: FIFO overrun/underrun\n", __func__);
+	dws->master->cur_msg->status = -EIO;
+	complete(&dws->dma_completion);
+	return IRQ_HANDLED;
+}
+
+static bool dw_spi_can_dma(struct spi_controller *master,
+			   struct spi_device *spi, struct spi_transfer *xfer)
+{
+	struct dw_spi *dws = spi_controller_get_devdata(master);
+
+	return xfer->len > dws->fifo_len;
+}
+
+static enum dma_slave_buswidth dw_spi_dma_convert_width(u8 n_bytes)
+{
+	if (n_bytes == 1)
+		return DMA_SLAVE_BUSWIDTH_1_BYTE;
+	else if (n_bytes == 2)
+		return DMA_SLAVE_BUSWIDTH_2_BYTES;
+
+	return DMA_SLAVE_BUSWIDTH_UNDEFINED;
+}
+
+static int dw_spi_dma_wait(struct dw_spi *dws, struct spi_transfer *xfer)
+{
+	unsigned long long ms;
+
+	ms = xfer->len * MSEC_PER_SEC * BITS_PER_BYTE;
+	do_div(ms, xfer->effective_speed_hz);
+	ms += ms + 200;
+
+	if (ms > UINT_MAX)
+		ms = UINT_MAX;
+
+	ms = wait_for_completion_timeout(&dws->dma_completion,
+					 msecs_to_jiffies(ms));
+
+	if (ms == 0) {
+		dev_err(&dws->master->cur_msg->spi->dev,
+			"DMA transaction timed out\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static inline bool dw_spi_dma_tx_busy(struct dw_spi *dws)
+{
+	return !(dw_readl(dws, DW_SPI_SR) & SR_TF_EMPT);
+}
+
+static int dw_spi_dma_wait_tx_done(struct dw_spi *dws,
+				   struct spi_transfer *xfer)
+{
+	int retry = WAIT_RETRIES;
+	struct spi_delay delay;
+	u32 nents;
+
+	nents = dw_readl(dws, DW_SPI_TXFLR);
+	delay.unit = SPI_DELAY_UNIT_SCK;
+	delay.value = nents * dws->n_bytes * BITS_PER_BYTE;
+
+	while (dw_spi_dma_tx_busy(dws) && retry--)
+		spi_delay_exec(&delay, xfer);
+
+	if (retry < 0) {
+		dev_err(&dws->master->dev, "Tx hanged up\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/*
+ * dws->dma_chan_busy is set before the dma transfer starts, callback for tx
+ * channel will clear a corresponding bit.
+ */
+static void dw_spi_dma_tx_done(void *arg)
+{
+	struct dw_spi *dws = arg;
+
+	clear_bit(TX_BUSY, &dws->dma_chan_busy);
+	if (test_bit(RX_BUSY, &dws->dma_chan_busy))
+		return;
+
+	dw_writel(dws, DW_SPI_DMACR, 0);
+	complete(&dws->dma_completion);
+}
+
+static struct dma_async_tx_descriptor *
+dw_spi_dma_prepare_tx(struct dw_spi *dws, struct spi_transfer *xfer)
+{
+	struct dma_slave_config txconf;
+	struct dma_async_tx_descriptor *txdesc;
+
+	if (!xfer->tx_buf)
+		return NULL;
+
+	memset(&txconf, 0, sizeof(txconf));
+	txconf.direction = DMA_MEM_TO_DEV;
+	txconf.dst_addr = dws->dma_addr;
+	txconf.dst_maxburst = dws->txburst;
+	txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	txconf.dst_addr_width = dw_spi_dma_convert_width(dws->n_bytes);
+	txconf.device_fc = false;
+
+	dmaengine_slave_config(dws->txchan, &txconf);
+
+	txdesc = dmaengine_prep_slave_sg(dws->txchan,
+				xfer->tx_sg.sgl,
+				xfer->tx_sg.nents,
+				DMA_MEM_TO_DEV,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!txdesc)
+		return NULL;
+
+	txdesc->callback = dw_spi_dma_tx_done;
+	txdesc->callback_param = dws;
+
+	return txdesc;
+}
+
+static inline bool dw_spi_dma_rx_busy(struct dw_spi *dws)
+{
+	return !!(dw_readl(dws, DW_SPI_SR) & SR_RF_NOT_EMPT);
+}
+
+static int dw_spi_dma_wait_rx_done(struct dw_spi *dws)
+{
+	int retry = WAIT_RETRIES;
+	struct spi_delay delay;
+	unsigned long ns, us;
+	u32 nents;
+
+	/*
+	 * It's unlikely that DMA engine is still doing the data fetching, but
+	 * if it's let's give it some reasonable time. The timeout calculation
+	 * is based on the synchronous APB/SSI reference clock rate, on a
+	 * number of data entries left in the Rx FIFO, times a number of clock
+	 * periods normally needed for a single APB read/write transaction
+	 * without PREADY signal utilized (which is true for the DW APB SSI
+	 * controller).
+	 */
+	nents = dw_readl(dws, DW_SPI_RXFLR);
+	ns = 4U * NSEC_PER_SEC / dws->max_freq * nents;
+	if (ns <= NSEC_PER_USEC) {
+		delay.unit = SPI_DELAY_UNIT_NSECS;
+		delay.value = ns;
+	} else {
+		us = DIV_ROUND_UP(ns, NSEC_PER_USEC);
+		delay.unit = SPI_DELAY_UNIT_USECS;
+		delay.value = clamp_val(us, 0, USHRT_MAX);
+	}
+
+	while (dw_spi_dma_rx_busy(dws) && retry--)
+		spi_delay_exec(&delay, NULL);
+
+	if (retry < 0) {
+		dev_err(&dws->master->dev, "Rx hanged up\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/*
+ * dws->dma_chan_busy is set before the dma transfer starts, callback for rx
+ * channel will clear a corresponding bit.
+ */
+static void dw_spi_dma_rx_done(void *arg)
+{
+	struct dw_spi *dws = arg;
+
+	clear_bit(RX_BUSY, &dws->dma_chan_busy);
+	if (test_bit(TX_BUSY, &dws->dma_chan_busy))
+		return;
+
+	dw_writel(dws, DW_SPI_DMACR, 0);
+	complete(&dws->dma_completion);
+}
+
+static struct dma_async_tx_descriptor *dw_spi_dma_prepare_rx(struct dw_spi *dws,
+		struct spi_transfer *xfer)
+{
+	struct dma_slave_config rxconf;
+	struct dma_async_tx_descriptor *rxdesc;
+
+	if (!xfer->rx_buf)
+		return NULL;
+
+	memset(&rxconf, 0, sizeof(rxconf));
+	rxconf.direction = DMA_DEV_TO_MEM;
+	rxconf.src_addr = dws->dma_addr;
+	rxconf.src_maxburst = dws->rxburst;
+	rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	rxconf.src_addr_width = dw_spi_dma_convert_width(dws->n_bytes);
+	rxconf.device_fc = false;
+
+	dmaengine_slave_config(dws->rxchan, &rxconf);
+
+	rxdesc = dmaengine_prep_slave_sg(dws->rxchan,
+				xfer->rx_sg.sgl,
+				xfer->rx_sg.nents,
+				DMA_DEV_TO_MEM,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!rxdesc)
+		return NULL;
+
+	rxdesc->callback = dw_spi_dma_rx_done;
+	rxdesc->callback_param = dws;
+
+	return rxdesc;
+}
+
+static int dw_spi_dma_setup(struct dw_spi *dws, struct spi_transfer *xfer)
+{
+	u16 imr = 0, dma_ctrl = 0;
+
+	dw_writel(dws, DW_SPI_DMARDLR, dws->rxburst - 1);
+	dw_writel(dws, DW_SPI_DMATDLR, dws->fifo_len - dws->txburst);
+
+	if (xfer->tx_buf)
+		dma_ctrl |= SPI_DMA_TDMAE;
+	if (xfer->rx_buf)
+		dma_ctrl |= SPI_DMA_RDMAE;
+	dw_writel(dws, DW_SPI_DMACR, dma_ctrl);
+
+	/* Set the interrupt mask */
+	if (xfer->tx_buf)
+		imr |= SPI_INT_TXOI;
+	if (xfer->rx_buf)
+		imr |= SPI_INT_RXUI | SPI_INT_RXOI;
+	spi_umask_intr(dws, imr);
+
+	reinit_completion(&dws->dma_completion);
+
+	dws->transfer_handler = dw_spi_dma_transfer_handler;
+
+	return 0;
+}
+
+static int dw_spi_dma_transfer(struct dw_spi *dws, struct spi_transfer *xfer)
+{
+	struct dma_async_tx_descriptor *txdesc, *rxdesc;
+	int ret;
+
+	/* Prepare the TX dma transfer */
+	txdesc = dw_spi_dma_prepare_tx(dws, xfer);
+
+	/* Prepare the RX dma transfer */
+	rxdesc = dw_spi_dma_prepare_rx(dws, xfer);
+
+	/* rx must be started before tx due to spi instinct */
+	if (rxdesc) {
+		set_bit(RX_BUSY, &dws->dma_chan_busy);
+		dmaengine_submit(rxdesc);
+		dma_async_issue_pending(dws->rxchan);
+	}
+
+	if (txdesc) {
+		set_bit(TX_BUSY, &dws->dma_chan_busy);
+		dmaengine_submit(txdesc);
+		dma_async_issue_pending(dws->txchan);
+	}
+
+	ret = dw_spi_dma_wait(dws, xfer);
+	if (ret)
+		return ret;
+
+	if (txdesc && dws->master->cur_msg->status == -EINPROGRESS) {
+		ret = dw_spi_dma_wait_tx_done(dws, xfer);
+		if (ret)
+			return ret;
+	}
+
+	if (rxdesc && dws->master->cur_msg->status == -EINPROGRESS)
+		ret = dw_spi_dma_wait_rx_done(dws);
+
+	return ret;
+}
+
+static void dw_spi_dma_stop(struct dw_spi *dws)
+{
+	if (test_bit(TX_BUSY, &dws->dma_chan_busy)) {
+		dmaengine_terminate_sync(dws->txchan);
+		clear_bit(TX_BUSY, &dws->dma_chan_busy);
+	}
+	if (test_bit(RX_BUSY, &dws->dma_chan_busy)) {
+		dmaengine_terminate_sync(dws->rxchan);
+		clear_bit(RX_BUSY, &dws->dma_chan_busy);
+	}
+
+	dw_writel(dws, DW_SPI_DMACR, 0);
+}
+
+static const struct dw_spi_dma_ops dw_spi_dma_mfld_ops = {
+	.dma_init	= dw_spi_dma_init_mfld,
+	.dma_exit	= dw_spi_dma_exit,
+	.dma_setup	= dw_spi_dma_setup,
+	.can_dma	= dw_spi_can_dma,
+	.dma_transfer	= dw_spi_dma_transfer,
+	.dma_stop	= dw_spi_dma_stop,
+};
+
+void dw_spi_dma_setup_mfld(struct dw_spi *dws)
+{
+	dws->dma_ops = &dw_spi_dma_mfld_ops;
+}
+EXPORT_SYMBOL_GPL(dw_spi_dma_setup_mfld);
+
+static const struct dw_spi_dma_ops dw_spi_dma_generic_ops = {
+	.dma_init	= dw_spi_dma_init_generic,
+	.dma_exit	= dw_spi_dma_exit,
+	.dma_setup	= dw_spi_dma_setup,
+	.can_dma	= dw_spi_can_dma,
+	.dma_transfer	= dw_spi_dma_transfer,
+	.dma_stop	= dw_spi_dma_stop,
+};
+
+void dw_spi_dma_setup_generic(struct dw_spi *dws)
+{
+	dws->dma_ops = &dw_spi_dma_generic_ops;
+}
+EXPORT_SYMBOL_GPL(dw_spi_dma_setup_generic);
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
deleted file mode 100644
index 0d86c37e0aeb..000000000000
--- a/drivers/spi/spi-dw-mid.c
+++ /dev/null
@@ -1,322 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Special handling for DW core on Intel MID platform
- *
- * Copyright (c) 2009, 2014 Intel Corporation.
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/dmaengine.h>
-#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/spi/spi.h>
-#include <linux/types.h>
-
-#include "spi-dw.h"
-
-#ifdef CONFIG_SPI_DW_MID_DMA
-#include <linux/pci.h>
-#include <linux/platform_data/dma-dw.h>
-
-#define RX_BUSY		0
-#define TX_BUSY		1
-
-static struct dw_dma_slave mid_dma_tx = { .dst_id = 1 };
-static struct dw_dma_slave mid_dma_rx = { .src_id = 0 };
-
-static bool mid_spi_dma_chan_filter(struct dma_chan *chan, void *param)
-{
-	struct dw_dma_slave *s = param;
-
-	if (s->dma_dev != chan->device->dev)
-		return false;
-
-	chan->private = s;
-	return true;
-}
-
-static int mid_spi_dma_init(struct dw_spi *dws)
-{
-	struct pci_dev *dma_dev;
-	struct dw_dma_slave *tx = dws->dma_tx;
-	struct dw_dma_slave *rx = dws->dma_rx;
-	dma_cap_mask_t mask;
-
-	/*
-	 * Get pci device for DMA controller, currently it could only
-	 * be the DMA controller of Medfield
-	 */
-	dma_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x0827, NULL);
-	if (!dma_dev)
-		return -ENODEV;
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-
-	/* 1. Init rx channel */
-	rx->dma_dev = &dma_dev->dev;
-	dws->rxchan = dma_request_channel(mask, mid_spi_dma_chan_filter, rx);
-	if (!dws->rxchan)
-		goto err_exit;
-	dws->master->dma_rx = dws->rxchan;
-
-	/* 2. Init tx channel */
-	tx->dma_dev = &dma_dev->dev;
-	dws->txchan = dma_request_channel(mask, mid_spi_dma_chan_filter, tx);
-	if (!dws->txchan)
-		goto free_rxchan;
-	dws->master->dma_tx = dws->txchan;
-
-	dws->dma_inited = 1;
-	return 0;
-
-free_rxchan:
-	dma_release_channel(dws->rxchan);
-err_exit:
-	return -EBUSY;
-}
-
-static void mid_spi_dma_exit(struct dw_spi *dws)
-{
-	if (!dws->dma_inited)
-		return;
-
-	dmaengine_terminate_sync(dws->txchan);
-	dma_release_channel(dws->txchan);
-
-	dmaengine_terminate_sync(dws->rxchan);
-	dma_release_channel(dws->rxchan);
-}
-
-static irqreturn_t dma_transfer(struct dw_spi *dws)
-{
-	u16 irq_status = dw_readl(dws, DW_SPI_ISR);
-
-	if (!irq_status)
-		return IRQ_NONE;
-
-	dw_readl(dws, DW_SPI_ICR);
-	spi_reset_chip(dws);
-
-	dev_err(&dws->master->dev, "%s: FIFO overrun/underrun\n", __func__);
-	dws->master->cur_msg->status = -EIO;
-	spi_finalize_current_transfer(dws->master);
-	return IRQ_HANDLED;
-}
-
-static bool mid_spi_can_dma(struct spi_controller *master,
-		struct spi_device *spi, struct spi_transfer *xfer)
-{
-	struct dw_spi *dws = spi_controller_get_devdata(master);
-
-	if (!dws->dma_inited)
-		return false;
-
-	return xfer->len > dws->fifo_len;
-}
-
-static enum dma_slave_buswidth convert_dma_width(u32 dma_width) {
-	if (dma_width == 1)
-		return DMA_SLAVE_BUSWIDTH_1_BYTE;
-	else if (dma_width == 2)
-		return DMA_SLAVE_BUSWIDTH_2_BYTES;
-
-	return DMA_SLAVE_BUSWIDTH_UNDEFINED;
-}
-
-/*
- * dws->dma_chan_busy is set before the dma transfer starts, callback for tx
- * channel will clear a corresponding bit.
- */
-static void dw_spi_dma_tx_done(void *arg)
-{
-	struct dw_spi *dws = arg;
-
-	clear_bit(TX_BUSY, &dws->dma_chan_busy);
-	if (test_bit(RX_BUSY, &dws->dma_chan_busy))
-		return;
-	spi_finalize_current_transfer(dws->master);
-}
-
-static struct dma_async_tx_descriptor *dw_spi_dma_prepare_tx(struct dw_spi *dws,
-		struct spi_transfer *xfer)
-{
-	struct dma_slave_config txconf;
-	struct dma_async_tx_descriptor *txdesc;
-
-	if (!xfer->tx_buf)
-		return NULL;
-
-	txconf.direction = DMA_MEM_TO_DEV;
-	txconf.dst_addr = dws->dma_addr;
-	txconf.dst_maxburst = 16;
-	txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	txconf.dst_addr_width = convert_dma_width(dws->dma_width);
-	txconf.device_fc = false;
-
-	dmaengine_slave_config(dws->txchan, &txconf);
-
-	txdesc = dmaengine_prep_slave_sg(dws->txchan,
-				xfer->tx_sg.sgl,
-				xfer->tx_sg.nents,
-				DMA_MEM_TO_DEV,
-				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-	if (!txdesc)
-		return NULL;
-
-	txdesc->callback = dw_spi_dma_tx_done;
-	txdesc->callback_param = dws;
-
-	return txdesc;
-}
-
-/*
- * dws->dma_chan_busy is set before the dma transfer starts, callback for rx
- * channel will clear a corresponding bit.
- */
-static void dw_spi_dma_rx_done(void *arg)
-{
-	struct dw_spi *dws = arg;
-
-	clear_bit(RX_BUSY, &dws->dma_chan_busy);
-	if (test_bit(TX_BUSY, &dws->dma_chan_busy))
-		return;
-	spi_finalize_current_transfer(dws->master);
-}
-
-static struct dma_async_tx_descriptor *dw_spi_dma_prepare_rx(struct dw_spi *dws,
-		struct spi_transfer *xfer)
-{
-	struct dma_slave_config rxconf;
-	struct dma_async_tx_descriptor *rxdesc;
-
-	if (!xfer->rx_buf)
-		return NULL;
-
-	rxconf.direction = DMA_DEV_TO_MEM;
-	rxconf.src_addr = dws->dma_addr;
-	rxconf.src_maxburst = 16;
-	rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	rxconf.src_addr_width = convert_dma_width(dws->dma_width);
-	rxconf.device_fc = false;
-
-	dmaengine_slave_config(dws->rxchan, &rxconf);
-
-	rxdesc = dmaengine_prep_slave_sg(dws->rxchan,
-				xfer->rx_sg.sgl,
-				xfer->rx_sg.nents,
-				DMA_DEV_TO_MEM,
-				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-	if (!rxdesc)
-		return NULL;
-
-	rxdesc->callback = dw_spi_dma_rx_done;
-	rxdesc->callback_param = dws;
-
-	return rxdesc;
-}
-
-static int mid_spi_dma_setup(struct dw_spi *dws, struct spi_transfer *xfer)
-{
-	u16 dma_ctrl = 0;
-
-	dw_writel(dws, DW_SPI_DMARDLR, 0xf);
-	dw_writel(dws, DW_SPI_DMATDLR, 0x10);
-
-	if (xfer->tx_buf)
-		dma_ctrl |= SPI_DMA_TDMAE;
-	if (xfer->rx_buf)
-		dma_ctrl |= SPI_DMA_RDMAE;
-	dw_writel(dws, DW_SPI_DMACR, dma_ctrl);
-
-	/* Set the interrupt mask */
-	spi_umask_intr(dws, SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI);
-
-	dws->transfer_handler = dma_transfer;
-
-	return 0;
-}
-
-static int mid_spi_dma_transfer(struct dw_spi *dws, struct spi_transfer *xfer)
-{
-	struct dma_async_tx_descriptor *txdesc, *rxdesc;
-
-	/* Prepare the TX dma transfer */
-	txdesc = dw_spi_dma_prepare_tx(dws, xfer);
-
-	/* Prepare the RX dma transfer */
-	rxdesc = dw_spi_dma_prepare_rx(dws, xfer);
-
-	/* rx must be started before tx due to spi instinct */
-	if (rxdesc) {
-		set_bit(RX_BUSY, &dws->dma_chan_busy);
-		dmaengine_submit(rxdesc);
-		dma_async_issue_pending(dws->rxchan);
-	}
-
-	if (txdesc) {
-		set_bit(TX_BUSY, &dws->dma_chan_busy);
-		dmaengine_submit(txdesc);
-		dma_async_issue_pending(dws->txchan);
-	}
-
-	return 0;
-}
-
-static void mid_spi_dma_stop(struct dw_spi *dws)
-{
-	if (test_bit(TX_BUSY, &dws->dma_chan_busy)) {
-		dmaengine_terminate_sync(dws->txchan);
-		clear_bit(TX_BUSY, &dws->dma_chan_busy);
-	}
-	if (test_bit(RX_BUSY, &dws->dma_chan_busy)) {
-		dmaengine_terminate_sync(dws->rxchan);
-		clear_bit(RX_BUSY, &dws->dma_chan_busy);
-	}
-}
-
-static const struct dw_spi_dma_ops mid_dma_ops = {
-	.dma_init	= mid_spi_dma_init,
-	.dma_exit	= mid_spi_dma_exit,
-	.dma_setup	= mid_spi_dma_setup,
-	.can_dma	= mid_spi_can_dma,
-	.dma_transfer	= mid_spi_dma_transfer,
-	.dma_stop	= mid_spi_dma_stop,
-};
-#endif
-
-/* Some specific info for SPI0 controller on Intel MID */
-
-/* HW info for MRST Clk Control Unit, 32b reg per controller */
-#define MRST_SPI_CLK_BASE	100000000	/* 100m */
-#define MRST_CLK_SPI_REG	0xff11d86c
-#define CLK_SPI_BDIV_OFFSET	0
-#define CLK_SPI_BDIV_MASK	0x00000007
-#define CLK_SPI_CDIV_OFFSET	9
-#define CLK_SPI_CDIV_MASK	0x00000e00
-#define CLK_SPI_DISABLE_OFFSET	8
-
-int dw_spi_mid_init(struct dw_spi *dws)
-{
-	void __iomem *clk_reg;
-	u32 clk_cdiv;
-
-	clk_reg = ioremap(MRST_CLK_SPI_REG, 16);
-	if (!clk_reg)
-		return -ENOMEM;
-
-	/* Get SPI controller operating freq info */
-	clk_cdiv = readl(clk_reg + dws->bus_num * sizeof(u32));
-	clk_cdiv &= CLK_SPI_CDIV_MASK;
-	clk_cdiv >>= CLK_SPI_CDIV_OFFSET;
-	dws->max_freq = MRST_SPI_CLK_BASE / (clk_cdiv + 1);
-
-	iounmap(clk_reg);
-
-#ifdef CONFIG_SPI_DW_MID_DMA
-	dws->dma_tx = &mid_dma_tx;
-	dws->dma_rx = &mid_dma_rx;
-	dws->dma_ops = &mid_dma_ops;
-#endif
-	return 0;
-}
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index 384a3ab6dc2d..403403deae66 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -7,7 +7,6 @@
 
 #include <linux/clk.h>
 #include <linux/err.h>
-#include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
@@ -20,6 +19,7 @@
 #include <linux/acpi.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
+#include <linux/reset.h>
 
 #include "spi-dw.h"
 
@@ -30,6 +30,7 @@ struct dw_spi_mmio {
 	struct clk     *clk;
 	struct clk     *pclk;
 	void           *priv;
+	struct reset_control *rstc;
 };
 
 #define MSCC_CPU_SYSTEM_CTRL_GENERAL_CTRL	0x24
@@ -44,6 +45,13 @@ struct dw_spi_mmio {
 #define MSCC_SPI_MST_SW_MODE_SW_PIN_CTRL_MODE	BIT(13)
 #define MSCC_SPI_MST_SW_MODE_SW_SPI_CS(x)	(x << 5)
 
+/*
+ * For Keem Bay, CTRLR0[31] is used to select controller mode.
+ * 0: SSI is slave
+ * 1: SSI is master
+ */
+#define KEEMBAY_CTRLR0_SSIC_IS_MST		BIT(31)
+
 struct dw_spi_mscc {
 	struct regmap       *syscon;
 	void __iomem        *spi_mst;
@@ -106,6 +114,9 @@ static int dw_spi_mscc_init(struct platform_device *pdev,
 	dwsmmio->dws.set_cs = dw_spi_mscc_set_cs;
 	dwsmmio->priv = dwsmscc;
 
+	/* Register hook to configure CTRLR0 */
+	dwsmmio->dws.update_cr0 = dw_spi_update_cr0;
+
 	return 0;
 }
 
@@ -128,6 +139,49 @@ static int dw_spi_alpine_init(struct platform_device *pdev,
 {
 	dwsmmio->dws.cs_override = 1;
 
+	/* Register hook to configure CTRLR0 */
+	dwsmmio->dws.update_cr0 = dw_spi_update_cr0;
+
+	return 0;
+}
+
+static int dw_spi_dw_apb_init(struct platform_device *pdev,
+			      struct dw_spi_mmio *dwsmmio)
+{
+	/* Register hook to configure CTRLR0 */
+	dwsmmio->dws.update_cr0 = dw_spi_update_cr0;
+
+	dw_spi_dma_setup_generic(&dwsmmio->dws);
+
+	return 0;
+}
+
+static int dw_spi_dwc_ssi_init(struct platform_device *pdev,
+			       struct dw_spi_mmio *dwsmmio)
+{
+	/* Register hook to configure CTRLR0 */
+	dwsmmio->dws.update_cr0 = dw_spi_update_cr0_v1_01a;
+
+	dw_spi_dma_setup_generic(&dwsmmio->dws);
+
+	return 0;
+}
+
+static u32 dw_spi_update_cr0_keembay(struct spi_controller *master,
+				     struct spi_device *spi,
+				     struct spi_transfer *transfer)
+{
+	u32 cr0 = dw_spi_update_cr0_v1_01a(master, spi, transfer);
+
+	return cr0 | KEEMBAY_CTRLR0_SSIC_IS_MST;
+}
+
+static int dw_spi_keembay_init(struct platform_device *pdev,
+			       struct dw_spi_mmio *dwsmmio)
+{
+	/* Register hook to configure CTRLR0 */
+	dwsmmio->dws.update_cr0 = dw_spi_update_cr0_keembay;
+
 	return 0;
 }
 
@@ -136,6 +190,7 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 	int (*init_func)(struct platform_device *pdev,
 			 struct dw_spi_mmio *dwsmmio);
 	struct dw_spi_mmio *dwsmmio;
+	struct resource *mem;
 	struct dw_spi *dws;
 	int ret;
 	int num_cs;
@@ -148,11 +203,11 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 	dws = &dwsmmio->dws;
 
 	/* Get basic io resource and map it */
-	dws->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(dws->regs)) {
-		dev_err(&pdev->dev, "SPI region map failed\n");
+	dws->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &mem);
+	if (IS_ERR(dws->regs))
 		return PTR_ERR(dws->regs);
-	}
+
+	dws->paddr = mem->start;
 
 	dws->irq = platform_get_irq(pdev, 0);
 	if (dws->irq < 0)
@@ -175,6 +230,14 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_clk;
 
+	/* find an optional reset controller */
+	dwsmmio->rstc = devm_reset_control_get_optional_exclusive(&pdev->dev, "spi");
+	if (IS_ERR(dwsmmio->rstc)) {
+		ret = PTR_ERR(dwsmmio->rstc);
+		goto out_clk;
+	}
+	reset_control_deassert(dwsmmio->rstc);
+
 	dws->bus_num = pdev->id;
 
 	dws->max_freq = clk_get_rate(dwsmmio->clk);
@@ -208,6 +271,8 @@ out:
 	clk_disable_unprepare(dwsmmio->pclk);
 out_clk:
 	clk_disable_unprepare(dwsmmio->clk);
+	reset_control_assert(dwsmmio->rstc);
+
 	return ret;
 }
 
@@ -219,25 +284,30 @@ static int dw_spi_mmio_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	clk_disable_unprepare(dwsmmio->pclk);
 	clk_disable_unprepare(dwsmmio->clk);
+	reset_control_assert(dwsmmio->rstc);
 
 	return 0;
 }
 
 static const struct of_device_id dw_spi_mmio_of_match[] = {
-	{ .compatible = "snps,dw-apb-ssi", },
+	{ .compatible = "snps,dw-apb-ssi", .data = dw_spi_dw_apb_init},
 	{ .compatible = "mscc,ocelot-spi", .data = dw_spi_mscc_ocelot_init},
 	{ .compatible = "mscc,jaguar2-spi", .data = dw_spi_mscc_jaguar2_init},
 	{ .compatible = "amazon,alpine-dw-apb-ssi", .data = dw_spi_alpine_init},
-	{ .compatible = "renesas,rzn1-spi", },
+	{ .compatible = "renesas,rzn1-spi", .data = dw_spi_dw_apb_init},
+	{ .compatible = "snps,dwc-ssi-1.01a", .data = dw_spi_dwc_ssi_init},
+	{ .compatible = "intel,keembay-ssi", .data = dw_spi_keembay_init},
 	{ /* end of table */}
 };
 MODULE_DEVICE_TABLE(of, dw_spi_mmio_of_match);
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id dw_spi_mmio_acpi_match[] = {
-	{"HISI0173", 0},
+	{"HISI0173", (kernel_ulong_t)dw_spi_dw_apb_init},
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, dw_spi_mmio_acpi_match);
+#endif
 
 static struct platform_driver dw_spi_mmio_driver = {
 	.probe		= dw_spi_mmio_probe,
diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c
index 12c131b5fb4e..2ea73809ca34 100644
--- a/drivers/spi/spi-dw-pci.c
+++ b/drivers/spi/spi-dw-pci.c
@@ -5,7 +5,6 @@
  * Copyright (c) 2009, 2014 Intel Corporation.
  */
 
-#include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
@@ -16,6 +15,15 @@
 
 #define DRIVER_NAME "dw_spi_pci"
 
+/* HW info for MRST Clk Control Unit, 32b reg per controller */
+#define MRST_SPI_CLK_BASE	100000000	/* 100m */
+#define MRST_CLK_SPI_REG	0xff11d86c
+#define CLK_SPI_BDIV_OFFSET	0
+#define CLK_SPI_BDIV_MASK	0x00000007
+#define CLK_SPI_CDIV_OFFSET	9
+#define CLK_SPI_CDIV_MASK	0x00000e00
+#define CLK_SPI_DISABLE_OFFSET	8
+
 struct spi_pci_desc {
 	int	(*setup)(struct dw_spi *);
 	u16	num_cs;
@@ -23,19 +31,55 @@ struct spi_pci_desc {
 	u32	max_freq;
 };
 
+static int spi_mid_init(struct dw_spi *dws)
+{
+	void __iomem *clk_reg;
+	u32 clk_cdiv;
+
+	clk_reg = ioremap(MRST_CLK_SPI_REG, 16);
+	if (!clk_reg)
+		return -ENOMEM;
+
+	/* Get SPI controller operating freq info */
+	clk_cdiv = readl(clk_reg + dws->bus_num * sizeof(u32));
+	clk_cdiv &= CLK_SPI_CDIV_MASK;
+	clk_cdiv >>= CLK_SPI_CDIV_OFFSET;
+	dws->max_freq = MRST_SPI_CLK_BASE / (clk_cdiv + 1);
+
+	iounmap(clk_reg);
+
+	/* Register hook to configure CTRLR0 */
+	dws->update_cr0 = dw_spi_update_cr0;
+
+	dw_spi_dma_setup_mfld(dws);
+
+	return 0;
+}
+
+static int spi_generic_init(struct dw_spi *dws)
+{
+	/* Register hook to configure CTRLR0 */
+	dws->update_cr0 = dw_spi_update_cr0;
+
+	dw_spi_dma_setup_generic(dws);
+
+	return 0;
+}
+
 static struct spi_pci_desc spi_pci_mid_desc_1 = {
-	.setup = dw_spi_mid_init,
+	.setup = spi_mid_init,
 	.num_cs = 5,
 	.bus_num = 0,
 };
 
 static struct spi_pci_desc spi_pci_mid_desc_2 = {
-	.setup = dw_spi_mid_init,
+	.setup = spi_mid_init,
 	.num_cs = 2,
 	.bus_num = 1,
 };
 
 static struct spi_pci_desc spi_pci_ehl_desc = {
+	.setup = spi_generic_init,
 	.num_cs = 2,
 	.bus_num = -1,
 	.max_freq = 100000000,
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index 1bf5713e047d..151ba316619e 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -2,18 +2,21 @@
 #ifndef DW_SPI_HEADER_H
 #define DW_SPI_HEADER_H
 
+#include <linux/completion.h>
+#include <linux/debugfs.h>
+#include <linux/irqreturn.h>
 #include <linux/io.h>
 #include <linux/scatterlist.h>
 
 /* Register offsets */
-#define DW_SPI_CTRL0			0x00
-#define DW_SPI_CTRL1			0x04
+#define DW_SPI_CTRLR0			0x00
+#define DW_SPI_CTRLR1			0x04
 #define DW_SPI_SSIENR			0x08
 #define DW_SPI_MWCR			0x0c
 #define DW_SPI_SER			0x10
 #define DW_SPI_BAUDR			0x14
-#define DW_SPI_TXFLTR			0x18
-#define DW_SPI_RXFLTR			0x1c
+#define DW_SPI_TXFTLR			0x18
+#define DW_SPI_RXFTLR			0x1c
 #define DW_SPI_TXFLR			0x20
 #define DW_SPI_RXFLR			0x24
 #define DW_SPI_SR			0x28
@@ -57,6 +60,15 @@
 #define SPI_SRL_OFFSET			11
 #define SPI_CFS_OFFSET			12
 
+/* Bit fields in CTRLR0 based on DWC_ssi_databook.pdf v1.01a */
+#define DWC_SSI_CTRLR0_SRL_OFFSET	13
+#define DWC_SSI_CTRLR0_TMOD_OFFSET	10
+#define DWC_SSI_CTRLR0_TMOD_MASK	GENMASK(11, 10)
+#define DWC_SSI_CTRLR0_SCPOL_OFFSET	9
+#define DWC_SSI_CTRLR0_SCPH_OFFSET	8
+#define DWC_SSI_CTRLR0_FRF_OFFSET	6
+#define DWC_SSI_CTRLR0_DFS_OFFSET	0
+
 /* Bit fields in SR, 7 bits */
 #define SR_MASK				0x7f		/* cover 7 bits */
 #define SR_BUSY				(1 << 0)
@@ -90,7 +102,7 @@ enum dw_ssi_type {
 
 struct dw_spi;
 struct dw_spi_dma_ops {
-	int (*dma_init)(struct dw_spi *dws);
+	int (*dma_init)(struct device *dev, struct dw_spi *dws);
 	void (*dma_exit)(struct dw_spi *dws);
 	int (*dma_setup)(struct dw_spi *dws, struct spi_transfer *xfer);
 	bool (*can_dma)(struct spi_controller *master, struct spi_device *spi,
@@ -114,6 +126,8 @@ struct dw_spi {
 	u16			bus_num;
 	u16			num_cs;		/* supported slave numbers */
 	void (*set_cs)(struct spi_device *spi, bool enable);
+	u32 (*update_cr0)(struct spi_controller *master, struct spi_device *spi,
+			  struct spi_transfer *transfer);
 
 	/* Current message transfer state info */
 	size_t			len;
@@ -124,24 +138,22 @@ struct dw_spi {
 	void			*rx_end;
 	int			dma_mapped;
 	u8			n_bytes;	/* current is a 1/2 bytes op */
-	u32			dma_width;
 	irqreturn_t		(*transfer_handler)(struct dw_spi *dws);
 	u32			current_freq;	/* frequency in hz */
 
 	/* DMA info */
-	int			dma_inited;
 	struct dma_chan		*txchan;
+	u32			txburst;
 	struct dma_chan		*rxchan;
+	u32			rxburst;
 	unsigned long		dma_chan_busy;
 	dma_addr_t		dma_addr; /* phy address of the Data register */
 	const struct dw_spi_dma_ops *dma_ops;
-	void			*dma_tx;
-	void			*dma_rx;
+	struct completion	dma_completion;
 
-	/* Bus interface info */
-	void			*priv;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs;
+	struct debugfs_regset32 regset;
 #endif
 };
 
@@ -235,24 +247,28 @@ static inline void spi_shutdown_chip(struct dw_spi *dws)
 	spi_set_clk(dws, 0);
 }
 
-/*
- * Each SPI slave device to work with dw_api controller should
- * has such a structure claiming its working mode (poll or PIO/DMA),
- * which can be save in the "controller_data" member of the
- * struct spi_device.
- */
-struct dw_spi_chip {
-	u8 poll_mode;	/* 1 for controller polling mode */
-	u8 type;	/* SPI/SSP/MicroWire */
-	void (*cs_control)(u32 command);
-};
-
 extern void dw_spi_set_cs(struct spi_device *spi, bool enable);
 extern int dw_spi_add_host(struct device *dev, struct dw_spi *dws);
 extern void dw_spi_remove_host(struct dw_spi *dws);
 extern int dw_spi_suspend_host(struct dw_spi *dws);
 extern int dw_spi_resume_host(struct dw_spi *dws);
+extern u32 dw_spi_update_cr0(struct spi_controller *master,
+			     struct spi_device *spi,
+			     struct spi_transfer *transfer);
+extern u32 dw_spi_update_cr0_v1_01a(struct spi_controller *master,
+				    struct spi_device *spi,
+				    struct spi_transfer *transfer);
+
+#ifdef CONFIG_SPI_DW_DMA
+
+extern void dw_spi_dma_setup_mfld(struct dw_spi *dws);
+extern void dw_spi_dma_setup_generic(struct dw_spi *dws);
+
+#else
+
+static inline void dw_spi_dma_setup_mfld(struct dw_spi *dws) {}
+static inline void dw_spi_dma_setup_generic(struct dw_spi *dws) {}
+
+#endif /* !CONFIG_SPI_DW_DMA */
 
-/* platform related setup */
-extern int dw_spi_mid_init(struct dw_spi *dws); /* Intel MID platforms */
 #endif /* DW_SPI_HEADER_H */
diff --git a/drivers/spi/spi-ep93xx.c b/drivers/spi/spi-ep93xx.c
index 4e1ccd4e52b6..8c854b187b1d 100644
--- a/drivers/spi/spi-ep93xx.c
+++ b/drivers/spi/spi-ep93xx.c
@@ -31,7 +31,8 @@
 #include <linux/platform_data/spi-ep93xx.h>
 
 #define SSPCR0			0x0000
-#define SSPCR0_MODE_SHIFT	6
+#define SSPCR0_SPO		BIT(6)
+#define SSPCR0_SPH		BIT(7)
 #define SSPCR0_SCR_SHIFT	8
 
 #define SSPCR1			0x0004
@@ -159,7 +160,10 @@ static int ep93xx_spi_chip_setup(struct spi_master *master,
 		return err;
 
 	cr0 = div_scr << SSPCR0_SCR_SHIFT;
-	cr0 |= (spi->mode & (SPI_CPHA | SPI_CPOL)) << SSPCR0_MODE_SHIFT;
+	if (spi->mode & SPI_CPOL)
+		cr0 |= SSPCR0_SPO;
+	if (spi->mode & SPI_CPHA)
+		cr0 |= SSPCR0_SPH;
 	cr0 |= dss;
 
 	dev_dbg(&master->dev, "setup: mode %d, cpsr %d, scr %d, dss %d\n",
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 50e41f66a2d7..a35faced0456 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0+
 //
 // Copyright 2013 Freescale Semiconductor, Inc.
+// Copyright 2020 NXP
 //
 // Freescale DSPI driver
 // This file contains a driver for the Freescale DSPI
@@ -26,6 +27,9 @@
 #define SPI_MCR_CLR_TXF			BIT(11)
 #define SPI_MCR_CLR_RXF			BIT(10)
 #define SPI_MCR_XSPI			BIT(3)
+#define SPI_MCR_DIS_TXF			BIT(13)
+#define SPI_MCR_DIS_RXF			BIT(12)
+#define SPI_MCR_HALT			BIT(0)
 
 #define SPI_TCR				0x08
 #define SPI_TCR_GET_TCNT(x)		(((x) & GENMASK(31, 16)) >> 16)
@@ -246,13 +250,33 @@ struct fsl_dspi {
 
 static void dspi_native_host_to_dev(struct fsl_dspi *dspi, u32 *txdata)
 {
-	memcpy(txdata, dspi->tx, dspi->oper_word_size);
+	switch (dspi->oper_word_size) {
+	case 1:
+		*txdata = *(u8 *)dspi->tx;
+		break;
+	case 2:
+		*txdata = *(u16 *)dspi->tx;
+		break;
+	case 4:
+		*txdata = *(u32 *)dspi->tx;
+		break;
+	}
 	dspi->tx += dspi->oper_word_size;
 }
 
 static void dspi_native_dev_to_host(struct fsl_dspi *dspi, u32 rxdata)
 {
-	memcpy(dspi->rx, &rxdata, dspi->oper_word_size);
+	switch (dspi->oper_word_size) {
+	case 1:
+		*(u8 *)dspi->rx = rxdata;
+		break;
+	case 2:
+		*(u16 *)dspi->rx = rxdata;
+		break;
+	case 4:
+		*(u32 *)dspi->rx = rxdata;
+		break;
+	}
 	dspi->rx += dspi->oper_word_size;
 }
 
@@ -1417,6 +1441,24 @@ static int dspi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static void dspi_shutdown(struct platform_device *pdev)
+{
+	struct spi_controller *ctlr = platform_get_drvdata(pdev);
+	struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+
+	/* Disable RX and TX */
+	regmap_update_bits(dspi->regmap, SPI_MCR,
+			   SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF,
+			   SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF);
+
+	/* Stop Running */
+	regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_HALT, SPI_MCR_HALT);
+
+	dspi_release_dma(dspi);
+	clk_disable_unprepare(dspi->clk);
+	spi_unregister_controller(dspi->ctlr);
+}
+
 static struct platform_driver fsl_dspi_driver = {
 	.driver.name		= DRIVER_NAME,
 	.driver.of_match_table	= fsl_dspi_dt_ids,
@@ -1424,6 +1466,7 @@ static struct platform_driver fsl_dspi_driver = {
 	.driver.pm		= &dspi_pm,
 	.probe			= dspi_probe,
 	.remove			= dspi_remove,
+	.shutdown		= dspi_shutdown,
 };
 module_platform_driver(fsl_dspi_driver);
 
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 8b41b70f6f5c..1552b28b9515 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -186,14 +186,13 @@ static bool fsl_lpspi_can_dma(struct spi_controller *controller,
 
 	bytes_per_word = fsl_lpspi_bytes_per_word(transfer->bits_per_word);
 
-	switch (bytes_per_word)
-	{
-		case 1:
-		case 2:
-		case 4:
-			break;
-		default:
-			return false;
+	switch (bytes_per_word) {
+	case 1:
+	case 2:
+	case 4:
+		break;
+	default:
+		return false;
 	}
 
 	return true;
@@ -941,7 +940,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	ret = pm_runtime_get_sync(fsl_lpspi->dev);
 	if (ret < 0) {
 		dev_err(fsl_lpspi->dev, "failed to enable clock\n");
-		goto out_controller_put;
+		goto out_pm_get;
 	}
 
 	temp = readl(fsl_lpspi->base + IMX7ULP_PARAM);
@@ -950,13 +949,15 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 
 	ret = fsl_lpspi_dma_init(&pdev->dev, fsl_lpspi, controller);
 	if (ret == -EPROBE_DEFER)
-		goto out_controller_put;
+		goto out_pm_get;
 
 	if (ret < 0)
 		dev_err(&pdev->dev, "dma setup error %d, use pio\n", ret);
 
 	return 0;
 
+out_pm_get:
+	pm_runtime_put_noidle(fsl_lpspi->dev);
 out_controller_put:
 	spi_controller_put(controller);
 
diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c
index 02e5cba0a5bb..6766262d7e75 100644
--- a/drivers/spi/spi-fsl-qspi.c
+++ b/drivers/spi/spi-fsl-qspi.c
@@ -876,14 +876,15 @@ static int fsl_qspi_probe(struct platform_device *pdev)
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 					"QuadSPI-memory");
-	q->ahb_addr = devm_ioremap_resource(dev, res);
-	if (IS_ERR(q->ahb_addr)) {
-		ret = PTR_ERR(q->ahb_addr);
+	q->memmap_phy = res->start;
+	/* Since there are 4 cs, map size required is 4 times ahb_buf_size */
+	q->ahb_addr = devm_ioremap(dev, q->memmap_phy,
+				   (q->devtype_data->ahb_buf_size * 4));
+	if (!q->ahb_addr) {
+		ret = -ENOMEM;
 		goto err_put_ctrl;
 	}
 
-	q->memmap_phy = res->start;
-
 	/* find the clocks */
 	q->clk_en = devm_clk_get(dev, "qspi_en");
 	if (IS_ERR(q->clk_en)) {
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index 3b81772fea0d..67f022b8c81d 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -588,7 +588,7 @@ static void fsl_spi_grlib_probe(struct device *dev)
 	pdata->cs_control = fsl_spi_grlib_cs_control;
 }
 
-static struct spi_master * fsl_spi_probe(struct device *dev,
+static struct spi_master *fsl_spi_probe(struct device *dev,
 		struct resource *mem, unsigned int irq)
 {
 	struct fsl_spi_platform_data *pdata = dev_get_platdata(dev);
diff --git a/drivers/spi/spi-hisi-sfc-v3xx.c b/drivers/spi/spi-hisi-sfc-v3xx.c
index e3b57252d075..64a18d08a4d9 100644
--- a/drivers/spi/spi-hisi-sfc-v3xx.c
+++ b/drivers/spi/spi-hisi-sfc-v3xx.c
@@ -17,6 +17,11 @@
 
 #define HISI_SFC_V3XX_VERSION (0x1f8)
 
+#define HISI_SFC_V3XX_INT_STAT (0x120)
+#define HISI_SFC_V3XX_INT_STAT_PP_ERR BIT(2)
+#define HISI_SFC_V3XX_INT_STAT_ADDR_IACCES BIT(5)
+#define HISI_SFC_V3XX_INT_CLR (0x12c)
+#define HISI_SFC_V3XX_INT_CLR_CLEAR (0xff)
 #define HISI_SFC_V3XX_CMD_CFG (0x300)
 #define HISI_SFC_V3XX_CMD_CFG_DUAL_IN_DUAL_OUT (1 << 17)
 #define HISI_SFC_V3XX_CMD_CFG_DUAL_IO (2 << 17)
@@ -163,7 +168,7 @@ static int hisi_sfc_v3xx_generic_exec_op(struct hisi_sfc_v3xx_host *host,
 					 u8 chip_select)
 {
 	int ret, len = op->data.nbytes;
-	u32 config = 0;
+	u32 int_stat, config = 0;
 
 	if (op->addr.nbytes)
 		config |= HISI_SFC_V3XX_CMD_CFG_ADDR_EN_MSK;
@@ -228,6 +233,25 @@ static int hisi_sfc_v3xx_generic_exec_op(struct hisi_sfc_v3xx_host *host,
 	if (ret)
 		return ret;
 
+	/*
+	 * The interrupt status register indicates whether an error occurs
+	 * after per operation. Check it, and clear the interrupts for
+	 * next time judgement.
+	 */
+	int_stat = readl(host->regbase + HISI_SFC_V3XX_INT_STAT);
+	writel(HISI_SFC_V3XX_INT_CLR_CLEAR,
+	       host->regbase + HISI_SFC_V3XX_INT_CLR);
+
+	if (int_stat & HISI_SFC_V3XX_INT_STAT_ADDR_IACCES) {
+		dev_err(host->dev, "fail to access protected address\n");
+		return -EIO;
+	}
+
+	if (int_stat & HISI_SFC_V3XX_INT_STAT_PP_ERR) {
+		dev_err(host->dev, "page program operation failed\n");
+		return -EIO;
+	}
+
 	if (op->data.dir == SPI_MEM_DATA_IN)
 		hisi_sfc_v3xx_read_databuf(host, op->data.buf.in, len);
 
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index f4f28a400a96..b7a85e3fe1c1 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -71,6 +71,7 @@ struct spi_imx_devtype_data {
 	void (*reset)(struct spi_imx_data *);
 	void (*setup_wml)(struct spi_imx_data *);
 	void (*disable)(struct spi_imx_data *);
+	void (*disable_dma)(struct spi_imx_data *);
 	bool has_dmamode;
 	bool has_slavemode;
 	unsigned int fifo_size;
@@ -485,6 +486,11 @@ static void mx51_ecspi_trigger(struct spi_imx_data *spi_imx)
 	writel(reg, spi_imx->base + MX51_ECSPI_CTRL);
 }
 
+static void mx51_disable_dma(struct spi_imx_data *spi_imx)
+{
+	writel(0, spi_imx->base + MX51_ECSPI_DMA);
+}
+
 static void mx51_ecspi_disable(struct spi_imx_data *spi_imx)
 {
 	u32 ctrl;
@@ -987,6 +993,7 @@ static struct spi_imx_devtype_data imx51_ecspi_devtype_data = {
 	.rx_available = mx51_ecspi_rx_available,
 	.reset = mx51_ecspi_reset,
 	.setup_wml = mx51_setup_wml,
+	.disable_dma = mx51_disable_dma,
 	.fifo_size = 64,
 	.has_dmamode = true,
 	.dynamic_burst = true,
@@ -1001,6 +1008,7 @@ static struct spi_imx_devtype_data imx53_ecspi_devtype_data = {
 	.prepare_transfer = mx51_ecspi_prepare_transfer,
 	.trigger = mx51_ecspi_trigger,
 	.rx_available = mx51_ecspi_rx_available,
+	.disable_dma = mx51_disable_dma,
 	.reset = mx51_ecspi_reset,
 	.fifo_size = 64,
 	.has_dmamode = true,
@@ -1385,6 +1393,7 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc_tx) {
 		dmaengine_terminate_all(master->dma_tx);
+		dmaengine_terminate_all(master->dma_rx);
 		return -EINVAL;
 	}
 
@@ -1498,6 +1507,7 @@ static int spi_imx_transfer(struct spi_device *spi,
 				struct spi_transfer *transfer)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
+	int ret;
 
 	/* flush rxfifo before transfer */
 	while (spi_imx->devtype_data->rx_available(spi_imx))
@@ -1506,10 +1516,23 @@ static int spi_imx_transfer(struct spi_device *spi,
 	if (spi_imx->slave_mode)
 		return spi_imx_pio_transfer_slave(spi, transfer);
 
-	if (spi_imx->usedma)
-		return spi_imx_dma_transfer(spi_imx, transfer);
-	else
-		return spi_imx_pio_transfer(spi, transfer);
+	/*
+	 * fallback PIO mode if dma setup error happen, for example sdma
+	 * firmware may not be updated as ERR009165 required.
+	 */
+	if (spi_imx->usedma) {
+		ret = spi_imx_dma_transfer(spi_imx, transfer);
+		if (ret != -EINVAL)
+			return ret;
+
+		spi_imx->devtype_data->disable_dma(spi_imx);
+
+		spi_imx->usedma = false;
+		spi_imx->dynamic_burst = spi_imx->devtype_data->dynamic_burst;
+		dev_dbg(&spi->dev, "Fallback to PIO mode\n");
+	}
+
+	return spi_imx_pio_transfer(spi, transfer);
 }
 
 static int spi_imx_setup(struct spi_device *spi)
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index adaa0c49f966..9a86cc27fcc0 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -108,15 +108,17 @@ static int spi_check_buswidth_req(struct spi_mem *mem, u8 buswidth, bool tx)
 		return 0;
 
 	case 2:
-		if ((tx && (mode & (SPI_TX_DUAL | SPI_TX_QUAD))) ||
-		    (!tx && (mode & (SPI_RX_DUAL | SPI_RX_QUAD))))
+		if ((tx &&
+		     (mode & (SPI_TX_DUAL | SPI_TX_QUAD | SPI_TX_OCTAL))) ||
+		    (!tx &&
+		     (mode & (SPI_RX_DUAL | SPI_RX_QUAD | SPI_RX_OCTAL))))
 			return 0;
 
 		break;
 
 	case 4:
-		if ((tx && (mode & SPI_TX_QUAD)) ||
-		    (!tx && (mode & SPI_RX_QUAD)))
+		if ((tx && (mode & (SPI_TX_QUAD | SPI_TX_OCTAL))) ||
+		    (!tx && (mode & (SPI_RX_QUAD | SPI_RX_OCTAL))))
 			return 0;
 
 		break;
diff --git a/drivers/spi/spi-mtk-nor.c b/drivers/spi/spi-mtk-nor.c
index c15a9910549f..7bc302b50396 100644
--- a/drivers/spi/spi-mtk-nor.c
+++ b/drivers/spi/spi-mtk-nor.c
@@ -391,7 +391,7 @@ static int mtk_nor_pp_unbuffered(struct mtk_nor *sp,
 	return mtk_nor_cmd_exec(sp, MTK_NOR_CMD_WRITE, 6 * BITS_PER_BYTE);
 }
 
-int mtk_nor_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
+static int mtk_nor_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 {
 	struct mtk_nor *sp = spi_controller_get_devdata(mem->spi->master);
 	int ret;
diff --git a/drivers/spi/spi-mux.c b/drivers/spi/spi-mux.c
index 4f94c9127fc1..cc9ef371db14 100644
--- a/drivers/spi/spi-mux.c
+++ b/drivers/spi/spi-mux.c
@@ -51,6 +51,10 @@ static int spi_mux_select(struct spi_device *spi)
 	struct spi_mux_priv *priv = spi_controller_get_devdata(spi->controller);
 	int ret;
 
+	ret = mux_control_select(priv->mux, spi->chip_select);
+	if (ret)
+		return ret;
+
 	if (priv->current_cs == spi->chip_select)
 		return 0;
 
@@ -62,10 +66,6 @@ static int spi_mux_select(struct spi_device *spi)
 	priv->spi->mode = spi->mode;
 	priv->spi->bits_per_word = spi->bits_per_word;
 
-	ret = mux_control_select(priv->mux, spi->chip_select);
-	if (ret)
-		return ret;
-
 	priv->current_cs = spi->chip_select;
 
 	return 0;
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 1f59beb7d27e..43f73db22f21 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -17,10 +17,8 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/clk.h>
 #include <linux/sizes.h>
-#include <linux/gpio.h>
 #include <asm/unaligned.h>
 
 #define DRIVER_NAME			"orion_spi"
@@ -98,7 +96,6 @@ struct orion_spi {
 	struct clk              *clk;
 	struct clk              *axi_clk;
 	const struct orion_spi_dev *devdata;
-	int			unused_hw_gpio;
 
 	struct orion_child_options	child[ORION_NUM_CHIPSELECTS];
 };
@@ -325,20 +322,27 @@ orion_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 static void orion_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	struct orion_spi *orion_spi;
-	int cs;
 
 	orion_spi = spi_master_get_devdata(spi->master);
 
-	if (gpio_is_valid(spi->cs_gpio))
-		cs = orion_spi->unused_hw_gpio;
-	else
-		cs = spi->chip_select;
-
+	/*
+	 * If this line is using a GPIO to control chip select, this internal
+	 * .set_cs() function will still be called, so we clear any previous
+	 * chip select. The CS we activate will not have any elecrical effect,
+	 * as it is handled by a GPIO, but that doesn't matter. What we need
+	 * is to deassert the old chip select and assert some other chip select.
+	 */
 	orion_spi_clrbits(orion_spi, ORION_SPI_IF_CTRL_REG, ORION_SPI_CS_MASK);
 	orion_spi_setbits(orion_spi, ORION_SPI_IF_CTRL_REG,
-				ORION_SPI_CS(cs));
+			  ORION_SPI_CS(spi->chip_select));
 
-	/* Chip select logic is inverted from spi_set_cs */
+	/*
+	 * Chip select logic is inverted from spi_set_cs(). For lines using a
+	 * GPIO to do chip select SPI_CS_HIGH is enforced and inversion happens
+	 * in the GPIO library, but we don't care about that, because in those
+	 * cases we are dealing with an unused native CS anyways so the polarity
+	 * doesn't matter.
+	 */
 	if (!enable)
 		orion_spi_setbits(orion_spi, ORION_SPI_IF_CTRL_REG, 0x1);
 	else
@@ -503,9 +507,6 @@ static int orion_spi_transfer_one(struct spi_master *master,
 
 static int orion_spi_setup(struct spi_device *spi)
 {
-	if (gpio_is_valid(spi->cs_gpio)) {
-		gpio_direction_output(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH));
-	}
 	return orion_spi_setup_transfer(spi, NULL);
 }
 
@@ -622,13 +623,13 @@ static int orion_spi_probe(struct platform_device *pdev)
 	master->setup = orion_spi_setup;
 	master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
 	master->auto_runtime_pm = true;
+	master->use_gpio_descriptors = true;
 	master->flags = SPI_MASTER_GPIO_SS;
 
 	platform_set_drvdata(pdev, master);
 
 	spi = spi_master_get_devdata(master);
 	spi->master = master;
-	spi->unused_hw_gpio = -1;
 
 	of_id = of_match_device(orion_spi_of_match_table, &pdev->dev);
 	devdata = (of_id) ? of_id->data : &orion_spi_dev_data;
@@ -683,7 +684,6 @@ static int orion_spi_probe(struct platform_device *pdev)
 	for_each_available_child_of_node(pdev->dev.of_node, np) {
 		struct orion_direct_acc *dir_acc;
 		u32 cs;
-		int cs_gpio;
 
 		/* Get chip-select number from the "reg" property */
 		status = of_property_read_u32(np, "reg", &cs);
@@ -695,44 +695,6 @@ static int orion_spi_probe(struct platform_device *pdev)
 		}
 
 		/*
-		 * Initialize the CS GPIO:
-		 * - properly request the actual GPIO signal
-		 * - de-assert the logical signal so that all GPIO CS lines
-		 *   are inactive when probing for slaves
-		 * - find an unused physical CS which will be driven for any
-		 *   slave which uses a CS GPIO
-		 */
-		cs_gpio = of_get_named_gpio(pdev->dev.of_node, "cs-gpios", cs);
-		if (cs_gpio > 0) {
-			char *gpio_name;
-			int cs_flags;
-
-			if (spi->unused_hw_gpio == -1) {
-				dev_info(&pdev->dev,
-					"Selected unused HW CS#%d for any GPIO CSes\n",
-					cs);
-				spi->unused_hw_gpio = cs;
-			}
-
-			gpio_name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-					"%s-CS%d", dev_name(&pdev->dev), cs);
-			if (!gpio_name) {
-				status = -ENOMEM;
-				goto out_rel_axi_clk;
-			}
-
-			cs_flags = of_property_read_bool(np, "spi-cs-high") ?
-				GPIOF_OUT_INIT_LOW : GPIOF_OUT_INIT_HIGH;
-			status = devm_gpio_request_one(&pdev->dev, cs_gpio,
-					cs_flags, gpio_name);
-			if (status) {
-				dev_err(&pdev->dev,
-					"Can't request GPIO for CS %d\n", cs);
-				goto out_rel_axi_clk;
-			}
-		}
-
-		/*
 		 * Check if an address is configured for this SPI device. If
 		 * not, the MBus mapping via the 'ranges' property in the 'soc'
 		 * node is not configured and this device should not use the
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 73d2a65d0b6e..6721910e5f2a 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -150,6 +150,7 @@ static const struct lpss_config lpss_platforms[] = {
 		.tx_threshold_hi = 48,
 		.cs_sel_shift = 8,
 		.cs_sel_mask = 3 << 8,
+		.cs_clk_stays_gated = true,
 	},
 	{	/* LPSS_CNL_SSP */
 		.offset = 0x200,
@@ -1884,7 +1885,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 
 	/* Register with the SPI framework */
 	platform_set_drvdata(pdev, drv_data);
-	status = devm_spi_register_controller(&pdev->dev, controller);
+	status = spi_register_controller(controller);
 	if (status != 0) {
 		dev_err(&pdev->dev, "problem registering spi controller\n");
 		goto out_error_pm_runtime_enabled;
@@ -1893,7 +1894,6 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	return status;
 
 out_error_pm_runtime_enabled:
-	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
 out_error_clock_enabled:
@@ -1916,6 +1916,8 @@ static int pxa2xx_spi_remove(struct platform_device *pdev)
 
 	pm_runtime_get_sync(&pdev->dev);
 
+	spi_unregister_controller(drv_data->controller);
+
 	/* Disable the SSP at the peripheral and SOC level */
 	pxa2xx_spi_write(drv_data, SSCR0, 0);
 	clk_disable_unprepare(ssp->clk);
diff --git a/drivers/spi/spi-rb4xx.c b/drivers/spi/spi-rb4xx.c
index 4c9620e0d18c..8aa51beb4ff3 100644
--- a/drivers/spi/spi-rb4xx.c
+++ b/drivers/spi/spi-rb4xx.c
@@ -14,6 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/spi/spi.h>
+#include <linux/of.h>
 
 #include <asm/mach-ath79/ar71xx_regs.h>
 
@@ -150,6 +151,7 @@ static int rb4xx_spi_probe(struct platform_device *pdev)
 	if (IS_ERR(ahb_clk))
 		return PTR_ERR(ahb_clk);
 
+	master->dev.of_node = pdev->dev.of_node;
 	master->bus_num = 0;
 	master->num_chipselect = 3;
 	master->mode_bits = SPI_TX_DUAL;
@@ -158,6 +160,11 @@ static int rb4xx_spi_probe(struct platform_device *pdev)
 	master->transfer_one = rb4xx_transfer_one;
 	master->set_cs = rb4xx_set_cs;
 
+	rbspi = spi_master_get_devdata(master);
+	rbspi->base = spi_base;
+	rbspi->clk = ahb_clk;
+	platform_set_drvdata(pdev, rbspi);
+
 	err = devm_spi_register_master(&pdev->dev, master);
 	if (err) {
 		dev_err(&pdev->dev, "failed to register SPI master\n");
@@ -168,11 +175,6 @@ static int rb4xx_spi_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	rbspi = spi_master_get_devdata(master);
-	rbspi->base = spi_base;
-	rbspi->clk = ahb_clk;
-	platform_set_drvdata(pdev, rbspi);
-
 	/* Enable SPI */
 	rb4xx_write(rbspi, AR71XX_SPI_REG_FS, AR71XX_SPI_FS_GPIO);
 
@@ -188,11 +190,18 @@ static int rb4xx_spi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id rb4xx_spi_dt_match[] = {
+	{ .compatible = "mikrotik,rb4xx-spi" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, rb4xx_spi_dt_match);
+
 static struct platform_driver rb4xx_spi_drv = {
 	.probe = rb4xx_spi_probe,
 	.remove = rb4xx_spi_remove,
 	.driver = {
 		.name = "rb4xx-spi",
+		.of_match_table = of_match_ptr(rb4xx_spi_dt_match),
 	},
 };
 
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 70ef63e0b6b8..9b8a5e1233c0 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -183,6 +183,8 @@ struct rockchip_spi {
 	u8 rsd;
 
 	bool cs_asserted[ROCKCHIP_SPI_MAX_CS_NUM];
+
+	bool slave_abort;
 };
 
 static inline void spi_enable_chip(struct rockchip_spi *rs, bool enable)
@@ -219,8 +221,8 @@ static u32 get_fifo_len(struct rockchip_spi *rs)
 
 static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 {
-	struct spi_master *master = spi->master;
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = spi->controller;
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 	bool cs_asserted = !enable;
 
 	/* Return immediately for no-op */
@@ -244,10 +246,10 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 	rs->cs_asserted[spi->chip_select] = cs_asserted;
 }
 
-static void rockchip_spi_handle_err(struct spi_master *master,
+static void rockchip_spi_handle_err(struct spi_controller *ctlr,
 				    struct spi_message *msg)
 {
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 
 	/* stop running spi transfer
 	 * this also flushes both rx and tx fifos
@@ -258,10 +260,10 @@ static void rockchip_spi_handle_err(struct spi_master *master,
 	writel_relaxed(0, rs->regs + ROCKCHIP_SPI_IMR);
 
 	if (atomic_read(&rs->state) & TXDMA)
-		dmaengine_terminate_async(master->dma_tx);
+		dmaengine_terminate_async(ctlr->dma_tx);
 
 	if (atomic_read(&rs->state) & RXDMA)
-		dmaengine_terminate_async(master->dma_rx);
+		dmaengine_terminate_async(ctlr->dma_rx);
 }
 
 static void rockchip_spi_pio_writer(struct rockchip_spi *rs)
@@ -319,8 +321,8 @@ static void rockchip_spi_pio_reader(struct rockchip_spi *rs)
 
 static irqreturn_t rockchip_spi_isr(int irq, void *dev_id)
 {
-	struct spi_master *master = dev_id;
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = dev_id;
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 
 	if (rs->tx_left)
 		rockchip_spi_pio_writer(rs);
@@ -329,7 +331,7 @@ static irqreturn_t rockchip_spi_isr(int irq, void *dev_id)
 	if (!rs->rx_left) {
 		spi_enable_chip(rs, false);
 		writel_relaxed(0, rs->regs + ROCKCHIP_SPI_IMR);
-		spi_finalize_current_transfer(master);
+		spi_finalize_current_transfer(ctlr);
 	}
 
 	return IRQ_HANDLED;
@@ -355,35 +357,35 @@ static int rockchip_spi_prepare_irq(struct rockchip_spi *rs,
 
 static void rockchip_spi_dma_rxcb(void *data)
 {
-	struct spi_master *master = data;
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = data;
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 	int state = atomic_fetch_andnot(RXDMA, &rs->state);
 
-	if (state & TXDMA)
+	if (state & TXDMA && !rs->slave_abort)
 		return;
 
 	spi_enable_chip(rs, false);
-	spi_finalize_current_transfer(master);
+	spi_finalize_current_transfer(ctlr);
 }
 
 static void rockchip_spi_dma_txcb(void *data)
 {
-	struct spi_master *master = data;
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = data;
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 	int state = atomic_fetch_andnot(TXDMA, &rs->state);
 
-	if (state & RXDMA)
+	if (state & RXDMA && !rs->slave_abort)
 		return;
 
 	/* Wait until the FIFO data completely. */
 	wait_for_idle(rs);
 
 	spi_enable_chip(rs, false);
-	spi_finalize_current_transfer(master);
+	spi_finalize_current_transfer(ctlr);
 }
 
 static int rockchip_spi_prepare_dma(struct rockchip_spi *rs,
-		struct spi_master *master, struct spi_transfer *xfer)
+		struct spi_controller *ctlr, struct spi_transfer *xfer)
 {
 	struct dma_async_tx_descriptor *rxdesc, *txdesc;
 
@@ -398,17 +400,17 @@ static int rockchip_spi_prepare_dma(struct rockchip_spi *rs,
 			.src_maxburst = 1,
 		};
 
-		dmaengine_slave_config(master->dma_rx, &rxconf);
+		dmaengine_slave_config(ctlr->dma_rx, &rxconf);
 
 		rxdesc = dmaengine_prep_slave_sg(
-				master->dma_rx,
+				ctlr->dma_rx,
 				xfer->rx_sg.sgl, xfer->rx_sg.nents,
 				DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT);
 		if (!rxdesc)
 			return -EINVAL;
 
 		rxdesc->callback = rockchip_spi_dma_rxcb;
-		rxdesc->callback_param = master;
+		rxdesc->callback_param = ctlr;
 	}
 
 	txdesc = NULL;
@@ -420,27 +422,27 @@ static int rockchip_spi_prepare_dma(struct rockchip_spi *rs,
 			.dst_maxburst = rs->fifo_len / 4,
 		};
 
-		dmaengine_slave_config(master->dma_tx, &txconf);
+		dmaengine_slave_config(ctlr->dma_tx, &txconf);
 
 		txdesc = dmaengine_prep_slave_sg(
-				master->dma_tx,
+				ctlr->dma_tx,
 				xfer->tx_sg.sgl, xfer->tx_sg.nents,
 				DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT);
 		if (!txdesc) {
 			if (rxdesc)
-				dmaengine_terminate_sync(master->dma_rx);
+				dmaengine_terminate_sync(ctlr->dma_rx);
 			return -EINVAL;
 		}
 
 		txdesc->callback = rockchip_spi_dma_txcb;
-		txdesc->callback_param = master;
+		txdesc->callback_param = ctlr;
 	}
 
 	/* rx must be started before tx due to spi instinct */
 	if (rxdesc) {
 		atomic_or(RXDMA, &rs->state);
 		dmaengine_submit(rxdesc);
-		dma_async_issue_pending(master->dma_rx);
+		dma_async_issue_pending(ctlr->dma_rx);
 	}
 
 	spi_enable_chip(rs, true);
@@ -448,7 +450,7 @@ static int rockchip_spi_prepare_dma(struct rockchip_spi *rs,
 	if (txdesc) {
 		atomic_or(TXDMA, &rs->state);
 		dmaengine_submit(txdesc);
-		dma_async_issue_pending(master->dma_tx);
+		dma_async_issue_pending(ctlr->dma_tx);
 	}
 
 	/* 1 means the transfer is in progress */
@@ -457,7 +459,7 @@ static int rockchip_spi_prepare_dma(struct rockchip_spi *rs,
 
 static void rockchip_spi_config(struct rockchip_spi *rs,
 		struct spi_device *spi, struct spi_transfer *xfer,
-		bool use_dma)
+		bool use_dma, bool slave_mode)
 {
 	u32 cr0 = CR0_FRF_SPI  << CR0_FRF_OFFSET
 	        | CR0_BHT_8BIT << CR0_BHT_OFFSET
@@ -466,6 +468,10 @@ static void rockchip_spi_config(struct rockchip_spi *rs,
 	u32 cr1;
 	u32 dmacr = 0;
 
+	if (slave_mode)
+		cr0 |= CR0_OPM_SLAVE << CR0_OPM_OFFSET;
+	rs->slave_abort = false;
+
 	cr0 |= rs->rsd << CR0_RSD_OFFSET;
 	cr0 |= (spi->mode & 0x3U) << CR0_SCPH_OFFSET;
 	if (spi->mode & SPI_LSB_FIRST)
@@ -493,7 +499,7 @@ static void rockchip_spi_config(struct rockchip_spi *rs,
 		break;
 	default:
 		/* we only whitelist 4, 8 and 16 bit words in
-		 * master->bits_per_word_mask, so this shouldn't
+		 * ctlr->bits_per_word_mask, so this shouldn't
 		 * happen
 		 */
 		unreachable();
@@ -535,12 +541,22 @@ static size_t rockchip_spi_max_transfer_size(struct spi_device *spi)
 	return ROCKCHIP_SPI_MAX_TRANLEN;
 }
 
+static int rockchip_spi_slave_abort(struct spi_controller *ctlr)
+{
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
+
+	rs->slave_abort = true;
+	complete(&ctlr->xfer_completion);
+
+	return 0;
+}
+
 static int rockchip_spi_transfer_one(
-		struct spi_master *master,
+		struct spi_controller *ctlr,
 		struct spi_device *spi,
 		struct spi_transfer *xfer)
 {
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 	bool use_dma;
 
 	WARN_ON(readl_relaxed(rs->regs + ROCKCHIP_SPI_SSIENR) &&
@@ -558,21 +574,21 @@ static int rockchip_spi_transfer_one(
 
 	rs->n_bytes = xfer->bits_per_word <= 8 ? 1 : 2;
 
-	use_dma = master->can_dma ? master->can_dma(master, spi, xfer) : false;
+	use_dma = ctlr->can_dma ? ctlr->can_dma(ctlr, spi, xfer) : false;
 
-	rockchip_spi_config(rs, spi, xfer, use_dma);
+	rockchip_spi_config(rs, spi, xfer, use_dma, ctlr->slave);
 
 	if (use_dma)
-		return rockchip_spi_prepare_dma(rs, master, xfer);
+		return rockchip_spi_prepare_dma(rs, ctlr, xfer);
 
 	return rockchip_spi_prepare_irq(rs, xfer);
 }
 
-static bool rockchip_spi_can_dma(struct spi_master *master,
+static bool rockchip_spi_can_dma(struct spi_controller *ctlr,
 				 struct spi_device *spi,
 				 struct spi_transfer *xfer)
 {
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 	unsigned int bytes_per_word = xfer->bits_per_word <= 8 ? 1 : 2;
 
 	/* if the numbor of spi words to transfer is less than the fifo
@@ -586,44 +602,55 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 {
 	int ret;
 	struct rockchip_spi *rs;
-	struct spi_master *master;
+	struct spi_controller *ctlr;
 	struct resource *mem;
+	struct device_node *np = pdev->dev.of_node;
 	u32 rsd_nsecs;
+	bool slave_mode;
+
+	slave_mode = of_property_read_bool(np, "spi-slave");
+
+	if (slave_mode)
+		ctlr = spi_alloc_slave(&pdev->dev,
+				sizeof(struct rockchip_spi));
+	else
+		ctlr = spi_alloc_master(&pdev->dev,
+				sizeof(struct rockchip_spi));
 
-	master = spi_alloc_master(&pdev->dev, sizeof(struct rockchip_spi));
-	if (!master)
+	if (!ctlr)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, master);
+	platform_set_drvdata(pdev, ctlr);
 
-	rs = spi_master_get_devdata(master);
+	rs = spi_controller_get_devdata(ctlr);
+	ctlr->slave = slave_mode;
 
 	/* Get basic io resource and map it */
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	rs->regs = devm_ioremap_resource(&pdev->dev, mem);
 	if (IS_ERR(rs->regs)) {
 		ret =  PTR_ERR(rs->regs);
-		goto err_put_master;
+		goto err_put_ctlr;
 	}
 
 	rs->apb_pclk = devm_clk_get(&pdev->dev, "apb_pclk");
 	if (IS_ERR(rs->apb_pclk)) {
 		dev_err(&pdev->dev, "Failed to get apb_pclk\n");
 		ret = PTR_ERR(rs->apb_pclk);
-		goto err_put_master;
+		goto err_put_ctlr;
 	}
 
 	rs->spiclk = devm_clk_get(&pdev->dev, "spiclk");
 	if (IS_ERR(rs->spiclk)) {
 		dev_err(&pdev->dev, "Failed to get spi_pclk\n");
 		ret = PTR_ERR(rs->spiclk);
-		goto err_put_master;
+		goto err_put_ctlr;
 	}
 
 	ret = clk_prepare_enable(rs->apb_pclk);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to enable apb_pclk\n");
-		goto err_put_master;
+		goto err_put_ctlr;
 	}
 
 	ret = clk_prepare_enable(rs->spiclk);
@@ -639,7 +666,7 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 		goto err_disable_spiclk;
 
 	ret = devm_request_threaded_irq(&pdev->dev, ret, rockchip_spi_isr, NULL,
-			IRQF_ONESHOT, dev_name(&pdev->dev), master);
+			IRQF_ONESHOT, dev_name(&pdev->dev), ctlr);
 	if (ret)
 		goto err_disable_spiclk;
 
@@ -673,78 +700,90 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	master->auto_runtime_pm = true;
-	master->bus_num = pdev->id;
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LOOP | SPI_LSB_FIRST;
-	master->num_chipselect = ROCKCHIP_SPI_MAX_CS_NUM;
-	master->dev.of_node = pdev->dev.of_node;
-	master->bits_per_word_mask = SPI_BPW_MASK(16) | SPI_BPW_MASK(8) | SPI_BPW_MASK(4);
-	master->min_speed_hz = rs->freq / BAUDR_SCKDV_MAX;
-	master->max_speed_hz = min(rs->freq / BAUDR_SCKDV_MIN, MAX_SCLK_OUT);
-
-	master->set_cs = rockchip_spi_set_cs;
-	master->transfer_one = rockchip_spi_transfer_one;
-	master->max_transfer_size = rockchip_spi_max_transfer_size;
-	master->handle_err = rockchip_spi_handle_err;
-	master->flags = SPI_MASTER_GPIO_SS;
-
-	master->dma_tx = dma_request_chan(rs->dev, "tx");
-	if (IS_ERR(master->dma_tx)) {
+	ctlr->auto_runtime_pm = true;
+	ctlr->bus_num = pdev->id;
+	ctlr->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LOOP | SPI_LSB_FIRST;
+	if (slave_mode) {
+		ctlr->mode_bits |= SPI_NO_CS;
+		ctlr->slave_abort = rockchip_spi_slave_abort;
+	} else {
+		ctlr->flags = SPI_MASTER_GPIO_SS;
+		ctlr->max_native_cs = ROCKCHIP_SPI_MAX_CS_NUM;
+		/*
+		 * rk spi0 has two native cs, spi1..5 one cs only
+		 * if num-cs is missing in the dts, default to 1
+		 */
+		if (of_property_read_u16(np, "num-cs", &ctlr->num_chipselect))
+			ctlr->num_chipselect = 1;
+		ctlr->use_gpio_descriptors = true;
+	}
+	ctlr->dev.of_node = pdev->dev.of_node;
+	ctlr->bits_per_word_mask = SPI_BPW_MASK(16) | SPI_BPW_MASK(8) | SPI_BPW_MASK(4);
+	ctlr->min_speed_hz = rs->freq / BAUDR_SCKDV_MAX;
+	ctlr->max_speed_hz = min(rs->freq / BAUDR_SCKDV_MIN, MAX_SCLK_OUT);
+
+	ctlr->set_cs = rockchip_spi_set_cs;
+	ctlr->transfer_one = rockchip_spi_transfer_one;
+	ctlr->max_transfer_size = rockchip_spi_max_transfer_size;
+	ctlr->handle_err = rockchip_spi_handle_err;
+
+	ctlr->dma_tx = dma_request_chan(rs->dev, "tx");
+	if (IS_ERR(ctlr->dma_tx)) {
 		/* Check tx to see if we need defer probing driver */
-		if (PTR_ERR(master->dma_tx) == -EPROBE_DEFER) {
+		if (PTR_ERR(ctlr->dma_tx) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
 			goto err_disable_pm_runtime;
 		}
 		dev_warn(rs->dev, "Failed to request TX DMA channel\n");
-		master->dma_tx = NULL;
+		ctlr->dma_tx = NULL;
 	}
 
-	master->dma_rx = dma_request_chan(rs->dev, "rx");
-	if (IS_ERR(master->dma_rx)) {
-		if (PTR_ERR(master->dma_rx) == -EPROBE_DEFER) {
+	ctlr->dma_rx = dma_request_chan(rs->dev, "rx");
+	if (IS_ERR(ctlr->dma_rx)) {
+		if (PTR_ERR(ctlr->dma_rx) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
 			goto err_free_dma_tx;
 		}
 		dev_warn(rs->dev, "Failed to request RX DMA channel\n");
-		master->dma_rx = NULL;
+		ctlr->dma_rx = NULL;
 	}
 
-	if (master->dma_tx && master->dma_rx) {
+	if (ctlr->dma_tx && ctlr->dma_rx) {
 		rs->dma_addr_tx = mem->start + ROCKCHIP_SPI_TXDR;
 		rs->dma_addr_rx = mem->start + ROCKCHIP_SPI_RXDR;
-		master->can_dma = rockchip_spi_can_dma;
+		ctlr->can_dma = rockchip_spi_can_dma;
 	}
 
-	ret = devm_spi_register_master(&pdev->dev, master);
+	ret = devm_spi_register_controller(&pdev->dev, ctlr);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to register master\n");
+		dev_err(&pdev->dev, "Failed to register controller\n");
 		goto err_free_dma_rx;
 	}
 
 	return 0;
 
 err_free_dma_rx:
-	if (master->dma_rx)
-		dma_release_channel(master->dma_rx);
+	if (ctlr->dma_rx)
+		dma_release_channel(ctlr->dma_rx);
 err_free_dma_tx:
-	if (master->dma_tx)
-		dma_release_channel(master->dma_tx);
+	if (ctlr->dma_tx)
+		dma_release_channel(ctlr->dma_tx);
 err_disable_pm_runtime:
 	pm_runtime_disable(&pdev->dev);
 err_disable_spiclk:
 	clk_disable_unprepare(rs->spiclk);
 err_disable_apbclk:
 	clk_disable_unprepare(rs->apb_pclk);
-err_put_master:
-	spi_master_put(master);
+err_put_ctlr:
+	spi_controller_put(ctlr);
 
 	return ret;
 }
 
 static int rockchip_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = spi_master_get(platform_get_drvdata(pdev));
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = spi_controller_get(platform_get_drvdata(pdev));
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 
 	pm_runtime_get_sync(&pdev->dev);
 
@@ -755,12 +794,12 @@ static int rockchip_spi_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
 
-	if (master->dma_tx)
-		dma_release_channel(master->dma_tx);
-	if (master->dma_rx)
-		dma_release_channel(master->dma_rx);
+	if (ctlr->dma_tx)
+		dma_release_channel(ctlr->dma_tx);
+	if (ctlr->dma_rx)
+		dma_release_channel(ctlr->dma_rx);
 
-	spi_master_put(master);
+	spi_controller_put(ctlr);
 
 	return 0;
 }
@@ -769,9 +808,9 @@ static int rockchip_spi_remove(struct platform_device *pdev)
 static int rockchip_spi_suspend(struct device *dev)
 {
 	int ret;
-	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_controller *ctlr = dev_get_drvdata(dev);
 
-	ret = spi_master_suspend(master);
+	ret = spi_controller_suspend(ctlr);
 	if (ret < 0)
 		return ret;
 
@@ -787,8 +826,8 @@ static int rockchip_spi_suspend(struct device *dev)
 static int rockchip_spi_resume(struct device *dev)
 {
 	int ret;
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = dev_get_drvdata(dev);
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 
 	pinctrl_pm_select_default_state(dev);
 
@@ -796,7 +835,7 @@ static int rockchip_spi_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	ret = spi_master_resume(master);
+	ret = spi_controller_resume(ctlr);
 	if (ret < 0) {
 		clk_disable_unprepare(rs->spiclk);
 		clk_disable_unprepare(rs->apb_pclk);
@@ -809,8 +848,8 @@ static int rockchip_spi_resume(struct device *dev)
 #ifdef CONFIG_PM
 static int rockchip_spi_runtime_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = dev_get_drvdata(dev);
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 
 	clk_disable_unprepare(rs->spiclk);
 	clk_disable_unprepare(rs->apb_pclk);
@@ -821,8 +860,8 @@ static int rockchip_spi_runtime_suspend(struct device *dev)
 static int rockchip_spi_runtime_resume(struct device *dev)
 {
 	int ret;
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = dev_get_drvdata(dev);
+	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 
 	ret = clk_prepare_enable(rs->apb_pclk);
 	if (ret < 0)
diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c
index 5497eeb3bf3e..ee0f3edf49cd 100644
--- a/drivers/spi/spi-sc18is602.c
+++ b/drivers/spi/spi-sc18is602.c
@@ -345,6 +345,6 @@ static struct i2c_driver sc18is602_driver = {
 
 module_i2c_driver(sc18is602_driver);
 
-MODULE_DESCRIPTION("SC18IC602/603 SPI Master Driver");
+MODULE_DESCRIPTION("SC18IS602/603 SPI Master Driver");
 MODULE_AUTHOR("Guenter Roeck");
 MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 1c11a00a2c36..b2579af0e3eb 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -1398,7 +1398,7 @@ static int sh_msiof_spi_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(sh_msiof_spi_pm_ops, sh_msiof_spi_suspend,
 			 sh_msiof_spi_resume);
-#define DEV_PM_OPS	&sh_msiof_spi_pm_ops
+#define DEV_PM_OPS	(&sh_msiof_spi_pm_ops)
 #else
 #define DEV_PM_OPS	NULL
 #endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/spi/spi-sprd-adi.c b/drivers/spi/spi-sprd-adi.c
index 87dadb6b8ebf..88e6543648cb 100644
--- a/drivers/spi/spi-sprd-adi.c
+++ b/drivers/spi/spi-sprd-adi.c
@@ -319,7 +319,7 @@ static int sprd_adi_transfer_one(struct spi_controller *ctlr,
 
 static void sprd_adi_set_wdt_rst_mode(struct sprd_adi *sadi)
 {
-#ifdef CONFIG_SPRD_WATCHDOG
+#if IS_ENABLED(CONFIG_SPRD_WATCHDOG)
 	u32 val;
 
 	/* Set default watchdog reboot mode */
diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c
index d066f5144c3e..3c44bb2fd9b1 100644
--- a/drivers/spi/spi-stm32-qspi.c
+++ b/drivers/spi/spi-stm32-qspi.c
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/pm_runtime.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
@@ -87,6 +88,7 @@
 #define STM32_BUSY_TIMEOUT_US 100000
 #define STM32_ABT_TIMEOUT_US 100000
 #define STM32_COMP_TIMEOUT_MS 1000
+#define STM32_AUTOSUSPEND_DELAY -1
 
 struct stm32_qspi_flash {
 	struct stm32_qspi *qspi;
@@ -431,10 +433,17 @@ static int stm32_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	struct stm32_qspi *qspi = spi_controller_get_devdata(mem->spi->master);
 	int ret;
 
+	ret = pm_runtime_get_sync(qspi->dev);
+	if (ret < 0)
+		return ret;
+
 	mutex_lock(&qspi->lock);
 	ret = stm32_qspi_send(mem, op);
 	mutex_unlock(&qspi->lock);
 
+	pm_runtime_mark_last_busy(qspi->dev);
+	pm_runtime_put_autosuspend(qspi->dev);
+
 	return ret;
 }
 
@@ -444,6 +453,7 @@ static int stm32_qspi_setup(struct spi_device *spi)
 	struct stm32_qspi *qspi = spi_controller_get_devdata(ctrl);
 	struct stm32_qspi_flash *flash;
 	u32 presc;
+	int ret;
 
 	if (ctrl->busy)
 		return -EBUSY;
@@ -451,6 +461,10 @@ static int stm32_qspi_setup(struct spi_device *spi)
 	if (!spi->max_speed_hz)
 		return -EINVAL;
 
+	ret = pm_runtime_get_sync(qspi->dev);
+	if (ret < 0)
+		return ret;
+
 	presc = DIV_ROUND_UP(qspi->clk_rate, spi->max_speed_hz) - 1;
 
 	flash = &qspi->flash[spi->chip_select];
@@ -467,6 +481,9 @@ static int stm32_qspi_setup(struct spi_device *spi)
 	writel_relaxed(qspi->dcr_reg, qspi->io_base + QSPI_DCR);
 	mutex_unlock(&qspi->lock);
 
+	pm_runtime_mark_last_busy(qspi->dev);
+	pm_runtime_put_autosuspend(qspi->dev);
+
 	return 0;
 }
 
@@ -538,10 +555,15 @@ static const struct spi_controller_mem_ops stm32_qspi_mem_ops = {
 
 static void stm32_qspi_release(struct stm32_qspi *qspi)
 {
+	pm_runtime_get_sync(qspi->dev);
 	/* disable qspi */
 	writel_relaxed(0, qspi->io_base + QSPI_CR);
 	stm32_qspi_dma_free(qspi);
 	mutex_destroy(&qspi->lock);
+	pm_runtime_put_noidle(qspi->dev);
+	pm_runtime_disable(qspi->dev);
+	pm_runtime_set_suspended(qspi->dev);
+	pm_runtime_dont_use_autosuspend(qspi->dev);
 	clk_disable_unprepare(qspi->clk);
 }
 
@@ -643,9 +665,20 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	ctrl->num_chipselect = STM32_QSPI_MAX_NORCHIP;
 	ctrl->dev.of_node = dev->of_node;
 
+	pm_runtime_set_autosuspend_delay(dev, STM32_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+	pm_runtime_get_noresume(dev);
+
 	ret = devm_spi_register_master(dev, ctrl);
-	if (!ret)
-		return 0;
+	if (ret)
+		goto err_qspi_release;
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return 0;
 
 err_qspi_release:
 	stm32_qspi_release(qspi);
@@ -660,14 +693,28 @@ static int stm32_qspi_remove(struct platform_device *pdev)
 	struct stm32_qspi *qspi = platform_get_drvdata(pdev);
 
 	stm32_qspi_release(qspi);
+
 	return 0;
 }
 
-static int __maybe_unused stm32_qspi_suspend(struct device *dev)
+static int __maybe_unused stm32_qspi_runtime_suspend(struct device *dev)
 {
 	struct stm32_qspi *qspi = dev_get_drvdata(dev);
 
 	clk_disable_unprepare(qspi->clk);
+
+	return 0;
+}
+
+static int __maybe_unused stm32_qspi_runtime_resume(struct device *dev)
+{
+	struct stm32_qspi *qspi = dev_get_drvdata(dev);
+
+	return clk_prepare_enable(qspi->clk);
+}
+
+static int __maybe_unused stm32_qspi_suspend(struct device *dev)
+{
 	pinctrl_pm_select_sleep_state(dev);
 
 	return 0;
@@ -683,10 +730,17 @@ static int __maybe_unused stm32_qspi_resume(struct device *dev)
 	writel_relaxed(qspi->cr_reg, qspi->io_base + QSPI_CR);
 	writel_relaxed(qspi->dcr_reg, qspi->io_base + QSPI_DCR);
 
+	pm_runtime_mark_last_busy(qspi->dev);
+	pm_runtime_put_autosuspend(qspi->dev);
+
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(stm32_qspi_pm_ops, stm32_qspi_suspend, stm32_qspi_resume);
+static const struct dev_pm_ops stm32_qspi_pm_ops = {
+	SET_RUNTIME_PM_OPS(stm32_qspi_runtime_suspend,
+			   stm32_qspi_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(stm32_qspi_suspend, stm32_qspi_resume)
+};
 
 static const struct of_device_id stm32_qspi_match[] = {
 	{.compatible = "st,stm32f469-qspi"},
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 44ac6eb3298d..4c643dfc7fbb 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -811,7 +811,9 @@ static irqreturn_t stm32f4_spi_irq_event(int irq, void *dev_id)
 		mask |= STM32F4_SPI_SR_TXE;
 	}
 
-	if (!spi->cur_usedma && spi->cur_comm == SPI_FULL_DUPLEX) {
+	if (!spi->cur_usedma && (spi->cur_comm == SPI_FULL_DUPLEX ||
+				spi->cur_comm == SPI_SIMPLEX_RX ||
+				spi->cur_comm == SPI_3WIRE_RX)) {
 		/* TXE flag is set and is handled when RXNE flag occurs */
 		sr &= ~STM32F4_SPI_SR_TXE;
 		mask |= STM32F4_SPI_SR_RXNE | STM32F4_SPI_SR_OVR;
@@ -850,7 +852,7 @@ static irqreturn_t stm32f4_spi_irq_event(int irq, void *dev_id)
 		stm32f4_spi_read_rx(spi);
 		if (spi->rx_len == 0)
 			end = true;
-		else /* Load data for discontinuous mode */
+		else if (spi->tx_buf)/* Load data for discontinuous mode */
 			stm32f4_spi_write_tx(spi);
 	}
 
@@ -1151,7 +1153,9 @@ static int stm32f4_spi_transfer_one_irq(struct stm32_spi *spi)
 	/* Enable the interrupts relative to the current communication mode */
 	if (spi->cur_comm == SPI_SIMPLEX_TX || spi->cur_comm == SPI_3WIRE_TX) {
 		cr2 |= STM32F4_SPI_CR2_TXEIE;
-	} else if (spi->cur_comm == SPI_FULL_DUPLEX) {
+	} else if (spi->cur_comm == SPI_FULL_DUPLEX ||
+				spi->cur_comm == SPI_SIMPLEX_RX ||
+				spi->cur_comm == SPI_3WIRE_RX) {
 		/* In transmit-only mode, the OVR flag is set in the SR register
 		 * since the received data are never read. Therefore set OVR
 		 * interrupt only when rx buffer is available.
@@ -1462,10 +1466,16 @@ static int stm32f4_spi_set_mode(struct stm32_spi *spi, unsigned int comm_type)
 		stm32_spi_set_bits(spi, STM32F4_SPI_CR1,
 					STM32F4_SPI_CR1_BIDIMODE |
 					STM32F4_SPI_CR1_BIDIOE);
-	} else if (comm_type == SPI_FULL_DUPLEX) {
+	} else if (comm_type == SPI_FULL_DUPLEX ||
+				comm_type == SPI_SIMPLEX_RX) {
 		stm32_spi_clr_bits(spi, STM32F4_SPI_CR1,
 					STM32F4_SPI_CR1_BIDIMODE |
 					STM32F4_SPI_CR1_BIDIOE);
+	} else if (comm_type == SPI_3WIRE_RX) {
+		stm32_spi_set_bits(spi, STM32F4_SPI_CR1,
+					STM32F4_SPI_CR1_BIDIMODE);
+		stm32_spi_clr_bits(spi, STM32F4_SPI_CR1,
+					STM32F4_SPI_CR1_BIDIOE);
 	} else {
 		return -EINVAL;
 	}
@@ -1906,6 +1916,7 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	master->prepare_message = stm32_spi_prepare_msg;
 	master->transfer_one = stm32_spi_transfer_one;
 	master->unprepare_message = stm32_spi_unprepare_msg;
+	master->flags = SPI_MASTER_MUST_TX;
 
 	spi->dma_tx = dma_request_chan(spi->dev, "tx");
 	if (IS_ERR(spi->dma_tx)) {
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index ec7967be9e2f..ecea15534c42 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -470,6 +470,7 @@ static int sun6i_spi_probe(struct platform_device *pdev)
 
 	master->max_speed_hz = 100 * 1000 * 1000;
 	master->min_speed_hz = 3 * 1000;
+	master->use_gpio_descriptors = true;
 	master->set_cs = sun6i_spi_set_cs;
 	master->transfer_one = sun6i_spi_transfer_one;
 	master->num_chipselect = 4;
diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c
index 83edabdb41ad..c2c58871a947 100644
--- a/drivers/spi/spi-tegra114.c
+++ b/drivers/spi/spi-tegra114.c
@@ -1398,6 +1398,7 @@ static int tegra_spi_probe(struct platform_device *pdev)
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret);
+		pm_runtime_put_noidle(&pdev->dev);
 		goto exit_pm_disable;
 	}
 
diff --git a/drivers/spi/spi-tegra20-sflash.c b/drivers/spi/spi-tegra20-sflash.c
index 514429379206..02cf5f463ba6 100644
--- a/drivers/spi/spi-tegra20-sflash.c
+++ b/drivers/spi/spi-tegra20-sflash.c
@@ -491,6 +491,7 @@ static int tegra_sflash_probe(struct platform_device *pdev)
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret);
+		pm_runtime_put_noidle(&pdev->dev);
 		goto exit_pm_disable;
 	}
 
diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c
index 7f4d932dade7..a07b72e9c344 100644
--- a/drivers/spi/spi-tegra20-slink.c
+++ b/drivers/spi/spi-tegra20-slink.c
@@ -1118,6 +1118,7 @@ static int tegra_slink_probe(struct platform_device *pdev)
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret);
+		pm_runtime_put_noidle(&pdev->dev);
 		goto exit_pm_disable;
 	}
 	tspi->def_command_reg  = SLINK_M_S;
diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c
index 0fa50979644d..6a9ef8ee3cc9 100644
--- a/drivers/spi/spi-uniphier.c
+++ b/drivers/spi/spi-uniphier.c
@@ -659,8 +659,7 @@ static int uniphier_spi_probe(struct platform_device *pdev)
 	priv->master = master;
 	priv->is_save_param = false;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
 	if (IS_ERR(priv->base)) {
 		ret = PTR_ERR(priv->base);
 		goto out_master_put;
@@ -716,8 +715,10 @@ static int uniphier_spi_probe(struct platform_device *pdev)
 
 	master->dma_tx = dma_request_chan(&pdev->dev, "tx");
 	if (IS_ERR_OR_NULL(master->dma_tx)) {
-		if (PTR_ERR(master->dma_tx) == -EPROBE_DEFER)
+		if (PTR_ERR(master->dma_tx) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
 			goto out_disable_clk;
+		}
 		master->dma_tx = NULL;
 		dma_tx_burst = INT_MAX;
 	} else {
@@ -732,8 +733,10 @@ static int uniphier_spi_probe(struct platform_device *pdev)
 
 	master->dma_rx = dma_request_chan(&pdev->dev, "rx");
 	if (IS_ERR_OR_NULL(master->dma_rx)) {
-		if (PTR_ERR(master->dma_rx) == -EPROBE_DEFER)
+		if (PTR_ERR(master->dma_rx) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
 			goto out_disable_clk;
+		}
 		master->dma_rx = NULL;
 		dma_rx_burst = INT_MAX;
 	} else {
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index c92c89467e7e..8158e281f354 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1023,7 +1023,8 @@ static int spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 	void *tmp;
 	unsigned int max_tx, max_rx;
 
-	if (ctlr->flags & (SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX)) {
+	if ((ctlr->flags & (SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX))
+		&& !(msg->spi->mode & SPI_3WIRE)) {
 		max_tx = 0;
 		max_rx = 0;
 
@@ -1075,7 +1076,7 @@ static int spi_transfer_wait(struct spi_controller *ctlr,
 {
 	struct spi_statistics *statm = &ctlr->statistics;
 	struct spi_statistics *stats = &msg->spi->statistics;
-	unsigned long long ms = 1;
+	unsigned long long ms;
 
 	if (spi_controller_is_slave(ctlr)) {
 		if (wait_for_completion_interruptible(&ctlr->xfer_completion)) {
@@ -1160,6 +1161,8 @@ int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer)
 {
 	int delay;
 
+	might_sleep();
+
 	if (!_delay)
 		return -EINVAL;
 
@@ -2111,6 +2114,7 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data)
 			}
 
 			lookup->max_speed_hz = sb->connection_speed;
+			lookup->bits_per_word = sb->data_bit_length;
 
 			if (sb->clock_phase == ACPI_SPI_SECOND_PHASE)
 				lookup->mode |= SPI_CPHA;
@@ -2760,6 +2764,8 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 	struct spi_controller *found;
 	int id = ctlr->bus_num;
 
+	device_for_each_child(&ctlr->dev, NULL, __unregister);
+
 	/* First make sure that this controller was ever added */
 	mutex_lock(&board_lock);
 	found = idr_find(&spi_master_idr, id);
@@ -2772,7 +2778,6 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 	list_del(&ctlr->list);
 	mutex_unlock(&board_lock);
 
-	device_for_each_child(&ctlr->dev, NULL, __unregister);
 	device_unregister(&ctlr->dev);
 	/* free bus id */
 	mutex_lock(&board_lock);
@@ -3853,8 +3858,7 @@ static u8	*buf;
  * is zero for success, else a negative errno status code.
  * This call may only be used from a context that may sleep.
  *
- * Parameters to this routine are always copied using a small buffer;
- * portable code should never use this for more than 32 bytes.
+ * Parameters to this routine are always copied using a small buffer.
  * Performance-sensitive or bulk transfer code should instead use
  * spi_{async,sync}() calls with dma-safe buffers.
  *
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 80dd1025b953..d753df700e9e 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -62,7 +62,8 @@ static DECLARE_BITMAP(minors, N_SPI_MINORS);
 #define SPI_MODE_MASK		(SPI_CPHA | SPI_CPOL | SPI_CS_HIGH \
 				| SPI_LSB_FIRST | SPI_3WIRE | SPI_LOOP \
 				| SPI_NO_CS | SPI_READY | SPI_TX_DUAL \
-				| SPI_TX_QUAD | SPI_RX_DUAL | SPI_RX_QUAD)
+				| SPI_TX_QUAD | SPI_TX_OCTAL | SPI_RX_DUAL \
+				| SPI_RX_QUAD | SPI_RX_OCTAL)
 
 struct spidev_data {
 	dev_t			devt;
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index 08d1bbbebf2d..e84b4fb493d6 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -2725,8 +2725,10 @@ static int comedi_open(struct inode *inode, struct file *file)
 	}
 
 	cfp = kzalloc(sizeof(*cfp), GFP_KERNEL);
-	if (!cfp)
+	if (!cfp) {
+		comedi_dev_put(dev);
 		return -ENOMEM;
+	}
 
 	cfp->dev = dev;
 
diff --git a/drivers/staging/comedi/drivers/dt2815.c b/drivers/staging/comedi/drivers/dt2815.c
index 83026ba63d1c..78a7c1b3448a 100644
--- a/drivers/staging/comedi/drivers/dt2815.c
+++ b/drivers/staging/comedi/drivers/dt2815.c
@@ -92,6 +92,7 @@ static int dt2815_ao_insn(struct comedi_device *dev, struct comedi_subdevice *s,
 	int ret;
 
 	for (i = 0; i < insn->n; i++) {
+		/* FIXME: lo bit 0 chooses voltage output or current output */
 		lo = ((data[i] & 0x0f) << 4) | (chan << 1) | 0x01;
 		hi = (data[i] & 0xff0) >> 4;
 
@@ -105,6 +106,8 @@ static int dt2815_ao_insn(struct comedi_device *dev, struct comedi_subdevice *s,
 		if (ret)
 			return ret;
 
+		outb(hi, dev->iobase + DT2815_DATA);
+
 		devpriv->ao_readback[chan] = data[i];
 	}
 	return i;
diff --git a/drivers/staging/gasket/apex_driver.c b/drivers/staging/gasket/apex_driver.c
index 46199c8ca441..f12f81c8dd2f 100644
--- a/drivers/staging/gasket/apex_driver.c
+++ b/drivers/staging/gasket/apex_driver.c
@@ -570,13 +570,6 @@ static const struct pci_device_id apex_pci_ids[] = {
 	{ PCI_DEVICE(APEX_PCI_VENDOR_ID, APEX_PCI_DEVICE_ID) }, { 0 }
 };
 
-static void apex_pci_fixup_class(struct pci_dev *pdev)
-{
-	pdev->class = (PCI_CLASS_SYSTEM_OTHER << 8) | pdev->class;
-}
-DECLARE_PCI_FIXUP_CLASS_HEADER(APEX_PCI_VENDOR_ID, APEX_PCI_DEVICE_ID,
-			       PCI_CLASS_NOT_DEFINED, 8, apex_pci_fixup_class);
-
 static int apex_pci_probe(struct pci_dev *pci_dev,
 			  const struct pci_device_id *id)
 {
diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c
index 8e0575fcb4c8..67325fbaf760 100644
--- a/drivers/staging/gasket/gasket_core.c
+++ b/drivers/staging/gasket/gasket_core.c
@@ -925,6 +925,10 @@ do_map_region(const struct gasket_dev *gasket_dev, struct vm_area_struct *vma,
 		gasket_get_bar_index(gasket_dev,
 				     (vma->vm_pgoff << PAGE_SHIFT) +
 				     driver_desc->legacy_mmap_address_offset);
+
+	if (bar_index < 0)
+		return DO_MAP_REGION_INVALID;
+
 	phys_base = gasket_dev->bar_data[bar_index].phys_base + phys_offset;
 	while (mapped_bytes < map_length) {
 		/*
diff --git a/drivers/staging/gasket/gasket_sysfs.c b/drivers/staging/gasket/gasket_sysfs.c
index a2d67c28f530..5f0e089573a2 100644
--- a/drivers/staging/gasket/gasket_sysfs.c
+++ b/drivers/staging/gasket/gasket_sysfs.c
@@ -228,8 +228,7 @@ int gasket_sysfs_create_entries(struct device *device,
 	}
 
 	mutex_lock(&mapping->mutex);
-	for (i = 0; strcmp(attrs[i].attr.attr.name, GASKET_ARRAY_END_MARKER);
-		i++) {
+	for (i = 0; attrs[i].attr.attr.name != NULL; i++) {
 		if (mapping->attribute_count == GASKET_SYSFS_MAX_NODES) {
 			dev_err(device,
 				"Maximum number of sysfs nodes reached for device\n");
diff --git a/drivers/staging/gasket/gasket_sysfs.h b/drivers/staging/gasket/gasket_sysfs.h
index 1d0eed66a7f4..ab5aa351d555 100644
--- a/drivers/staging/gasket/gasket_sysfs.h
+++ b/drivers/staging/gasket/gasket_sysfs.h
@@ -30,10 +30,6 @@
  */
 #define GASKET_SYSFS_MAX_NODES 196
 
-/* End markers for sysfs struct arrays. */
-#define GASKET_ARRAY_END_TOKEN GASKET_RESERVED_ARRAY_END
-#define GASKET_ARRAY_END_MARKER __stringify(GASKET_ARRAY_END_TOKEN)
-
 /*
  * Terminator struct for a gasket_sysfs_attr array. Must be at the end of
  * all gasket_sysfs_attribute arrays.
diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c
index 55c51143bb09..4ffb334cd5cd 100644
--- a/drivers/staging/greybus/uart.c
+++ b/drivers/staging/greybus/uart.c
@@ -537,9 +537,9 @@ static void gb_tty_set_termios(struct tty_struct *tty,
 	}
 
 	if (C_CRTSCTS(tty) && C_BAUD(tty) != B0)
-		newline.flow_control |= GB_SERIAL_AUTO_RTSCTS_EN;
+		newline.flow_control = GB_SERIAL_AUTO_RTSCTS_EN;
 	else
-		newline.flow_control &= ~GB_SERIAL_AUTO_RTSCTS_EN;
+		newline.flow_control = 0;
 
 	if (memcmp(&gb_tty->line_coding, &newline, sizeof(newline))) {
 		memcpy(&gb_tty->line_coding, &newline, sizeof(newline));
diff --git a/drivers/staging/iio/resolver/ad2s1210.c b/drivers/staging/iio/resolver/ad2s1210.c
index 4b25a3a314ed..ed404355ea4c 100644
--- a/drivers/staging/iio/resolver/ad2s1210.c
+++ b/drivers/staging/iio/resolver/ad2s1210.c
@@ -130,17 +130,24 @@ static int ad2s1210_config_write(struct ad2s1210_state *st, u8 data)
 static int ad2s1210_config_read(struct ad2s1210_state *st,
 				unsigned char address)
 {
-	struct spi_transfer xfer = {
-		.len = 2,
-		.rx_buf = st->rx,
-		.tx_buf = st->tx,
+	struct spi_transfer xfers[] = {
+		{
+			.len = 1,
+			.rx_buf = &st->rx[0],
+			.tx_buf = &st->tx[0],
+			.cs_change = 1,
+		}, {
+			.len = 1,
+			.rx_buf = &st->rx[1],
+			.tx_buf = &st->tx[1],
+		},
 	};
 	int ret = 0;
 
 	ad2s1210_set_mode(MOD_CONFIG, st);
 	st->tx[0] = address | AD2S1210_MSB_IS_HIGH;
 	st->tx[1] = AD2S1210_REG_FAULT;
-	ret = spi_sync_transfer(st->sdev, &xfer, 1);
+	ret = spi_sync_transfer(st->sdev, xfers, 2);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/staging/kpc2000/kpc2000/core.c b/drivers/staging/kpc2000/kpc2000/core.c
index 7b00d7069e21..358d7b2f4ad1 100644
--- a/drivers/staging/kpc2000/kpc2000/core.c
+++ b/drivers/staging/kpc2000/kpc2000/core.c
@@ -298,7 +298,6 @@ static int kp2000_pcie_probe(struct pci_dev *pdev,
 {
 	int err = 0;
 	struct kp2000_device *pcard;
-	int rv;
 	unsigned long reg_bar_phys_addr;
 	unsigned long reg_bar_phys_len;
 	unsigned long dma_bar_phys_addr;
@@ -445,11 +444,11 @@ static int kp2000_pcie_probe(struct pci_dev *pdev,
 	if (err < 0)
 		goto err_release_dma;
 
-	rv = request_irq(pcard->pdev->irq, kp2000_irq_handler, IRQF_SHARED,
-			 pcard->name, pcard);
-	if (rv) {
+	err = request_irq(pcard->pdev->irq, kp2000_irq_handler, IRQF_SHARED,
+			  pcard->name, pcard);
+	if (err) {
 		dev_err(&pcard->pdev->dev,
-			"%s: failed to request_irq: %d\n", __func__, rv);
+			"%s: failed to request_irq: %d\n", __func__, err);
 		goto err_disable_msi;
 	}
 
diff --git a/drivers/staging/ks7010/TODO b/drivers/staging/ks7010/TODO
index 87a6dac4890d..ab6f39175d99 100644
--- a/drivers/staging/ks7010/TODO
+++ b/drivers/staging/ks7010/TODO
@@ -30,5 +30,4 @@ Now the TODOs:
 
 Please send any patches to:
 Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-Wolfram Sang <wsa@the-dreams.de>
 Linux Driver Project Developer List <driverdev-devel@linuxdriverproject.org>
diff --git a/drivers/staging/vt6656/key.c b/drivers/staging/vt6656/key.c
index 41b73f9670e2..ac3b188984d0 100644
--- a/drivers/staging/vt6656/key.c
+++ b/drivers/staging/vt6656/key.c
@@ -83,9 +83,6 @@ static int vnt_set_keymode(struct ieee80211_hw *hw, u8 *mac_addr,
 	case  VNT_KEY_PAIRWISE:
 		key_mode |= mode;
 		key_inx = 4;
-		/* Don't save entry for pairwise key for station mode */
-		if (priv->op_mode == NL80211_IFTYPE_STATION)
-			clear_bit(entry, &priv->key_entry_inuse);
 		break;
 	default:
 		return -EINVAL;
@@ -109,7 +106,6 @@ static int vnt_set_keymode(struct ieee80211_hw *hw, u8 *mac_addr,
 int vnt_set_keys(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 		 struct ieee80211_vif *vif, struct ieee80211_key_conf *key)
 {
-	struct ieee80211_bss_conf *conf = &vif->bss_conf;
 	struct vnt_private *priv = hw->priv;
 	u8 *mac_addr = NULL;
 	u8 key_dec_mode = 0;
@@ -154,16 +150,12 @@ int vnt_set_keys(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 		return -EOPNOTSUPP;
 	}
 
-	if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) {
+	if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE)
 		vnt_set_keymode(hw, mac_addr, key, VNT_KEY_PAIRWISE,
 				key_dec_mode, true);
-	} else {
-		vnt_set_keymode(hw, mac_addr, key, VNT_KEY_DEFAULTKEY,
+	else
+		vnt_set_keymode(hw, mac_addr, key, VNT_KEY_GROUP_ADDRESS,
 				key_dec_mode, true);
 
-		vnt_set_keymode(hw, (u8 *)conf->bssid, key,
-				VNT_KEY_GROUP_ADDRESS, key_dec_mode, true);
-	}
-
 	return 0;
 }
diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c
index 8e7269c87ea9..5f78cad3b647 100644
--- a/drivers/staging/vt6656/main_usb.c
+++ b/drivers/staging/vt6656/main_usb.c
@@ -625,8 +625,6 @@ static int vnt_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 
 	priv->op_mode = vif->type;
 
-	vnt_set_bss_mode(priv);
-
 	/* LED blink on TX */
 	vnt_mac_set_led(priv, LEDSTS_STS, LEDSTS_INTER);
 
@@ -713,7 +711,6 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw,
 		priv->basic_rates = conf->basic_rates;
 
 		vnt_update_top_rates(priv);
-		vnt_set_bss_mode(priv);
 
 		dev_dbg(&priv->usb->dev, "basic rates %x\n", conf->basic_rates);
 	}
@@ -742,11 +739,14 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw,
 			priv->short_slot_time = false;
 
 		vnt_set_short_slot_time(priv);
-		vnt_update_ifs(priv);
 		vnt_set_vga_gain_offset(priv, priv->bb_vga[0]);
 		vnt_update_pre_ed_threshold(priv, false);
 	}
 
+	if (changed & (BSS_CHANGED_BASIC_RATES | BSS_CHANGED_ERP_PREAMBLE |
+		       BSS_CHANGED_ERP_SLOT))
+		vnt_set_bss_mode(priv);
+
 	if (changed & BSS_CHANGED_TXPOWER)
 		vnt_rf_setpower(priv, priv->current_rate,
 				conf->chandef.chan->hw_value);
@@ -770,12 +770,15 @@ static void vnt_bss_info_changed(struct ieee80211_hw *hw,
 			vnt_mac_reg_bits_on(priv, MAC_REG_TFTCTL,
 					    TFTCTL_TSFCNTREN);
 
-			vnt_adjust_tsf(priv, conf->beacon_rate->hw_value,
-				       conf->sync_tsf, priv->current_tsf);
-
 			vnt_mac_set_beacon_interval(priv, conf->beacon_int);
 
 			vnt_reset_next_tbtt(priv, conf->beacon_int);
+
+			vnt_adjust_tsf(priv, conf->beacon_rate->hw_value,
+				       conf->sync_tsf, priv->current_tsf);
+
+			vnt_update_next_tbtt(priv,
+					     conf->sync_tsf, conf->beacon_int);
 		} else {
 			vnt_clear_current_tsf(priv);
 
@@ -809,15 +812,11 @@ static void vnt_configure(struct ieee80211_hw *hw,
 {
 	struct vnt_private *priv = hw->priv;
 	u8 rx_mode = 0;
-	int rc;
 
 	*total_flags &= FIF_ALLMULTI | FIF_OTHER_BSS | FIF_BCN_PRBRESP_PROMISC;
 
-	rc = vnt_control_in(priv, MESSAGE_TYPE_READ, MAC_REG_RCR,
-			    MESSAGE_REQUEST_MACREG, sizeof(u8), &rx_mode);
-
-	if (!rc)
-		rx_mode = RCR_MULTICAST | RCR_BROADCAST;
+	vnt_control_in(priv, MESSAGE_TYPE_READ, MAC_REG_RCR,
+		       MESSAGE_REQUEST_MACREG, sizeof(u8), &rx_mode);
 
 	dev_dbg(&priv->usb->dev, "rx mode in = %x\n", rx_mode);
 
@@ -856,8 +855,12 @@ static int vnt_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	case SET_KEY:
 		return vnt_set_keys(hw, sta, vif, key);
 	case DISABLE_KEY:
-		if (test_bit(key->hw_key_idx, &priv->key_entry_inuse))
+		if (test_bit(key->hw_key_idx, &priv->key_entry_inuse)) {
 			clear_bit(key->hw_key_idx, &priv->key_entry_inuse);
+
+			vnt_mac_disable_keyentry(priv, key->hw_key_idx);
+		}
+
 	default:
 		break;
 	}
diff --git a/drivers/staging/vt6656/usbpipe.c b/drivers/staging/vt6656/usbpipe.c
index eae211e5860f..91b62c3dff7b 100644
--- a/drivers/staging/vt6656/usbpipe.c
+++ b/drivers/staging/vt6656/usbpipe.c
@@ -207,7 +207,8 @@ static void vnt_int_process_data(struct vnt_private *priv)
 				priv->wake_up_count =
 					priv->hw->conf.listen_interval;
 
-			--priv->wake_up_count;
+			if (priv->wake_up_count)
+				--priv->wake_up_count;
 
 			/* Turn on wake up to listen next beacon */
 			if (priv->wake_up_count == 1)
diff --git a/drivers/staging/wfx/scan.c b/drivers/staging/wfx/scan.c
index 6e1e50048651..9aa14331affd 100644
--- a/drivers/staging/wfx/scan.c
+++ b/drivers/staging/wfx/scan.c
@@ -57,8 +57,10 @@ static int send_scan_req(struct wfx_vif *wvif,
 	wvif->scan_abort = false;
 	reinit_completion(&wvif->scan_complete);
 	timeout = hif_scan(wvif, req, start_idx, i - start_idx);
-	if (timeout < 0)
+	if (timeout < 0) {
+		wfx_tx_unlock(wvif->wdev);
 		return timeout;
+	}
 	ret = wait_for_completion_timeout(&wvif->scan_complete, timeout);
 	if (req->channels[start_idx]->max_power != wvif->vif->bss_conf.txpower)
 		hif_set_output_power(wvif, wvif->vif->bss_conf.txpower);
diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c
index 6b4b354c88aa..1e031d81e59e 100644
--- a/drivers/target/target_core_fabric_lib.c
+++ b/drivers/target/target_core_fabric_lib.c
@@ -63,7 +63,7 @@ static int fc_get_pr_transport_id(
 	 * encoded TransportID.
 	 */
 	ptr = &se_nacl->initiatorname[0];
-	for (i = 0; i < 24; ) {
+	for (i = 0; i < 23; ) {
 		if (!strncmp(&ptr[i], ":", 1)) {
 			i++;
 			continue;
@@ -341,7 +341,8 @@ static char *iscsi_parse_pr_out_transport_id(
 			*p = tolower(*p);
 			p++;
 		}
-	}
+	} else
+		*port_nexus_ptr = NULL;
 
 	return &buf[4];
 }
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 51ffd5c002de..1c181d31f4c8 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -432,7 +432,7 @@ iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd)
 				target_to_linux_sector(dev, cmd->t_task_lba),
 				target_to_linux_sector(dev,
 					sbc_get_write_same_sectors(cmd)),
-				GFP_KERNEL, false);
+				GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
 	if (ret)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 594b724bbf79..264a822c0bfa 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -3350,6 +3350,7 @@ static void target_tmr_work(struct work_struct *work)
 
 	cmd->se_tfo->queue_tm_rsp(cmd);
 
+	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 	return;
 
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 0b9dfa6b17bc..f769bb1e3735 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -2073,6 +2073,7 @@ static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level)
 	mb->cmd_tail = 0;
 	mb->cmd_head = 0;
 	tcmu_flush_dcache_range(mb, sizeof(*mb));
+	clear_bit(TCMU_DEV_BIT_BROKEN, &udev->flags);
 
 	del_timer(&udev->cmd_timer);
 
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index 3d084cec136f..50c7534ba31e 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -182,6 +182,9 @@ static int usb4_switch_op(struct tb_switch *sw, u16 opcode, u8 *status)
 		return ret;
 
 	ret = tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_26, 1);
+	if (ret)
+		return ret;
+
 	if (val & ROUTER_CS_26_ONS)
 		return -EOPNOTSUPP;
 
diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig
index 31b7e1b03749..d1b27b0522a3 100644
--- a/drivers/tty/hvc/Kconfig
+++ b/drivers/tty/hvc/Kconfig
@@ -88,7 +88,7 @@ config HVC_DCC
 
 config HVC_RISCV_SBI
 	bool "RISC-V SBI console support"
-	depends on RISCV_SBI
+	depends on RISCV_SBI_V01
 	select HVC_DRIVER
 	help
 	  This enables support for console output via RISC-V SBI calls, which
diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index 27284a2dcd2b..436cc51c92c3 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -302,10 +302,6 @@ int hvc_instantiate(uint32_t vtermno, int index, const struct hv_ops *ops)
 	vtermnos[index] = vtermno;
 	cons_ops[index] = ops;
 
-	/* reserve all indices up to and including this index */
-	if (last_hvc < index)
-		last_hvc = index;
-
 	/* check if we need to re-register the kernel console */
 	hvc_check_console(index);
 
@@ -960,13 +956,22 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 		    cons_ops[i] == hp->ops)
 			break;
 
-	/* no matching slot, just use a counter */
-	if (i >= MAX_NR_HVC_CONSOLES)
-		i = ++last_hvc;
+	if (i >= MAX_NR_HVC_CONSOLES) {
+
+		/* find 'empty' slot for console */
+		for (i = 0; i < MAX_NR_HVC_CONSOLES && vtermnos[i] != -1; i++) {
+		}
+
+		/* no matching slot, just use a counter */
+		if (i == MAX_NR_HVC_CONSOLES)
+			i = ++last_hvc + MAX_NR_HVC_CONSOLES;
+	}
 
 	hp->index = i;
-	cons_ops[i] = ops;
-	vtermnos[i] = vtermno;
+	if (i < MAX_NR_HVC_CONSOLES) {
+		cons_ops[i] = ops;
+		vtermnos[i] = vtermno;
+	}
 
 	list_add_tail(&(hp->next), &hvc_structs);
 	mutex_unlock(&hvc_structs_mutex);
diff --git a/drivers/tty/rocket.c b/drivers/tty/rocket.c
index fbaa4ec85560..e2138e7d5dc6 100644
--- a/drivers/tty/rocket.c
+++ b/drivers/tty/rocket.c
@@ -632,18 +632,21 @@ init_r_port(int board, int aiop, int chan, struct pci_dev *pci_dev)
 	tty_port_init(&info->port);
 	info->port.ops = &rocket_port_ops;
 	info->flags &= ~ROCKET_MODE_MASK;
-	switch (pc104[board][line]) {
-	case 422:
-		info->flags |= ROCKET_MODE_RS422;
-		break;
-	case 485:
-		info->flags |= ROCKET_MODE_RS485;
-		break;
-	case 232:
-	default:
+	if (board < ARRAY_SIZE(pc104) && line < ARRAY_SIZE(pc104_1))
+		switch (pc104[board][line]) {
+		case 422:
+			info->flags |= ROCKET_MODE_RS422;
+			break;
+		case 485:
+			info->flags |= ROCKET_MODE_RS485;
+			break;
+		case 232:
+		default:
+			info->flags |= ROCKET_MODE_RS232;
+			break;
+		}
+	else
 		info->flags |= ROCKET_MODE_RS232;
-		break;
-	}
 
 	info->intmask = RXF_TRIG | TXFIFO_MT | SRC_INT | DELTA_CD | DELTA_CTS | DELTA_DSR;
 	if (sInitChan(ctlp, &info->channel, aiop, chan) == 0) {
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 0aea76cd67ff..adf9e80e7dc9 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -86,7 +86,7 @@ config SERIAL_EARLYCON_ARM_SEMIHOST
 
 config SERIAL_EARLYCON_RISCV_SBI
 	bool "Early console using RISC-V SBI"
-	depends on RISCV_SBI
+	depends on RISCV_SBI_V01
 	select SERIAL_CORE
 	select SERIAL_CORE_CONSOLE
 	select SERIAL_EARLYCON
diff --git a/drivers/tty/serial/owl-uart.c b/drivers/tty/serial/owl-uart.c
index 42c8cc93b603..c149f8c30007 100644
--- a/drivers/tty/serial/owl-uart.c
+++ b/drivers/tty/serial/owl-uart.c
@@ -680,6 +680,12 @@ static int owl_uart_probe(struct platform_device *pdev)
 		return PTR_ERR(owl_port->clk);
 	}
 
+	ret = clk_prepare_enable(owl_port->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "could not enable clk\n");
+		return ret;
+	}
+
 	owl_port->port.dev = &pdev->dev;
 	owl_port->port.line = pdev->id;
 	owl_port->port.type = PORT_OWL;
@@ -712,6 +718,7 @@ static int owl_uart_remove(struct platform_device *pdev)
 
 	uart_remove_one_port(&owl_uart_driver, &owl_port->port);
 	owl_uart_ports[pdev->id] = NULL;
+	clk_disable_unprepare(owl_port->clk);
 
 	return 0;
 }
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index c073aa7001c4..e1179e74a2b8 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -870,9 +870,16 @@ static void sci_receive_chars(struct uart_port *port)
 				tty_insert_flip_char(tport, c, TTY_NORMAL);
 		} else {
 			for (i = 0; i < count; i++) {
-				char c = serial_port_in(port, SCxRDR);
-
-				status = serial_port_in(port, SCxSR);
+				char c;
+
+				if (port->type == PORT_SCIF ||
+				    port->type == PORT_HSCIF) {
+					status = serial_port_in(port, SCxSR);
+					c = serial_port_in(port, SCxRDR);
+				} else {
+					c = serial_port_in(port, SCxRDR);
+					status = serial_port_in(port, SCxSR);
+				}
 				if (uart_handle_sysrq_char(port, c)) {
 					count--; i--;
 					continue;
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index 13eadcb8aec4..0b5110dad051 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -883,6 +883,7 @@ console_initcall(sifive_console_init);
 
 static void __ssp_add_console_port(struct sifive_serial_port *ssp)
 {
+	spin_lock_init(&ssp->port.lock);
 	sifive_serial_console_ports[ssp->port.line] = ssp;
 }
 
diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index eafada8fb6fa..e35073e93a5b 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -567,6 +567,9 @@ static int hv_probe(struct platform_device *op)
 	sunserial_console_match(&sunhv_console, op->dev.of_node,
 				&sunhv_reg, port->line, false);
 
+	/* We need to initialize lock even for non-registered console */
+	spin_lock_init(&port->lock);
+
 	err = uart_add_one_port(&sunhv_reg, port);
 	if (err)
 		goto out_unregister_driver;
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 6b26f767768e..35e9e8faf8de 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -26,13 +26,15 @@
 
 #define CDNS_UART_TTY_NAME	"ttyPS"
 #define CDNS_UART_NAME		"xuartps"
+#define CDNS_UART_MAJOR		0	/* use dynamic node allocation */
+#define CDNS_UART_MINOR		0	/* works best with devtmpfs */
+#define CDNS_UART_NR_PORTS	16
 #define CDNS_UART_FIFO_SIZE	64	/* FIFO size */
 #define CDNS_UART_REGISTER_SPACE	0x1000
 #define TX_TIMEOUT		500000
 
 /* Rx Trigger level */
 static int rx_trigger_level = 56;
-static int uartps_major;
 module_param(rx_trigger_level, uint, 0444);
 MODULE_PARM_DESC(rx_trigger_level, "Rx trigger level, 1-63 bytes");
 
@@ -188,7 +190,6 @@ MODULE_PARM_DESC(rx_timeout, "Rx timeout, 1-255");
  * @pclk:		APB clock
  * @cdns_uart_driver:	Pointer to UART driver
  * @baud:		Current baud rate
- * @id:			Port ID
  * @clk_rate_change_nb:	Notifier block for clock changes
  * @quirks:		Flags for RXBS support.
  */
@@ -198,7 +199,6 @@ struct cdns_uart {
 	struct clk		*pclk;
 	struct uart_driver	*cdns_uart_driver;
 	unsigned int		baud;
-	int			id;
 	struct notifier_block	clk_rate_change_nb;
 	u32			quirks;
 	bool cts_override;
@@ -1133,6 +1133,8 @@ static const struct uart_ops cdns_uart_ops = {
 #endif
 };
 
+static struct uart_driver cdns_uart_uart_driver;
+
 #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
 /**
  * cdns_uart_console_putchar - write the character to the FIFO buffer
@@ -1272,6 +1274,16 @@ static int cdns_uart_console_setup(struct console *co, char *options)
 
 	return uart_set_options(port, co, baud, parity, bits, flow);
 }
+
+static struct console cdns_uart_console = {
+	.name	= CDNS_UART_TTY_NAME,
+	.write	= cdns_uart_console_write,
+	.device	= uart_console_device,
+	.setup	= cdns_uart_console_setup,
+	.flags	= CON_PRINTBUFFER,
+	.index	= -1, /* Specified on the cmdline (e.g. console=ttyPS ) */
+	.data	= &cdns_uart_uart_driver,
+};
 #endif /* CONFIG_SERIAL_XILINX_PS_UART_CONSOLE */
 
 #ifdef CONFIG_PM_SLEEP
@@ -1403,89 +1415,8 @@ static const struct of_device_id cdns_uart_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, cdns_uart_of_match);
 
-/*
- * Maximum number of instances without alias IDs but if there is alias
- * which target "< MAX_UART_INSTANCES" range this ID can't be used.
- */
-#define MAX_UART_INSTANCES	32
-
-/* Stores static aliases list */
-static DECLARE_BITMAP(alias_bitmap, MAX_UART_INSTANCES);
-static int alias_bitmap_initialized;
-
-/* Stores actual bitmap of allocated IDs with alias IDs together */
-static DECLARE_BITMAP(bitmap, MAX_UART_INSTANCES);
-/* Protect bitmap operations to have unique IDs */
-static DEFINE_MUTEX(bitmap_lock);
-
-static int cdns_get_id(struct platform_device *pdev)
-{
-	int id, ret;
-
-	mutex_lock(&bitmap_lock);
-
-	/* Alias list is stable that's why get alias bitmap only once */
-	if (!alias_bitmap_initialized) {
-		ret = of_alias_get_alias_list(cdns_uart_of_match, "serial",
-					      alias_bitmap, MAX_UART_INSTANCES);
-		if (ret && ret != -EOVERFLOW) {
-			mutex_unlock(&bitmap_lock);
-			return ret;
-		}
-
-		alias_bitmap_initialized++;
-	}
-
-	/* Make sure that alias ID is not taken by instance without alias */
-	bitmap_or(bitmap, bitmap, alias_bitmap, MAX_UART_INSTANCES);
-
-	dev_dbg(&pdev->dev, "Alias bitmap: %*pb\n",
-		MAX_UART_INSTANCES, bitmap);
-
-	/* Look for a serialN alias */
-	id = of_alias_get_id(pdev->dev.of_node, "serial");
-	if (id < 0) {
-		dev_warn(&pdev->dev,
-			 "No serial alias passed. Using the first free id\n");
-
-		/*
-		 * Start with id 0 and check if there is no serial0 alias
-		 * which points to device which is compatible with this driver.
-		 * If alias exists then try next free position.
-		 */
-		id = 0;
-
-		for (;;) {
-			dev_info(&pdev->dev, "Checking id %d\n", id);
-			id = find_next_zero_bit(bitmap, MAX_UART_INSTANCES, id);
-
-			/* No free empty instance */
-			if (id == MAX_UART_INSTANCES) {
-				dev_err(&pdev->dev, "No free ID\n");
-				mutex_unlock(&bitmap_lock);
-				return -EINVAL;
-			}
-
-			dev_dbg(&pdev->dev, "The empty id is %d\n", id);
-			/* Check if ID is empty */
-			if (!test_and_set_bit(id, bitmap)) {
-				/* Break the loop if bit is taken */
-				dev_dbg(&pdev->dev,
-					"Selected ID %d allocation passed\n",
-					id);
-				break;
-			}
-			dev_dbg(&pdev->dev,
-				"Selected ID %d allocation failed\n", id);
-			/* if taking bit fails then try next one */
-			id++;
-		}
-	}
-
-	mutex_unlock(&bitmap_lock);
-
-	return id;
-}
+/* Temporary variable for storing number of instances */
+static int instances;
 
 /**
  * cdns_uart_probe - Platform driver probe
@@ -1495,16 +1426,11 @@ static int cdns_get_id(struct platform_device *pdev)
  */
 static int cdns_uart_probe(struct platform_device *pdev)
 {
-	int rc, irq;
+	int rc, id, irq;
 	struct uart_port *port;
 	struct resource *res;
 	struct cdns_uart *cdns_uart_data;
 	const struct of_device_id *match;
-	struct uart_driver *cdns_uart_uart_driver;
-	char *driver_name;
-#ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
-	struct console *cdns_uart_console;
-#endif
 
 	cdns_uart_data = devm_kzalloc(&pdev->dev, sizeof(*cdns_uart_data),
 			GFP_KERNEL);
@@ -1514,64 +1440,36 @@ static int cdns_uart_probe(struct platform_device *pdev)
 	if (!port)
 		return -ENOMEM;
 
-	cdns_uart_uart_driver = devm_kzalloc(&pdev->dev,
-					     sizeof(*cdns_uart_uart_driver),
-					     GFP_KERNEL);
-	if (!cdns_uart_uart_driver)
-		return -ENOMEM;
-
-	cdns_uart_data->id = cdns_get_id(pdev);
-	if (cdns_uart_data->id < 0)
-		return cdns_uart_data->id;
+	/* Look for a serialN alias */
+	id = of_alias_get_id(pdev->dev.of_node, "serial");
+	if (id < 0)
+		id = 0;
 
-	/* There is a need to use unique driver name */
-	driver_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s%d",
-				     CDNS_UART_NAME, cdns_uart_data->id);
-	if (!driver_name) {
-		rc = -ENOMEM;
-		goto err_out_id;
+	if (id >= CDNS_UART_NR_PORTS) {
+		dev_err(&pdev->dev, "Cannot get uart_port structure\n");
+		return -ENODEV;
 	}
 
-	cdns_uart_uart_driver->owner = THIS_MODULE;
-	cdns_uart_uart_driver->driver_name = driver_name;
-	cdns_uart_uart_driver->dev_name	= CDNS_UART_TTY_NAME;
-	cdns_uart_uart_driver->major = uartps_major;
-	cdns_uart_uart_driver->minor = cdns_uart_data->id;
-	cdns_uart_uart_driver->nr = 1;
-
+	if (!cdns_uart_uart_driver.state) {
+		cdns_uart_uart_driver.owner = THIS_MODULE;
+		cdns_uart_uart_driver.driver_name = CDNS_UART_NAME;
+		cdns_uart_uart_driver.dev_name = CDNS_UART_TTY_NAME;
+		cdns_uart_uart_driver.major = CDNS_UART_MAJOR;
+		cdns_uart_uart_driver.minor = CDNS_UART_MINOR;
+		cdns_uart_uart_driver.nr = CDNS_UART_NR_PORTS;
 #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
-	cdns_uart_console = devm_kzalloc(&pdev->dev, sizeof(*cdns_uart_console),
-					 GFP_KERNEL);
-	if (!cdns_uart_console) {
-		rc = -ENOMEM;
-		goto err_out_id;
-	}
-
-	strncpy(cdns_uart_console->name, CDNS_UART_TTY_NAME,
-		sizeof(cdns_uart_console->name));
-	cdns_uart_console->index = cdns_uart_data->id;
-	cdns_uart_console->write = cdns_uart_console_write;
-	cdns_uart_console->device = uart_console_device;
-	cdns_uart_console->setup = cdns_uart_console_setup;
-	cdns_uart_console->flags = CON_PRINTBUFFER;
-	cdns_uart_console->data = cdns_uart_uart_driver;
-	cdns_uart_uart_driver->cons = cdns_uart_console;
+		cdns_uart_uart_driver.cons = &cdns_uart_console;
+		cdns_uart_console.index = id;
 #endif
 
-	rc = uart_register_driver(cdns_uart_uart_driver);
-	if (rc < 0) {
-		dev_err(&pdev->dev, "Failed to register driver\n");
-		goto err_out_id;
+		rc = uart_register_driver(&cdns_uart_uart_driver);
+		if (rc < 0) {
+			dev_err(&pdev->dev, "Failed to register driver\n");
+			return rc;
+		}
 	}
 
-	cdns_uart_data->cdns_uart_driver = cdns_uart_uart_driver;
-
-	/*
-	 * Setting up proper name_base needs to be done after uart
-	 * registration because tty_driver structure is not filled.
-	 * name_base is 0 by default.
-	 */
-	cdns_uart_uart_driver->tty_driver->name_base = cdns_uart_data->id;
+	cdns_uart_data->cdns_uart_driver = &cdns_uart_uart_driver;
 
 	match = of_match_node(cdns_uart_of_match, pdev->dev.of_node);
 	if (match && match->data) {
@@ -1649,6 +1547,7 @@ static int cdns_uart_probe(struct platform_device *pdev)
 	port->ops	= &cdns_uart_ops;
 	port->fifosize	= CDNS_UART_FIFO_SIZE;
 	port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_XILINX_PS_UART_CONSOLE);
+	port->line	= id;
 
 	/*
 	 * Register the port.
@@ -1680,7 +1579,7 @@ static int cdns_uart_probe(struct platform_device *pdev)
 		console_port = port;
 #endif
 
-	rc = uart_add_one_port(cdns_uart_uart_driver, port);
+	rc = uart_add_one_port(&cdns_uart_uart_driver, port);
 	if (rc) {
 		dev_err(&pdev->dev,
 			"uart_add_one_port() failed; err=%i\n", rc);
@@ -1690,13 +1589,15 @@ static int cdns_uart_probe(struct platform_device *pdev)
 #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE
 	/* This is not port which is used for console that's why clean it up */
 	if (console_port == port &&
-	    !(cdns_uart_uart_driver->cons->flags & CON_ENABLED))
+	    !(cdns_uart_uart_driver.cons->flags & CON_ENABLED))
 		console_port = NULL;
 #endif
 
-	uartps_major = cdns_uart_uart_driver->tty_driver->major;
 	cdns_uart_data->cts_override = of_property_read_bool(pdev->dev.of_node,
 							     "cts-override");
+
+	instances++;
+
 	return 0;
 
 err_out_pm_disable:
@@ -1712,12 +1613,8 @@ err_out_clk_disable:
 err_out_clk_dis_pclk:
 	clk_disable_unprepare(cdns_uart_data->pclk);
 err_out_unregister_driver:
-	uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
-err_out_id:
-	mutex_lock(&bitmap_lock);
-	if (cdns_uart_data->id < MAX_UART_INSTANCES)
-		clear_bit(cdns_uart_data->id, bitmap);
-	mutex_unlock(&bitmap_lock);
+	if (!instances)
+		uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
 	return rc;
 }
 
@@ -1740,10 +1637,6 @@ static int cdns_uart_remove(struct platform_device *pdev)
 #endif
 	rc = uart_remove_one_port(cdns_uart_data->cdns_uart_driver, port);
 	port->mapbase = 0;
-	mutex_lock(&bitmap_lock);
-	if (cdns_uart_data->id < MAX_UART_INSTANCES)
-		clear_bit(cdns_uart_data->id, bitmap);
-	mutex_unlock(&bitmap_lock);
 	clk_disable_unprepare(cdns_uart_data->uartclk);
 	clk_disable_unprepare(cdns_uart_data->pclk);
 	pm_runtime_disable(&pdev->dev);
@@ -1756,13 +1649,8 @@ static int cdns_uart_remove(struct platform_device *pdev)
 		console_port = NULL;
 #endif
 
-	/* If this is last instance major number should be initialized */
-	mutex_lock(&bitmap_lock);
-	if (bitmap_empty(bitmap, MAX_UART_INSTANCES))
-		uartps_major = 0;
-	mutex_unlock(&bitmap_lock);
-
-	uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
+	if (!--instances)
+		uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
 	return rc;
 }
 
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 5e0d0813da55..0dc3878794fd 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -74,6 +74,7 @@ int sysrq_mask(void)
 		return 1;
 	return sysrq_enabled;
 }
+EXPORT_SYMBOL_GPL(sysrq_mask);
 
 /*
  * A value of 1 means 'all', other nonzero values are an op mask:
@@ -1058,6 +1059,7 @@ int sysrq_toggle_support(int enable_mask)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(sysrq_toggle_support);
 
 static int __sysrq_swap_key_ops(int key, struct sysrq_key_op *insert_op_p,
                                 struct sysrq_key_op *remove_op_p)
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 309a39197be0..48a8199f7845 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -81,6 +81,7 @@
 #include <linux/errno.h>
 #include <linux/kd.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/major.h>
 #include <linux/mm.h>
 #include <linux/console.h>
@@ -350,7 +351,7 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows)
 	/* allocate everything in one go */
 	memsize = cols * rows * sizeof(char32_t);
 	memsize += rows * sizeof(char32_t *);
-	p = kmalloc(memsize, GFP_KERNEL);
+	p = vmalloc(memsize);
 	if (!p)
 		return NULL;
 
@@ -364,9 +365,14 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows)
 	return uniscr;
 }
 
+static void vc_uniscr_free(struct uni_screen *uniscr)
+{
+	vfree(uniscr);
+}
+
 static void vc_uniscr_set(struct vc_data *vc, struct uni_screen *new_uniscr)
 {
-	kfree(vc->vc_uni_screen);
+	vc_uniscr_free(vc->vc_uni_screen);
 	vc->vc_uni_screen = new_uniscr;
 }
 
@@ -1206,7 +1212,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	if (new_cols == vc->vc_cols && new_rows == vc->vc_rows)
 		return 0;
 
-	if (new_screen_size > (4 << 20))
+	if (new_screen_size > KMALLOC_MAX_SIZE)
 		return -EINVAL;
 	newscreen = kzalloc(new_screen_size, GFP_USER);
 	if (!newscreen)
@@ -1229,7 +1235,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
 	err = resize_screen(vc, new_cols, new_rows, user);
 	if (err) {
 		kfree(newscreen);
-		kfree(new_uniscr);
+		vc_uniscr_free(new_uniscr);
 		return err;
 	}
 
diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c
index 372460ea4df9..4d43f3b28309 100644
--- a/drivers/usb/cdns3/gadget.c
+++ b/drivers/usb/cdns3/gadget.c
@@ -82,7 +82,7 @@ static int cdns3_ep_run_stream_transfer(struct cdns3_endpoint *priv_ep,
  * @ptr: address of device controller register to be read and changed
  * @mask: bits requested to clar
  */
-void cdns3_clear_register_bit(void __iomem *ptr, u32 mask)
+static void cdns3_clear_register_bit(void __iomem *ptr, u32 mask)
 {
 	mask = readl(ptr) & ~mask;
 	writel(mask, ptr);
@@ -137,7 +137,7 @@ struct usb_request *cdns3_next_request(struct list_head *list)
  *
  * Returns buffer or NULL if no buffers in list
  */
-struct cdns3_aligned_buf *cdns3_next_align_buf(struct list_head *list)
+static struct cdns3_aligned_buf *cdns3_next_align_buf(struct list_head *list)
 {
 	return list_first_entry_or_null(list, struct cdns3_aligned_buf, list);
 }
@@ -148,7 +148,7 @@ struct cdns3_aligned_buf *cdns3_next_align_buf(struct list_head *list)
  *
  * Returns request or NULL if no requests in list
  */
-struct cdns3_request *cdns3_next_priv_request(struct list_head *list)
+static struct cdns3_request *cdns3_next_priv_request(struct list_head *list)
 {
 	return list_first_entry_or_null(list, struct cdns3_request, list);
 }
@@ -190,7 +190,7 @@ dma_addr_t cdns3_trb_virt_to_dma(struct cdns3_endpoint *priv_ep,
 	return priv_ep->trb_pool_dma + offset;
 }
 
-int cdns3_ring_size(struct cdns3_endpoint *priv_ep)
+static int cdns3_ring_size(struct cdns3_endpoint *priv_ep)
 {
 	switch (priv_ep->type) {
 	case USB_ENDPOINT_XFER_ISOC:
@@ -345,7 +345,7 @@ static void cdns3_ep_inc_deq(struct cdns3_endpoint *priv_ep)
 	cdns3_ep_inc_trb(&priv_ep->dequeue, &priv_ep->ccs, priv_ep->num_trbs);
 }
 
-void cdns3_move_deq_to_next_trb(struct cdns3_request *priv_req)
+static void cdns3_move_deq_to_next_trb(struct cdns3_request *priv_req)
 {
 	struct cdns3_endpoint *priv_ep = priv_req->priv_ep;
 	int current_trb = priv_req->start_trb;
@@ -511,7 +511,7 @@ static void cdns3_wa2_descmiss_copy_data(struct cdns3_endpoint *priv_ep,
 	}
 }
 
-struct usb_request *cdns3_wa2_gadget_giveback(struct cdns3_device *priv_dev,
+static struct usb_request *cdns3_wa2_gadget_giveback(struct cdns3_device *priv_dev,
 					      struct cdns3_endpoint *priv_ep,
 					      struct cdns3_request *priv_req)
 {
@@ -551,7 +551,7 @@ struct usb_request *cdns3_wa2_gadget_giveback(struct cdns3_device *priv_dev,
 	return &priv_req->request;
 }
 
-int cdns3_wa2_gadget_ep_queue(struct cdns3_device *priv_dev,
+static int cdns3_wa2_gadget_ep_queue(struct cdns3_device *priv_dev,
 			      struct cdns3_endpoint *priv_ep,
 			      struct cdns3_request *priv_req)
 {
@@ -836,7 +836,7 @@ void cdns3_gadget_giveback(struct cdns3_endpoint *priv_ep,
 		cdns3_gadget_ep_free_request(&priv_ep->endpoint, request);
 }
 
-void cdns3_wa1_restore_cycle_bit(struct cdns3_endpoint *priv_ep)
+static void cdns3_wa1_restore_cycle_bit(struct cdns3_endpoint *priv_ep)
 {
 	/* Work around for stale data address in TRB*/
 	if (priv_ep->wa1_set) {
@@ -1904,7 +1904,7 @@ static int cdns3_ep_onchip_buffer_reserve(struct cdns3_device *priv_dev,
 	return 0;
 }
 
-void cdns3_stream_ep_reconfig(struct cdns3_device *priv_dev,
+static void cdns3_stream_ep_reconfig(struct cdns3_device *priv_dev,
 			      struct cdns3_endpoint *priv_ep)
 {
 	if (!priv_ep->use_streams || priv_dev->gadget.speed < USB_SPEED_SUPER)
@@ -1925,7 +1925,7 @@ void cdns3_stream_ep_reconfig(struct cdns3_device *priv_dev,
 			       EP_CFG_TDL_CHK | EP_CFG_SID_CHK);
 }
 
-void cdns3_configure_dmult(struct cdns3_device *priv_dev,
+static void cdns3_configure_dmult(struct cdns3_device *priv_dev,
 			   struct cdns3_endpoint *priv_ep)
 {
 	struct cdns3_usb_regs __iomem *regs = priv_dev->regs;
@@ -2548,7 +2548,7 @@ found:
 	link_trb = priv_req->trb;
 
 	/* Update ring only if removed request is on pending_req_list list */
-	if (req_on_hw_ring) {
+	if (req_on_hw_ring && link_trb) {
 		link_trb->buffer = TRB_BUFFER(priv_ep->trb_pool_dma +
 			((priv_req->end_trb + 1) * TRB_SIZE));
 		link_trb->control = (link_trb->control & TRB_CYCLE) |
diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c
index af648ba6544d..46105457e1ca 100644
--- a/drivers/usb/chipidea/ci_hdrc_msm.c
+++ b/drivers/usb/chipidea/ci_hdrc_msm.c
@@ -114,7 +114,7 @@ static int ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event)
 			hw_write_id_reg(ci, HS_PHY_GENCONFIG_2,
 					HS_PHY_ULPI_TX_PKT_EN_CLR_FIX, 0);
 
-		if (!IS_ERR(ci->platdata->vbus_extcon.edev)) {
+		if (!IS_ERR(ci->platdata->vbus_extcon.edev) || ci->role_switch) {
 			hw_write_id_reg(ci, HS_PHY_GENCONFIG_2,
 					HS_PHY_SESS_VLD_CTRL_EN,
 					HS_PHY_SESS_VLD_CTRL_EN);
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 84d6f7df09a4..ded8d93834ca 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -412,9 +412,12 @@ static void acm_ctrl_irq(struct urb *urb)
 
 exit:
 	retval = usb_submit_urb(urb, GFP_ATOMIC);
-	if (retval && retval != -EPERM)
+	if (retval && retval != -EPERM && retval != -ENODEV)
 		dev_err(&acm->control->dev,
 			"%s - usb_submit_urb failed: %d\n", __func__, retval);
+	else
+		dev_vdbg(&acm->control->dev,
+			"control resubmission terminated %d\n", retval);
 }
 
 static int acm_submit_read_urb(struct acm *acm, int index, gfp_t mem_flags)
@@ -430,6 +433,8 @@ static int acm_submit_read_urb(struct acm *acm, int index, gfp_t mem_flags)
 			dev_err(&acm->data->dev,
 				"urb %d failed submission with %d\n",
 				index, res);
+		} else {
+			dev_vdbg(&acm->data->dev, "intended failure %d\n", res);
 		}
 		set_bit(index, &acm->read_urbs_free);
 		return res;
@@ -471,6 +476,7 @@ static void acm_read_bulk_callback(struct urb *urb)
 	int status = urb->status;
 	bool stopped = false;
 	bool stalled = false;
+	bool cooldown = false;
 
 	dev_vdbg(&acm->data->dev, "got urb %d, len %d, status %d\n",
 		rb->index, urb->actual_length, status);
@@ -497,6 +503,14 @@ static void acm_read_bulk_callback(struct urb *urb)
 			__func__, status);
 		stopped = true;
 		break;
+	case -EOVERFLOW:
+	case -EPROTO:
+		dev_dbg(&acm->data->dev,
+			"%s - cooling babbling device\n", __func__);
+		usb_mark_last_busy(acm->dev);
+		set_bit(rb->index, &acm->urbs_in_error_delay);
+		cooldown = true;
+		break;
 	default:
 		dev_dbg(&acm->data->dev,
 			"%s - nonzero urb status received: %d\n",
@@ -518,9 +532,11 @@ static void acm_read_bulk_callback(struct urb *urb)
 	 */
 	smp_mb__after_atomic();
 
-	if (stopped || stalled) {
+	if (stopped || stalled || cooldown) {
 		if (stalled)
 			schedule_work(&acm->work);
+		else if (cooldown)
+			schedule_delayed_work(&acm->dwork, HZ / 2);
 		return;
 	}
 
@@ -557,14 +573,20 @@ static void acm_softint(struct work_struct *work)
 	struct acm *acm = container_of(work, struct acm, work);
 
 	if (test_bit(EVENT_RX_STALL, &acm->flags)) {
-		if (!(usb_autopm_get_interface(acm->data))) {
+		smp_mb(); /* against acm_suspend() */
+		if (!acm->susp_count) {
 			for (i = 0; i < acm->rx_buflimit; i++)
 				usb_kill_urb(acm->read_urbs[i]);
 			usb_clear_halt(acm->dev, acm->in);
 			acm_submit_read_urbs(acm, GFP_KERNEL);
-			usb_autopm_put_interface(acm->data);
+			clear_bit(EVENT_RX_STALL, &acm->flags);
 		}
-		clear_bit(EVENT_RX_STALL, &acm->flags);
+	}
+
+	if (test_and_clear_bit(ACM_ERROR_DELAY, &acm->flags)) {
+		for (i = 0; i < ACM_NR; i++) 
+			if (test_and_clear_bit(i, &acm->urbs_in_error_delay))
+					acm_submit_read_urb(acm, i, GFP_NOIO);
 	}
 
 	if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags))
@@ -1333,6 +1355,7 @@ made_compressed_probe:
 	acm->readsize = readsize;
 	acm->rx_buflimit = num_rx_buf;
 	INIT_WORK(&acm->work, acm_softint);
+	INIT_DELAYED_WORK(&acm->dwork, acm_softint);
 	init_waitqueue_head(&acm->wioctl);
 	spin_lock_init(&acm->write_lock);
 	spin_lock_init(&acm->read_lock);
@@ -1542,6 +1565,7 @@ static void acm_disconnect(struct usb_interface *intf)
 
 	acm_kill_urbs(acm);
 	cancel_work_sync(&acm->work);
+	cancel_delayed_work_sync(&acm->dwork);
 
 	tty_unregister_device(acm_tty_driver, acm->minor);
 
@@ -1584,6 +1608,8 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 
 	acm_kill_urbs(acm);
 	cancel_work_sync(&acm->work);
+	cancel_delayed_work_sync(&acm->dwork);
+	acm->urbs_in_error_delay = 0;
 
 	return 0;
 }
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index ca1c026382c2..cd5e9d8ab237 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -109,8 +109,11 @@ struct acm {
 #		define EVENT_TTY_WAKEUP	0
 #		define EVENT_RX_STALL	1
 #		define ACM_THROTTLED	2
+#		define ACM_ERROR_DELAY	3
+	unsigned long urbs_in_error_delay;		/* these need to be restarted after a delay */
 	struct usb_cdc_line_coding line;		/* bits, stop, parity */
-	struct work_struct work;			/* work queue entry for line discipline waking up */
+	struct work_struct work;			/* work queue entry for various purposes*/
+	struct delayed_work dwork;			/* for cool downs needed in error recovery */
 	unsigned int ctrlin;				/* input control lines (DCD, DSR, RI, break, overruns) */
 	unsigned int ctrlout;				/* output control lines (DTR, RTS) */
 	struct async_icount iocount;			/* counters for control line changes */
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 6833c918abce..d93d94d7ff50 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -217,6 +217,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct usb_memory *usbm = NULL;
 	struct usb_dev_state *ps = file->private_data;
+	struct usb_hcd *hcd = bus_to_hcd(ps->dev->bus);
 	size_t size = vma->vm_end - vma->vm_start;
 	void *mem;
 	unsigned long flags;
@@ -250,11 +251,19 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma)
 	usbm->vma_use_count = 1;
 	INIT_LIST_HEAD(&usbm->memlist);
 
-	if (remap_pfn_range(vma, vma->vm_start,
-			virt_to_phys(usbm->mem) >> PAGE_SHIFT,
-			size, vma->vm_page_prot) < 0) {
-		dec_usb_memory_use_count(usbm, &usbm->vma_use_count);
-		return -EAGAIN;
+	if (hcd->localmem_pool || !hcd_uses_dma(hcd)) {
+		if (remap_pfn_range(vma, vma->vm_start,
+				    virt_to_phys(usbm->mem) >> PAGE_SHIFT,
+				    size, vma->vm_page_prot) < 0) {
+			dec_usb_memory_use_count(usbm, &usbm->vma_use_count);
+			return -EAGAIN;
+		}
+	} else {
+		if (dma_mmap_coherent(hcd->self.sysdev, vma, mem, dma_handle,
+				      size)) {
+			dec_usb_memory_use_count(usbm, &usbm->vma_use_count);
+			return -EAGAIN;
+		}
 	}
 
 	vma->vm_flags |= VM_IO;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 54cd8ef795ec..fc748c731832 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -39,6 +39,7 @@
 
 #define USB_VENDOR_GENESYS_LOGIC		0x05e3
 #define USB_VENDOR_SMSC				0x0424
+#define USB_PRODUCT_USB5534B			0x5534
 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	0x01
 #define HUB_QUIRK_DISABLE_AUTOSUSPEND		0x02
 
@@ -1223,6 +1224,11 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 #ifdef CONFIG_PM
 			udev->reset_resume = 1;
 #endif
+			/* Don't set the change_bits when the device
+			 * was powered off.
+			 */
+			if (test_bit(port1, hub->power_bits))
+				set_bit(port1, hub->change_bits);
 
 		} else {
 			/* The power session is gone; tell hub_wq */
@@ -2723,13 +2729,11 @@ static bool use_new_scheme(struct usb_device *udev, int retry,
 {
 	int old_scheme_first_port =
 		port_dev->quirks & USB_PORT_QUIRK_OLD_SCHEME;
-	int quick_enumeration = (udev->speed == USB_SPEED_HIGH);
 
 	if (udev->speed >= USB_SPEED_SUPER)
 		return false;
 
-	return USE_NEW_SCHEME(retry, old_scheme_first_port || old_scheme_first
-			      || quick_enumeration);
+	return USE_NEW_SCHEME(retry, old_scheme_first_port || old_scheme_first);
 }
 
 /* Is a USB 3.0 port in the Inactive or Compliance Mode state?
@@ -3088,6 +3092,15 @@ static int check_port_resume_type(struct usb_device *udev,
 		if (portchange & USB_PORT_STAT_C_ENABLE)
 			usb_clear_port_feature(hub->hdev, port1,
 					USB_PORT_FEAT_C_ENABLE);
+
+		/*
+		 * Whatever made this reset-resume necessary may have
+		 * turned on the port1 bit in hub->change_bits.  But after
+		 * a successful reset-resume we want the bit to be clear;
+		 * if it was on it would indicate that something happened
+		 * following the reset-resume.
+		 */
+		clear_bit(port1, hub->change_bits);
 	}
 
 	return status;
@@ -5609,8 +5622,11 @@ out_hdev_lock:
 }
 
 static const struct usb_device_id hub_id_table[] = {
-    { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS,
+    { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+                   | USB_DEVICE_ID_MATCH_PRODUCT
+                   | USB_DEVICE_ID_MATCH_INT_CLASS,
       .idVendor = USB_VENDOR_SMSC,
+      .idProduct = USB_PRODUCT_USB5534B,
       .bInterfaceClass = USB_CLASS_HUB,
       .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
     { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index d5f834f16993..6197938dcc2d 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -589,12 +589,13 @@ void usb_sg_cancel(struct usb_sg_request *io)
 	int i, retval;
 
 	spin_lock_irqsave(&io->lock, flags);
-	if (io->status) {
+	if (io->status || io->count == 0) {
 		spin_unlock_irqrestore(&io->lock, flags);
 		return;
 	}
 	/* shut everything down */
 	io->status = -ECONNRESET;
+	io->count++;		/* Keep the request alive until we're done */
 	spin_unlock_irqrestore(&io->lock, flags);
 
 	for (i = io->entries - 1; i >= 0; --i) {
@@ -608,6 +609,12 @@ void usb_sg_cancel(struct usb_sg_request *io)
 			dev_warn(&io->dev->dev, "%s, unlink --> %d\n",
 				 __func__, retval);
 	}
+
+	spin_lock_irqsave(&io->lock, flags);
+	io->count--;
+	if (!io->count)
+		complete(&io->complete);
+	spin_unlock_irqrestore(&io->lock, flags);
 }
 EXPORT_SYMBOL_GPL(usb_sg_cancel);
 
@@ -1137,11 +1144,11 @@ void usb_disable_endpoint(struct usb_device *dev, unsigned int epaddr,
 
 	if (usb_endpoint_out(epaddr)) {
 		ep = dev->ep_out[epnum];
-		if (reset_hardware)
+		if (reset_hardware && epnum != 0)
 			dev->ep_out[epnum] = NULL;
 	} else {
 		ep = dev->ep_in[epnum];
-		if (reset_hardware)
+		if (reset_hardware && epnum != 0)
 			dev->ep_in[epnum] = NULL;
 	}
 	if (ep) {
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index da30b5664ff3..3e8efe759c3e 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -430,6 +430,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Corsair K70 LUX */
 	{ USB_DEVICE(0x1b1c, 0x1b36), .driver_info = USB_QUIRK_DELAY_INIT },
 
+	/* Corsair K70 RGB RAPDIFIRE */
+	{ USB_DEVICE(0x1b1c, 0x1b38), .driver_info = USB_QUIRK_DELAY_INIT |
+	  USB_QUIRK_DELAY_CTRL_MSG },
+
 	/* MIDI keyboard WORLDE MINI */
 	{ USB_DEVICE(0x1c75, 0x0204), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig
index 206caa0ea1c6..7a2304565a73 100644
--- a/drivers/usb/dwc3/Kconfig
+++ b/drivers/usb/dwc3/Kconfig
@@ -4,6 +4,7 @@ config USB_DWC3
 	tristate "DesignWare USB3 DRD Core Support"
 	depends on (USB || USB_GADGET) && HAS_DMA
 	select USB_XHCI_PLATFORM if USB_XHCI_HCD
+	select USB_ROLE_SWITCH if USB_DWC3_DUAL_ROLE
 	help
 	  Say Y or M here if your system has a Dual Role SuperSpeed
 	  USB controller based on the DesignWare USB3 IP Core.
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 6846eb0cba13..4c171a8e215f 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -307,10 +307,14 @@
 
 /* Global TX Fifo Size Register */
 #define DWC31_GTXFIFOSIZ_TXFRAMNUM	BIT(15)		/* DWC_usb31 only */
-#define DWC31_GTXFIFOSIZ_TXFDEF(n)	((n) & 0x7fff)	/* DWC_usb31 only */
-#define DWC3_GTXFIFOSIZ_TXFDEF(n)	((n) & 0xffff)
+#define DWC31_GTXFIFOSIZ_TXFDEP(n)	((n) & 0x7fff)	/* DWC_usb31 only */
+#define DWC3_GTXFIFOSIZ_TXFDEP(n)	((n) & 0xffff)
 #define DWC3_GTXFIFOSIZ_TXFSTADDR(n)	((n) & 0xffff0000)
 
+/* Global RX Fifo Size Register */
+#define DWC31_GRXFIFOSIZ_RXFDEP(n)	((n) & 0x7fff)	/* DWC_usb31 only */
+#define DWC3_GRXFIFOSIZ_RXFDEP(n)	((n) & 0xffff)
+
 /* Global Event Size Registers */
 #define DWC3_GEVNTSIZ_INTMASK		BIT(31)
 #define DWC3_GEVNTSIZ_SIZE(n)		((n) & 0xffff)
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 7051611229c9..b67372737dc9 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -114,6 +114,7 @@ static const struct property_entry dwc3_pci_intel_properties[] = {
 
 static const struct property_entry dwc3_pci_mrfld_properties[] = {
 	PROPERTY_ENTRY_STRING("dr_mode", "otg"),
+	PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"),
 	PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"),
 	{}
 };
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 4d3c79d90a6e..585cb3deea7a 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1728,7 +1728,6 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc)
 	u32			reg;
 
 	u8			link_state;
-	u8			speed;
 
 	/*
 	 * According to the Databook Remote wakeup request should
@@ -1738,16 +1737,13 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc)
 	 */
 	reg = dwc3_readl(dwc->regs, DWC3_DSTS);
 
-	speed = reg & DWC3_DSTS_CONNECTSPD;
-	if ((speed == DWC3_DSTS_SUPERSPEED) ||
-	    (speed == DWC3_DSTS_SUPERSPEED_PLUS))
-		return 0;
-
 	link_state = DWC3_DSTS_USBLNKST(reg);
 
 	switch (link_state) {
+	case DWC3_LINK_STATE_RESET:
 	case DWC3_LINK_STATE_RX_DET:	/* in HS, means Early Suspend */
 	case DWC3_LINK_STATE_U3:	/* in HS, means SUSPEND */
+	case DWC3_LINK_STATE_RESUME:
 		break;
 	default:
 		return -EINVAL;
@@ -2227,7 +2223,6 @@ static int dwc3_gadget_init_in_endpoint(struct dwc3_ep *dep)
 {
 	struct dwc3 *dwc = dep->dwc;
 	int mdwidth;
-	int kbytes;
 	int size;
 
 	mdwidth = DWC3_MDWIDTH(dwc->hwparams.hwparams0);
@@ -2236,24 +2231,24 @@ static int dwc3_gadget_init_in_endpoint(struct dwc3_ep *dep)
 
 	size = dwc3_readl(dwc->regs, DWC3_GTXFIFOSIZ(dep->number >> 1));
 	if (dwc3_is_usb31(dwc))
-		size = DWC31_GTXFIFOSIZ_TXFDEF(size);
+		size = DWC31_GTXFIFOSIZ_TXFDEP(size);
 	else
-		size = DWC3_GTXFIFOSIZ_TXFDEF(size);
+		size = DWC3_GTXFIFOSIZ_TXFDEP(size);
 
 	/* FIFO Depth is in MDWDITH bytes. Multiply */
 	size *= mdwidth;
 
-	kbytes = size / 1024;
-	if (kbytes == 0)
-		kbytes = 1;
-
 	/*
-	 * FIFO sizes account an extra MDWIDTH * (kbytes + 1) bytes for
-	 * internal overhead. We don't really know how these are used,
-	 * but documentation say it exists.
+	 * To meet performance requirement, a minimum TxFIFO size of 3x
+	 * MaxPacketSize is recommended for endpoints that support burst and a
+	 * minimum TxFIFO size of 2x MaxPacketSize for endpoints that don't
+	 * support burst. Use those numbers and we can calculate the max packet
+	 * limit as below.
 	 */
-	size -= mdwidth * (kbytes + 1);
-	size /= kbytes;
+	if (dwc->maximum_speed >= USB_SPEED_SUPER)
+		size /= 3;
+	else
+		size /= 2;
 
 	usb_ep_set_maxpacket_limit(&dep->endpoint, size);
 
@@ -2271,8 +2266,39 @@ static int dwc3_gadget_init_in_endpoint(struct dwc3_ep *dep)
 static int dwc3_gadget_init_out_endpoint(struct dwc3_ep *dep)
 {
 	struct dwc3 *dwc = dep->dwc;
+	int mdwidth;
+	int size;
+
+	mdwidth = DWC3_MDWIDTH(dwc->hwparams.hwparams0);
 
-	usb_ep_set_maxpacket_limit(&dep->endpoint, 1024);
+	/* MDWIDTH is represented in bits, convert to bytes */
+	mdwidth /= 8;
+
+	/* All OUT endpoints share a single RxFIFO space */
+	size = dwc3_readl(dwc->regs, DWC3_GRXFIFOSIZ(0));
+	if (dwc3_is_usb31(dwc))
+		size = DWC31_GRXFIFOSIZ_RXFDEP(size);
+	else
+		size = DWC3_GRXFIFOSIZ_RXFDEP(size);
+
+	/* FIFO depth is in MDWDITH bytes */
+	size *= mdwidth;
+
+	/*
+	 * To meet performance requirement, a minimum recommended RxFIFO size
+	 * is defined as follow:
+	 * RxFIFO size >= (3 x MaxPacketSize) +
+	 * (3 x 8 bytes setup packets size) + (16 bytes clock crossing margin)
+	 *
+	 * Then calculate the max packet limit as below.
+	 */
+	size -= (3 * 8) + 16;
+	if (size < 0)
+		size = 0;
+	else
+		size /= 3;
+
+	usb_ep_set_maxpacket_limit(&dep->endpoint, size);
 	dep->endpoint.max_streams = 15;
 	dep->endpoint.ops = &dwc3_gadget_ep_ops;
 	list_add_tail(&dep->endpoint.ep_list,
@@ -2457,9 +2483,6 @@ static int dwc3_gadget_ep_reclaim_trb_sg(struct dwc3_ep *dep,
 	for_each_sg(sg, s, pending, i) {
 		trb = &dep->trb_pool[dep->trb_dequeue];
 
-		if (trb->ctrl & DWC3_TRB_CTRL_HWO)
-			break;
-
 		req->sg = sg_next(s);
 		req->num_pending_sgs--;
 
@@ -2484,14 +2507,7 @@ static int dwc3_gadget_ep_reclaim_trb_linear(struct dwc3_ep *dep,
 
 static bool dwc3_gadget_ep_request_completed(struct dwc3_request *req)
 {
-	/*
-	 * For OUT direction, host may send less than the setup
-	 * length. Return true for all OUT requests.
-	 */
-	if (!req->direction)
-		return true;
-
-	return req->request.actual == req->request.length;
+	return req->num_pending_sgs == 0;
 }
 
 static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep,
@@ -2515,8 +2531,7 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep,
 
 	req->request.actual = req->request.length - req->remaining;
 
-	if (!dwc3_gadget_ep_request_completed(req) ||
-			req->num_pending_sgs) {
+	if (!dwc3_gadget_ep_request_completed(req)) {
 		__dwc3_gadget_kick_transfer(dep);
 		goto out;
 	}
diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c
index 971c6b92484a..171280c80228 100644
--- a/drivers/usb/early/xhci-dbc.c
+++ b/drivers/usb/early/xhci-dbc.c
@@ -728,19 +728,19 @@ static void xdbc_handle_tx_event(struct xdbc_trb *evt_trb)
 	case COMP_USB_TRANSACTION_ERROR:
 	case COMP_STALL_ERROR:
 	default:
-		if (ep_id == XDBC_EPID_OUT)
+		if (ep_id == XDBC_EPID_OUT || ep_id == XDBC_EPID_OUT_INTEL)
 			xdbc.flags |= XDBC_FLAGS_OUT_STALL;
-		if (ep_id == XDBC_EPID_IN)
+		if (ep_id == XDBC_EPID_IN || ep_id == XDBC_EPID_IN_INTEL)
 			xdbc.flags |= XDBC_FLAGS_IN_STALL;
 
 		xdbc_trace("endpoint %d stalled\n", ep_id);
 		break;
 	}
 
-	if (ep_id == XDBC_EPID_IN) {
+	if (ep_id == XDBC_EPID_IN || ep_id == XDBC_EPID_IN_INTEL) {
 		xdbc.flags &= ~XDBC_FLAGS_IN_PROCESS;
 		xdbc_bulk_transfer(NULL, XDBC_MAX_PACKET, true);
-	} else if (ep_id == XDBC_EPID_OUT) {
+	} else if (ep_id == XDBC_EPID_OUT || ep_id == XDBC_EPID_OUT_INTEL) {
 		xdbc.flags &= ~XDBC_FLAGS_OUT_PROCESS;
 	} else {
 		xdbc_trace("invalid endpoint id %d\n", ep_id);
diff --git a/drivers/usb/early/xhci-dbc.h b/drivers/usb/early/xhci-dbc.h
index 673686eeddd7..6e2b7266a695 100644
--- a/drivers/usb/early/xhci-dbc.h
+++ b/drivers/usb/early/xhci-dbc.h
@@ -120,8 +120,22 @@ struct xdbc_ring {
 	u32			cycle_state;
 };
 
-#define XDBC_EPID_OUT		2
-#define XDBC_EPID_IN		3
+/*
+ * These are the "Endpoint ID" (also known as "Context Index") values for the
+ * OUT Transfer Ring and the IN Transfer Ring of a Debug Capability Context data
+ * structure.
+ * According to the "eXtensible Host Controller Interface for Universal Serial
+ * Bus (xHCI)" specification, section "7.6.3.2 Endpoint Contexts and Transfer
+ * Rings", these should be 0 and 1, and those are the values AMD machines give
+ * you; but Intel machines seem to use the formula from section "4.5.1 Device
+ * Context Index", which is supposed to be used for the Device Context only.
+ * Luckily the values from Intel don't overlap with those from AMD, so we can
+ * just test for both.
+ */
+#define XDBC_EPID_OUT		0
+#define XDBC_EPID_IN		1
+#define XDBC_EPID_OUT_INTEL	2
+#define XDBC_EPID_IN_INTEL	3
 
 struct xdbc_state {
 	u16			vendor;
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 32b637e3e1fa..6a9aa4413d64 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -260,6 +260,9 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item,
 	char *name;
 	int ret;
 
+	if (strlen(page) < len)
+		return -EOVERFLOW;
+
 	name = kstrdup(page, GFP_KERNEL);
 	if (!name)
 		return -ENOMEM;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index c81023b195c3..10f01f974f67 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1813,6 +1813,10 @@ static void ffs_data_reset(struct ffs_data *ffs)
 	ffs->state = FFS_READ_DESCRIPTORS;
 	ffs->setup_state = FFS_NO_SETUP;
 	ffs->flags = 0;
+
+	ffs->ms_os_descs_ext_prop_count = 0;
+	ffs->ms_os_descs_ext_prop_name_len = 0;
+	ffs->ms_os_descs_ext_prop_data_len = 0;
 }
 
 
diff --git a/drivers/usb/gadget/legacy/audio.c b/drivers/usb/gadget/legacy/audio.c
index dd81fd538cb8..a748ed0842e8 100644
--- a/drivers/usb/gadget/legacy/audio.c
+++ b/drivers/usb/gadget/legacy/audio.c
@@ -300,8 +300,10 @@ static int audio_bind(struct usb_composite_dev *cdev)
 		struct usb_descriptor_header *usb_desc;
 
 		usb_desc = usb_otg_descriptor_alloc(cdev->gadget);
-		if (!usb_desc)
+		if (!usb_desc) {
+			status = -ENOMEM;
 			goto fail;
+		}
 		usb_otg_descriptor_init(cdev->gadget, usb_desc);
 		otg_desc[0] = usb_desc;
 		otg_desc[1] = NULL;
diff --git a/drivers/usb/gadget/legacy/cdc2.c b/drivers/usb/gadget/legacy/cdc2.c
index 8d7a556ece30..563363aba48f 100644
--- a/drivers/usb/gadget/legacy/cdc2.c
+++ b/drivers/usb/gadget/legacy/cdc2.c
@@ -179,8 +179,10 @@ static int cdc_bind(struct usb_composite_dev *cdev)
 		struct usb_descriptor_header *usb_desc;
 
 		usb_desc = usb_otg_descriptor_alloc(gadget);
-		if (!usb_desc)
+		if (!usb_desc) {
+			status = -ENOMEM;
 			goto fail1;
+		}
 		usb_otg_descriptor_init(gadget, usb_desc);
 		otg_desc[0] = usb_desc;
 		otg_desc[1] = NULL;
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index aa0de9e35afa..3afddd3bea6e 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -1361,7 +1361,6 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 
 	req->buf = dev->rbuf;
 	req->context = NULL;
-	value = -EOPNOTSUPP;
 	switch (ctrl->bRequest) {
 
 	case USB_REQ_GET_DESCRIPTOR:
@@ -1784,7 +1783,7 @@ static ssize_t
 dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 {
 	struct dev_data		*dev = fd->private_data;
-	ssize_t			value = len, length = len;
+	ssize_t			value, length = len;
 	unsigned		total;
 	u32			tag;
 	char			*kbuf;
diff --git a/drivers/usb/gadget/legacy/ncm.c b/drivers/usb/gadget/legacy/ncm.c
index c61e71ba7045..0f1b45e3abd1 100644
--- a/drivers/usb/gadget/legacy/ncm.c
+++ b/drivers/usb/gadget/legacy/ncm.c
@@ -156,8 +156,10 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 		struct usb_descriptor_header *usb_desc;
 
 		usb_desc = usb_otg_descriptor_alloc(gadget);
-		if (!usb_desc)
+		if (!usb_desc) {
+			status = -ENOMEM;
 			goto fail;
+		}
 		usb_otg_descriptor_init(gadget, usb_desc);
 		otg_desc[0] = usb_desc;
 		otg_desc[1] = NULL;
diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c
index 76406343fbe5..e01e366d89cd 100644
--- a/drivers/usb/gadget/legacy/raw_gadget.c
+++ b/drivers/usb/gadget/legacy/raw_gadget.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/compiler.h>
+#include <linux/ctype.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/kref.h>
@@ -81,6 +82,7 @@ static int raw_event_queue_add(struct raw_event_queue *queue,
 static struct usb_raw_event *raw_event_queue_fetch(
 				struct raw_event_queue *queue)
 {
+	int ret;
 	unsigned long flags;
 	struct usb_raw_event *event;
 
@@ -89,11 +91,18 @@ static struct usb_raw_event *raw_event_queue_fetch(
 	 * there's at least one event queued by decrementing the semaphore,
 	 * and then take the lock to protect queue struct fields.
 	 */
-	if (down_interruptible(&queue->sema))
-		return NULL;
+	ret = down_interruptible(&queue->sema);
+	if (ret)
+		return ERR_PTR(ret);
 	spin_lock_irqsave(&queue->lock, flags);
-	if (WARN_ON(!queue->size))
-		return NULL;
+	/*
+	 * queue->size must have the same value as queue->sema counter (before
+	 * the down_interruptible() call above), so this check is a fail-safe.
+	 */
+	if (WARN_ON(!queue->size)) {
+		spin_unlock_irqrestore(&queue->lock, flags);
+		return ERR_PTR(-ENODEV);
+	}
 	event = queue->events[0];
 	queue->size--;
 	memmove(&queue->events[0], &queue->events[1],
@@ -115,8 +124,6 @@ static void raw_event_queue_destroy(struct raw_event_queue *queue)
 
 struct raw_dev;
 
-#define USB_RAW_MAX_ENDPOINTS 32
-
 enum ep_state {
 	STATE_EP_DISABLED,
 	STATE_EP_ENABLED,
@@ -126,6 +133,7 @@ struct raw_ep {
 	struct raw_dev		*dev;
 	enum ep_state		state;
 	struct usb_ep		*ep;
+	u8			addr;
 	struct usb_request	*req;
 	bool			urb_queued;
 	bool			disabling;
@@ -160,7 +168,8 @@ struct raw_dev {
 	bool				ep0_out_pending;
 	bool				ep0_urb_queued;
 	ssize_t				ep0_status;
-	struct raw_ep			eps[USB_RAW_MAX_ENDPOINTS];
+	struct raw_ep			eps[USB_RAW_EPS_NUM_MAX];
+	int				eps_num;
 
 	struct completion		ep0_done;
 	struct raw_event_queue		queue;
@@ -194,8 +203,8 @@ static void dev_free(struct kref *kref)
 		usb_ep_free_request(dev->gadget->ep0, dev->req);
 	}
 	raw_event_queue_destroy(&dev->queue);
-	for (i = 0; i < USB_RAW_MAX_ENDPOINTS; i++) {
-		if (dev->eps[i].state != STATE_EP_ENABLED)
+	for (i = 0; i < dev->eps_num; i++) {
+		if (dev->eps[i].state == STATE_EP_DISABLED)
 			continue;
 		usb_ep_disable(dev->eps[i].ep);
 		usb_ep_free_request(dev->eps[i].ep, dev->eps[i].req);
@@ -241,12 +250,26 @@ static void gadget_ep0_complete(struct usb_ep *ep, struct usb_request *req)
 	complete(&dev->ep0_done);
 }
 
+static u8 get_ep_addr(const char *name)
+{
+	/* If the endpoint has fixed function (named as e.g. "ep12out-bulk"),
+	 * parse the endpoint address from its name. We deliberately use
+	 * deprecated simple_strtoul() function here, as the number isn't
+	 * followed by '\0' nor '\n'.
+	 */
+	if (isdigit(name[2]))
+		return simple_strtoul(&name[2], NULL, 10);
+	/* Otherwise the endpoint is configurable (named as e.g. "ep-a"). */
+	return USB_RAW_EP_ADDR_ANY;
+}
+
 static int gadget_bind(struct usb_gadget *gadget,
 			struct usb_gadget_driver *driver)
 {
-	int ret = 0;
+	int ret = 0, i = 0;
 	struct raw_dev *dev = container_of(driver, struct raw_dev, driver);
 	struct usb_request *req;
+	struct usb_ep *ep;
 	unsigned long flags;
 
 	if (strcmp(gadget->name, dev->udc_name) != 0)
@@ -265,6 +288,13 @@ static int gadget_bind(struct usb_gadget *gadget,
 	dev->req->context = dev;
 	dev->req->complete = gadget_ep0_complete;
 	dev->gadget = gadget;
+	gadget_for_each_ep(ep, dev->gadget) {
+		dev->eps[i].ep = ep;
+		dev->eps[i].addr = get_ep_addr(ep->name);
+		dev->eps[i].state = STATE_EP_DISABLED;
+		i++;
+	}
+	dev->eps_num = i;
 	spin_unlock_irqrestore(&dev->lock, flags);
 
 	/* Matches kref_put() in gadget_unbind(). */
@@ -392,9 +422,8 @@ static int raw_ioctl_init(struct raw_dev *dev, unsigned long value)
 	char *udc_device_name;
 	unsigned long flags;
 
-	ret = copy_from_user(&arg, (void __user *)value, sizeof(arg));
-	if (ret)
-		return ret;
+	if (copy_from_user(&arg, (void __user *)value, sizeof(arg)))
+		return -EFAULT;
 
 	switch (arg.speed) {
 	case USB_SPEED_UNKNOWN:
@@ -501,15 +530,13 @@ out_unlock:
 
 static int raw_ioctl_event_fetch(struct raw_dev *dev, unsigned long value)
 {
-	int ret = 0;
 	struct usb_raw_event arg;
 	unsigned long flags;
 	struct usb_raw_event *event;
 	uint32_t length;
 
-	ret = copy_from_user(&arg, (void __user *)value, sizeof(arg));
-	if (ret)
-		return ret;
+	if (copy_from_user(&arg, (void __user *)value, sizeof(arg)))
+		return -EFAULT;
 
 	spin_lock_irqsave(&dev->lock, flags);
 	if (dev->state != STATE_DEV_RUNNING) {
@@ -525,26 +552,32 @@ static int raw_ioctl_event_fetch(struct raw_dev *dev, unsigned long value)
 	spin_unlock_irqrestore(&dev->lock, flags);
 
 	event = raw_event_queue_fetch(&dev->queue);
-	if (!event) {
+	if (PTR_ERR(event) == -EINTR) {
 		dev_dbg(&dev->gadget->dev, "event fetching interrupted\n");
 		return -EINTR;
 	}
+	if (IS_ERR(event)) {
+		dev_err(&dev->gadget->dev, "failed to fetch event\n");
+		spin_lock_irqsave(&dev->lock, flags);
+		dev->state = STATE_DEV_FAILED;
+		spin_unlock_irqrestore(&dev->lock, flags);
+		return -ENODEV;
+	}
 	length = min(arg.length, event->length);
-	ret = copy_to_user((void __user *)value, event,
-				sizeof(*event) + length);
-	return ret;
+	if (copy_to_user((void __user *)value, event, sizeof(*event) + length))
+		return -EFAULT;
+
+	return 0;
 }
 
 static void *raw_alloc_io_data(struct usb_raw_ep_io *io, void __user *ptr,
 				bool get_from_user)
 {
-	int ret;
 	void *data;
 
-	ret = copy_from_user(io, ptr, sizeof(*io));
-	if (ret)
-		return ERR_PTR(ret);
-	if (io->ep >= USB_RAW_MAX_ENDPOINTS)
+	if (copy_from_user(io, ptr, sizeof(*io)))
+		return ERR_PTR(-EFAULT);
+	if (io->ep >= USB_RAW_EPS_NUM_MAX)
 		return ERR_PTR(-EINVAL);
 	if (!usb_raw_io_flags_valid(io->flags))
 		return ERR_PTR(-EINVAL);
@@ -658,42 +691,61 @@ static int raw_ioctl_ep0_read(struct raw_dev *dev, unsigned long value)
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 	ret = raw_process_ep0_io(dev, &io, data, false);
-	if (ret < 0) {
-		kfree(data);
-		return ret;
-	}
+	if (ret < 0)
+		goto free;
+
 	length = min(io.length, (unsigned int)ret);
-	ret = copy_to_user((void __user *)(value + sizeof(io)), data, length);
+	if (copy_to_user((void __user *)(value + sizeof(io)), data, length))
+		ret = -EFAULT;
+	else
+		ret = length;
+free:
 	kfree(data);
 	return ret;
 }
 
-static bool check_ep_caps(struct usb_ep *ep,
-				struct usb_endpoint_descriptor *desc)
+static int raw_ioctl_ep0_stall(struct raw_dev *dev, unsigned long value)
 {
-	switch (usb_endpoint_type(desc)) {
-	case USB_ENDPOINT_XFER_ISOC:
-		if (!ep->caps.type_iso)
-			return false;
-		break;
-	case USB_ENDPOINT_XFER_BULK:
-		if (!ep->caps.type_bulk)
-			return false;
-		break;
-	case USB_ENDPOINT_XFER_INT:
-		if (!ep->caps.type_int)
-			return false;
-		break;
-	default:
-		return false;
+	int ret = 0;
+	unsigned long flags;
+
+	if (value)
+		return -EINVAL;
+	spin_lock_irqsave(&dev->lock, flags);
+	if (dev->state != STATE_DEV_RUNNING) {
+		dev_dbg(dev->dev, "fail, device is not running\n");
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+	if (!dev->gadget) {
+		dev_dbg(dev->dev, "fail, gadget is not bound\n");
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+	if (dev->ep0_urb_queued) {
+		dev_dbg(&dev->gadget->dev, "fail, urb already queued\n");
+		ret = -EBUSY;
+		goto out_unlock;
 	}
+	if (!dev->ep0_in_pending && !dev->ep0_out_pending) {
+		dev_dbg(&dev->gadget->dev, "fail, no request pending\n");
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	ret = usb_ep_set_halt(dev->gadget->ep0);
+	if (ret < 0)
+		dev_err(&dev->gadget->dev,
+				"fail, usb_ep_set_halt returned %d\n", ret);
 
-	if (usb_endpoint_dir_in(desc) && !ep->caps.dir_in)
-		return false;
-	if (usb_endpoint_dir_out(desc) && !ep->caps.dir_out)
-		return false;
+	if (dev->ep0_in_pending)
+		dev->ep0_in_pending = false;
+	else
+		dev->ep0_out_pending = false;
 
-	return true;
+out_unlock:
+	spin_unlock_irqrestore(&dev->lock, flags);
+	return ret;
 }
 
 static int raw_ioctl_ep_enable(struct raw_dev *dev, unsigned long value)
@@ -701,7 +753,7 @@ static int raw_ioctl_ep_enable(struct raw_dev *dev, unsigned long value)
 	int ret = 0, i;
 	unsigned long flags;
 	struct usb_endpoint_descriptor *desc;
-	struct usb_ep *ep = NULL;
+	struct raw_ep *ep;
 
 	desc = memdup_user((void __user *)value, sizeof(*desc));
 	if (IS_ERR(desc))
@@ -729,41 +781,32 @@ static int raw_ioctl_ep_enable(struct raw_dev *dev, unsigned long value)
 		goto out_free;
 	}
 
-	for (i = 0; i < USB_RAW_MAX_ENDPOINTS; i++) {
-		if (dev->eps[i].state == STATE_EP_ENABLED)
+	for (i = 0; i < dev->eps_num; i++) {
+		ep = &dev->eps[i];
+		if (ep->state != STATE_EP_DISABLED)
 			continue;
-		break;
-	}
-	if (i == USB_RAW_MAX_ENDPOINTS) {
-		dev_dbg(&dev->gadget->dev,
-				"fail, no device endpoints available\n");
-		ret = -EBUSY;
-		goto out_free;
-	}
-
-	gadget_for_each_ep(ep, dev->gadget) {
-		if (ep->enabled)
+		if (ep->addr != usb_endpoint_num(desc) &&
+				ep->addr != USB_RAW_EP_ADDR_ANY)
 			continue;
-		if (!check_ep_caps(ep, desc))
+		if (!usb_gadget_ep_match_desc(dev->gadget, ep->ep, desc, NULL))
 			continue;
-		ep->desc = desc;
-		ret = usb_ep_enable(ep);
+		ep->ep->desc = desc;
+		ret = usb_ep_enable(ep->ep);
 		if (ret < 0) {
 			dev_err(&dev->gadget->dev,
 				"fail, usb_ep_enable returned %d\n", ret);
 			goto out_free;
 		}
-		dev->eps[i].req = usb_ep_alloc_request(ep, GFP_ATOMIC);
-		if (!dev->eps[i].req) {
+		ep->req = usb_ep_alloc_request(ep->ep, GFP_ATOMIC);
+		if (!ep->req) {
 			dev_err(&dev->gadget->dev,
 				"fail, usb_ep_alloc_request failed\n");
-			usb_ep_disable(ep);
+			usb_ep_disable(ep->ep);
 			ret = -ENOMEM;
 			goto out_free;
 		}
-		dev->eps[i].ep = ep;
-		dev->eps[i].state = STATE_EP_ENABLED;
-		ep->driver_data = &dev->eps[i];
+		ep->state = STATE_EP_ENABLED;
+		ep->ep->driver_data = ep;
 		ret = i;
 		goto out_unlock;
 	}
@@ -782,10 +825,6 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value)
 {
 	int ret = 0, i = value;
 	unsigned long flags;
-	const void *desc;
-
-	if (i < 0 || i >= USB_RAW_MAX_ENDPOINTS)
-		return -EINVAL;
 
 	spin_lock_irqsave(&dev->lock, flags);
 	if (dev->state != STATE_DEV_RUNNING) {
@@ -798,7 +837,12 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value)
 		ret = -EBUSY;
 		goto out_unlock;
 	}
-	if (dev->eps[i].state != STATE_EP_ENABLED) {
+	if (i < 0 || i >= dev->eps_num) {
+		dev_dbg(dev->dev, "fail, invalid endpoint\n");
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+	if (dev->eps[i].state == STATE_EP_DISABLED) {
 		dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n");
 		ret = -EINVAL;
 		goto out_unlock;
@@ -822,10 +866,8 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value)
 
 	spin_lock_irqsave(&dev->lock, flags);
 	usb_ep_free_request(dev->eps[i].ep, dev->eps[i].req);
-	desc = dev->eps[i].ep->desc;
-	dev->eps[i].ep = NULL;
+	kfree(dev->eps[i].ep->desc);
 	dev->eps[i].state = STATE_EP_DISABLED;
-	kfree(desc);
 	dev->eps[i].disabling = false;
 
 out_unlock:
@@ -833,6 +875,74 @@ out_unlock:
 	return ret;
 }
 
+static int raw_ioctl_ep_set_clear_halt_wedge(struct raw_dev *dev,
+		unsigned long value, bool set, bool halt)
+{
+	int ret = 0, i = value;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	if (dev->state != STATE_DEV_RUNNING) {
+		dev_dbg(dev->dev, "fail, device is not running\n");
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+	if (!dev->gadget) {
+		dev_dbg(dev->dev, "fail, gadget is not bound\n");
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+	if (i < 0 || i >= dev->eps_num) {
+		dev_dbg(dev->dev, "fail, invalid endpoint\n");
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+	if (dev->eps[i].state == STATE_EP_DISABLED) {
+		dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n");
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+	if (dev->eps[i].disabling) {
+		dev_dbg(&dev->gadget->dev,
+				"fail, disable is in progress\n");
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+	if (dev->eps[i].urb_queued) {
+		dev_dbg(&dev->gadget->dev,
+				"fail, waiting for urb completion\n");
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+	if (usb_endpoint_xfer_isoc(dev->eps[i].ep->desc)) {
+		dev_dbg(&dev->gadget->dev,
+				"fail, can't halt/wedge ISO endpoint\n");
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (set && halt) {
+		ret = usb_ep_set_halt(dev->eps[i].ep);
+		if (ret < 0)
+			dev_err(&dev->gadget->dev,
+				"fail, usb_ep_set_halt returned %d\n", ret);
+	} else if (!set && halt) {
+		ret = usb_ep_clear_halt(dev->eps[i].ep);
+		if (ret < 0)
+			dev_err(&dev->gadget->dev,
+				"fail, usb_ep_clear_halt returned %d\n", ret);
+	} else if (set && !halt) {
+		ret = usb_ep_set_wedge(dev->eps[i].ep);
+		if (ret < 0)
+			dev_err(&dev->gadget->dev,
+				"fail, usb_ep_set_wedge returned %d\n", ret);
+	}
+
+out_unlock:
+	spin_unlock_irqrestore(&dev->lock, flags);
+	return ret;
+}
+
 static void gadget_ep_complete(struct usb_ep *ep, struct usb_request *req)
 {
 	struct raw_ep *r_ep = (struct raw_ep *)ep->driver_data;
@@ -854,7 +964,7 @@ static int raw_process_ep_io(struct raw_dev *dev, struct usb_raw_ep_io *io,
 {
 	int ret = 0;
 	unsigned long flags;
-	struct raw_ep *ep = &dev->eps[io->ep];
+	struct raw_ep *ep;
 	DECLARE_COMPLETION_ONSTACK(done);
 
 	spin_lock_irqsave(&dev->lock, flags);
@@ -868,6 +978,12 @@ static int raw_process_ep_io(struct raw_dev *dev, struct usb_raw_ep_io *io,
 		ret = -EBUSY;
 		goto out_unlock;
 	}
+	if (io->ep >= dev->eps_num) {
+		dev_dbg(&dev->gadget->dev, "fail, invalid endpoint\n");
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+	ep = &dev->eps[io->ep];
 	if (ep->state != STATE_EP_ENABLED) {
 		dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n");
 		ret = -EBUSY;
@@ -952,12 +1068,15 @@ static int raw_ioctl_ep_read(struct raw_dev *dev, unsigned long value)
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 	ret = raw_process_ep_io(dev, &io, data, false);
-	if (ret < 0) {
-		kfree(data);
-		return ret;
-	}
+	if (ret < 0)
+		goto free;
+
 	length = min(io.length, (unsigned int)ret);
-	ret = copy_to_user((void __user *)(value + sizeof(io)), data, length);
+	if (copy_to_user((void __user *)(value + sizeof(io)), data, length))
+		ret = -EFAULT;
+	else
+		ret = length;
+free:
 	kfree(data);
 	return ret;
 }
@@ -1010,6 +1129,71 @@ out_unlock:
 	return ret;
 }
 
+static void fill_ep_caps(struct usb_ep_caps *caps,
+				struct usb_raw_ep_caps *raw_caps)
+{
+	raw_caps->type_control = caps->type_control;
+	raw_caps->type_iso = caps->type_iso;
+	raw_caps->type_bulk = caps->type_bulk;
+	raw_caps->type_int = caps->type_int;
+	raw_caps->dir_in = caps->dir_in;
+	raw_caps->dir_out = caps->dir_out;
+}
+
+static void fill_ep_limits(struct usb_ep *ep, struct usb_raw_ep_limits *limits)
+{
+	limits->maxpacket_limit = ep->maxpacket_limit;
+	limits->max_streams = ep->max_streams;
+}
+
+static int raw_ioctl_eps_info(struct raw_dev *dev, unsigned long value)
+{
+	int ret = 0, i;
+	unsigned long flags;
+	struct usb_raw_eps_info *info;
+	struct raw_ep *ep;
+
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	spin_lock_irqsave(&dev->lock, flags);
+	if (dev->state != STATE_DEV_RUNNING) {
+		dev_dbg(dev->dev, "fail, device is not running\n");
+		ret = -EINVAL;
+		spin_unlock_irqrestore(&dev->lock, flags);
+		goto out_free;
+	}
+	if (!dev->gadget) {
+		dev_dbg(dev->dev, "fail, gadget is not bound\n");
+		ret = -EBUSY;
+		spin_unlock_irqrestore(&dev->lock, flags);
+		goto out_free;
+	}
+
+	memset(info, 0, sizeof(*info));
+	for (i = 0; i < dev->eps_num; i++) {
+		ep = &dev->eps[i];
+		strscpy(&info->eps[i].name[0], ep->ep->name,
+				USB_RAW_EP_NAME_MAX);
+		info->eps[i].addr = ep->addr;
+		fill_ep_caps(&ep->ep->caps, &info->eps[i].caps);
+		fill_ep_limits(ep->ep, &info->eps[i].limits);
+	}
+	ret = dev->eps_num;
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	if (copy_to_user((void __user *)value, info, sizeof(*info)))
+		ret = -EFAULT;
+
+out_free:
+	kfree(info);
+out:
+	return ret;
+}
+
 static long raw_ioctl(struct file *fd, unsigned int cmd, unsigned long value)
 {
 	struct raw_dev *dev = fd->private_data;
@@ -1052,6 +1236,24 @@ static long raw_ioctl(struct file *fd, unsigned int cmd, unsigned long value)
 	case USB_RAW_IOCTL_VBUS_DRAW:
 		ret = raw_ioctl_vbus_draw(dev, value);
 		break;
+	case USB_RAW_IOCTL_EPS_INFO:
+		ret = raw_ioctl_eps_info(dev, value);
+		break;
+	case USB_RAW_IOCTL_EP0_STALL:
+		ret = raw_ioctl_ep0_stall(dev, value);
+		break;
+	case USB_RAW_IOCTL_EP_SET_HALT:
+		ret = raw_ioctl_ep_set_clear_halt_wedge(
+					dev, value, true, true);
+		break;
+	case USB_RAW_IOCTL_EP_CLEAR_HALT:
+		ret = raw_ioctl_ep_set_clear_halt_wedge(
+					dev, value, false, true);
+		break;
+	case USB_RAW_IOCTL_EP_SET_WEDGE:
+		ret = raw_ioctl_ep_set_clear_halt_wedge(
+					dev, value, true, false);
+		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 6e0432141c40..b771a854e29c 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -185,7 +185,7 @@ static int regs_dbg_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-const struct file_operations queue_dbg_fops = {
+static const struct file_operations queue_dbg_fops = {
 	.owner		= THIS_MODULE,
 	.open		= queue_dbg_open,
 	.llseek		= no_llseek,
@@ -193,7 +193,7 @@ const struct file_operations queue_dbg_fops = {
 	.release	= queue_dbg_release,
 };
 
-const struct file_operations regs_dbg_fops = {
+static const struct file_operations regs_dbg_fops = {
 	.owner		= THIS_MODULE,
 	.open		= regs_dbg_open,
 	.llseek		= generic_file_llseek,
@@ -1951,10 +1951,10 @@ static irqreturn_t usba_vbus_irq_thread(int irq, void *devid)
 			usba_start(udc);
 		} else {
 			udc->suspended = false;
-			usba_stop(udc);
-
 			if (udc->driver->disconnect)
 				udc->driver->disconnect(&udc->gadget);
+
+			usba_stop(udc);
 		}
 		udc->vbus_prev = vbus;
 	}
diff --git a/drivers/usb/gadget/udc/bdc/bdc_ep.c b/drivers/usb/gadget/udc/bdc/bdc_ep.c
index a4d9b5e1e50e..d49c6dc1082d 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_ep.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_ep.c
@@ -540,7 +540,7 @@ static void bdc_req_complete(struct bdc_ep *ep, struct bdc_req *req,
 {
 	struct bdc *bdc = ep->bdc;
 
-	if (req == NULL  || &req->queue == NULL || &req->usb_req == NULL)
+	if (req == NULL)
 		return;
 
 	dev_dbg(bdc->dev, "%s ep:%s status:%d\n", __func__, ep->name, status);
diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c
index a8273b589456..5af0fe9c61d7 100644
--- a/drivers/usb/gadget/udc/net2272.c
+++ b/drivers/usb/gadget/udc/net2272.c
@@ -2647,6 +2647,8 @@ net2272_plat_probe(struct platform_device *pdev)
  err_req:
 	release_mem_region(base, len);
  err:
+	kfree(dev);
+
 	return ret;
 }
 
diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c
index 52a6add961f4..dfabc54cdc27 100644
--- a/drivers/usb/gadget/udc/tegra-xudc.c
+++ b/drivers/usb/gadget/udc/tegra-xudc.c
@@ -3840,11 +3840,11 @@ static int __maybe_unused tegra_xudc_suspend(struct device *dev)
 
 	flush_work(&xudc->usb_role_sw_work);
 
-	/* Forcibly disconnect before powergating. */
-	tegra_xudc_device_mode_off(xudc);
-
-	if (!pm_runtime_status_suspended(dev))
+	if (!pm_runtime_status_suspended(dev)) {
+		/* Forcibly disconnect before powergating. */
+		tegra_xudc_device_mode_off(xudc);
 		tegra_xudc_powergate(xudc);
+	}
 
 	pm_runtime_disable(dev);
 
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 9eca1fe81061..f37316d2c8fa 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1571,6 +1571,8 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
 		}
 		if ((temp & PORT_RC))
 			reset_change = true;
+		if (temp & PORT_OC)
+			status = 1;
 	}
 	if (!status && !reset_change) {
 		xhci_dbg(xhci, "%s: stopping port polling.\n", __func__);
@@ -1636,6 +1638,13 @@ retry:
 				 port_index);
 			goto retry;
 		}
+		/* bail out if port detected a over-current condition */
+		if (t1 & PORT_OC) {
+			bus_state->bus_suspended = 0;
+			spin_unlock_irqrestore(&xhci->lock, flags);
+			xhci_dbg(xhci, "Bus suspend bailout, port over-current detected\n");
+			return -EBUSY;
+		}
 		/* suspend ports in U0, or bail out for new connect changes */
 		if ((t1 & PORT_PE) && (t1 & PORT_PLS_MASK) == XDEV_U0) {
 			if ((t1 & PORT_CSC) && wake_enabled) {
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 1d4f6f85f0fe..ea460b9682d5 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -362,6 +362,7 @@ static int xhci_plat_remove(struct platform_device *dev)
 	struct clk *reg_clk = xhci->reg_clk;
 	struct usb_hcd *shared_hcd = xhci->shared_hcd;
 
+	pm_runtime_get_sync(&dev->dev);
 	xhci->xhc_state |= XHCI_STATE_REMOVING;
 
 	usb_remove_hcd(shared_hcd);
@@ -375,8 +376,9 @@ static int xhci_plat_remove(struct platform_device *dev)
 	clk_disable_unprepare(reg_clk);
 	usb_put_hcd(hcd);
 
-	pm_runtime_set_suspended(&dev->dev);
 	pm_runtime_disable(&dev->dev);
+	pm_runtime_put_noidle(&dev->dev);
+	pm_runtime_set_suspended(&dev->dev);
 
 	return 0;
 }
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index a78787bb5133..2c255d0620b0 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -547,6 +547,23 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 				stream_id);
 		return;
 	}
+	/*
+	 * A cancelled TD can complete with a stall if HW cached the trb.
+	 * In this case driver can't find cur_td, but if the ring is empty we
+	 * can move the dequeue pointer to the current enqueue position.
+	 */
+	if (!cur_td) {
+		if (list_empty(&ep_ring->td_list)) {
+			state->new_deq_seg = ep_ring->enq_seg;
+			state->new_deq_ptr = ep_ring->enqueue;
+			state->new_cycle_state = ep_ring->cycle_state;
+			goto done;
+		} else {
+			xhci_warn(xhci, "Can't find new dequeue state, missing cur_td\n");
+			return;
+		}
+	}
+
 	/* Dig out the cycle state saved by the xHC during the stop ep cmd */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"Finding endpoint context");
@@ -592,6 +609,7 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 	state->new_deq_seg = new_seg;
 	state->new_deq_ptr = new_deq;
 
+done:
 	/* Don't update the ring cycle state for the producer (us). */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"Cycle state = 0x%x", state->new_cycle_state);
@@ -1856,8 +1874,8 @@ static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci,
 
 	if (reset_type == EP_HARD_RESET) {
 		ep->ep_state |= EP_HARD_CLEAR_TOGGLE;
-		xhci_cleanup_stalled_ring(xhci, ep_index, stream_id, td);
-		xhci_clear_hub_tt_buffer(xhci, td, ep);
+		xhci_cleanup_stalled_ring(xhci, slot_id, ep_index, stream_id,
+					  td);
 	}
 	xhci_ring_cmd_db(xhci);
 }
@@ -1978,11 +1996,18 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td,
 	if (trb_comp_code == COMP_STALL_ERROR ||
 		xhci_requires_manual_halt_cleanup(xhci, ep_ctx,
 						trb_comp_code)) {
-		/* Issue a reset endpoint command to clear the host side
-		 * halt, followed by a set dequeue command to move the
-		 * dequeue pointer past the TD.
-		 * The class driver clears the device side halt later.
+		/*
+		 * xhci internal endpoint state will go to a "halt" state for
+		 * any stall, including default control pipe protocol stall.
+		 * To clear the host side halt we need to issue a reset endpoint
+		 * command, followed by a set dequeue command to move past the
+		 * TD.
+		 * Class drivers clear the device side halt from a functional
+		 * stall later. Hub TT buffer should only be cleared for FS/LS
+		 * devices behind HS hubs for functional stalls.
 		 */
+		if ((ep_index != 0) || (trb_comp_code != COMP_STALL_ERROR))
+			xhci_clear_hub_tt_buffer(xhci, td, ep);
 		xhci_cleanup_halted_endpoint(xhci, slot_id, ep_index,
 					ep_ring->stream_id, td, EP_HARD_RESET);
 	} else {
@@ -2539,6 +2564,15 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 				xhci_dbg(xhci, "td_list is empty while skip flag set. Clear skip flag for slot %u ep %u.\n",
 					 slot_id, ep_index);
 			}
+			if (trb_comp_code == COMP_STALL_ERROR ||
+			    xhci_requires_manual_halt_cleanup(xhci, ep_ctx,
+							      trb_comp_code)) {
+				xhci_cleanup_halted_endpoint(xhci, slot_id,
+							     ep_index,
+							     ep_ring->stream_id,
+							     NULL,
+							     EP_HARD_RESET);
+			}
 			goto cleanup;
 		}
 
@@ -3399,8 +3433,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 			/* New sg entry */
 			--num_sgs;
 			sent_len -= block_len;
-			if (num_sgs != 0) {
-				sg = sg_next(sg);
+			sg = sg_next(sg);
+			if (num_sgs != 0 && sg) {
 				block_len = sg_dma_len(sg);
 				addr = (u64) sg_dma_address(sg);
 				addr += sent_len;
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index fe38275363e0..bee5deccc83d 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3031,19 +3031,19 @@ static void xhci_setup_input_ctx_for_quirk(struct xhci_hcd *xhci,
 			added_ctxs, added_ctxs);
 }
 
-void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
-			       unsigned int stream_id, struct xhci_td *td)
+void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int slot_id,
+			       unsigned int ep_index, unsigned int stream_id,
+			       struct xhci_td *td)
 {
 	struct xhci_dequeue_state deq_state;
-	struct usb_device *udev = td->urb->dev;
 
 	xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep,
 			"Cleaning up stalled endpoint ring");
 	/* We need to move the HW's dequeue pointer past this TD,
 	 * or it will attempt to resend it on the next doorbell ring.
 	 */
-	xhci_find_new_dequeue_state(xhci, udev->slot_id,
-			ep_index, stream_id, td, &deq_state);
+	xhci_find_new_dequeue_state(xhci, slot_id, ep_index, stream_id, td,
+				    &deq_state);
 
 	if (!deq_state.new_deq_ptr || !deq_state.new_deq_seg)
 		return;
@@ -3054,7 +3054,7 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
 	if (!(xhci->quirks & XHCI_RESET_EP_QUIRK)) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep,
 				"Queueing new dequeue state");
-		xhci_queue_new_dequeue_state(xhci, udev->slot_id,
+		xhci_queue_new_dequeue_state(xhci, slot_id,
 				ep_index, &deq_state);
 	} else {
 		/* Better hope no one uses the input context between now and the
@@ -3065,7 +3065,7 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
 		xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
 				"Setting up input context for "
 				"configure endpoint command");
-		xhci_setup_input_ctx_for_quirk(xhci, udev->slot_id,
+		xhci_setup_input_ctx_for_quirk(xhci, slot_id,
 				ep_index, &deq_state);
 	}
 }
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 3289bb516201..86cfefdd6632 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -2116,8 +2116,9 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 void xhci_queue_new_dequeue_state(struct xhci_hcd *xhci,
 		unsigned int slot_id, unsigned int ep_index,
 		struct xhci_dequeue_state *deq_state);
-void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
-		unsigned int stream_id, struct xhci_td *td);
+void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int slot_id,
+			       unsigned int ep_index, unsigned int stream_id,
+			       struct xhci_td *td);
 void xhci_stop_endpoint_command_watchdog(struct timer_list *t);
 void xhci_handle_command_timeout(struct work_struct *work);
 
diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c
index 2ab9600d0898..fc8a5da4a07c 100644
--- a/drivers/usb/misc/sisusbvga/sisusb.c
+++ b/drivers/usb/misc/sisusbvga/sisusb.c
@@ -1199,18 +1199,18 @@ static int sisusb_read_mem_bulk(struct sisusb_usb_data *sisusb, u32 addr,
 /* High level: Gfx (indexed) register access */
 
 #ifdef CONFIG_USB_SISUSBVGA_CON
-int sisusb_setreg(struct sisusb_usb_data *sisusb, int port, u8 data)
+int sisusb_setreg(struct sisusb_usb_data *sisusb, u32 port, u8 data)
 {
 	return sisusb_write_memio_byte(sisusb, SISUSB_TYPE_IO, port, data);
 }
 
-int sisusb_getreg(struct sisusb_usb_data *sisusb, int port, u8 *data)
+int sisusb_getreg(struct sisusb_usb_data *sisusb, u32 port, u8 *data)
 {
 	return sisusb_read_memio_byte(sisusb, SISUSB_TYPE_IO, port, data);
 }
 #endif
 
-int sisusb_setidxreg(struct sisusb_usb_data *sisusb, int port,
+int sisusb_setidxreg(struct sisusb_usb_data *sisusb, u32 port,
 		u8 index, u8 data)
 {
 	int ret;
@@ -1220,7 +1220,7 @@ int sisusb_setidxreg(struct sisusb_usb_data *sisusb, int port,
 	return ret;
 }
 
-int sisusb_getidxreg(struct sisusb_usb_data *sisusb, int port,
+int sisusb_getidxreg(struct sisusb_usb_data *sisusb, u32 port,
 		u8 index, u8 *data)
 {
 	int ret;
@@ -1230,7 +1230,7 @@ int sisusb_getidxreg(struct sisusb_usb_data *sisusb, int port,
 	return ret;
 }
 
-int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, int port, u8 idx,
+int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, u32 port, u8 idx,
 		u8 myand, u8 myor)
 {
 	int ret;
@@ -1245,7 +1245,7 @@ int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, int port, u8 idx,
 }
 
 static int sisusb_setidxregmask(struct sisusb_usb_data *sisusb,
-		int port, u8 idx, u8 data, u8 mask)
+		u32 port, u8 idx, u8 data, u8 mask)
 {
 	int ret;
 	u8 tmp;
@@ -1258,13 +1258,13 @@ static int sisusb_setidxregmask(struct sisusb_usb_data *sisusb,
 	return ret;
 }
 
-int sisusb_setidxregor(struct sisusb_usb_data *sisusb, int port,
+int sisusb_setidxregor(struct sisusb_usb_data *sisusb, u32 port,
 		u8 index, u8 myor)
 {
 	return sisusb_setidxregandor(sisusb, port, index, 0xff, myor);
 }
 
-int sisusb_setidxregand(struct sisusb_usb_data *sisusb, int port,
+int sisusb_setidxregand(struct sisusb_usb_data *sisusb, u32 port,
 		u8 idx, u8 myand)
 {
 	return sisusb_setidxregandor(sisusb, port, idx, myand, 0x00);
@@ -2785,8 +2785,8 @@ static loff_t sisusb_lseek(struct file *file, loff_t offset, int orig)
 static int sisusb_handle_command(struct sisusb_usb_data *sisusb,
 		struct sisusb_command *y, unsigned long arg)
 {
-	int	retval, port, length;
-	u32	address;
+	int	retval, length;
+	u32	port, address;
 
 	/* All our commands require the device
 	 * to be initialized.
diff --git a/drivers/usb/misc/sisusbvga/sisusb_init.h b/drivers/usb/misc/sisusbvga/sisusb_init.h
index 1782c759c4ad..ace09985dae4 100644
--- a/drivers/usb/misc/sisusbvga/sisusb_init.h
+++ b/drivers/usb/misc/sisusbvga/sisusb_init.h
@@ -812,17 +812,17 @@ static const struct SiS_VCLKData SiSUSB_VCLKData[] = {
 int SiSUSBSetMode(struct SiS_Private *SiS_Pr, unsigned short ModeNo);
 int SiSUSBSetVESAMode(struct SiS_Private *SiS_Pr, unsigned short VModeNo);
 
-extern int sisusb_setreg(struct sisusb_usb_data *sisusb, int port, u8 data);
-extern int sisusb_getreg(struct sisusb_usb_data *sisusb, int port, u8 * data);
-extern int sisusb_setidxreg(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_setreg(struct sisusb_usb_data *sisusb, u32 port, u8 data);
+extern int sisusb_getreg(struct sisusb_usb_data *sisusb, u32 port, u8 * data);
+extern int sisusb_setidxreg(struct sisusb_usb_data *sisusb, u32 port,
 			    u8 index, u8 data);
-extern int sisusb_getidxreg(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_getidxreg(struct sisusb_usb_data *sisusb, u32 port,
 			    u8 index, u8 * data);
-extern int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_setidxregandor(struct sisusb_usb_data *sisusb, u32 port,
 				 u8 idx, u8 myand, u8 myor);
-extern int sisusb_setidxregor(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_setidxregor(struct sisusb_usb_data *sisusb, u32 port,
 			      u8 index, u8 myor);
-extern int sisusb_setidxregand(struct sisusb_usb_data *sisusb, int port,
+extern int sisusb_setidxregand(struct sisusb_usb_data *sisusb, u32 port,
 			       u8 idx, u8 myand);
 
 void sisusb_delete(struct kref *kref);
diff --git a/drivers/usb/mtu3/mtu3_debugfs.c b/drivers/usb/mtu3/mtu3_debugfs.c
index c96e5dab0a48..fdeade6254ae 100644
--- a/drivers/usb/mtu3/mtu3_debugfs.c
+++ b/drivers/usb/mtu3/mtu3_debugfs.c
@@ -276,7 +276,7 @@ static const struct file_operations mtu3_ep_fops = {
 	.release = single_release,
 };
 
-static struct debugfs_reg32 mtu3_prb_regs[] = {
+static const struct debugfs_reg32 mtu3_prb_regs[] = {
 	dump_prb_reg("enable", U3D_SSUSB_PRB_CTRL0),
 	dump_prb_reg("byte-sell", U3D_SSUSB_PRB_CTRL1),
 	dump_prb_reg("byte-selh", U3D_SSUSB_PRB_CTRL2),
@@ -349,7 +349,7 @@ static const struct file_operations mtu3_probe_fops = {
 static void mtu3_debugfs_create_prb_files(struct mtu3 *mtu)
 {
 	struct ssusb_mtk *ssusb = mtu->ssusb;
-	struct debugfs_reg32 *regs;
+	const struct debugfs_reg32 *regs;
 	struct dentry *dir_prb;
 	int i;
 
diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c
index bfebf1f2e991..9a7e655d5280 100644
--- a/drivers/usb/phy/phy-twl6030-usb.c
+++ b/drivers/usb/phy/phy-twl6030-usb.c
@@ -377,7 +377,7 @@ static int twl6030_usb_probe(struct platform_device *pdev)
 	if (status < 0) {
 		dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 			twl->irq1, status);
-		return status;
+		goto err_put_regulator;
 	}
 
 	status = request_threaded_irq(twl->irq2, NULL, twl6030_usb_irq,
@@ -386,8 +386,7 @@ static int twl6030_usb_probe(struct platform_device *pdev)
 	if (status < 0) {
 		dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 			twl->irq2, status);
-		free_irq(twl->irq1, twl);
-		return status;
+		goto err_free_irq1;
 	}
 
 	twl->asleep = 0;
@@ -396,6 +395,13 @@ static int twl6030_usb_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "Initialized TWL6030 USB module\n");
 
 	return 0;
+
+err_free_irq1:
+	free_irq(twl->irq1, twl);
+err_put_regulator:
+	regulator_put(twl->usb3v3);
+
+	return status;
 }
 
 static int twl6030_usb_remove(struct platform_device *pdev)
diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c
index ffd984142171..d63072fee099 100644
--- a/drivers/usb/serial/garmin_gps.c
+++ b/drivers/usb/serial/garmin_gps.c
@@ -1138,8 +1138,8 @@ static void garmin_read_process(struct garmin_data *garmin_data_p,
 		   send it directly to the tty port */
 		if (garmin_data_p->flags & FLAGS_QUEUING) {
 			pkt_add(garmin_data_p, data, data_length);
-		} else if (bulk_data ||
-			   getLayerId(data) == GARMIN_LAYERID_APPL) {
+		} else if (bulk_data || (data_length >= sizeof(u32) &&
+				getLayerId(data) == GARMIN_LAYERID_APPL)) {
 
 			spin_lock_irqsave(&garmin_data_p->lock, flags);
 			garmin_data_p->flags |= APP_RESP_SEEN;
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 613f91add03d..ce0401d3137f 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -173,6 +173,7 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x413c, 0x81b3)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{DEVICE_SWI(0x413c, 0x81b5)},	/* Dell Wireless 5811e QDL */
 	{DEVICE_SWI(0x413c, 0x81b6)},	/* Dell Wireless 5811e QDL */
+	{DEVICE_SWI(0x413c, 0x81cc)},	/* Dell Wireless 5816e */
 	{DEVICE_SWI(0x413c, 0x81cf)},   /* Dell Wireless 5819 */
 	{DEVICE_SWI(0x413c, 0x81d0)},   /* Dell Wireless 5819 */
 	{DEVICE_SWI(0x413c, 0x81d1)},   /* Dell Wireless 5818 */
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 3670fda02c34..d592071119ba 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -81,6 +81,19 @@ static void uas_free_streams(struct uas_dev_info *devinfo);
 static void uas_log_cmd_state(struct scsi_cmnd *cmnd, const char *prefix,
 				int status);
 
+/*
+ * This driver needs its own workqueue, as we need to control memory allocation.
+ *
+ * In the course of error handling and power management uas_wait_for_pending_cmnds()
+ * needs to flush pending work items. In these contexts we cannot allocate memory
+ * by doing block IO as we would deadlock. For the same reason we cannot wait
+ * for anything allocating memory not heeding these constraints.
+ *
+ * So we have to control all work items that can be on the workqueue we flush.
+ * Hence we cannot share a queue and need our own.
+ */
+static struct workqueue_struct *workqueue;
+
 static void uas_do_work(struct work_struct *work)
 {
 	struct uas_dev_info *devinfo =
@@ -109,7 +122,7 @@ static void uas_do_work(struct work_struct *work)
 		if (!err)
 			cmdinfo->state &= ~IS_IN_WORK_LIST;
 		else
-			schedule_work(&devinfo->work);
+			queue_work(workqueue, &devinfo->work);
 	}
 out:
 	spin_unlock_irqrestore(&devinfo->lock, flags);
@@ -134,7 +147,7 @@ static void uas_add_work(struct uas_cmd_info *cmdinfo)
 
 	lockdep_assert_held(&devinfo->lock);
 	cmdinfo->state |= IS_IN_WORK_LIST;
-	schedule_work(&devinfo->work);
+	queue_work(workqueue, &devinfo->work);
 }
 
 static void uas_zap_pending(struct uas_dev_info *devinfo, int result)
@@ -190,6 +203,9 @@ static void uas_log_cmd_state(struct scsi_cmnd *cmnd, const char *prefix,
 	struct uas_cmd_info *ci = (void *)&cmnd->SCp;
 	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
 
+	if (status == -ENODEV) /* too late */
+		return;
+
 	scmd_printk(KERN_INFO, cmnd,
 		    "%s %d uas-tag %d inflight:%s%s%s%s%s%s%s%s%s%s%s%s ",
 		    prefix, status, cmdinfo->uas_tag,
@@ -1226,7 +1242,31 @@ static struct usb_driver uas_driver = {
 	.id_table = uas_usb_ids,
 };
 
-module_usb_driver(uas_driver);
+static int __init uas_init(void)
+{
+	int rv;
+
+	workqueue = alloc_workqueue("uas", WQ_MEM_RECLAIM, 0);
+	if (!workqueue)
+		return -ENOMEM;
+
+	rv = usb_register(&uas_driver);
+	if (rv) {
+		destroy_workqueue(workqueue);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void __exit uas_exit(void)
+{
+	usb_deregister(&uas_driver);
+	destroy_workqueue(workqueue);
+}
+
+module_init(uas_init);
+module_exit(uas_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_IMPORT_NS(USB_STORAGE);
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 1880f3e13f57..f6c3681fa2e9 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2323,6 +2323,13 @@ UNUSUAL_DEV(  0x3340, 0xffff, 0x0000, 0x0000,
 		USB_SC_DEVICE,USB_PR_DEVICE,NULL,
 		US_FL_MAX_SECTORS_64 ),
 
+/* Reported by Cyril Roelandt <tipecaml@gmail.com> */
+UNUSUAL_DEV(  0x357d, 0x7788, 0x0114, 0x0114,
+		"JMicron",
+		"USB to ATA/ATAPI Bridge",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_BROKEN_FUA ),
+
 /* Reported by Andrey Rahmatullin <wrar@altlinux.org> */
 UNUSUAL_DEV(  0x4102, 0x1020, 0x0100,  0x0100,
 		"iRiver",
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 1b23741036ee..37157ed9a881 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -28,6 +28,13 @@
  * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org>
  */
 
+/* Reported-by: Julian Groß <julian.g@posteo.de> */
+UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999,
+		"LaCie",
+		"2Big Quadra USB3",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
+
 /*
  * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI
  * commands in UAS mode.  Observed with the 1.28 firmware; are there others?
diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c
index c823122f9cb7..e8ddb81cb6df 100644
--- a/drivers/usb/typec/bus.c
+++ b/drivers/usb/typec/bus.c
@@ -198,7 +198,10 @@ EXPORT_SYMBOL_GPL(typec_altmode_vdm);
 const struct typec_altmode *
 typec_altmode_get_partner(struct typec_altmode *adev)
 {
-	return adev ? &to_altmode(adev)->partner->adev : NULL;
+	if (!adev || !to_altmode(adev)->partner)
+		return NULL;
+
+	return &to_altmode(adev)->partner->adev;
 }
 EXPORT_SYMBOL_GPL(typec_altmode_get_partner);
 
diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c
index f5c5e0aef66f..c22e5c4bbf1a 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -63,6 +63,7 @@ enum {
 #define PMC_USB_ALTMODE_DP_MODE_SHIFT	8
 
 /* TBT specific Mode Data bits */
+#define PMC_USB_ALTMODE_HPD_HIGH	BIT(14)
 #define PMC_USB_ALTMODE_TBT_TYPE	BIT(17)
 #define PMC_USB_ALTMODE_CABLE_TYPE	BIT(18)
 #define PMC_USB_ALTMODE_ACTIVE_LINK	BIT(20)
@@ -74,8 +75,8 @@ enum {
 #define PMC_USB_ALTMODE_TBT_GEN(_g_)	(((_g_) & GENMASK(1, 0)) << 28)
 
 /* Display HPD Request bits */
+#define PMC_USB_DP_HPD_LVL		BIT(4)
 #define PMC_USB_DP_HPD_IRQ		BIT(5)
-#define PMC_USB_DP_HPD_LVL		BIT(6)
 
 struct pmc_usb;
 
@@ -157,6 +158,9 @@ pmc_usb_mux_dp(struct pmc_usb_port *port, struct typec_mux_state *state)
 	req.mode_data |= (state->mode - TYPEC_STATE_MODAL) <<
 			 PMC_USB_ALTMODE_DP_MODE_SHIFT;
 
+	if (data->status & DP_STATUS_HPD_STATE)
+		req.mode_data |= PMC_USB_ALTMODE_HPD_HIGH;
+
 	return pmc_usb_command(port, (void *)&req, sizeof(req));
 }
 
@@ -298,11 +302,11 @@ static int pmc_usb_register_port(struct pmc_usb *pmc, int index,
 	struct typec_mux_desc mux_desc = { };
 	int ret;
 
-	ret = fwnode_property_read_u8(fwnode, "usb2-port", &port->usb2_port);
+	ret = fwnode_property_read_u8(fwnode, "usb2-port-number", &port->usb2_port);
 	if (ret)
 		return ret;
 
-	ret = fwnode_property_read_u8(fwnode, "usb3-port", &port->usb3_port);
+	ret = fwnode_property_read_u8(fwnode, "usb3-port-number", &port->usb3_port);
 	if (ret)
 		return ret;
 
diff --git a/drivers/usb/typec/mux/pi3usb30532.c b/drivers/usb/typec/mux/pi3usb30532.c
index 46457c133d2b..7afe275b17d0 100644
--- a/drivers/usb/typec/mux/pi3usb30532.c
+++ b/drivers/usb/typec/mux/pi3usb30532.c
@@ -114,8 +114,8 @@ pi3usb30532_mux_set(struct typec_mux *mux, struct typec_mux_state *state)
 static int pi3usb30532_probe(struct i2c_client *client)
 {
 	struct device *dev = &client->dev;
-	struct typec_switch_desc sw_desc;
-	struct typec_mux_desc mux_desc;
+	struct typec_switch_desc sw_desc = { };
+	struct typec_mux_desc mux_desc = { };
 	struct pi3usb30532 *pi;
 	int ret;
 
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index de3576e6530a..82b19ebd7838 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -3794,6 +3794,14 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1,
 		 */
 		break;
 
+	case PORT_RESET:
+	case PORT_RESET_WAIT_OFF:
+		/*
+		 * State set back to default mode once the timer completes.
+		 * Ignore CC changes here.
+		 */
+		break;
+
 	default:
 		if (tcpm_port_is_disconnected(port))
 			tcpm_set_state(port, unattached_state(port), 0);
@@ -3855,6 +3863,15 @@ static void _tcpm_pd_vbus_on(struct tcpm_port *port)
 	case SRC_TRY_DEBOUNCE:
 		/* Do nothing, waiting for sink detection */
 		break;
+
+	case PORT_RESET:
+	case PORT_RESET_WAIT_OFF:
+		/*
+		 * State set back to default mode once the timer completes.
+		 * Ignore vbus changes here.
+		 */
+		break;
+
 	default:
 		break;
 	}
@@ -3908,10 +3925,19 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port)
 	case PORT_RESET_WAIT_OFF:
 		tcpm_set_state(port, tcpm_default_state(port), 0);
 		break;
+
 	case SRC_TRY_WAIT:
 	case SRC_TRY_DEBOUNCE:
 		/* Do nothing, waiting for sink detection */
 		break;
+
+	case PORT_RESET:
+		/*
+		 * State set back to default mode once the timer completes.
+		 * Ignore vbus changes here.
+		 */
+		break;
+
 	default:
 		if (port->pwr_role == TYPEC_SINK &&
 		    port->attached)
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index 7db1460104b7..e8140065c8a5 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -1,21 +1,16 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config VDPA
-	tristate
+menuconfig VDPA
+	tristate "vDPA drivers"
 	help
 	  Enable this module to support vDPA device that uses a
 	  datapath which complies with virtio specifications with
 	  vendor specific control path.
 
-menuconfig VDPA_MENU
-	bool "VDPA drivers"
-	default n
-
-if VDPA_MENU
+if VDPA
 
 config VDPA_SIM
 	tristate "vDPA device simulator"
-	depends on RUNTIME_TESTING_MENU
-	select VDPA
+	depends on RUNTIME_TESTING_MENU && HAS_DMA && VHOST_DPN
 	select VHOST_RING
 	default n
 	help
@@ -24,9 +19,8 @@ config VDPA_SIM
 	  development of vDPA.
 
 config IFCVF
-	tristate "Intel IFC VF VDPA driver"
+	tristate "Intel IFC VF vDPA driver"
 	depends on PCI_MSI
-	select VDPA
 	default n
 	help
 	  This kernel module can drive Intel IFC VF NIC to offload
@@ -34,4 +28,4 @@ config IFCVF
 	  To compile this driver as a module, choose M here: the module will
 	  be called ifcvf.
 
-endif # VDPA_MENU
+endif # VDPA
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c
index b61b06ea26d3..e24371d644b5 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.c
+++ b/drivers/vdpa/ifcvf/ifcvf_base.c
@@ -301,12 +301,10 @@ int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num)
 
 static int ifcvf_hw_enable(struct ifcvf_hw *hw)
 {
-	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
 	struct virtio_pci_common_cfg __iomem *cfg;
 	struct ifcvf_adapter *ifcvf;
 	u32 i;
 
-	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
 	ifcvf = vf_to_adapter(hw);
 	cfg = hw->common_cfg;
 	ifc_iowrite16(IFCVF_MSI_CONFIG_OFF, &cfg->msix_config);
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 8d54dc5b08d2..abf6a061cab6 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -31,11 +31,9 @@ static irqreturn_t ifcvf_intr_handler(int irq, void *arg)
 static int ifcvf_start_datapath(void *private)
 {
 	struct ifcvf_hw *vf = ifcvf_private_to_vf(private);
-	struct ifcvf_adapter *ifcvf;
 	u8 status;
 	int ret;
 
-	ifcvf = vf_to_adapter(vf);
 	vf->nr_vring = IFCVF_MAX_QUEUE_PAIRS * 2;
 	ret = ifcvf_start_hw(vf);
 	if (ret < 0) {
@@ -228,7 +226,7 @@ static u32 ifcvf_vdpa_get_vendor_id(struct vdpa_device *vdpa_dev)
 	return IFCVF_SUBSYS_VENDOR_ID;
 }
 
-static u16 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev)
+static u32 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev)
 {
 	return IFCVF_QUEUE_ALIGNMENT;
 }
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index e9ed6a2b635b..ff6562f602e0 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -116,7 +116,7 @@ EXPORT_SYMBOL_GPL(__vdpa_alloc_device);
 
 /**
  * vdpa_register_device - register a vDPA device
- * Callers must have a succeed call of vdpa_init_device() before.
+ * Callers must have a succeed call of vdpa_alloc_device() before.
  * @vdev: the vdpa device to be registered to vDPA bus
  *
  * Returns an error when fail to add to vDPA bus
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 6e8a0cf2fdeb..01c456f7c1f7 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -89,15 +89,14 @@ static struct vdpasim *dev_to_sim(struct device *dev)
 static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx)
 {
 	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
-	int ret;
 
-	ret = vringh_init_iotlb(&vq->vring, vdpasim_features,
-				VDPASIM_QUEUE_MAX, false,
-				(struct vring_desc *)(uintptr_t)vq->desc_addr,
-				(struct vring_avail *)
-				(uintptr_t)vq->driver_addr,
-				(struct vring_used *)
-				(uintptr_t)vq->device_addr);
+	vringh_init_iotlb(&vq->vring, vdpasim_features,
+			  VDPASIM_QUEUE_MAX, false,
+			  (struct vring_desc *)(uintptr_t)vq->desc_addr,
+			  (struct vring_avail *)
+			  (uintptr_t)vq->driver_addr,
+			  (struct vring_used *)
+			  (uintptr_t)vq->device_addr);
 }
 
 static void vdpasim_vq_reset(struct vdpasim_virtqueue *vq)
@@ -435,7 +434,7 @@ static u64 vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx)
 	return vrh->last_avail_idx;
 }
 
-static u16 vdpasim_get_vq_align(struct vdpa_device *vdpa)
+static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
 {
 	return VDPASIM_QUEUE_ALIGN;
 }
@@ -488,7 +487,7 @@ static u8 vdpasim_get_status(struct vdpa_device *vdpa)
 	status = vdpasim->status;
 	spin_unlock(&vdpasim->lock);
 
-	return vdpasim->status;
+	return status;
 }
 
 static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 85b32c325282..cc1d64765ce7 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -342,8 +342,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 	vma = find_vma_intersection(mm, vaddr, vaddr + 1);
 
 	if (vma && vma->vm_flags & VM_PFNMAP) {
-		*pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
-		if (is_invalid_reserved_pfn(*pfn))
+		if (!follow_pfn(vma, vaddr, pfn) &&
+		    is_invalid_reserved_pfn(*pfn))
 			ret = 0;
 	}
 done:
@@ -555,7 +555,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 			continue;
 		}
 
-		remote_vaddr = dma->vaddr + iova - dma->iova;
+		remote_vaddr = dma->vaddr + (iova - dma->iova);
 		ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn[i],
 					     do_accounting);
 		if (ret)
@@ -2345,10 +2345,10 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu,
 	vaddr = dma->vaddr + offset;
 
 	if (write)
-		*copied = __copy_to_user((void __user *)vaddr, data,
+		*copied = copy_to_user((void __user *)vaddr, data,
 					 count) ? 0 : count;
 	else
-		*copied = __copy_from_user(data, (void __user *)vaddr,
+		*copied = copy_from_user(data, (void __user *)vaddr,
 					   count) ? 0 : count;
 	if (kthread)
 		unuse_mm(mm);
diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
index 362b832f5338..c4f273793595 100644
--- a/drivers/vhost/Kconfig
+++ b/drivers/vhost/Kconfig
@@ -3,6 +3,8 @@ config VHOST_IOTLB
 	tristate
 	help
 	  Generic IOTLB implementation for vhost and vringh.
+	  This option is selected by any driver which needs to support
+	  an IOMMU in software.
 
 config VHOST_RING
 	tristate
@@ -11,6 +13,15 @@ config VHOST_RING
 	  This option is selected by any driver which needs to access
 	  the host side of a virtio ring.
 
+config VHOST_DPN
+	bool
+	depends on !ARM || AEABI
+	default y
+	help
+	  Anything selecting VHOST or VHOST_RING must depend on VHOST_DPN.
+	  This excludes the deprecated ARM ABI since that forces a 4 byte
+	  alignment on all structs - incompatible with virtio spec requirements.
+
 config VHOST
 	tristate
 	select VHOST_IOTLB
@@ -26,7 +37,7 @@ if VHOST_MENU
 
 config VHOST_NET
 	tristate "Host kernel accelerator for virtio net"
-	depends on NET && EVENTFD && (TUN || !TUN) && (TAP || !TAP)
+	depends on NET && EVENTFD && (TUN || !TUN) && (TAP || !TAP) && VHOST_DPN
 	select VHOST
 	---help---
 	  This kernel module can be loaded in host kernel to accelerate
@@ -38,7 +49,7 @@ config VHOST_NET
 
 config VHOST_SCSI
 	tristate "VHOST_SCSI TCM fabric driver"
-	depends on TARGET_CORE && EVENTFD
+	depends on TARGET_CORE && EVENTFD && VHOST_DPN
 	select VHOST
 	default n
 	---help---
@@ -47,7 +58,7 @@ config VHOST_SCSI
 
 config VHOST_VSOCK
 	tristate "vhost virtio-vsock driver"
-	depends on VSOCKETS && EVENTFD
+	depends on VSOCKETS && EVENTFD && VHOST_DPN
 	select VHOST
 	select VIRTIO_VSOCKETS_COMMON
 	default n
@@ -61,9 +72,9 @@ config VHOST_VSOCK
 
 config VHOST_VDPA
 	tristate "Vhost driver for vDPA-based backend"
-	depends on EVENTFD
+	depends on EVENTFD && VHOST_DPN
 	select VHOST
-	select VDPA
+	depends on VDPA
 	help
 	  This kernel module can be loaded in host kernel to accelerate
 	  guest virtio devices with the vDPA-based backends.
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 87469d67ede8..2927f02cc7e1 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -424,7 +424,7 @@ static void vhost_net_disable_vq(struct vhost_net *n,
 	struct vhost_net_virtqueue *nvq =
 		container_of(vq, struct vhost_net_virtqueue, vq);
 	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
-	if (!vq->private_data)
+	if (!vhost_vq_get_backend(vq))
 		return;
 	vhost_poll_stop(poll);
 }
@@ -437,7 +437,7 @@ static int vhost_net_enable_vq(struct vhost_net *n,
 	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
 	struct socket *sock;
 
-	sock = vq->private_data;
+	sock = vhost_vq_get_backend(vq);
 	if (!sock)
 		return 0;
 
@@ -524,7 +524,7 @@ static void vhost_net_busy_poll(struct vhost_net *net,
 		return;
 
 	vhost_disable_notify(&net->dev, vq);
-	sock = rvq->private_data;
+	sock = vhost_vq_get_backend(rvq);
 
 	busyloop_timeout = poll_rx ? rvq->busyloop_timeout:
 				     tvq->busyloop_timeout;
@@ -570,8 +570,10 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 
 	if (r == tvq->num && tvq->busyloop_timeout) {
 		/* Flush batched packets first */
-		if (!vhost_sock_zcopy(tvq->private_data))
-			vhost_tx_batch(net, tnvq, tvq->private_data, msghdr);
+		if (!vhost_sock_zcopy(vhost_vq_get_backend(tvq)))
+			vhost_tx_batch(net, tnvq,
+				       vhost_vq_get_backend(tvq),
+				       msghdr);
 
 		vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, false);
 
@@ -685,7 +687,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 	struct vhost_virtqueue *vq = &nvq->vq;
 	struct vhost_net *net = container_of(vq->dev, struct vhost_net,
 					     dev);
-	struct socket *sock = vq->private_data;
+	struct socket *sock = vhost_vq_get_backend(vq);
 	struct page_frag *alloc_frag = &net->page_frag;
 	struct virtio_net_hdr *gso;
 	struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp];
@@ -952,7 +954,7 @@ static void handle_tx(struct vhost_net *net)
 	struct socket *sock;
 
 	mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_TX);
-	sock = vq->private_data;
+	sock = vhost_vq_get_backend(vq);
 	if (!sock)
 		goto out;
 
@@ -1121,7 +1123,7 @@ static void handle_rx(struct vhost_net *net)
 	int recv_pkts = 0;
 
 	mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_RX);
-	sock = vq->private_data;
+	sock = vhost_vq_get_backend(vq);
 	if (!sock)
 		goto out;
 
@@ -1345,9 +1347,9 @@ static struct socket *vhost_net_stop_vq(struct vhost_net *n,
 		container_of(vq, struct vhost_net_virtqueue, vq);
 
 	mutex_lock(&vq->mutex);
-	sock = vq->private_data;
+	sock = vhost_vq_get_backend(vq);
 	vhost_net_disable_vq(n, vq);
-	vq->private_data = NULL;
+	vhost_vq_set_backend(vq, NULL);
 	vhost_net_buf_unproduce(nvq);
 	nvq->rx_ring = NULL;
 	mutex_unlock(&vq->mutex);
@@ -1521,7 +1523,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 	}
 
 	/* start polling new socket */
-	oldsock = vq->private_data;
+	oldsock = vhost_vq_get_backend(vq);
 	if (sock != oldsock) {
 		ubufs = vhost_net_ubuf_alloc(vq,
 					     sock && vhost_sock_zcopy(sock));
@@ -1531,7 +1533,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 		}
 
 		vhost_net_disable_vq(n, vq);
-		vq->private_data = sock;
+		vhost_vq_set_backend(vq, sock);
 		vhost_net_buf_unproduce(nvq);
 		r = vhost_vq_init_access(vq);
 		if (r)
@@ -1568,7 +1570,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 	return 0;
 
 err_used:
-	vq->private_data = oldsock;
+	vhost_vq_set_backend(vq, oldsock);
 	vhost_net_enable_vq(n, vq);
 	if (ubufs)
 		vhost_net_ubuf_put_wait_and_free(ubufs);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 7653667a8cdc..c39952243fd3 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -452,7 +452,7 @@ vhost_scsi_do_evt_work(struct vhost_scsi *vs, struct vhost_scsi_evt *evt)
 	unsigned out, in;
 	int head, ret;
 
-	if (!vq->private_data) {
+	if (!vhost_vq_get_backend(vq)) {
 		vs->vs_events_missed = true;
 		return;
 	}
@@ -892,7 +892,7 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc,
 	} else {
 		struct vhost_scsi_tpg **vs_tpg, *tpg;
 
-		vs_tpg = vq->private_data;	/* validated at handler entry */
+		vs_tpg = vhost_vq_get_backend(vq);	/* validated at handler entry */
 
 		tpg = READ_ONCE(vs_tpg[*vc->target]);
 		if (unlikely(!tpg)) {
@@ -929,7 +929,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 	 * We can handle the vq only after the endpoint is setup by calling the
 	 * VHOST_SCSI_SET_ENDPOINT ioctl.
 	 */
-	vs_tpg = vq->private_data;
+	vs_tpg = vhost_vq_get_backend(vq);
 	if (!vs_tpg)
 		goto out;
 
@@ -1184,7 +1184,7 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 	 * We can handle the vq only after the endpoint is setup by calling the
 	 * VHOST_SCSI_SET_ENDPOINT ioctl.
 	 */
-	if (!vq->private_data)
+	if (!vhost_vq_get_backend(vq))
 		goto out;
 
 	memset(&vc, 0, sizeof(vc));
@@ -1322,7 +1322,7 @@ static void vhost_scsi_evt_handle_kick(struct vhost_work *work)
 	struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev);
 
 	mutex_lock(&vq->mutex);
-	if (!vq->private_data)
+	if (!vhost_vq_get_backend(vq))
 		goto out;
 
 	if (vs->vs_events_missed)
@@ -1460,7 +1460,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
 			vq = &vs->vqs[i].vq;
 			mutex_lock(&vq->mutex);
-			vq->private_data = vs_tpg;
+			vhost_vq_set_backend(vq, vs_tpg);
 			vhost_vq_init_access(vq);
 			mutex_unlock(&vq->mutex);
 		}
@@ -1547,7 +1547,7 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs,
 		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
 			vq = &vs->vqs[i].vq;
 			mutex_lock(&vq->mutex);
-			vq->private_data = NULL;
+			vhost_vq_set_backend(vq, NULL);
 			mutex_unlock(&vq->mutex);
 		}
 	}
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index e37c92d4d7ad..9a3a09005e03 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -49,7 +49,7 @@ static void handle_vq(struct vhost_test *n)
 	void *private;
 
 	mutex_lock(&vq->mutex);
-	private = vq->private_data;
+	private = vhost_vq_get_backend(vq);
 	if (!private) {
 		mutex_unlock(&vq->mutex);
 		return;
@@ -120,7 +120,7 @@ static int vhost_test_open(struct inode *inode, struct file *f)
 	vqs[VHOST_TEST_VQ] = &n->vqs[VHOST_TEST_VQ];
 	n->vqs[VHOST_TEST_VQ].handle_kick = handle_vq_kick;
 	vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX, UIO_MAXIOV,
-		       VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT);
+		       VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT, NULL);
 
 	f->private_data = n;
 
@@ -133,8 +133,8 @@ static void *vhost_test_stop_vq(struct vhost_test *n,
 	void *private;
 
 	mutex_lock(&vq->mutex);
-	private = vq->private_data;
-	vq->private_data = NULL;
+	private = vhost_vq_get_backend(vq);
+	vhost_vq_set_backend(vq, NULL);
 	mutex_unlock(&vq->mutex);
 	return private;
 }
@@ -198,8 +198,8 @@ static long vhost_test_run(struct vhost_test *n, int test)
 		priv = test ? n : NULL;
 
 		/* start polling new socket */
-		oldpriv = vq->private_data;
-		vq->private_data = priv;
+		oldpriv = vhost_vq_get_backend(vq);
+		vhost_vq_set_backend(vq, priv);
 
 		r = vhost_vq_init_access(&n->vqs[index]);
 
@@ -225,7 +225,7 @@ static long vhost_test_reset_owner(struct vhost_test *n)
 {
 	void *priv = NULL;
 	long err;
-	struct vhost_umem *umem;
+	struct vhost_iotlb *umem;
 
 	mutex_lock(&n->dev.mutex);
 	err = vhost_dev_check_owner(&n->dev);
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 421f02a8530a..0968361e3b77 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -296,7 +296,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 	struct vdpa_callback cb;
 	struct vhost_virtqueue *vq;
 	struct vhost_vring_state s;
-	u8 status;
 	u32 idx;
 	long r;
 
@@ -310,8 +309,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 	idx = array_index_nospec(idx, v->nvqs);
 	vq = &v->vqs[idx];
 
-	status = ops->get_status(vdpa);
-
 	if (cmd == VHOST_VDPA_SET_VRING_ENABLE) {
 		if (copy_from_user(&s, argp, sizeof(s)))
 			return -EFAULT;
@@ -678,8 +675,6 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)
 	int nvqs, i, r, opened;
 
 	v = container_of(inode->i_cdev, struct vhost_vdpa, cdev);
-	if (!v)
-		return -ENODEV;
 
 	opened = atomic_cmpxchg(&v->opened, 0, 1);
 	if (opened)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index d450e16c5c25..21a59b598ed8 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -730,7 +730,7 @@ static inline void __user *vhost_vq_meta_fetch(struct vhost_virtqueue *vq,
 	if (!map)
 		return NULL;
 
-	return (void *)(uintptr_t)(map->addr + addr - map->start);
+	return (void __user *)(uintptr_t)(map->addr + addr - map->start);
 }
 
 /* Can we switch to this memory table? */
@@ -869,7 +869,7 @@ static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq,
  * not happen in this case.
  */
 static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
-					    void *addr, unsigned int size,
+					    void __user *addr, unsigned int size,
 					    int type)
 {
 	void __user *uaddr = vhost_vq_meta_fetch(vq,
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 181382185bbc..f8403bd46b85 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -231,6 +231,33 @@ enum {
 			 (1ULL << VIRTIO_F_VERSION_1)
 };
 
+/**
+ * vhost_vq_set_backend - Set backend.
+ *
+ * @vq            Virtqueue.
+ * @private_data  The private data.
+ *
+ * Context: Need to call with vq->mutex acquired.
+ */
+static inline void vhost_vq_set_backend(struct vhost_virtqueue *vq,
+					void *private_data)
+{
+	vq->private_data = private_data;
+}
+
+/**
+ * vhost_vq_get_backend - Get backend.
+ *
+ * @vq            Virtqueue.
+ *
+ * Context: Need to call with vq->mutex acquired.
+ * Return: Private data previously set with vhost_vq_set_backend.
+ */
+static inline void *vhost_vq_get_backend(struct vhost_virtqueue *vq)
+{
+	return vq->private_data;
+}
+
 static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
 {
 	return vq->acked_features & (1ULL << bit);
diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index ee0491f579ac..ba8e0d6cfd97 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -13,9 +13,11 @@
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#if IS_REACHABLE(CONFIG_VHOST_IOTLB)
 #include <linux/bvec.h>
 #include <linux/highmem.h>
 #include <linux/vhost_iotlb.h>
+#endif
 #include <uapi/linux/virtio_config.h>
 
 static __printf(1,2) __cold void vringh_bad(const char *fmt, ...)
@@ -1059,6 +1061,8 @@ int vringh_need_notify_kern(struct vringh *vrh)
 }
 EXPORT_SYMBOL(vringh_need_notify_kern);
 
+#if IS_REACHABLE(CONFIG_VHOST_IOTLB)
+
 static int iotlb_translate(const struct vringh *vrh,
 			   u64 addr, u64 len, struct bio_vec iov[],
 			   int iov_size, u32 perm)
@@ -1416,5 +1420,6 @@ int vringh_need_notify_iotlb(struct vringh *vrh)
 }
 EXPORT_SYMBOL(vringh_need_notify_iotlb);
 
+#endif
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 97669484a3f6..fb4e944c4d0d 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -91,7 +91,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 
 	mutex_lock(&vq->mutex);
 
-	if (!vq->private_data)
+	if (!vhost_vq_get_backend(vq))
 		goto out;
 
 	/* Avoid further vmexits, we're already processing the virtqueue */
@@ -181,14 +181,14 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			break;
 		}
 
-		vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len);
-		added = true;
-
-		/* Deliver to monitoring devices all correctly transmitted
-		 * packets.
+		/* Deliver to monitoring devices all packets that we
+		 * will transmit.
 		 */
 		virtio_transport_deliver_tap_pkt(pkt);
 
+		vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len);
+		added = true;
+
 		pkt->off += payload_len;
 		total_len += payload_len;
 
@@ -196,6 +196,12 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		 * to send it with the next available buffer.
 		 */
 		if (pkt->off < pkt->len) {
+			/* We are queueing the same virtio_vsock_pkt to handle
+			 * the remaining bytes, and we want to deliver it
+			 * to monitoring devices in the next iteration.
+			 */
+			pkt->tap_delivered = false;
+
 			spin_lock_bh(&vsock->send_pkt_list_lock);
 			list_add(&pkt->list, &vsock->send_pkt_list);
 			spin_unlock_bh(&vsock->send_pkt_list_lock);
@@ -440,7 +446,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 
 	mutex_lock(&vq->mutex);
 
-	if (!vq->private_data)
+	if (!vhost_vq_get_backend(vq))
 		goto out;
 
 	vhost_disable_notify(&vsock->dev, vq);
@@ -533,8 +539,8 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 			goto err_vq;
 		}
 
-		if (!vq->private_data) {
-			vq->private_data = vsock;
+		if (!vhost_vq_get_backend(vq)) {
+			vhost_vq_set_backend(vq, vsock);
 			ret = vhost_vq_init_access(vq);
 			if (ret)
 				goto err_vq;
@@ -543,18 +549,23 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 		mutex_unlock(&vq->mutex);
 	}
 
+	/* Some packets may have been queued before the device was started,
+	 * let's kick the send worker to send them.
+	 */
+	vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
+
 	mutex_unlock(&vsock->dev.mutex);
 	return 0;
 
 err_vq:
-	vq->private_data = NULL;
+	vhost_vq_set_backend(vq, NULL);
 	mutex_unlock(&vq->mutex);
 
 	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
 		vq = &vsock->vqs[i];
 
 		mutex_lock(&vq->mutex);
-		vq->private_data = NULL;
+		vhost_vq_set_backend(vq, NULL);
 		mutex_unlock(&vq->mutex);
 	}
 err:
@@ -577,7 +588,7 @@ static int vhost_vsock_stop(struct vhost_vsock *vsock)
 		struct vhost_virtqueue *vq = &vsock->vqs[i];
 
 		mutex_lock(&vq->mutex);
-		vq->private_data = NULL;
+		vhost_vq_set_backend(vq, NULL);
 		mutex_unlock(&vq->mutex);
 	}
 
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 2bbf94b15bba..69a32dfc318a 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -45,7 +45,7 @@ config VIRTIO_PCI_LEGACY
 
 config VIRTIO_VDPA
 	tristate "vDPA driver for virtio devices"
-	select VDPA
+	depends on VDPA
 	select VIRTIO
 	help
 	  This driver provides support for virtio based paravirtual
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0ef16566c3f3..51086a5afdd4 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -165,7 +165,7 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
 
 }
 
-int virtballoon_free_page_report(struct page_reporting_dev_info *pr_dev_info,
+static int virtballoon_free_page_report(struct page_reporting_dev_info *pr_dev_info,
 				   struct scatterlist *sg, unsigned int nents)
 {
 	struct virtio_balloon *vb =
@@ -580,7 +580,7 @@ static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb)
 	if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
 			       &vb->config_read_bitmap))
 		virtio_cread(vb->vdev, struct virtio_balloon_config,
-			     free_page_report_cmd_id,
+			     free_page_hint_cmd_id,
 			     &vb->cmd_id_received_cache);
 
 	return vb->cmd_id_received_cache;
diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c
index 5ae529671b3d..efaf65b0f42d 100644
--- a/drivers/virtio/virtio_input.c
+++ b/drivers/virtio/virtio_input.c
@@ -3,6 +3,7 @@
 #include <linux/virtio.h>
 #include <linux/virtio_config.h>
 #include <linux/input.h>
+#include <linux/slab.h>
 
 #include <uapi/linux/virtio_ids.h>
 #include <uapi/linux/virtio_input.h>
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 53e04926a7b2..190d26e2e75f 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -137,10 +137,14 @@ wdt_restart(struct watchdog_device *wdd, unsigned long mode, void *cmd)
 {
 	struct sp805_wdt *wdt = watchdog_get_drvdata(wdd);
 
+	writel_relaxed(UNLOCK, wdt->base + WDTLOCK);
 	writel_relaxed(0, wdt->base + WDTCONTROL);
 	writel_relaxed(0, wdt->base + WDTLOAD);
 	writel_relaxed(INT_ENABLE | RESET_ENABLE, wdt->base + WDTCONTROL);
 
+	/* Flush posted writes. */
+	readl_relaxed(wdt->base + WDTLOCK);
+
 	return 0;
 }
 
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 385843256865..040d2a43e8e3 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -448,7 +448,14 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn);
 int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs,
 			   unsigned int nr_grefs, void **vaddr)
 {
-	return ring_ops->map(dev, gnt_refs, nr_grefs, vaddr);
+	int err;
+
+	err = ring_ops->map(dev, gnt_refs, nr_grefs, vaddr);
+	/* Some hypervisors are buggy and can return 1. */
+	if (err > 0)
+		err = GNTST_general_error;
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(xenbus_map_ring_valloc);
 
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 3fbbd54f50fd..04f86b8c100e 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -36,6 +36,12 @@ config COMPAT_BINFMT_ELF
 config ARCH_BINFMT_ELF_STATE
 	bool
 
+config ARCH_HAVE_ELF_PROT
+	bool
+
+config ARCH_USE_GNU_PROPERTY
+	bool
+
 config BINFMT_ELF_FDPIC
 	bool "Kernel support for FDPIC ELF binaries"
 	default y if !BINFMT_ELF
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 6765949b3aab..380ad5ace7cf 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -169,7 +169,7 @@ static int afs_record_cm_probe(struct afs_call *call, struct afs_server *server)
 
 	spin_lock(&server->probe_lock);
 
-	if (!test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) {
+	if (!test_and_set_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) {
 		server->cm_epoch = call->epoch;
 		server->probe.cm_epoch = call->epoch;
 		goto out;
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 5c794f4b051a..d1e1caa23c8b 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -1032,7 +1032,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	struct dentry *parent;
 	struct inode *inode;
 	struct key *key;
-	afs_dataversion_t dir_version;
+	afs_dataversion_t dir_version, invalid_before;
 	long de_version;
 	int ret;
 
@@ -1084,8 +1084,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	if (de_version == (long)dir_version)
 		goto out_valid_noupdate;
 
-	dir_version = dir->invalid_before;
-	if (de_version - (long)dir_version >= 0)
+	invalid_before = dir->invalid_before;
+	if (de_version - (long)invalid_before >= 0)
 		goto out_valid;
 
 	_debug("dir modified");
@@ -1275,6 +1275,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct afs_fs_cursor fc;
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	mode |= S_IFDIR;
@@ -1295,7 +1296,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -1316,10 +1317,14 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		goto error_key;
 	}
 
-	if (ret == 0 &&
-	    test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
-		afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid,
-				 afs_edit_dir_for_create);
+	if (ret == 0) {
+		down_write(&dvnode->validate_lock);
+		if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+		    dvnode->status.data_version == data_version)
+			afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid,
+					 afs_edit_dir_for_create);
+		up_write(&dvnode->validate_lock);
+	}
 
 	key_put(key);
 	kfree(scb);
@@ -1360,6 +1365,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct afs_fs_cursor fc;
 	struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL;
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	_enter("{%llx:%llu},{%pd}",
@@ -1391,7 +1397,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -1404,9 +1410,12 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 		ret = afs_end_vnode_operation(&fc);
 		if (ret == 0) {
 			afs_dir_remove_subdir(dentry);
-			if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+			down_write(&dvnode->validate_lock);
+			if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+			    dvnode->status.data_version == data_version)
 				afs_edit_dir_remove(dvnode, &dentry->d_name,
 						    afs_edit_dir_for_rmdir);
+			up_write(&dvnode->validate_lock);
 		}
 	}
 
@@ -1544,10 +1553,15 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
 		ret = afs_end_vnode_operation(&fc);
 		if (ret == 0 && !(scb[1].have_status || scb[1].have_error))
 			ret = afs_dir_remove_link(dvnode, dentry, key);
-		if (ret == 0 &&
-		    test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
-			afs_edit_dir_remove(dvnode, &dentry->d_name,
-					    afs_edit_dir_for_unlink);
+
+		if (ret == 0) {
+			down_write(&dvnode->validate_lock);
+			if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+			    dvnode->status.data_version == data_version)
+				afs_edit_dir_remove(dvnode, &dentry->d_name,
+						    afs_edit_dir_for_unlink);
+			up_write(&dvnode->validate_lock);
+		}
 	}
 
 	if (need_rehash && ret < 0 && ret != -ENOENT)
@@ -1573,6 +1587,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	struct afs_status_cb *scb;
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	mode |= S_IFREG;
@@ -1597,7 +1612,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -1618,9 +1633,12 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		goto error_key;
 	}
 
-	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+	down_write(&dvnode->validate_lock);
+	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+	    dvnode->status.data_version == data_version)
 		afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid,
 				 afs_edit_dir_for_create);
+	up_write(&dvnode->validate_lock);
 
 	kfree(scb);
 	key_put(key);
@@ -1648,6 +1666,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct afs_vnode *vnode = AFS_FS_I(d_inode(from));
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	_enter("{%llx:%llu},{%llx:%llu},{%pd}",
@@ -1672,7 +1691,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		if (mutex_lock_interruptible_nested(&vnode->io_lock, 1) < 0) {
 			afs_end_vnode_operation(&fc);
@@ -1702,9 +1721,12 @@ static int afs_link(struct dentry *from, struct inode *dir,
 		goto error_key;
 	}
 
-	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+	down_write(&dvnode->validate_lock);
+	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+	    dvnode->status.data_version == data_version)
 		afs_edit_dir_add(dvnode, &dentry->d_name, &vnode->fid,
 				 afs_edit_dir_for_link);
+	up_write(&dvnode->validate_lock);
 
 	key_put(key);
 	kfree(scb);
@@ -1732,6 +1754,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
 	struct afs_status_cb *scb;
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct key *key;
+	afs_dataversion_t data_version;
 	int ret;
 
 	_enter("{%llx:%llu},{%pd},%s",
@@ -1759,7 +1782,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t data_version = dvnode->status.data_version + 1;
+		data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -1780,9 +1803,12 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
 		goto error_key;
 	}
 
-	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+	down_write(&dvnode->validate_lock);
+	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+	    dvnode->status.data_version == data_version)
 		afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid,
 				 afs_edit_dir_for_symlink);
+	up_write(&dvnode->validate_lock);
 
 	key_put(key);
 	kfree(scb);
@@ -1812,6 +1838,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct dentry *tmp = NULL, *rehash = NULL;
 	struct inode *new_inode;
 	struct key *key;
+	afs_dataversion_t orig_data_version;
+	afs_dataversion_t new_data_version;
 	bool new_negative = d_is_negative(new_dentry);
 	int ret;
 
@@ -1890,10 +1918,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) {
-		afs_dataversion_t orig_data_version;
-		afs_dataversion_t new_data_version;
-		struct afs_status_cb *new_scb = &scb[1];
-
 		orig_data_version = orig_dvnode->status.data_version + 1;
 
 		if (orig_dvnode != new_dvnode) {
@@ -1904,7 +1928,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			new_data_version = new_dvnode->status.data_version + 1;
 		} else {
 			new_data_version = orig_data_version;
-			new_scb = &scb[0];
 		}
 
 		while (afs_select_fileserver(&fc)) {
@@ -1912,7 +1935,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode);
 			afs_fs_rename(&fc, old_dentry->d_name.name,
 				      new_dvnode, new_dentry->d_name.name,
-				      &scb[0], new_scb);
+				      &scb[0], &scb[1]);
 		}
 
 		afs_vnode_commit_status(&fc, orig_dvnode, fc.cb_break,
@@ -1930,18 +1953,25 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (ret == 0) {
 		if (rehash)
 			d_rehash(rehash);
-		if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags))
-		    afs_edit_dir_remove(orig_dvnode, &old_dentry->d_name,
-					afs_edit_dir_for_rename_0);
+		down_write(&orig_dvnode->validate_lock);
+		if (test_bit(AFS_VNODE_DIR_VALID, &orig_dvnode->flags) &&
+		    orig_dvnode->status.data_version == orig_data_version)
+			afs_edit_dir_remove(orig_dvnode, &old_dentry->d_name,
+					    afs_edit_dir_for_rename_0);
+		if (orig_dvnode != new_dvnode) {
+			up_write(&orig_dvnode->validate_lock);
 
-		if (!new_negative &&
-		    test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags))
-			afs_edit_dir_remove(new_dvnode, &new_dentry->d_name,
-					    afs_edit_dir_for_rename_1);
+			down_write(&new_dvnode->validate_lock);
+		}
+		if (test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags) &&
+		    orig_dvnode->status.data_version == new_data_version) {
+			if (!new_negative)
+				afs_edit_dir_remove(new_dvnode, &new_dentry->d_name,
+						    afs_edit_dir_for_rename_1);
 
-		if (test_bit(AFS_VNODE_DIR_VALID, &new_dvnode->flags))
 			afs_edit_dir_add(new_dvnode, &new_dentry->d_name,
 					 &vnode->fid, afs_edit_dir_for_rename_2);
+		}
 
 		new_inode = d_inode(new_dentry);
 		if (new_inode) {
@@ -1957,14 +1987,10 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		 * Note that if we ever implement RENAME_EXCHANGE, we'll have
 		 * to update both dentries with opposing dir versions.
 		 */
-		if (new_dvnode != orig_dvnode) {
-			afs_update_dentry_version(&fc, old_dentry, &scb[1]);
-			afs_update_dentry_version(&fc, new_dentry, &scb[1]);
-		} else {
-			afs_update_dentry_version(&fc, old_dentry, &scb[0]);
-			afs_update_dentry_version(&fc, new_dentry, &scb[0]);
-		}
+		afs_update_dentry_version(&fc, old_dentry, &scb[1]);
+		afs_update_dentry_version(&fc, new_dentry, &scb[1]);
 		d_move(old_dentry, new_dentry);
+		up_write(&new_dvnode->validate_lock);
 		goto error_tmp;
 	}
 
diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c
index 361088a5edb9..d94e2b7cddff 100644
--- a/fs/afs/dir_silly.c
+++ b/fs/afs/dir_silly.c
@@ -21,6 +21,7 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode
 {
 	struct afs_fs_cursor fc;
 	struct afs_status_cb *scb;
+	afs_dataversion_t dir_data_version;
 	int ret = -ERESTARTSYS;
 
 	_enter("%pd,%pd", old, new);
@@ -31,7 +32,7 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode
 
 	trace_afs_silly_rename(vnode, false);
 	if (afs_begin_vnode_operation(&fc, dvnode, key, true)) {
-		afs_dataversion_t dir_data_version = dvnode->status.data_version + 1;
+		dir_data_version = dvnode->status.data_version + 1;
 
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(dvnode);
@@ -54,12 +55,15 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode
 			dvnode->silly_key = key_get(key);
 		}
 
-		if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
+		down_write(&dvnode->validate_lock);
+		if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+		    dvnode->status.data_version == dir_data_version) {
 			afs_edit_dir_remove(dvnode, &old->d_name,
 					    afs_edit_dir_for_silly_0);
-		if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
 			afs_edit_dir_add(dvnode, &new->d_name,
 					 &vnode->fid, afs_edit_dir_for_silly_1);
+		}
+		up_write(&dvnode->validate_lock);
 	}
 
 	kfree(scb);
@@ -181,10 +185,14 @@ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode
 				clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
 			}
 		}
-		if (ret == 0 &&
-		    test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
-			afs_edit_dir_remove(dvnode, &dentry->d_name,
-					    afs_edit_dir_for_unlink);
+		if (ret == 0) {
+			down_write(&dvnode->validate_lock);
+			if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) &&
+			    dvnode->status.data_version == dir_data_version)
+				afs_edit_dir_remove(dvnode, &dentry->d_name,
+						    afs_edit_dir_for_unlink);
+			up_write(&dvnode->validate_lock);
+		}
 	}
 
 	kfree(scb);
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index e1b9ed679045..37d1bba57b00 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -32,9 +32,8 @@ void afs_fileserver_probe_result(struct afs_call *call)
 	struct afs_server *server = call->server;
 	unsigned int server_index = call->server_index;
 	unsigned int index = call->addr_ix;
-	unsigned int rtt = UINT_MAX;
+	unsigned int rtt_us = 0;
 	bool have_result = false;
-	u64 _rtt;
 	int ret = call->error;
 
 	_enter("%pU,%u", &server->uuid, index);
@@ -93,15 +92,9 @@ responded:
 		}
 	}
 
-	/* Get the RTT and scale it to fit into a 32-bit value that represents
-	 * over a minute of time so that we can access it with one instruction
-	 * on a 32-bit system.
-	 */
-	_rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall);
-	_rtt /= 64;
-	rtt = (_rtt > UINT_MAX) ? UINT_MAX : _rtt;
-	if (rtt < server->probe.rtt) {
-		server->probe.rtt = rtt;
+	rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall);
+	if (rtt_us < server->probe.rtt) {
+		server->probe.rtt = rtt_us;
 		alist->preferred = index;
 		have_result = true;
 	}
@@ -113,15 +106,11 @@ out:
 	spin_unlock(&server->probe_lock);
 
 	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
-	       server_index, index, &alist->addrs[index].transport,
-	       (unsigned int)rtt, ret);
+	       server_index, index, &alist->addrs[index].transport, rtt_us, ret);
 
 	have_result |= afs_fs_probe_done(server);
-	if (have_result) {
-		server->probe.have_result = true;
-		wake_up_var(&server->probe.have_result);
+	if (have_result)
 		wake_up_all(&server->probe_wq);
-	}
 }
 
 /*
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 1f9c5d8e6fe5..d2b3798c1932 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -65,6 +65,7 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp,
 	bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus);
 	u64 data_version, size;
 	u32 type, abort_code;
+	int ret;
 
 	abort_code = ntohl(xdr->abort_code);
 
@@ -78,7 +79,7 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp,
 			 */
 			status->abort_code = abort_code;
 			scb->have_error = true;
-			return 0;
+			goto good;
 		}
 
 		pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version));
@@ -87,7 +88,8 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp,
 
 	if (abort_code != 0 && inline_error) {
 		status->abort_code = abort_code;
-		return 0;
+		scb->have_error = true;
+		goto good;
 	}
 
 	type = ntohl(xdr->type);
@@ -123,13 +125,16 @@ static int xdr_decode_AFSFetchStatus(const __be32 **_bp,
 	data_version |= (u64)ntohl(xdr->data_version_hi) << 32;
 	status->data_version = data_version;
 	scb->have_status = true;
-
+good:
+	ret = 0;
+advance:
 	*_bp = (const void *)*_bp + sizeof(*xdr);
-	return 0;
+	return ret;
 
 bad:
 	xdr_dump_bad(*_bp);
-	return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status);
+	ret = afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status);
+	goto advance;
 }
 
 static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry)
@@ -380,8 +385,6 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		ASSERTCMP(req->offset, <=, PAGE_SIZE);
 		if (req->offset == PAGE_SIZE) {
 			req->offset = 0;
-			if (req->page_done)
-				req->page_done(req);
 			req->index++;
 			if (req->remain > 0)
 				goto begin_page;
@@ -435,11 +438,13 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		if (req->offset < PAGE_SIZE)
 			zero_user_segment(req->pages[req->index],
 					  req->offset, PAGE_SIZE);
-		if (req->page_done)
-			req->page_done(req);
 		req->offset = 0;
 	}
 
+	if (req->page_done)
+		for (req->index = 0; req->index < req->nr_pages; req->index++)
+			req->page_done(req);
+
 	_leave(" = 0 [done]");
 	return 0;
 }
@@ -981,16 +986,16 @@ static int afs_deliver_fs_rename(struct afs_call *call)
 	if (ret < 0)
 		return ret;
 
-	/* unmarshall the reply once we've received all of it */
+	/* If the two dirs are the same, we have two copies of the same status
+	 * report, so we just decode it twice.
+	 */
 	bp = call->buffer;
 	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb);
 	if (ret < 0)
 		return ret;
-	if (call->out_dir_scb != call->out_scb) {
-		ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
-		if (ret < 0)
-			return ret;
-	}
+	ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb);
+	if (ret < 0)
+		return ret;
 	xdr_decode_AFSVolSync(&bp, call->out_volsync);
 
 	_leave(" = 0 [done]");
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index ef732dd4e7ef..80255513e230 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -533,12 +533,10 @@ struct afs_server {
 		u32		abort_code;
 		u32		cm_epoch;
 		short		error;
-		bool		have_result;
 		bool		responded:1;
 		bool		is_yfs:1;
 		bool		not_yfs:1;
 		bool		local_failure:1;
-		bool		no_epoch:1;
 		bool		cm_probed:1;
 		bool		said_rebooted:1;
 		bool		said_inconsistent:1;
@@ -1335,7 +1333,7 @@ extern struct afs_volume *afs_create_volume(struct afs_fs_context *);
 extern void afs_activate_volume(struct afs_volume *);
 extern void afs_deactivate_volume(struct afs_volume *);
 extern void afs_put_volume(struct afs_cell *, struct afs_volume *);
-extern int afs_check_volume_status(struct afs_volume *, struct key *);
+extern int afs_check_volume_status(struct afs_volume *, struct afs_fs_cursor *);
 
 /*
  * write.c
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 172ba569cd60..2a3305e42b14 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -192,7 +192,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 			write_unlock(&vnode->volume->servers_lock);
 
 			set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags);
-			error = afs_check_volume_status(vnode->volume, fc->key);
+			error = afs_check_volume_status(vnode->volume, fc);
 			if (error < 0)
 				goto failed_set_error;
 
@@ -281,7 +281,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 
 			set_bit(AFS_VOLUME_WAIT, &vnode->volume->flags);
 			set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags);
-			error = afs_check_volume_status(vnode->volume, fc->key);
+			error = afs_check_volume_status(vnode->volume, fc);
 			if (error < 0)
 				goto failed_set_error;
 
@@ -341,7 +341,7 @@ start:
 	/* See if we need to do an update of the volume record.  Note that the
 	 * volume may have moved or even have been deleted.
 	 */
-	error = afs_check_volume_status(vnode->volume, fc->key);
+	error = afs_check_volume_status(vnode->volume, fc);
 	if (error < 0)
 		goto failed_set_error;
 
diff --git a/fs/afs/server.c b/fs/afs/server.c
index b7f3cb2130ca..11b90ac7ea30 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -594,12 +594,9 @@ retry:
 	}
 
 	ret = wait_on_bit(&server->flags, AFS_SERVER_FL_UPDATING,
-			  TASK_INTERRUPTIBLE);
+			  (fc->flags & AFS_FS_CURSOR_INTR) ?
+			  TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 	if (ret == -ERESTARTSYS) {
-		if (!(fc->flags & AFS_FS_CURSOR_INTR) && server->addresses) {
-			_leave(" = t [intr]");
-			return true;
-		}
 		fc->error = ret;
 		_leave(" = f [intr]");
 		return false;
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index 858498cc1b05..e3aa013c2177 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -31,10 +31,9 @@ void afs_vlserver_probe_result(struct afs_call *call)
 	struct afs_addr_list *alist = call->alist;
 	struct afs_vlserver *server = call->vlserver;
 	unsigned int server_index = call->server_index;
+	unsigned int rtt_us = 0;
 	unsigned int index = call->addr_ix;
-	unsigned int rtt = UINT_MAX;
 	bool have_result = false;
-	u64 _rtt;
 	int ret = call->error;
 
 	_enter("%s,%u,%u,%d,%d", server->name, server_index, index, ret, call->abort_code);
@@ -93,15 +92,9 @@ responded:
 		}
 	}
 
-	/* Get the RTT and scale it to fit into a 32-bit value that represents
-	 * over a minute of time so that we can access it with one instruction
-	 * on a 32-bit system.
-	 */
-	_rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall);
-	_rtt /= 64;
-	rtt = (_rtt > UINT_MAX) ? UINT_MAX : _rtt;
-	if (rtt < server->probe.rtt) {
-		server->probe.rtt = rtt;
+	rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall);
+	if (rtt_us < server->probe.rtt) {
+		server->probe.rtt = rtt_us;
 		alist->preferred = index;
 		have_result = true;
 	}
@@ -113,8 +106,7 @@ out:
 	spin_unlock(&server->probe_lock);
 
 	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
-	       server_index, index, &alist->addrs[index].transport,
-	       (unsigned int)rtt, ret);
+	       server_index, index, &alist->addrs[index].transport, rtt_us, ret);
 
 	have_result |= afs_vl_probe_done(server);
 	if (have_result) {
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index 9a5ce9687779..72eacc14e6e1 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -302,8 +302,8 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 				pr_notice("VC:  - nr=%u/%u/%u pf=%u\n",
 					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
 					  a->preferred);
-				pr_notice("VC:  - pr=%lx R=%lx F=%lx\n",
-					  a->probed, a->responded, a->failed);
+				pr_notice("VC:  - R=%lx F=%lx\n",
+					  a->responded, a->failed);
 				if (a == vc->ac.alist)
 					pr_notice("VC:  - current\n");
 			}
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 92ca5e27573b..4310336b9bb8 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -281,7 +281,7 @@ error:
 /*
  * Make sure the volume record is up to date.
  */
-int afs_check_volume_status(struct afs_volume *volume, struct key *key)
+int afs_check_volume_status(struct afs_volume *volume, struct afs_fs_cursor *fc)
 {
 	time64_t now = ktime_get_real_seconds();
 	int ret, retries = 0;
@@ -299,7 +299,7 @@ retry:
 	}
 
 	if (!test_and_set_bit_lock(AFS_VOLUME_UPDATING, &volume->flags)) {
-		ret = afs_update_volume_status(volume, key);
+		ret = afs_update_volume_status(volume, fc->key);
 		clear_bit_unlock(AFS_VOLUME_WAIT, &volume->flags);
 		clear_bit_unlock(AFS_VOLUME_UPDATING, &volume->flags);
 		wake_up_bit(&volume->flags, AFS_VOLUME_WAIT);
@@ -312,7 +312,9 @@ retry:
 		return 0;
 	}
 
-	ret = wait_on_bit(&volume->flags, AFS_VOLUME_WAIT, TASK_INTERRUPTIBLE);
+	ret = wait_on_bit(&volume->flags, AFS_VOLUME_WAIT,
+			  (fc->flags & AFS_FS_CURSOR_INTR) ?
+			  TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 	if (ret == -ERESTARTSYS) {
 		_leave(" = %d", ret);
 		return ret;
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index a26126ac7bf1..fe413e7a5cf4 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -165,15 +165,15 @@ static void xdr_dump_bad(const __be32 *bp)
 	int i;
 
 	pr_notice("YFS XDR: Bad status record\n");
-	for (i = 0; i < 5 * 4 * 4; i += 16) {
+	for (i = 0; i < 6 * 4 * 4; i += 16) {
 		memcpy(x, bp, 16);
 		bp += 4;
 		pr_notice("%03x: %08x %08x %08x %08x\n",
 			  i, ntohl(x[0]), ntohl(x[1]), ntohl(x[2]), ntohl(x[3]));
 	}
 
-	memcpy(x, bp, 4);
-	pr_notice("0x50: %08x\n", ntohl(x[0]));
+	memcpy(x, bp, 8);
+	pr_notice("0x60: %08x %08x\n", ntohl(x[0]), ntohl(x[1]));
 }
 
 /*
@@ -186,13 +186,14 @@ static int xdr_decode_YFSFetchStatus(const __be32 **_bp,
 	const struct yfs_xdr_YFSFetchStatus *xdr = (const void *)*_bp;
 	struct afs_file_status *status = &scb->status;
 	u32 type;
+	int ret;
 
 	status->abort_code = ntohl(xdr->abort_code);
 	if (status->abort_code != 0) {
 		if (status->abort_code == VNOVNODE)
 			status->nlink = 0;
 		scb->have_error = true;
-		return 0;
+		goto good;
 	}
 
 	type = ntohl(xdr->type);
@@ -220,13 +221,16 @@ static int xdr_decode_YFSFetchStatus(const __be32 **_bp,
 	status->size		= xdr_to_u64(xdr->size);
 	status->data_version	= xdr_to_u64(xdr->data_version);
 	scb->have_status	= true;
-
+good:
+	ret = 0;
+advance:
 	*_bp += xdr_size(xdr);
-	return 0;
+	return ret;
 
 bad:
 	xdr_dump_bad(*_bp);
-	return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status);
+	ret = afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status);
+	goto advance;
 }
 
 /*
@@ -493,8 +497,6 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		ASSERTCMP(req->offset, <=, PAGE_SIZE);
 		if (req->offset == PAGE_SIZE) {
 			req->offset = 0;
-			if (req->page_done)
-				req->page_done(req);
 			req->index++;
 			if (req->remain > 0)
 				goto begin_page;
@@ -552,11 +554,13 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		if (req->offset < PAGE_SIZE)
 			zero_user_segment(req->pages[req->index],
 					  req->offset, PAGE_SIZE);
-		if (req->page_done)
-			req->page_done(req);
 		req->offset = 0;
 	}
 
+	if (req->page_done)
+		for (req->index = 0; req->index < req->nr_pages; req->index++)
+			req->page_done(req);
+
 	_leave(" = 0 [done]");
 	return 0;
 }
@@ -1153,11 +1157,9 @@ static int yfs_deliver_fs_rename(struct afs_call *call)
 	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb);
 	if (ret < 0)
 		return ret;
-	if (call->out_dir_scb != call->out_scb) {
-		ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
-		if (ret < 0)
-			return ret;
-	}
+	ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb);
+	if (ret < 0)
+		return ret;
 
 	xdr_decode_YFSVolSync(&bp, call->out_volsync);
 	_leave(" = 0 [done]");
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 13f25e241ac4..92402c5606a1 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -40,12 +40,18 @@
 #include <linux/sched/coredump.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/sizes.h>
+#include <linux/types.h>
 #include <linux/cred.h>
 #include <linux/dax.h>
 #include <linux/uaccess.h>
 #include <asm/param.h>
 #include <asm/page.h>
 
+#ifndef ELF_COMPAT
+#define ELF_COMPAT 0
+#endif
+
 #ifndef user_long_t
 #define user_long_t long
 #endif
@@ -539,7 +545,8 @@ static inline int arch_check_elf(struct elfhdr *ehdr, bool has_interp,
 
 #endif /* !CONFIG_ARCH_BINFMT_ELF_STATE */
 
-static inline int make_prot(u32 p_flags)
+static inline int make_prot(u32 p_flags, struct arch_elf_state *arch_state,
+			    bool has_interp, bool is_interp)
 {
 	int prot = 0;
 
@@ -549,7 +556,8 @@ static inline int make_prot(u32 p_flags)
 		prot |= PROT_WRITE;
 	if (p_flags & PF_X)
 		prot |= PROT_EXEC;
-	return prot;
+
+	return arch_elf_adjust_prot(prot, arch_state, has_interp, is_interp);
 }
 
 /* This is much more generalized than the library routine read function,
@@ -559,7 +567,8 @@ static inline int make_prot(u32 p_flags)
 
 static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 		struct file *interpreter,
-		unsigned long no_base, struct elf_phdr *interp_elf_phdata)
+		unsigned long no_base, struct elf_phdr *interp_elf_phdata,
+		struct arch_elf_state *arch_state)
 {
 	struct elf_phdr *eppnt;
 	unsigned long load_addr = 0;
@@ -591,7 +600,8 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 	for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) {
 		if (eppnt->p_type == PT_LOAD) {
 			int elf_type = MAP_PRIVATE | MAP_DENYWRITE;
-			int elf_prot = make_prot(eppnt->p_flags);
+			int elf_prot = make_prot(eppnt->p_flags, arch_state,
+						 true, true);
 			unsigned long vaddr = 0;
 			unsigned long k, map_addr;
 
@@ -682,6 +692,111 @@ out:
  * libraries.  There is no binary dependent code anywhere else.
  */
 
+static int parse_elf_property(const char *data, size_t *off, size_t datasz,
+			      struct arch_elf_state *arch,
+			      bool have_prev_type, u32 *prev_type)
+{
+	size_t o, step;
+	const struct gnu_property *pr;
+	int ret;
+
+	if (*off == datasz)
+		return -ENOENT;
+
+	if (WARN_ON_ONCE(*off > datasz || *off % ELF_GNU_PROPERTY_ALIGN))
+		return -EIO;
+	o = *off;
+	datasz -= *off;
+
+	if (datasz < sizeof(*pr))
+		return -ENOEXEC;
+	pr = (const struct gnu_property *)(data + o);
+	o += sizeof(*pr);
+	datasz -= sizeof(*pr);
+
+	if (pr->pr_datasz > datasz)
+		return -ENOEXEC;
+
+	WARN_ON_ONCE(o % ELF_GNU_PROPERTY_ALIGN);
+	step = round_up(pr->pr_datasz, ELF_GNU_PROPERTY_ALIGN);
+	if (step > datasz)
+		return -ENOEXEC;
+
+	/* Properties are supposed to be unique and sorted on pr_type: */
+	if (have_prev_type && pr->pr_type <= *prev_type)
+		return -ENOEXEC;
+	*prev_type = pr->pr_type;
+
+	ret = arch_parse_elf_property(pr->pr_type, data + o,
+				      pr->pr_datasz, ELF_COMPAT, arch);
+	if (ret)
+		return ret;
+
+	*off = o + step;
+	return 0;
+}
+
+#define NOTE_DATA_SZ SZ_1K
+#define GNU_PROPERTY_TYPE_0_NAME "GNU"
+#define NOTE_NAME_SZ (sizeof(GNU_PROPERTY_TYPE_0_NAME))
+
+static int parse_elf_properties(struct file *f, const struct elf_phdr *phdr,
+				struct arch_elf_state *arch)
+{
+	union {
+		struct elf_note nhdr;
+		char data[NOTE_DATA_SZ];
+	} note;
+	loff_t pos;
+	ssize_t n;
+	size_t off, datasz;
+	int ret;
+	bool have_prev_type;
+	u32 prev_type;
+
+	if (!IS_ENABLED(CONFIG_ARCH_USE_GNU_PROPERTY) || !phdr)
+		return 0;
+
+	/* load_elf_binary() shouldn't call us unless this is true... */
+	if (WARN_ON_ONCE(phdr->p_type != PT_GNU_PROPERTY))
+		return -ENOEXEC;
+
+	/* If the properties are crazy large, that's too bad (for now): */
+	if (phdr->p_filesz > sizeof(note))
+		return -ENOEXEC;
+
+	pos = phdr->p_offset;
+	n = kernel_read(f, &note, phdr->p_filesz, &pos);
+
+	BUILD_BUG_ON(sizeof(note) < sizeof(note.nhdr) + NOTE_NAME_SZ);
+	if (n < 0 || n < sizeof(note.nhdr) + NOTE_NAME_SZ)
+		return -EIO;
+
+	if (note.nhdr.n_type != NT_GNU_PROPERTY_TYPE_0 ||
+	    note.nhdr.n_namesz != NOTE_NAME_SZ ||
+	    strncmp(note.data + sizeof(note.nhdr),
+		    GNU_PROPERTY_TYPE_0_NAME, n - sizeof(note.nhdr)))
+		return -ENOEXEC;
+
+	off = round_up(sizeof(note.nhdr) + NOTE_NAME_SZ,
+		       ELF_GNU_PROPERTY_ALIGN);
+	if (off > n)
+		return -ENOEXEC;
+
+	if (note.nhdr.n_descsz > n - off)
+		return -ENOEXEC;
+	datasz = off + note.nhdr.n_descsz;
+
+	have_prev_type = false;
+	do {
+		ret = parse_elf_property(note.data, &off, datasz, arch,
+					 have_prev_type, &prev_type);
+		have_prev_type = true;
+	} while (!ret);
+
+	return ret == -ENOENT ? 0 : ret;
+}
+
 static int load_elf_binary(struct linux_binprm *bprm)
 {
 	struct file *interpreter = NULL; /* to shut gcc up */
@@ -689,6 +804,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	int load_addr_set = 0;
 	unsigned long error;
 	struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL;
+	struct elf_phdr *elf_property_phdata = NULL;
 	unsigned long elf_bss, elf_brk;
 	int bss_prot = 0;
 	int retval, i;
@@ -726,6 +842,11 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	for (i = 0; i < elf_ex->e_phnum; i++, elf_ppnt++) {
 		char *elf_interpreter;
 
+		if (elf_ppnt->p_type == PT_GNU_PROPERTY) {
+			elf_property_phdata = elf_ppnt;
+			continue;
+		}
+
 		if (elf_ppnt->p_type != PT_INTERP)
 			continue;
 
@@ -819,9 +940,14 @@ out_free_interp:
 			goto out_free_dentry;
 
 		/* Pass PT_LOPROC..PT_HIPROC headers to arch code */
+		elf_property_phdata = NULL;
 		elf_ppnt = interp_elf_phdata;
 		for (i = 0; i < interp_elf_ex->e_phnum; i++, elf_ppnt++)
 			switch (elf_ppnt->p_type) {
+			case PT_GNU_PROPERTY:
+				elf_property_phdata = elf_ppnt;
+				break;
+
 			case PT_LOPROC ... PT_HIPROC:
 				retval = arch_elf_pt_proc(interp_elf_ex,
 							  elf_ppnt, interpreter,
@@ -832,6 +958,11 @@ out_free_interp:
 			}
 	}
 
+	retval = parse_elf_properties(interpreter ?: bprm->file,
+				      elf_property_phdata, &arch_state);
+	if (retval)
+		goto out_free_dentry;
+
 	/*
 	 * Allow arch code to reject the ELF at this point, whilst it's
 	 * still possible to return an error to the code that invoked
@@ -913,7 +1044,8 @@ out_free_interp:
 			}
 		}
 
-		elf_prot = make_prot(elf_ppnt->p_flags);
+		elf_prot = make_prot(elf_ppnt->p_flags, &arch_state,
+				     !!interpreter, false);
 
 		elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE;
 
@@ -1056,7 +1188,8 @@ out_free_interp:
 	if (interpreter) {
 		elf_entry = load_elf_interp(interp_elf_ex,
 					    interpreter,
-					    load_bias, interp_elf_phdata);
+					    load_bias, interp_elf_phdata,
+					    &arch_state);
 		if (!IS_ERR((void *)elf_entry)) {
 			/*
 			 * load_elf_interp() returns relocation
@@ -1733,7 +1866,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 		    (!regset->active || regset->active(t->task, regset) > 0)) {
 			int ret;
 			size_t size = regset_size(t->task, regset);
-			void *data = kmalloc(size, GFP_KERNEL);
+			void *data = kzalloc(size, GFP_KERNEL);
 			if (unlikely(!data))
 				return 0;
 			ret = regset->get(t->task, regset,
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 52b6f646cdbd..93672c3f1c78 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -19,7 +19,6 @@
 #include <linux/module.h>
 #include <linux/blkpg.h>
 #include <linux/magic.h>
-#include <linux/dax.h>
 #include <linux/buffer_head.h>
 #include <linux/swap.h>
 #include <linux/pagevec.h>
@@ -1893,6 +1892,16 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 	struct gendisk *disk = bdev->bd_disk;
 	struct block_device *victim = NULL;
 
+	/*
+	 * Sync early if it looks like we're the last one.  If someone else
+	 * opens the block device between now and the decrement of bd_openers
+	 * then we did a sync that we didn't need to, but that's not the end
+	 * of the world and we want to avoid long (could be several minute)
+	 * syncs while holding the mutex.
+	 */
+	if (bdev->bd_openers == 1)
+		sync_blockdev(bdev);
+
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (for_part)
 		bdev->bd_part_count--;
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 9c380e7edf62..0cc02577577b 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -391,7 +391,7 @@ static int is_shared_data_backref(struct preftrees *preftrees, u64 bytenr)
 	struct rb_node **p = &preftrees->direct.root.rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct prelim_ref *ref = NULL;
-	struct prelim_ref target = {0};
+	struct prelim_ref target = {};
 	int result;
 
 	target.parent = bytenr;
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 786849fcc319..696f47103cfc 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -916,7 +916,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_put_group;
 	}
 
 	/*
@@ -954,7 +954,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		if (ret) {
 			btrfs_add_delayed_iput(inode);
-			goto out;
+			goto out_put_group;
 		}
 		clear_nlink(inode);
 		/* One for the block groups ref */
@@ -977,13 +977,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
 	if (ret < 0)
-		goto out;
+		goto out_put_group;
 	if (ret > 0)
 		btrfs_release_path(path);
 	if (ret == 0) {
 		ret = btrfs_del_item(trans, tree_root, path);
 		if (ret)
-			goto out;
+			goto out_put_group;
 		btrfs_release_path(path);
 	}
 
@@ -1102,9 +1102,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	ret = remove_block_group_free_space(trans, block_group);
 	if (ret)
-		goto out;
+		goto out_put_group;
 
-	btrfs_put_block_group(block_group);
+	/* Once for the block groups rbtree */
 	btrfs_put_block_group(block_group);
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
@@ -1127,6 +1127,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		/* once for the tree */
 		free_extent_map(em);
 	}
+
+out_put_group:
+	/* Once for the lookup reference */
+	btrfs_put_block_group(block_group);
 out:
 	if (remove_rsv)
 		btrfs_delayed_refs_rsv_release(fs_info, 1);
@@ -1288,11 +1292,15 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto err;
 	mutex_unlock(&fs_info->unused_bg_unpin_mutex);
+	if (prev_trans)
+		btrfs_put_transaction(prev_trans);
 
 	return true;
 
 err:
 	mutex_unlock(&fs_info->unused_bg_unpin_mutex);
+	if (prev_trans)
+		btrfs_put_transaction(prev_trans);
 	btrfs_dec_block_group_ro(bg);
 	return false;
 }
@@ -3370,6 +3378,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 			    space_info->bytes_reserved > 0 ||
 			    space_info->bytes_may_use > 0))
 			btrfs_dump_space_info(info, space_info, 0, 0);
+		WARN_ON(space_info->reclaim_size > 0);
 		list_del(&space_info->list);
 		btrfs_sysfs_remove_space_info(space_info);
 	}
diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h
index 21a15776dac4..353228d62f5a 100644
--- a/fs/btrfs/discard.h
+++ b/fs/btrfs/discard.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifndef BTRFS_DISCARD_H
 #define BTRFS_DISCARD_H
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a6cb5cbbdb9f..d10c7be10f3b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2036,9 +2036,6 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
 		for (i = 0; i < ret; i++)
 			btrfs_drop_and_free_fs_root(fs_info, gang[i]);
 	}
-
-	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
-		btrfs_free_log_root_tree(NULL, fs_info);
 }
 
 static void btrfs_init_scrub(struct btrfs_fs_info *fs_info)
@@ -3888,7 +3885,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 	spin_unlock(&fs_info->fs_roots_radix_lock);
 
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
-		btrfs_free_log(NULL, root);
+		ASSERT(root->log_root == NULL);
 		if (root->reloc_root) {
 			btrfs_put_root(root->reloc_root);
 			root->reloc_root = NULL;
@@ -4211,6 +4208,36 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
 	up_write(&fs_info->cleanup_work_sem);
 }
 
+static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_root *gang[8];
+	u64 root_objectid = 0;
+	int ret;
+
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+					     (void **)gang, root_objectid,
+					     ARRAY_SIZE(gang))) != 0) {
+		int i;
+
+		for (i = 0; i < ret; i++)
+			gang[i] = btrfs_grab_root(gang[i]);
+		spin_unlock(&fs_info->fs_roots_radix_lock);
+
+		for (i = 0; i < ret; i++) {
+			if (!gang[i])
+				continue;
+			root_objectid = gang[i]->root_key.objectid;
+			btrfs_free_log(NULL, gang[i]);
+			btrfs_put_root(gang[i]);
+		}
+		root_objectid++;
+		spin_lock(&fs_info->fs_roots_radix_lock);
+	}
+	spin_unlock(&fs_info->fs_roots_radix_lock);
+	btrfs_free_log_root_tree(NULL, fs_info);
+}
+
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
 {
 	struct btrfs_ordered_extent *ordered;
@@ -4603,6 +4630,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_delayed_inodes(fs_info);
 	btrfs_assert_delayed_root_empty(fs_info);
 	btrfs_destroy_all_delalloc_inodes(fs_info);
+	btrfs_drop_all_logs(fs_info);
 	mutex_unlock(&fs_info->transaction_kthread_mutex);
 
 	return 0;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 8a144f9cb7ac..719e68ab552c 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2098,6 +2098,21 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	atomic_inc(&root->log_batch);
 
 	/*
+	 * If the inode needs a full sync, make sure we use a full range to
+	 * avoid log tree corruption, due to hole detection racing with ordered
+	 * extent completion for adjacent ranges and races between logging and
+	 * completion of ordered extents for adjancent ranges - both races
+	 * could lead to file extent items in the log with overlapping ranges.
+	 * Do this while holding the inode lock, to avoid races with other
+	 * tasks.
+	 */
+	if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+		     &BTRFS_I(inode)->runtime_flags)) {
+		start = 0;
+		end = LLONG_MAX;
+	}
+
+	/*
 	 * Before we acquired the inode's lock, someone may have dirtied more
 	 * pages in the target range. We need to make sure that writeback for
 	 * any such pages does not start while we are logging the inode, because
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index d1973141d3bb..040009d1cc31 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -264,6 +264,7 @@ copy_inline_extent:
 			    size);
 	inode_add_bytes(dst, datal);
 	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(dst)->runtime_flags);
+	ret = btrfs_inode_set_file_extent_range(BTRFS_I(dst), 0, aligned_end);
 out:
 	if (!ret && !trans) {
 		/*
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index f65595602aa8..03bc7134e8cb 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -611,8 +611,8 @@ static int should_ignore_root(struct btrfs_root *root)
 	if (!reloc_root)
 		return 0;
 
-	if (btrfs_root_last_snapshot(&reloc_root->root_item) ==
-	    root->fs_info->running_transaction->transid - 1)
+	if (btrfs_header_generation(reloc_root->commit_root) ==
+	    root->fs_info->running_transaction->transid)
 		return 0;
 	/*
 	 * if there is reloc tree and it was created in previous
@@ -1527,8 +1527,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
 	int clear_rsv = 0;
 	int ret;
 
-	if (!rc || !rc->create_reloc_tree ||
-	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+	if (!rc)
 		return 0;
 
 	/*
@@ -1538,12 +1537,28 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
 	if (reloc_root_is_dead(root))
 		return 0;
 
+	/*
+	 * This is subtle but important.  We do not do
+	 * record_root_in_transaction for reloc roots, instead we record their
+	 * corresponding fs root, and then here we update the last trans for the
+	 * reloc root.  This means that we have to do this for the entire life
+	 * of the reloc root, regardless of which stage of the relocation we are
+	 * in.
+	 */
 	if (root->reloc_root) {
 		reloc_root = root->reloc_root;
 		reloc_root->last_trans = trans->transid;
 		return 0;
 	}
 
+	/*
+	 * We are merging reloc roots, we do not need new reloc trees.  Also
+	 * reloc trees never need their own reloc tree.
+	 */
+	if (!rc->create_reloc_tree ||
+	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+		return 0;
+
 	if (!trans->reloc_reserved) {
 		rsv = trans->block_rsv;
 		trans->block_rsv = rc->block_rsv;
@@ -4544,6 +4559,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 		if (IS_ERR(fs_root)) {
 			err = PTR_ERR(fs_root);
 			list_add_tail(&reloc_root->root_list, &reloc_roots);
+			btrfs_end_transaction(trans);
 			goto out_unset;
 		}
 
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 8b0fe053a25d..ff17a4420358 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -361,6 +361,16 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+static void remove_ticket(struct btrfs_space_info *space_info,
+			  struct reserve_ticket *ticket)
+{
+	if (!list_empty(&ticket->list)) {
+		list_del_init(&ticket->list);
+		ASSERT(space_info->reclaim_size >= ticket->bytes);
+		space_info->reclaim_size -= ticket->bytes;
+	}
+}
+
 /*
  * This is for space we already have accounted in space_info->bytes_may_use, so
  * basically when we're returning space from block_rsv's.
@@ -388,9 +398,7 @@ again:
 			btrfs_space_info_update_bytes_may_use(fs_info,
 							      space_info,
 							      ticket->bytes);
-			list_del_init(&ticket->list);
-			ASSERT(space_info->reclaim_size >= ticket->bytes);
-			space_info->reclaim_size -= ticket->bytes;
+			remove_ticket(space_info, ticket);
 			ticket->bytes = 0;
 			space_info->tickets_id++;
 			wake_up(&ticket->wait);
@@ -899,7 +907,7 @@ static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info,
 			btrfs_info(fs_info, "failing ticket with %llu bytes",
 				   ticket->bytes);
 
-		list_del_init(&ticket->list);
+		remove_ticket(space_info, ticket);
 		ticket->error = -ENOSPC;
 		wake_up(&ticket->wait);
 
@@ -1063,7 +1071,7 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info,
 			 * despite getting an error, resulting in a space leak
 			 * (bytes_may_use counter of our space_info).
 			 */
-			list_del_init(&ticket->list);
+			remove_ticket(space_info, ticket);
 			ticket->error = -EINTR;
 			break;
 		}
@@ -1121,7 +1129,7 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info,
 		 * either the async reclaim job deletes the ticket from the list
 		 * or we delete it ourselves at wait_reserve_ticket().
 		 */
-		list_del_init(&ticket->list);
+		remove_ticket(space_info, ticket);
 		if (!ret)
 			ret = -ENOSPC;
 	}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8cede6eb9843..2d5498136e5e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -662,10 +662,19 @@ again:
 	}
 
 got_it:
-	btrfs_record_root_in_trans(h, root);
-
 	if (!current->journal_info)
 		current->journal_info = h;
+
+	/*
+	 * btrfs_record_root_in_trans() needs to alloc new extents, and may
+	 * call btrfs_join_transaction() while we're also starting a
+	 * transaction.
+	 *
+	 * Thus it need to be called after current->journal_info initialized,
+	 * or we can deadlock.
+	 */
+	btrfs_record_root_in_trans(h, root);
+
 	return h;
 
 join_fail:
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 58c111474ba5..02ebdd9edc19 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -96,8 +96,8 @@ enum {
 static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, struct btrfs_inode *inode,
 			   int inode_only,
-			   u64 start,
-			   u64 end,
+			   const loff_t start,
+			   const loff_t end,
 			   struct btrfs_log_ctx *ctx);
 static int link_to_fixup_dir(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
@@ -4226,6 +4226,9 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	const u64 ino = btrfs_ino(inode);
 	struct btrfs_path *dst_path = NULL;
 	bool dropped_extents = false;
+	u64 truncate_offset = i_size;
+	struct extent_buffer *leaf;
+	int slot;
 	int ins_nr = 0;
 	int start_slot;
 	int ret;
@@ -4240,9 +4243,43 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 	if (ret < 0)
 		goto out;
 
+	/*
+	 * We must check if there is a prealloc extent that starts before the
+	 * i_size and crosses the i_size boundary. This is to ensure later we
+	 * truncate down to the end of that extent and not to the i_size, as
+	 * otherwise we end up losing part of the prealloc extent after a log
+	 * replay and with an implicit hole if there is another prealloc extent
+	 * that starts at an offset beyond i_size.
+	 */
+	ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY);
+	if (ret < 0)
+		goto out;
+
+	if (ret == 0) {
+		struct btrfs_file_extent_item *ei;
+
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+
+		if (btrfs_file_extent_type(leaf, ei) ==
+		    BTRFS_FILE_EXTENT_PREALLOC) {
+			u64 extent_end;
+
+			btrfs_item_key_to_cpu(leaf, &key, slot);
+			extent_end = key.offset +
+				btrfs_file_extent_num_bytes(leaf, ei);
+
+			if (extent_end > i_size)
+				truncate_offset = extent_end;
+		}
+	} else {
+		ret = 0;
+	}
+
 	while (true) {
-		struct extent_buffer *leaf = path->nodes[0];
-		int slot = path->slots[0];
+		leaf = path->nodes[0];
+		slot = path->slots[0];
 
 		if (slot >= btrfs_header_nritems(leaf)) {
 			if (ins_nr > 0) {
@@ -4280,7 +4317,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 				ret = btrfs_truncate_inode_items(trans,
 							 root->log_root,
 							 &inode->vfs_inode,
-							 i_size,
+							 truncate_offset,
 							 BTRFS_EXTENT_DATA_KEY);
 			} while (ret == -EAGAIN);
 			if (ret)
@@ -4533,15 +4570,13 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 static int btrfs_log_holes(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct btrfs_inode *inode,
-			   struct btrfs_path *path,
-			   const u64 start,
-			   const u64 end)
+			   struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_key key;
 	const u64 ino = btrfs_ino(inode);
 	const u64 i_size = i_size_read(&inode->vfs_inode);
-	u64 prev_extent_end = start;
+	u64 prev_extent_end = 0;
 	int ret;
 
 	if (!btrfs_fs_incompat(fs_info, NO_HOLES) || i_size == 0)
@@ -4549,21 +4584,14 @@ static int btrfs_log_holes(struct btrfs_trans_handle *trans,
 
 	key.objectid = ino;
 	key.type = BTRFS_EXTENT_DATA_KEY;
-	key.offset = start;
+	key.offset = 0;
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		return ret;
 
-	if (ret > 0 && path->slots[0] > 0) {
-		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1);
-		if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY)
-			path->slots[0]--;
-	}
-
 	while (true) {
 		struct extent_buffer *leaf = path->nodes[0];
-		u64 extent_end;
 
 		if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
 			ret = btrfs_next_leaf(root, path);
@@ -4580,18 +4608,9 @@ static int btrfs_log_holes(struct btrfs_trans_handle *trans,
 		if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY)
 			break;
 
-		extent_end = btrfs_file_extent_end(path);
-		if (extent_end <= start)
-			goto next_slot;
-
 		/* We have a hole, log it. */
 		if (prev_extent_end < key.offset) {
-			u64 hole_len;
-
-			if (key.offset >= end)
-				hole_len = end - prev_extent_end;
-			else
-				hole_len = key.offset - prev_extent_end;
+			const u64 hole_len = key.offset - prev_extent_end;
 
 			/*
 			 * Release the path to avoid deadlocks with other code
@@ -4621,20 +4640,16 @@ static int btrfs_log_holes(struct btrfs_trans_handle *trans,
 			leaf = path->nodes[0];
 		}
 
-		prev_extent_end = min(extent_end, end);
-		if (extent_end >= end)
-			break;
-next_slot:
+		prev_extent_end = btrfs_file_extent_end(path);
 		path->slots[0]++;
 		cond_resched();
 	}
 
-	if (prev_extent_end < end && prev_extent_end < i_size) {
+	if (prev_extent_end < i_size) {
 		u64 hole_len;
 
 		btrfs_release_path(path);
-		hole_len = min(ALIGN(i_size, fs_info->sectorsize), end);
-		hole_len -= prev_extent_end;
+		hole_len = ALIGN(i_size - prev_extent_end, fs_info->sectorsize);
 		ret = btrfs_insert_file_extent(trans, root->log_root,
 					       ino, prev_extent_end, 0, 0,
 					       hole_len, 0, hole_len,
@@ -4971,8 +4986,6 @@ static int copy_inode_items_to_log(struct btrfs_trans_handle *trans,
 				   const u64 logged_isize,
 				   const bool recursive_logging,
 				   const int inode_only,
-				   const u64 start,
-				   const u64 end,
 				   struct btrfs_log_ctx *ctx,
 				   bool *need_log_inode_item)
 {
@@ -4981,21 +4994,6 @@ static int copy_inode_items_to_log(struct btrfs_trans_handle *trans,
 	int ins_nr = 0;
 	int ret;
 
-	/*
-	 * We must make sure we don't copy extent items that are entirely out of
-	 * the range [start, end - 1]. This is not just an optimization to avoid
-	 * copying but also needed to avoid a corruption where we end up with
-	 * file extent items in the log tree that have overlapping ranges - this
-	 * can happen if we race with ordered extent completion for ranges that
-	 * are outside our target range. For example we copy an extent item and
-	 * when we move to the next leaf, that extent was trimmed and a new one
-	 * covering a subrange of it, but with a higher key, was inserted - we
-	 * would then copy this other extent too, resulting in a log tree with
-	 * 2 extent items that represent overlapping ranges.
-	 *
-	 * We can copy the entire extents at the range bondaries however, even
-	 * if they cover an area outside the target range. That's ok.
-	 */
 	while (1) {
 		ret = btrfs_search_forward(root, min_key, path, trans->transid);
 		if (ret < 0)
@@ -5063,29 +5061,6 @@ again:
 			goto next_slot;
 		}
 
-		if (min_key->type == BTRFS_EXTENT_DATA_KEY) {
-			const u64 extent_end = btrfs_file_extent_end(path);
-
-			if (extent_end <= start) {
-				if (ins_nr > 0) {
-					ret = copy_items(trans, inode, dst_path,
-							 path, ins_start_slot,
-							 ins_nr, inode_only,
-							 logged_isize);
-					if (ret < 0)
-						return ret;
-					ins_nr = 0;
-				}
-				goto next_slot;
-			}
-			if (extent_end >= end) {
-				ins_nr++;
-				if (ins_nr == 1)
-					ins_start_slot = path->slots[0];
-				break;
-			}
-		}
-
 		if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) {
 			ins_nr++;
 			goto next_slot;
@@ -5151,8 +5126,8 @@ next_key:
 static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, struct btrfs_inode *inode,
 			   int inode_only,
-			   u64 start,
-			   u64 end,
+			   const loff_t start,
+			   const loff_t end,
 			   struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -5180,9 +5155,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	}
 
-	start = ALIGN_DOWN(start, fs_info->sectorsize);
-	end = ALIGN(end, fs_info->sectorsize);
-
 	min_key.objectid = ino;
 	min_key.type = BTRFS_INODE_ITEM_KEY;
 	min_key.offset = 0;
@@ -5298,8 +5270,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
 	err = copy_inode_items_to_log(trans, inode, &min_key, &max_key,
 				      path, dst_path, logged_isize,
-				      recursive_logging, inode_only,
-				      start, end, ctx, &need_log_inode_item);
+				      recursive_logging, inode_only, ctx,
+				      &need_log_inode_item);
 	if (err)
 		goto out_unlock;
 
@@ -5312,7 +5284,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
 		btrfs_release_path(path);
 		btrfs_release_path(dst_path);
-		err = btrfs_log_holes(trans, root, inode, path, start, end);
+		err = btrfs_log_holes(trans, root, inode, path);
 		if (err)
 			goto out_unlock;
 	}
diff --git a/fs/buffer.c b/fs/buffer.c
index f73276d746bb..a60f60396cfa 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -967,7 +967,7 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	struct page *page;
 	struct buffer_head *bh;
 	sector_t end_block;
-	int ret = 0;		/* Will call free_more_memory() */
+	int ret = 0;
 	gfp_t gfp_mask;
 
 	gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp;
@@ -1371,6 +1371,17 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
 }
 EXPORT_SYMBOL(__breadahead);
 
+void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size,
+		      gfp_t gfp)
+{
+	struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
+	if (likely(bh)) {
+		ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+		brelse(bh);
+	}
+}
+EXPORT_SYMBOL(__breadahead_gfp);
+
 /**
  *  __bread_gfp() - reads a specified block and returns the bh
  *  @bdev: the block_device to read from
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 1dc97f2d6201..e7726f5f1241 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -60,9 +60,9 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 	object = container_of(op->op.object, struct cachefiles_object, fscache);
 	spin_lock(&object->work_lock);
 	list_add_tail(&monitor->op_link, &op->to_do);
+	fscache_enqueue_retrieval(op);
 	spin_unlock(&object->work_lock);
 
-	fscache_enqueue_retrieval(op);
 	fscache_put_retrieval(op);
 	return 0;
 }
@@ -398,7 +398,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 	struct inode *inode;
 	sector_t block;
 	unsigned shift;
-	int ret;
+	int ret, ret2;
 
 	object = container_of(op->op.object,
 			      struct cachefiles_object, fscache);
@@ -430,8 +430,8 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 	block = page->index;
 	block <<= shift;
 
-	ret = bmap(inode, &block);
-	ASSERT(ret < 0);
+	ret2 = bmap(inode, &block);
+	ASSERT(ret2 == 0);
 
 	_debug("%llx -> %llx",
 	       (unsigned long long) (page->index << shift),
@@ -739,8 +739,8 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 		block = page->index;
 		block <<= shift;
 
-		ret = bmap(inode, &block);
-		ASSERT(!ret);
+		ret2 = bmap(inode, &block);
+		ASSERT(ret2 == 0);
 
 		_debug("%llx -> %llx",
 		       (unsigned long long) (page->index << shift),
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 185db76300b3..f1acde6fb9a6 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2749,7 +2749,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
 
 	ret = try_get_cap_refs(inode, need, want, 0, flags, got);
 	/* three special error codes */
-	if (ret == -EAGAIN || ret == -EFBIG || ret == -EAGAIN)
+	if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE)
 		ret = 0;
 	return ret;
 }
@@ -3746,6 +3746,7 @@ retry:
 		WARN_ON(1);
 		tsession = NULL;
 		target = -1;
+		mutex_lock(&session->s_mutex);
 	}
 	goto retry;
 
@@ -3990,7 +3991,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 			__ceph_queue_cap_release(session, cap);
 			spin_unlock(&session->s_cap_lock);
 		}
-		goto done;
+		goto flush_cap_releases;
 	}
 
 	/* these will work even if we don't have a cap yet */
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 481ac97b4d25..dcaed75de9e6 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -271,7 +271,7 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 				    &congestion_kb_fops);
 
 	snprintf(name, sizeof(name), "../../bdi/%s",
-		 dev_name(fsc->sb->s_bdi->dev));
+		 bdi_dev_name(fsc->sb->s_bdi));
 	fsc->debugfs_bdi =
 		debugfs_create_symlink("bdi",
 				       fsc->client->debugfs_dir,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index d594c2627430..4c4202c93b71 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1051,8 +1051,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 
 	/* If op failed, mark everyone involved for errors */
 	if (result) {
-		int pathlen;
-		u64 base;
+		int pathlen = 0;
+		u64 base = 0;
 		char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
 						  &base, 0);
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 4a5ccbb7e808..afdfca965a7f 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -527,8 +527,8 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
 
 	if (result) {
 		struct dentry *dentry = req->r_dentry;
-		int pathlen;
-		u64 base;
+		int pathlen = 0;
+		u64 base = 0;
 		char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
 						  &base, 0);
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 486f91f9685b..7c63abf5bea9 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3251,8 +3251,7 @@ static void handle_session(struct ceph_mds_session *session,
 	void *end = p + msg->front.iov_len;
 	struct ceph_mds_session_head *h;
 	u32 op;
-	u64 seq;
-	unsigned long features = 0;
+	u64 seq, features = 0;
 	int wake = 0;
 	bool blacklisted = false;
 
@@ -3271,9 +3270,8 @@ static void handle_session(struct ceph_mds_session *session,
 			goto bad;
 		/* version >= 3, feature bits */
 		ceph_decode_32_safe(&p, end, len, bad);
-		ceph_decode_need(&p, end, len, bad);
-		memcpy(&features, p, min_t(size_t, len, sizeof(features)));
-		p += len;
+		ceph_decode_64_safe(&p, end, features, bad);
+		p += len - sizeof(features);
 	}
 
 	mutex_lock(&mdsc->mutex);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 4e5be79bf080..903d9edfd4bf 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -521,7 +521,7 @@ extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
 
 static inline void ceph_mdsc_free_path(char *path, int len)
 {
-	if (path)
+	if (!IS_ERR_OR_NULL(path))
 		__putname(path - (PATH_MAX - 1 - len));
 }
 
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index de56dee60540..19507e2fdb57 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -159,8 +159,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
 	}
 
 	if (IS_ERR(in)) {
-		pr_warn("Can't lookup inode %llx (err: %ld)\n",
-			realm->ino, PTR_ERR(in));
+		dout("Can't lookup inode %llx (err: %ld)\n",
+		     realm->ino, PTR_ERR(in));
 		qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */
 	} else {
 		qri->timeout = 0;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 05dd3dea684b..39b708d9d86d 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1891,7 +1891,8 @@ GLOBAL_EXTERN struct list_head		cifs_tcp_ses_list;
 /*
  * This lock protects the cifs_tcp_ses_list, the list of smb sessions per
  * tcp session, and the list of tcon's per smb session. It also protects
- * the reference counters for the server, smb session, and tcon. Finally,
+ * the reference counters for the server, smb session, and tcon. It also
+ * protects some fields in the TCP_Server_Info struct such as dstaddr. Finally,
  * changes to the tcon->tidStatus should be done while holding this lock.
  * generally the locks should be taken in order tcp_ses_lock before
  * tcon->open_file_lock and that before file->file_info_lock since the
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 140efc1a9374..5014a82391ff 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -594,6 +594,8 @@ decode_lanman_negprot_rsp(struct TCP_Server_Info *server, NEGOTIATE_RSP *pSMBr)
 			       cifs_max_pending);
 	set_credits(server, server->maxReq);
 	server->maxBuf = le16_to_cpu(rsp->MaxBufSize);
+	/* set up max_read for readpages check */
+	server->max_read = server->maxBuf;
 	/* even though we do not use raw we might as well set this
 	accurately, in case we ever find a need for it */
 	if ((le16_to_cpu(rsp->RawMode) & RAW_ENABLE) == RAW_ENABLE) {
@@ -755,6 +757,8 @@ CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses)
 	set_credits(server, server->maxReq);
 	/* probably no need to store and check maxvcs */
 	server->maxBuf = le32_to_cpu(pSMBr->MaxBufferSize);
+	/* set up max_read for readpages check */
+	server->max_read = server->maxBuf;
 	server->max_rw = le32_to_cpu(pSMBr->MaxRawSize);
 	cifs_dbg(NOISY, "Max buf = %d\n", ses->server->maxBuf);
 	server->capabilities = le32_to_cpu(pSMBr->Capabilities);
@@ -2148,8 +2152,8 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
 			}
 		}
 
+		kref_put(&wdata2->refcount, cifs_writedata_release);
 		if (rc) {
-			kref_put(&wdata2->refcount, cifs_writedata_release);
 			if (is_retryable_error(rc))
 				continue;
 			i += nr_pages;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 95b3ab0ca8c0..28268ed461b8 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -375,8 +375,10 @@ static int reconn_set_ipaddr(struct TCP_Server_Info *server)
 		return rc;
 	}
 
+	spin_lock(&cifs_tcp_ses_lock);
 	rc = cifs_convert_address((struct sockaddr *)&server->dstaddr, ipaddr,
 				  strlen(ipaddr));
+	spin_unlock(&cifs_tcp_ses_lock);
 	kfree(ipaddr);
 
 	return !rc ? -1 : 0;
@@ -3373,6 +3375,10 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &ses->tcon_list) {
 		tcon = list_entry(tmp, struct cifs_tcon, tcon_list);
+#ifdef CONFIG_CIFS_DFS_UPCALL
+		if (tcon->dfs_path)
+			continue;
+#endif
 		if (!match_tcon(tcon, volume_info))
 			continue;
 		++tcon->tc_count;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0b1528edebcf..75ddce8ef456 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4060,7 +4060,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
 			 * than it negotiated since it will refuse the read
 			 * then.
 			 */
-			if ((tcon->ses) && !(tcon->ses->capabilities &
+			if (!(tcon->ses->capabilities &
 				tcon->ses->server->vals->cap_large_files)) {
 				current_read_size = min_t(uint,
 					current_read_size, CIFSMaxBufSize);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 8fbbdcdad8ff..5d2965a23730 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -61,7 +61,7 @@ static void cifs_set_ops(struct inode *inode)
 		}
 
 		/* check if server can support readpages */
-		if (cifs_sb_master_tcon(cifs_sb)->ses->server->maxBuf <
+		if (cifs_sb_master_tcon(cifs_sb)->ses->server->max_read <
 				PAGE_SIZE + MAX_CIFS_HDR_SIZE)
 			inode->i_data.a_ops = &cifs_addr_ops_smallbuf;
 		else
@@ -730,7 +730,7 @@ static __u64 simple_hashstr(const char *str)
  * cifs_backup_query_path_info - SMB1 fallback code to get ino
  *
  * Fallback code to get file metadata when we don't have access to
- * @full_path (EACCESS) and have backup creds.
+ * @full_path (EACCES) and have backup creds.
  *
  * @data will be set to search info result buffer
  * @resp_buf will be set to cifs resp buf and needs to be freed with
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index a456febd4109..550ce9020a3e 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -1025,51 +1025,99 @@ int copy_path_name(char *dst, const char *src)
 }
 
 struct super_cb_data {
-	struct TCP_Server_Info *server;
+	void *data;
 	struct super_block *sb;
 };
 
-static void super_cb(struct super_block *sb, void *arg)
+static void tcp_super_cb(struct super_block *sb, void *arg)
 {
-	struct super_cb_data *d = arg;
+	struct super_cb_data *sd = arg;
+	struct TCP_Server_Info *server = sd->data;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
 
-	if (d->sb)
+	if (sd->sb)
 		return;
 
 	cifs_sb = CIFS_SB(sb);
 	tcon = cifs_sb_master_tcon(cifs_sb);
-	if (tcon->ses->server == d->server)
-		d->sb = sb;
+	if (tcon->ses->server == server)
+		sd->sb = sb;
 }
 
-struct super_block *cifs_get_tcp_super(struct TCP_Server_Info *server)
+static struct super_block *__cifs_get_super(void (*f)(struct super_block *, void *),
+					    void *data)
 {
-	struct super_cb_data d = {
-		.server = server,
+	struct super_cb_data sd = {
+		.data = data,
 		.sb = NULL,
 	};
 
-	iterate_supers_type(&cifs_fs_type, super_cb, &d);
+	iterate_supers_type(&cifs_fs_type, f, &sd);
 
-	if (unlikely(!d.sb))
-		return ERR_PTR(-ENOENT);
+	if (!sd.sb)
+		return ERR_PTR(-EINVAL);
 	/*
 	 * Grab an active reference in order to prevent automounts (DFS links)
 	 * of expiring and then freeing up our cifs superblock pointer while
 	 * we're doing failover.
 	 */
-	cifs_sb_active(d.sb);
-	return d.sb;
+	cifs_sb_active(sd.sb);
+	return sd.sb;
 }
 
-void cifs_put_tcp_super(struct super_block *sb)
+static void __cifs_put_super(struct super_block *sb)
 {
 	if (!IS_ERR_OR_NULL(sb))
 		cifs_sb_deactive(sb);
 }
 
+struct super_block *cifs_get_tcp_super(struct TCP_Server_Info *server)
+{
+	return __cifs_get_super(tcp_super_cb, server);
+}
+
+void cifs_put_tcp_super(struct super_block *sb)
+{
+	__cifs_put_super(sb);
+}
+
+#ifdef CONFIG_CIFS_DFS_UPCALL
+static void tcon_super_cb(struct super_block *sb, void *arg)
+{
+	struct super_cb_data *sd = arg;
+	struct cifs_tcon *tcon = sd->data;
+	struct cifs_sb_info *cifs_sb;
+
+	if (sd->sb)
+		return;
+
+	cifs_sb = CIFS_SB(sb);
+	if (tcon->dfs_path && cifs_sb->origin_fullpath &&
+	    !strcasecmp(tcon->dfs_path, cifs_sb->origin_fullpath))
+		sd->sb = sb;
+}
+
+static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon)
+{
+	return __cifs_get_super(tcon_super_cb, tcon);
+}
+
+static inline void cifs_put_tcon_super(struct super_block *sb)
+{
+	__cifs_put_super(sb);
+}
+#else
+static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void cifs_put_tcon_super(struct super_block *sb)
+{
+}
+#endif
+
 int update_super_prepath(struct cifs_tcon *tcon, const char *prefix,
 			 size_t prefix_len)
 {
@@ -1077,7 +1125,7 @@ int update_super_prepath(struct cifs_tcon *tcon, const char *prefix,
 	struct cifs_sb_info *cifs_sb;
 	int rc = 0;
 
-	sb = cifs_get_tcp_super(tcon->ses->server);
+	sb = cifs_get_tcon_super(tcon);
 	if (IS_ERR(sb))
 		return PTR_ERR(sb);
 
@@ -1099,6 +1147,6 @@ int update_super_prepath(struct cifs_tcon *tcon, const char *prefix,
 	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
 
 out:
-	cifs_put_tcp_super(sb);
+	cifs_put_tcon_super(sb);
 	return rc;
 }
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index b36c46f48705..f829f4165d38 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -687,6 +687,11 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
+	if (!server->ops->new_lease_key)
+		return -EIO;
+
+	server->ops->new_lease_key(pfid);
+
 	memset(rqst, 0, sizeof(rqst));
 	resp_buftype[0] = resp_buftype[1] = CIFS_NO_BUFFER;
 	memset(rsp_iov, 0, sizeof(rsp_iov));
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 47d3e382ecaa..b30aa3cdd845 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1552,6 +1552,21 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
 	}
 
 	rc = SMB2_sess_establish_session(sess_data);
+#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS
+	if (ses->server->dialect < SMB30_PROT_ID) {
+		cifs_dbg(VFS, "%s: dumping generated SMB2 session keys\n", __func__);
+		/*
+		 * The session id is opaque in terms of endianness, so we can't
+		 * print it as a long long. we dump it as we got it on the wire
+		 */
+		cifs_dbg(VFS, "Session Id    %*ph\n", (int)sizeof(ses->Suid),
+			 &ses->Suid);
+		cifs_dbg(VFS, "Session Key   %*ph\n",
+			 SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response);
+		cifs_dbg(VFS, "Signing Key   %*ph\n",
+			 SMB3_SIGN_KEY_SIZE, ses->auth_key.response);
+	}
+#endif
 out:
 	kfree(ntlmssp_blob);
 	SMB2_sess_free_buffer(sess_data);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 1a6c227ada8f..c0348e3b1695 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -660,8 +660,8 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 		return rc;
 
 	if (memcmp(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE)) {
-		dump_stack();
-		cifs_dbg(VFS, "sign fail cmd 0x%x message id 0x%llx\n", shdr->Command, shdr->MessageId);
+		cifs_dbg(VFS, "sign fail cmd 0x%x message id 0x%llx\n",
+			shdr->Command, shdr->MessageId);
 		return -EACCES;
 	} else
 		return 0;
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index aaad4ca1217e..13a087bc816b 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -17,6 +17,8 @@
 #include <linux/elfcore-compat.h>
 #include <linux/time.h>
 
+#define ELF_COMPAT	1
+
 /*
  * Rename the basic ELF layout types to refer to the 32-bit class of files.
  */
@@ -28,11 +30,13 @@
 #undef	elf_shdr
 #undef	elf_note
 #undef	elf_addr_t
+#undef	ELF_GNU_PROPERTY_ALIGN
 #define elfhdr		elf32_hdr
 #define elf_phdr	elf32_phdr
 #define elf_shdr	elf32_shdr
 #define elf_note	elf32_note
 #define elf_addr_t	Elf32_Addr
+#define ELF_GNU_PROPERTY_ALIGN	ELF32_GNU_PROPERTY_ALIGN
 
 /*
  * Some data types as stored in coredump.
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index cf7b7e1d5bd7..cb733652ecca 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1519,6 +1519,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
 		spin_lock(&configfs_dirent_lock);
 		configfs_detach_rollback(dentry);
 		spin_unlock(&configfs_dirent_lock);
+		config_item_put(parent_item);
 		return -EINTR;
 	}
 	frag->frag_dead = true;
diff --git a/fs/coredump.c b/fs/coredump.c
index f8296a82d01d..478a0d810136 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -211,6 +211,8 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm,
 			return -ENOMEM;
 		(*argv)[(*argc)++] = 0;
 		++pat_ptr;
+		if (!(*pat_ptr))
+			return -ENOMEM;
 	}
 
 	/* Repeat as long as we have more pattern to process and more output
@@ -786,6 +788,14 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 	if (displaced)
 		put_files_struct(displaced);
 	if (!dump_interrupted()) {
+		/*
+		 * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would
+		 * have this set to NULL.
+		 */
+		if (!cprm.file) {
+			pr_info("Core dump to |%s disabled\n", cn.corename);
+			goto close_fail;
+		}
 		file_start_write(cprm.file);
 		core_dumped = binfmt->core_dump(&cprm);
 		file_end_write(cprm.file);
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 1ecaac7ee3cb..ed015cb66c7c 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -54,6 +54,7 @@ struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags)
 
 /**
  * fscrypt_free_bounce_page() - free a ciphertext bounce page
+ * @bounce_page: the bounce page to free, or NULL
  *
  * Free a bounce page that was allocated by fscrypt_encrypt_pagecache_blocks(),
  * or by fscrypt_alloc_bounce_page() directly.
@@ -76,8 +77,12 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
 	memset(iv, 0, ci->ci_mode->ivsize);
 
 	if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) {
-		WARN_ON_ONCE((u32)lblk_num != lblk_num);
+		WARN_ON_ONCE(lblk_num > U32_MAX);
+		WARN_ON_ONCE(ci->ci_inode->i_ino > U32_MAX);
 		lblk_num |= (u64)ci->ci_inode->i_ino << 32;
+	} else if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) {
+		WARN_ON_ONCE(lblk_num > U32_MAX);
+		lblk_num = (u32)(ci->ci_hashed_ino + lblk_num);
 	} else if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) {
 		memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE);
 	}
@@ -132,7 +137,8 @@ int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw,
 }
 
 /**
- * fscrypt_encrypt_pagecache_blocks() - Encrypt filesystem blocks from a pagecache page
+ * fscrypt_encrypt_pagecache_blocks() - Encrypt filesystem blocks from a
+ *					pagecache page
  * @page:      The locked pagecache page containing the block(s) to encrypt
  * @len:       Total size of the block(s) to encrypt.  Must be a nonzero
  *		multiple of the filesystem's block size.
@@ -222,7 +228,8 @@ int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page,
 EXPORT_SYMBOL(fscrypt_encrypt_block_inplace);
 
 /**
- * fscrypt_decrypt_pagecache_blocks() - Decrypt filesystem blocks in a pagecache page
+ * fscrypt_decrypt_pagecache_blocks() - Decrypt filesystem blocks in a
+ *					pagecache page
  * @page:      The locked pagecache page containing the block(s) to decrypt
  * @len:       Total size of the block(s) to decrypt.  Must be a nonzero
  *		multiple of the filesystem's block size.
@@ -346,6 +353,8 @@ void fscrypt_msg(const struct inode *inode, const char *level,
 
 /**
  * fscrypt_init() - Set up for fs encryption.
+ *
+ * Return: 0 on success; -errno on failure
  */
 static int __init fscrypt_init(void)
 {
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 4c212442a8f7..83ca5f1e7934 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -18,7 +18,7 @@
 #include <crypto/skcipher.h>
 #include "fscrypt_private.h"
 
-/**
+/*
  * struct fscrypt_nokey_name - identifier for directory entry when key is absent
  *
  * When userspace lists an encrypted directory without access to the key, the
@@ -83,13 +83,8 @@ static int fscrypt_do_sha256(const u8 *data, unsigned int data_len, u8 *result)
 			tfm = prev_tfm;
 		}
 	}
-	{
-		SHASH_DESC_ON_STACK(desc, tfm);
 
-		desc->tfm = tfm;
-
-		return crypto_shash_digest(desc, data, data_len, result);
-	}
+	return crypto_shash_tfm_digest(tfm, data, data_len, result);
 }
 
 static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
@@ -105,9 +100,12 @@ static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
 
 /**
  * fscrypt_fname_encrypt() - encrypt a filename
- *
- * The output buffer must be at least as large as the input buffer.
- * Any extra space is filled with NUL padding before encryption.
+ * @inode: inode of the parent directory (for regular filenames)
+ *	   or of the symlink (for symlink targets)
+ * @iname: the filename to encrypt
+ * @out: (output) the encrypted filename
+ * @olen: size of the encrypted filename.  It must be at least @iname->len.
+ *	  Any extra space is filled with NUL padding before encryption.
  *
  * Return: 0 on success, -errno on failure
  */
@@ -157,8 +155,11 @@ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
 
 /**
  * fname_decrypt() - decrypt a filename
- *
- * The caller must have allocated sufficient memory for the @oname string.
+ * @inode: inode of the parent directory (for regular filenames)
+ *	   or of the symlink (for symlink targets)
+ * @iname: the encrypted filename to decrypt
+ * @oname: (output) the decrypted filename.  The caller must have allocated
+ *	   enough space for this, e.g. using fscrypt_fname_alloc_buffer().
  *
  * Return: 0 on success, -errno on failure
  */
@@ -206,7 +207,10 @@ static const char lookup_table[65] =
 #define BASE64_CHARS(nbytes)	DIV_ROUND_UP((nbytes) * 4, 3)
 
 /**
- * base64_encode() -
+ * base64_encode() - base64-encode some bytes
+ * @src: the bytes to encode
+ * @len: number of bytes to encode
+ * @dst: (output) the base64-encoded string.  Not NUL-terminated.
  *
  * Encodes the input string using characters from the set [A-Za-z0-9+,].
  * The encoded string is roughly 4/3 times the size of the input string.
@@ -272,7 +276,12 @@ bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
 }
 
 /**
- * fscrypt_fname_alloc_buffer - allocate a buffer for presented filenames
+ * fscrypt_fname_alloc_buffer() - allocate a buffer for presented filenames
+ * @inode: inode of the parent directory (for regular filenames)
+ *	   or of the symlink (for symlink targets)
+ * @max_encrypted_len: maximum length of encrypted filenames the buffer will be
+ *		       used to present
+ * @crypto_str: (output) buffer to allocate
  *
  * Allocate a buffer that is large enough to hold any decrypted or encoded
  * filename (null-terminated), for the given maximum encrypted filename length.
@@ -297,9 +306,10 @@ int fscrypt_fname_alloc_buffer(const struct inode *inode,
 EXPORT_SYMBOL(fscrypt_fname_alloc_buffer);
 
 /**
- * fscrypt_fname_free_buffer - free the buffer for presented filenames
+ * fscrypt_fname_free_buffer() - free a buffer for presented filenames
+ * @crypto_str: the buffer to free
  *
- * Free the buffer allocated by fscrypt_fname_alloc_buffer().
+ * Free a buffer that was allocated by fscrypt_fname_alloc_buffer().
  */
 void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
 {
@@ -311,10 +321,19 @@ void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
 EXPORT_SYMBOL(fscrypt_fname_free_buffer);
 
 /**
- * fscrypt_fname_disk_to_usr() - converts a filename from disk space to user
- * space
- *
- * The caller must have allocated sufficient memory for the @oname string.
+ * fscrypt_fname_disk_to_usr() - convert an encrypted filename to
+ *				 user-presentable form
+ * @inode: inode of the parent directory (for regular filenames)
+ *	   or of the symlink (for symlink targets)
+ * @hash: first part of the name's dirhash, if applicable.  This only needs to
+ *	  be provided if the filename is located in an indexed directory whose
+ *	  encryption key may be unavailable.  Not needed for symlink targets.
+ * @minor_hash: second part of the name's dirhash, if applicable
+ * @iname: encrypted filename to convert.  May also be "." or "..", which
+ *	   aren't actually encrypted.
+ * @oname: output buffer for the user-presentable filename.  The caller must
+ *	   have allocated enough space for this, e.g. using
+ *	   fscrypt_fname_alloc_buffer().
  *
  * If the key is available, we'll decrypt the disk name.  Otherwise, we'll
  * encode it for presentation in fscrypt_nokey_name format.
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index dbced2937ec8..eb7fcd2b7fb8 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -43,7 +43,7 @@ struct fscrypt_context_v2 {
 	u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
 };
 
-/**
+/*
  * fscrypt_context - the encryption context of an inode
  *
  * This is the on-disk equivalent of an fscrypt_policy, stored alongside each
@@ -157,7 +157,7 @@ fscrypt_policy_flags(const union fscrypt_policy *policy)
 	BUG();
 }
 
-/**
+/*
  * For encrypted symlinks, the ciphertext length is stored at the beginning
  * of the string in little-endian format.
  */
@@ -222,6 +222,9 @@ struct fscrypt_info {
 
 	/* This inode's nonce, copied from the fscrypt_context */
 	u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE];
+
+	/* Hashed inode number.  Only set for IV_INO_LBLK_32 */
+	u32 ci_hashed_ino;
 };
 
 typedef enum {
@@ -231,15 +234,14 @@ typedef enum {
 
 /* crypto.c */
 extern struct kmem_cache *fscrypt_info_cachep;
-extern int fscrypt_initialize(unsigned int cop_flags);
-extern int fscrypt_crypt_block(const struct inode *inode,
-			       fscrypt_direction_t rw, u64 lblk_num,
-			       struct page *src_page, struct page *dest_page,
-			       unsigned int len, unsigned int offs,
-			       gfp_t gfp_flags);
-extern struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags);
-
-extern void __printf(3, 4) __cold
+int fscrypt_initialize(unsigned int cop_flags);
+int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw,
+			u64 lblk_num, struct page *src_page,
+			struct page *dest_page, unsigned int len,
+			unsigned int offs, gfp_t gfp_flags);
+struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags);
+
+void __printf(3, 4) __cold
 fscrypt_msg(const struct inode *inode, const char *level, const char *fmt, ...);
 
 #define fscrypt_warn(inode, fmt, ...)		\
@@ -264,12 +266,10 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
 			 const struct fscrypt_info *ci);
 
 /* fname.c */
-extern int fscrypt_fname_encrypt(const struct inode *inode,
-				 const struct qstr *iname,
-				 u8 *out, unsigned int olen);
-extern bool fscrypt_fname_encrypted_size(const struct inode *inode,
-					 u32 orig_len, u32 max_len,
-					 u32 *encrypted_len_ret);
+int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
+			  u8 *out, unsigned int olen);
+bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
+				  u32 max_len, u32 *encrypted_len_ret);
 extern const struct dentry_operations fscrypt_d_ops;
 
 /* hkdf.c */
@@ -278,8 +278,8 @@ struct fscrypt_hkdf {
 	struct crypto_shash *hmac_tfm;
 };
 
-extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
-			     unsigned int master_key_size);
+int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
+		      unsigned int master_key_size);
 
 /*
  * The list of contexts in which fscrypt uses HKDF.  These values are used as
@@ -293,12 +293,14 @@ extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
 #define HKDF_CONTEXT_DIRECT_KEY		3
 #define HKDF_CONTEXT_IV_INO_LBLK_64_KEY	4
 #define HKDF_CONTEXT_DIRHASH_KEY	5
+#define HKDF_CONTEXT_IV_INO_LBLK_32_KEY	6
+#define HKDF_CONTEXT_INODE_HASH_KEY	7
 
-extern int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context,
-			       const u8 *info, unsigned int infolen,
-			       u8 *okm, unsigned int okmlen);
+int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context,
+			const u8 *info, unsigned int infolen,
+			u8 *okm, unsigned int okmlen);
 
-extern void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf);
+void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf);
 
 /* keyring.c */
 
@@ -389,14 +391,17 @@ struct fscrypt_master_key {
 	struct list_head	mk_decrypted_inodes;
 	spinlock_t		mk_decrypted_inodes_lock;
 
-	/* Crypto API transforms for DIRECT_KEY policies, allocated on-demand */
-	struct crypto_skcipher	*mk_direct_tfms[__FSCRYPT_MODE_MAX + 1];
-
 	/*
-	 * Crypto API transforms for filesystem-layer implementation of
-	 * IV_INO_LBLK_64 policies, allocated on-demand.
+	 * Per-mode encryption keys for the various types of encryption policies
+	 * that use them.  Allocated and derived on-demand.
 	 */
-	struct crypto_skcipher	*mk_iv_ino_lblk_64_tfms[__FSCRYPT_MODE_MAX + 1];
+	struct crypto_skcipher *mk_direct_keys[__FSCRYPT_MODE_MAX + 1];
+	struct crypto_skcipher *mk_iv_ino_lblk_64_keys[__FSCRYPT_MODE_MAX + 1];
+	struct crypto_skcipher *mk_iv_ino_lblk_32_keys[__FSCRYPT_MODE_MAX + 1];
+
+	/* Hash key for inode numbers.  Initialized only when needed. */
+	siphash_key_t		mk_ino_hash_key;
+	bool			mk_ino_hash_key_initialized;
 
 } __randomize_layout;
 
@@ -436,14 +441,17 @@ static inline int master_key_spec_len(const struct fscrypt_key_specifier *spec)
 	return 0;
 }
 
-extern struct key *
+struct key *
 fscrypt_find_master_key(struct super_block *sb,
 			const struct fscrypt_key_specifier *mk_spec);
 
-extern int fscrypt_verify_key_added(struct super_block *sb,
-				    const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]);
+int fscrypt_add_test_dummy_key(struct super_block *sb,
+			       struct fscrypt_key_specifier *key_spec);
+
+int fscrypt_verify_key_added(struct super_block *sb,
+			     const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]);
 
-extern int __init fscrypt_init_keyring(void);
+int __init fscrypt_init_keyring(void);
 
 /* keysetup.c */
 
@@ -457,33 +465,32 @@ struct fscrypt_mode {
 
 extern struct fscrypt_mode fscrypt_modes[];
 
-extern struct crypto_skcipher *
-fscrypt_allocate_skcipher(struct fscrypt_mode *mode, const u8 *raw_key,
-			  const struct inode *inode);
+struct crypto_skcipher *fscrypt_allocate_skcipher(struct fscrypt_mode *mode,
+						  const u8 *raw_key,
+						  const struct inode *inode);
 
-extern int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci,
-					const u8 *raw_key);
+int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key);
 
-extern int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
-				      const struct fscrypt_master_key *mk);
+int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
+			       const struct fscrypt_master_key *mk);
 
 /* keysetup_v1.c */
 
-extern void fscrypt_put_direct_key(struct fscrypt_direct_key *dk);
+void fscrypt_put_direct_key(struct fscrypt_direct_key *dk);
+
+int fscrypt_setup_v1_file_key(struct fscrypt_info *ci,
+			      const u8 *raw_master_key);
 
-extern int fscrypt_setup_v1_file_key(struct fscrypt_info *ci,
-				     const u8 *raw_master_key);
+int fscrypt_setup_v1_file_key_via_subscribed_keyrings(struct fscrypt_info *ci);
 
-extern int fscrypt_setup_v1_file_key_via_subscribed_keyrings(
-					struct fscrypt_info *ci);
 /* policy.c */
 
-extern bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
-				   const union fscrypt_policy *policy2);
-extern bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
-				     const struct inode *inode);
-extern int fscrypt_policy_from_context(union fscrypt_policy *policy_u,
-				       const union fscrypt_context *ctx_u,
-				       int ctx_size);
+bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
+			    const union fscrypt_policy *policy2);
+bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
+			      const struct inode *inode);
+int fscrypt_policy_from_context(union fscrypt_policy *policy_u,
+				const union fscrypt_context *ctx_u,
+				int ctx_size);
 
 #endif /* _FSCRYPT_PRIVATE_H */
diff --git a/fs/crypto/hkdf.c b/fs/crypto/hkdf.c
index efb95bd19a89..0cba7928446d 100644
--- a/fs/crypto/hkdf.c
+++ b/fs/crypto/hkdf.c
@@ -44,17 +44,13 @@ static int hkdf_extract(struct crypto_shash *hmac_tfm, const u8 *ikm,
 			unsigned int ikmlen, u8 prk[HKDF_HASHLEN])
 {
 	static const u8 default_salt[HKDF_HASHLEN];
-	SHASH_DESC_ON_STACK(desc, hmac_tfm);
 	int err;
 
 	err = crypto_shash_setkey(hmac_tfm, default_salt, HKDF_HASHLEN);
 	if (err)
 		return err;
 
-	desc->tfm = hmac_tfm;
-	err = crypto_shash_digest(desc, ikm, ikmlen, prk);
-	shash_desc_zero(desc);
-	return err;
+	return crypto_shash_tfm_digest(hmac_tfm, ikm, ikmlen, prk);
 }
 
 /*
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 5ef861742921..09fb8aa0f2e9 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -10,7 +10,7 @@
 #include "fscrypt_private.h"
 
 /**
- * fscrypt_file_open - prepare to open a possibly-encrypted regular file
+ * fscrypt_file_open() - prepare to open a possibly-encrypted regular file
  * @inode: the inode being opened
  * @filp: the struct file being set up
  *
@@ -262,7 +262,7 @@ err_free_sd:
 EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink);
 
 /**
- * fscrypt_get_symlink - get the target of an encrypted symlink
+ * fscrypt_get_symlink() - get the target of an encrypted symlink
  * @inode: the symlink inode
  * @caddr: the on-disk contents of the symlink
  * @max_size: size of @caddr buffer
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index ab41b25d4fa1..e24eb48bfbe1 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -20,6 +20,7 @@
 
 #include <crypto/skcipher.h>
 #include <linux/key-type.h>
+#include <linux/random.h>
 #include <linux/seq_file.h>
 
 #include "fscrypt_private.h"
@@ -44,8 +45,9 @@ static void free_master_key(struct fscrypt_master_key *mk)
 	wipe_master_key_secret(&mk->mk_secret);
 
 	for (i = 0; i <= __FSCRYPT_MODE_MAX; i++) {
-		crypto_free_skcipher(mk->mk_direct_tfms[i]);
-		crypto_free_skcipher(mk->mk_iv_ino_lblk_64_tfms[i]);
+		crypto_free_skcipher(mk->mk_direct_keys[i]);
+		crypto_free_skcipher(mk->mk_iv_ino_lblk_64_keys[i]);
+		crypto_free_skcipher(mk->mk_iv_ino_lblk_32_keys[i]);
 	}
 
 	key_put(mk->mk_users);
@@ -424,9 +426,9 @@ static int add_existing_master_key(struct fscrypt_master_key *mk,
 	return 0;
 }
 
-static int add_master_key(struct super_block *sb,
-			  struct fscrypt_master_key_secret *secret,
-			  const struct fscrypt_key_specifier *mk_spec)
+static int do_add_master_key(struct super_block *sb,
+			     struct fscrypt_master_key_secret *secret,
+			     const struct fscrypt_key_specifier *mk_spec)
 {
 	static DEFINE_MUTEX(fscrypt_add_key_mutex);
 	struct key *key;
@@ -465,6 +467,35 @@ out_unlock:
 	return err;
 }
 
+static int add_master_key(struct super_block *sb,
+			  struct fscrypt_master_key_secret *secret,
+			  struct fscrypt_key_specifier *key_spec)
+{
+	int err;
+
+	if (key_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) {
+		err = fscrypt_init_hkdf(&secret->hkdf, secret->raw,
+					secret->size);
+		if (err)
+			return err;
+
+		/*
+		 * Now that the HKDF context is initialized, the raw key is no
+		 * longer needed.
+		 */
+		memzero_explicit(secret->raw, secret->size);
+
+		/* Calculate the key identifier */
+		err = fscrypt_hkdf_expand(&secret->hkdf,
+					  HKDF_CONTEXT_KEY_IDENTIFIER, NULL, 0,
+					  key_spec->u.identifier,
+					  FSCRYPT_KEY_IDENTIFIER_SIZE);
+		if (err)
+			return err;
+	}
+	return do_add_master_key(sb, secret, key_spec);
+}
+
 static int fscrypt_provisioning_key_preparse(struct key_preparsed_payload *prep)
 {
 	const struct fscrypt_provisioning_key_payload *payload = prep->data;
@@ -609,6 +640,15 @@ int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg)
 	if (memchr_inv(arg.__reserved, 0, sizeof(arg.__reserved)))
 		return -EINVAL;
 
+	/*
+	 * Only root can add keys that are identified by an arbitrary descriptor
+	 * rather than by a cryptographic hash --- since otherwise a malicious
+	 * user could add the wrong key.
+	 */
+	if (arg.key_spec.type == FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR &&
+	    !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
 	memset(&secret, 0, sizeof(secret));
 	if (arg.key_id) {
 		if (arg.raw_size != 0)
@@ -626,48 +666,17 @@ int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg)
 			goto out_wipe_secret;
 	}
 
-	switch (arg.key_spec.type) {
-	case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR:
-		/*
-		 * Only root can add keys that are identified by an arbitrary
-		 * descriptor rather than by a cryptographic hash --- since
-		 * otherwise a malicious user could add the wrong key.
-		 */
-		err = -EACCES;
-		if (!capable(CAP_SYS_ADMIN))
-			goto out_wipe_secret;
-		break;
-	case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER:
-		err = fscrypt_init_hkdf(&secret.hkdf, secret.raw, secret.size);
-		if (err)
-			goto out_wipe_secret;
-
-		/*
-		 * Now that the HKDF context is initialized, the raw key is no
-		 * longer needed.
-		 */
-		memzero_explicit(secret.raw, secret.size);
-
-		/* Calculate the key identifier and return it to userspace. */
-		err = fscrypt_hkdf_expand(&secret.hkdf,
-					  HKDF_CONTEXT_KEY_IDENTIFIER,
-					  NULL, 0, arg.key_spec.u.identifier,
-					  FSCRYPT_KEY_IDENTIFIER_SIZE);
-		if (err)
-			goto out_wipe_secret;
-		err = -EFAULT;
-		if (copy_to_user(uarg->key_spec.u.identifier,
-				 arg.key_spec.u.identifier,
-				 FSCRYPT_KEY_IDENTIFIER_SIZE))
-			goto out_wipe_secret;
-		break;
-	default:
-		WARN_ON(1);
-		err = -EINVAL;
+	err = add_master_key(sb, &secret, &arg.key_spec);
+	if (err)
 		goto out_wipe_secret;
-	}
 
-	err = add_master_key(sb, &secret, &arg.key_spec);
+	/* Return the key identifier to userspace, if applicable */
+	err = -EFAULT;
+	if (arg.key_spec.type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER &&
+	    copy_to_user(uarg->key_spec.u.identifier, arg.key_spec.u.identifier,
+			 FSCRYPT_KEY_IDENTIFIER_SIZE))
+		goto out_wipe_secret;
+	err = 0;
 out_wipe_secret:
 	wipe_master_key_secret(&secret);
 	return err;
@@ -675,6 +684,29 @@ out_wipe_secret:
 EXPORT_SYMBOL_GPL(fscrypt_ioctl_add_key);
 
 /*
+ * Add the key for '-o test_dummy_encryption' to the filesystem keyring.
+ *
+ * Use a per-boot random key to prevent people from misusing this option.
+ */
+int fscrypt_add_test_dummy_key(struct super_block *sb,
+			       struct fscrypt_key_specifier *key_spec)
+{
+	static u8 test_key[FSCRYPT_MAX_KEY_SIZE];
+	struct fscrypt_master_key_secret secret;
+	int err;
+
+	get_random_once(test_key, FSCRYPT_MAX_KEY_SIZE);
+
+	memset(&secret, 0, sizeof(secret));
+	secret.size = FSCRYPT_MAX_KEY_SIZE;
+	memcpy(secret.raw, test_key, FSCRYPT_MAX_KEY_SIZE);
+
+	err = add_master_key(sb, &secret, key_spec);
+	wipe_master_key_secret(&secret);
+	return err;
+}
+
+/*
  * Verify that the current user has added a master key with the given identifier
  * (returns -ENOKEY if not).  This is needed to prevent a user from encrypting
  * their files using some other user's key which they don't actually know.
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index 302375e9f719..1129adfa097d 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -46,6 +46,8 @@ struct fscrypt_mode fscrypt_modes[] = {
 	},
 };
 
+static DEFINE_MUTEX(fscrypt_mode_key_setup_mutex);
+
 static struct fscrypt_mode *
 select_encryption_mode(const union fscrypt_policy *policy,
 		       const struct inode *inode)
@@ -130,7 +132,7 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci,
 	const struct super_block *sb = inode->i_sb;
 	struct fscrypt_mode *mode = ci->ci_mode;
 	const u8 mode_num = mode - fscrypt_modes;
-	struct crypto_skcipher *tfm, *prev_tfm;
+	struct crypto_skcipher *tfm;
 	u8 mode_key[FSCRYPT_MAX_KEY_SIZE];
 	u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)];
 	unsigned int hkdf_infolen = 0;
@@ -139,10 +141,17 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci,
 	if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX))
 		return -EINVAL;
 
-	/* pairs with cmpxchg() below */
+	/* pairs with smp_store_release() below */
 	tfm = READ_ONCE(tfms[mode_num]);
-	if (likely(tfm != NULL))
-		goto done;
+	if (likely(tfm != NULL)) {
+		ci->ci_ctfm = tfm;
+		return 0;
+	}
+
+	mutex_lock(&fscrypt_mode_key_setup_mutex);
+
+	if (tfms[mode_num])
+		goto done_unlock;
 
 	BUILD_BUG_ON(sizeof(mode_num) != 1);
 	BUILD_BUG_ON(sizeof(sb->s_uuid) != 16);
@@ -157,21 +166,21 @@ static int setup_per_mode_enc_key(struct fscrypt_info *ci,
 				  hkdf_context, hkdf_info, hkdf_infolen,
 				  mode_key, mode->keysize);
 	if (err)
-		return err;
+		goto out_unlock;
 	tfm = fscrypt_allocate_skcipher(mode, mode_key, inode);
 	memzero_explicit(mode_key, mode->keysize);
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
-
-	/* pairs with READ_ONCE() above */
-	prev_tfm = cmpxchg(&tfms[mode_num], NULL, tfm);
-	if (prev_tfm != NULL) {
-		crypto_free_skcipher(tfm);
-		tfm = prev_tfm;
+	if (IS_ERR(tfm)) {
+		err = PTR_ERR(tfm);
+		goto out_unlock;
 	}
-done:
+	/* pairs with READ_ONCE() above */
+	smp_store_release(&tfms[mode_num], tfm);
+done_unlock:
 	ci->ci_ctfm = tfm;
-	return 0;
+	err = 0;
+out_unlock:
+	mutex_unlock(&fscrypt_mode_key_setup_mutex);
+	return err;
 }
 
 int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
@@ -189,6 +198,43 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
 	return 0;
 }
 
+static int fscrypt_setup_iv_ino_lblk_32_key(struct fscrypt_info *ci,
+					    struct fscrypt_master_key *mk)
+{
+	int err;
+
+	err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_32_keys,
+				     HKDF_CONTEXT_IV_INO_LBLK_32_KEY, true);
+	if (err)
+		return err;
+
+	/* pairs with smp_store_release() below */
+	if (!smp_load_acquire(&mk->mk_ino_hash_key_initialized)) {
+
+		mutex_lock(&fscrypt_mode_key_setup_mutex);
+
+		if (mk->mk_ino_hash_key_initialized)
+			goto unlock;
+
+		err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf,
+					  HKDF_CONTEXT_INODE_HASH_KEY, NULL, 0,
+					  (u8 *)&mk->mk_ino_hash_key,
+					  sizeof(mk->mk_ino_hash_key));
+		if (err)
+			goto unlock;
+		/* pairs with smp_load_acquire() above */
+		smp_store_release(&mk->mk_ino_hash_key_initialized, true);
+unlock:
+		mutex_unlock(&fscrypt_mode_key_setup_mutex);
+		if (err)
+			return err;
+	}
+
+	ci->ci_hashed_ino = (u32)siphash_1u64(ci->ci_inode->i_ino,
+					      &mk->mk_ino_hash_key);
+	return 0;
+}
+
 static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
 				     struct fscrypt_master_key *mk)
 {
@@ -203,7 +249,7 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
 		 * encryption key.  This ensures that the master key is
 		 * consistently used only for HKDF, avoiding key reuse issues.
 		 */
-		err = setup_per_mode_enc_key(ci, mk, mk->mk_direct_tfms,
+		err = setup_per_mode_enc_key(ci, mk, mk->mk_direct_keys,
 					     HKDF_CONTEXT_DIRECT_KEY, false);
 	} else if (ci->ci_policy.v2.flags &
 		   FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) {
@@ -211,11 +257,14 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
 		 * IV_INO_LBLK_64: encryption keys are derived from (master_key,
 		 * mode_num, filesystem_uuid), and inode number is included in
 		 * the IVs.  This format is optimized for use with inline
-		 * encryption hardware compliant with the UFS or eMMC standards.
+		 * encryption hardware compliant with the UFS standard.
 		 */
-		err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_64_tfms,
+		err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_64_keys,
 					     HKDF_CONTEXT_IV_INO_LBLK_64_KEY,
 					     true);
+	} else if (ci->ci_policy.v2.flags &
+		   FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) {
+		err = fscrypt_setup_iv_ino_lblk_32_key(ci, mk);
 	} else {
 		u8 derived_key[FSCRYPT_MAX_KEY_SIZE];
 
@@ -395,21 +444,18 @@ int fscrypt_get_encryption_info(struct inode *inode)
 
 	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
 	if (res < 0) {
-		if (!fscrypt_dummy_context_enabled(inode) ||
-		    IS_ENCRYPTED(inode)) {
+		const union fscrypt_context *dummy_ctx =
+			fscrypt_get_dummy_context(inode->i_sb);
+
+		if (IS_ENCRYPTED(inode) || !dummy_ctx) {
 			fscrypt_warn(inode,
 				     "Error %d getting encryption context",
 				     res);
 			return res;
 		}
 		/* Fake up a context for an unencrypted directory */
-		memset(&ctx, 0, sizeof(ctx));
-		ctx.version = FSCRYPT_CONTEXT_V1;
-		ctx.v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
-		ctx.v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
-		memset(ctx.v1.master_key_descriptor, 0x42,
-		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
-		res = sizeof(ctx.v1);
+		res = fscrypt_context_size(dummy_ctx);
+		memcpy(&ctx, dummy_ctx, res);
 	}
 
 	crypt_info = kmem_cache_zalloc(fscrypt_info_cachep, GFP_NOFS);
@@ -475,7 +521,8 @@ out:
 EXPORT_SYMBOL(fscrypt_get_encryption_info);
 
 /**
- * fscrypt_put_encryption_info - free most of an inode's fscrypt data
+ * fscrypt_put_encryption_info() - free most of an inode's fscrypt data
+ * @inode: an inode being evicted
  *
  * Free the inode's fscrypt_info.  Filesystems must call this when the inode is
  * being evicted.  An RCU grace period need not have elapsed yet.
@@ -488,7 +535,8 @@ void fscrypt_put_encryption_info(struct inode *inode)
 EXPORT_SYMBOL(fscrypt_put_encryption_info);
 
 /**
- * fscrypt_free_inode - free an inode's fscrypt data requiring RCU delay
+ * fscrypt_free_inode() - free an inode's fscrypt data requiring RCU delay
+ * @inode: an inode being freed
  *
  * Free the inode's cached decrypted symlink target, if any.  Filesystems must
  * call this after an RCU grace period, just before they free the inode.
@@ -503,7 +551,8 @@ void fscrypt_free_inode(struct inode *inode)
 EXPORT_SYMBOL(fscrypt_free_inode);
 
 /**
- * fscrypt_drop_inode - check whether the inode's master key has been removed
+ * fscrypt_drop_inode() - check whether the inode's master key has been removed
+ * @inode: an inode being considered for eviction
  *
  * Filesystems supporting fscrypt must call this from their ->drop_inode()
  * method so that encrypted inodes are evicted as soon as they're no longer in
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 10ccf945020c..d23ff162c78b 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -11,12 +11,15 @@
  */
 
 #include <linux/random.h>
+#include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/mount.h>
 #include "fscrypt_private.h"
 
 /**
- * fscrypt_policies_equal - check whether two encryption policies are the same
+ * fscrypt_policies_equal() - check whether two encryption policies are the same
+ * @policy1: the first policy
+ * @policy2: the second policy
  *
  * Return: %true if equal, else %false
  */
@@ -66,18 +69,14 @@ static bool supported_direct_key_modes(const struct inode *inode,
 	return true;
 }
 
-static bool supported_iv_ino_lblk_64_policy(
-					const struct fscrypt_policy_v2 *policy,
-					const struct inode *inode)
+static bool supported_iv_ino_lblk_policy(const struct fscrypt_policy_v2 *policy,
+					 const struct inode *inode,
+					 const char *type,
+					 int max_ino_bits, int max_lblk_bits)
 {
 	struct super_block *sb = inode->i_sb;
 	int ino_bits = 64, lblk_bits = 64;
 
-	if (policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) {
-		fscrypt_warn(inode,
-			     "The DIRECT_KEY and IV_INO_LBLK_64 flags are mutually exclusive");
-		return false;
-	}
 	/*
 	 * It's unsafe to include inode numbers in the IVs if the filesystem can
 	 * potentially renumber inodes, e.g. via filesystem shrinking.
@@ -85,16 +84,22 @@ static bool supported_iv_ino_lblk_64_policy(
 	if (!sb->s_cop->has_stable_inodes ||
 	    !sb->s_cop->has_stable_inodes(sb)) {
 		fscrypt_warn(inode,
-			     "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't have stable inode numbers",
-			     sb->s_id);
+			     "Can't use %s policy on filesystem '%s' because it doesn't have stable inode numbers",
+			     type, sb->s_id);
 		return false;
 	}
 	if (sb->s_cop->get_ino_and_lblk_bits)
 		sb->s_cop->get_ino_and_lblk_bits(sb, &ino_bits, &lblk_bits);
-	if (ino_bits > 32 || lblk_bits > 32) {
+	if (ino_bits > max_ino_bits) {
+		fscrypt_warn(inode,
+			     "Can't use %s policy on filesystem '%s' because its inode numbers are too long",
+			     type, sb->s_id);
+		return false;
+	}
+	if (lblk_bits > max_lblk_bits) {
 		fscrypt_warn(inode,
-			     "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't use 32-bit inode and block numbers",
-			     sb->s_id);
+			     "Can't use %s policy on filesystem '%s' because its block numbers are too long",
+			     type, sb->s_id);
 		return false;
 	}
 	return true;
@@ -137,6 +142,8 @@ static bool fscrypt_supported_v1_policy(const struct fscrypt_policy_v1 *policy,
 static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy,
 					const struct inode *inode)
 {
+	int count = 0;
+
 	if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode,
 				     policy->filenames_encryption_mode)) {
 		fscrypt_warn(inode,
@@ -152,13 +159,29 @@ static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy,
 		return false;
 	}
 
+	count += !!(policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY);
+	count += !!(policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64);
+	count += !!(policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32);
+	if (count > 1) {
+		fscrypt_warn(inode, "Mutually exclusive encryption flags (0x%02x)",
+			     policy->flags);
+		return false;
+	}
+
 	if ((policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) &&
 	    !supported_direct_key_modes(inode, policy->contents_encryption_mode,
 					policy->filenames_encryption_mode))
 		return false;
 
 	if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) &&
-	    !supported_iv_ino_lblk_64_policy(policy, inode))
+	    !supported_iv_ino_lblk_policy(policy, inode, "IV_INO_LBLK_64",
+					  32, 32))
+		return false;
+
+	if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) &&
+	    /* This uses hashed inode numbers, so ino_bits doesn't matter. */
+	    !supported_iv_ino_lblk_policy(policy, inode, "IV_INO_LBLK_32",
+					  INT_MAX, 32))
 		return false;
 
 	if (memchr_inv(policy->__reserved, 0, sizeof(policy->__reserved))) {
@@ -170,7 +193,9 @@ static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy,
 }
 
 /**
- * fscrypt_supported_policy - check whether an encryption policy is supported
+ * fscrypt_supported_policy() - check whether an encryption policy is supported
+ * @policy_u: the encryption policy
+ * @inode: the inode on which the policy will be used
  *
  * Given an encryption policy, check whether all its encryption modes and other
  * settings are supported by this kernel on the given inode.  (But we don't
@@ -192,7 +217,10 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
 }
 
 /**
- * fscrypt_new_context_from_policy - create a new fscrypt_context from a policy
+ * fscrypt_new_context_from_policy() - create a new fscrypt_context from
+ *				       an fscrypt_policy
+ * @ctx_u: output context
+ * @policy_u: input policy
  *
  * Create an fscrypt_context for an inode that is being assigned the given
  * encryption policy.  A new nonce is randomly generated.
@@ -242,7 +270,11 @@ static int fscrypt_new_context_from_policy(union fscrypt_context *ctx_u,
 }
 
 /**
- * fscrypt_policy_from_context - convert an fscrypt_context to an fscrypt_policy
+ * fscrypt_policy_from_context() - convert an fscrypt_context to
+ *				   an fscrypt_policy
+ * @policy_u: output policy
+ * @ctx_u: input context
+ * @ctx_size: size of input context in bytes
  *
  * Given an fscrypt_context, build the corresponding fscrypt_policy.
  *
@@ -354,6 +386,9 @@ static int set_encryption_policy(struct inode *inode,
 					       policy->v2.master_key_identifier);
 		if (err)
 			return err;
+		if (policy->v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)
+			pr_warn_once("%s (pid %d) is setting an IV_INO_LBLK_32 encryption policy.  This should only be used if there are certain hardware limitations.\n",
+				     current->comm, current->pid);
 		break;
 	default:
 		WARN_ON(1);
@@ -605,3 +640,127 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 	return preload ? fscrypt_get_encryption_info(child): 0;
 }
 EXPORT_SYMBOL(fscrypt_inherit_context);
+
+/**
+ * fscrypt_set_test_dummy_encryption() - handle '-o test_dummy_encryption'
+ * @sb: the filesystem on which test_dummy_encryption is being specified
+ * @arg: the argument to the test_dummy_encryption option.
+ *	 If no argument was specified, then @arg->from == NULL.
+ * @dummy_ctx: the filesystem's current dummy context (input/output, see below)
+ *
+ * Handle the test_dummy_encryption mount option by creating a dummy encryption
+ * context, saving it in @dummy_ctx, and adding the corresponding dummy
+ * encryption key to the filesystem.  If the @dummy_ctx is already set, then
+ * instead validate that it matches @arg.  Don't support changing it via
+ * remount, as that is difficult to do safely.
+ *
+ * The reason we use an fscrypt_context rather than an fscrypt_policy is because
+ * we mustn't generate a new nonce each time we access a dummy-encrypted
+ * directory, as that would change the way filenames are encrypted.
+ *
+ * Return: 0 on success (dummy context set, or the same context is already set);
+ *         -EEXIST if a different dummy context is already set;
+ *         or another -errno value.
+ */
+int fscrypt_set_test_dummy_encryption(struct super_block *sb,
+				      const substring_t *arg,
+				      struct fscrypt_dummy_context *dummy_ctx)
+{
+	const char *argstr = "v2";
+	const char *argstr_to_free = NULL;
+	struct fscrypt_key_specifier key_spec = { 0 };
+	int version;
+	union fscrypt_context *ctx = NULL;
+	int err;
+
+	if (arg->from) {
+		argstr = argstr_to_free = match_strdup(arg);
+		if (!argstr)
+			return -ENOMEM;
+	}
+
+	if (!strcmp(argstr, "v1")) {
+		version = FSCRYPT_CONTEXT_V1;
+		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR;
+		memset(key_spec.u.descriptor, 0x42,
+		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
+	} else if (!strcmp(argstr, "v2")) {
+		version = FSCRYPT_CONTEXT_V2;
+		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER;
+		/* key_spec.u.identifier gets filled in when adding the key */
+	} else {
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (dummy_ctx->ctx) {
+		/*
+		 * Note: if we ever make test_dummy_encryption support
+		 * specifying other encryption settings, such as the encryption
+		 * modes, we'll need to compare those settings here.
+		 */
+		if (dummy_ctx->ctx->version == version)
+			err = 0;
+		else
+			err = -EEXIST;
+		goto out;
+	}
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = fscrypt_add_test_dummy_key(sb, &key_spec);
+	if (err)
+		goto out;
+
+	ctx->version = version;
+	switch (ctx->version) {
+	case FSCRYPT_CONTEXT_V1:
+		ctx->v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
+		ctx->v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
+		memcpy(ctx->v1.master_key_descriptor, key_spec.u.descriptor,
+		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
+		break;
+	case FSCRYPT_CONTEXT_V2:
+		ctx->v2.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
+		ctx->v2.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
+		memcpy(ctx->v2.master_key_identifier, key_spec.u.identifier,
+		       FSCRYPT_KEY_IDENTIFIER_SIZE);
+		break;
+	default:
+		WARN_ON(1);
+		err = -EINVAL;
+		goto out;
+	}
+	dummy_ctx->ctx = ctx;
+	ctx = NULL;
+	err = 0;
+out:
+	kfree(ctx);
+	kfree(argstr_to_free);
+	return err;
+}
+EXPORT_SYMBOL_GPL(fscrypt_set_test_dummy_encryption);
+
+/**
+ * fscrypt_show_test_dummy_encryption() - show '-o test_dummy_encryption'
+ * @seq: the seq_file to print the option to
+ * @sep: the separator character to use
+ * @sb: the filesystem whose options are being shown
+ *
+ * Show the test_dummy_encryption mount option, if it was specified.
+ * This is mainly used for /proc/mounts.
+ */
+void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
+					struct super_block *sb)
+{
+	const union fscrypt_context *ctx = fscrypt_get_dummy_context(sb);
+
+	if (!ctx)
+		return;
+	seq_printf(seq, "%ctest_dummy_encryption=v%d", sep, ctx->version);
+}
+EXPORT_SYMBOL_GPL(fscrypt_show_test_dummy_encryption);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 2d357680094c..ae49a55bda00 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -506,20 +506,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n");
  * This function creates a file in debugfs with the given name that
  * contains the value of the variable @value.  If the @mode variable is so
  * set, it can be read from, and written to.
- *
- * This function will return a pointer to a dentry if it succeeds.  This
- * pointer must be passed to the debugfs_remove() function when the file is
- * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, ERR_PTR(-ERROR) will be
- * returned.
- *
- * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
- * be returned.
  */
-struct dentry *debugfs_create_u32(const char *name, umode_t mode,
-				 struct dentry *parent, u32 *value)
+void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent,
+			u32 *value)
 {
-	return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32,
+	debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32,
 				   &fops_u32_ro, &fops_u32_wo);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_u32);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 2c449aed1b92..0681540c48d9 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -48,18 +48,6 @@ void ecryptfs_from_hex(char *dst, char *src, int dst_size)
 	}
 }
 
-static int ecryptfs_hash_digest(struct crypto_shash *tfm,
-				char *src, int len, char *dst)
-{
-	SHASH_DESC_ON_STACK(desc, tfm);
-	int err;
-
-	desc->tfm = tfm;
-	err = crypto_shash_digest(desc, src, len, dst);
-	shash_desc_zero(desc);
-	return err;
-}
-
 /**
  * ecryptfs_calculate_md5 - calculates the md5 of @src
  * @dst: Pointer to 16 bytes of allocated memory
@@ -74,11 +62,8 @@ static int ecryptfs_calculate_md5(char *dst,
 				  struct ecryptfs_crypt_stat *crypt_stat,
 				  char *src, int len)
 {
-	struct crypto_shash *tfm;
-	int rc = 0;
+	int rc = crypto_shash_tfm_digest(crypt_stat->hash_tfm, src, len, dst);
 
-	tfm = crypt_stat->hash_tfm;
-	rc = ecryptfs_hash_digest(tfm, src, len, dst);
 	if (rc) {
 		printk(KERN_ERR
 		       "%s: Error computing crypto hash; rc = [%d]\n",
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8c596641a72b..12eebcdea9c8 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1171,6 +1171,10 @@ static inline bool chain_epi_lockless(struct epitem *epi)
 {
 	struct eventpoll *ep = epi->ep;
 
+	/* Fast preliminary check */
+	if (epi->next != EP_UNACTIVE_PTR)
+		return false;
+
 	/* Check that the same epi has not been just chained from another CPU */
 	if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR)
 		return false;
@@ -1237,16 +1241,12 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 	 * chained in ep->ovflist and requeued later on.
 	 */
 	if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) {
-		if (epi->next == EP_UNACTIVE_PTR &&
-		    chain_epi_lockless(epi))
+		if (chain_epi_lockless(epi))
+			ep_pm_stay_awake_rcu(epi);
+	} else if (!ep_is_linked(epi)) {
+		/* In the usual case, add event to ready list. */
+		if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist))
 			ep_pm_stay_awake_rcu(epi);
-		goto out_unlock;
-	}
-
-	/* If this file is already in the ready list we exit soon */
-	if (!ep_is_linked(epi) &&
-	    list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) {
-		ep_pm_stay_awake_rcu(epi);
 	}
 
 	/*
@@ -1822,7 +1822,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 {
 	int res = 0, eavail, timed_out = 0;
 	u64 slack = 0;
-	bool waiter = false;
 	wait_queue_entry_t wait;
 	ktime_t expires, *to = NULL;
 
@@ -1867,55 +1866,75 @@ fetch_events:
 	 */
 	ep_reset_busy_poll_napi_id(ep);
 
-	/*
-	 * We don't have any available event to return to the caller.  We need
-	 * to sleep here, and we will be woken by ep_poll_callback() when events
-	 * become available.
-	 */
-	if (!waiter) {
-		waiter = true;
-		init_waitqueue_entry(&wait, current);
+	do {
+		/*
+		 * Internally init_wait() uses autoremove_wake_function(),
+		 * thus wait entry is removed from the wait queue on each
+		 * wakeup. Why it is important? In case of several waiters
+		 * each new wakeup will hit the next waiter, giving it the
+		 * chance to harvest new event. Otherwise wakeup can be
+		 * lost. This is also good performance-wise, because on
+		 * normal wakeup path no need to call __remove_wait_queue()
+		 * explicitly, thus ep->lock is not taken, which halts the
+		 * event delivery.
+		 */
+		init_wait(&wait);
 
 		write_lock_irq(&ep->lock);
-		__add_wait_queue_exclusive(&ep->wq, &wait);
-		write_unlock_irq(&ep->lock);
-	}
-
-	for (;;) {
 		/*
-		 * We don't want to sleep if the ep_poll_callback() sends us
-		 * a wakeup in between. That's why we set the task state
-		 * to TASK_INTERRUPTIBLE before doing the checks.
+		 * Barrierless variant, waitqueue_active() is called under
+		 * the same lock on wakeup ep_poll_callback() side, so it
+		 * is safe to avoid an explicit barrier.
 		 */
-		set_current_state(TASK_INTERRUPTIBLE);
+		__set_current_state(TASK_INTERRUPTIBLE);
+
 		/*
-		 * Always short-circuit for fatal signals to allow
-		 * threads to make a timely exit without the chance of
-		 * finding more events available and fetching
-		 * repeatedly.
+		 * Do the final check under the lock. ep_scan_ready_list()
+		 * plays with two lists (->rdllist and ->ovflist) and there
+		 * is always a race when both lists are empty for short
+		 * period of time although events are pending, so lock is
+		 * important.
 		 */
-		if (fatal_signal_pending(current)) {
-			res = -EINTR;
-			break;
+		eavail = ep_events_available(ep);
+		if (!eavail) {
+			if (signal_pending(current))
+				res = -EINTR;
+			else
+				__add_wait_queue_exclusive(&ep->wq, &wait);
 		}
+		write_unlock_irq(&ep->lock);
 
-		eavail = ep_events_available(ep);
-		if (eavail)
+		if (eavail || res)
 			break;
-		if (signal_pending(current)) {
-			res = -EINTR;
-			break;
-		}
 
 		if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) {
 			timed_out = 1;
 			break;
 		}
-	}
+
+		/* We were woken up, thus go and try to harvest some events */
+		eavail = 1;
+
+	} while (0);
 
 	__set_current_state(TASK_RUNNING);
 
+	if (!list_empty_careful(&wait.entry)) {
+		write_lock_irq(&ep->lock);
+		__remove_wait_queue(&ep->wq, &wait);
+		write_unlock_irq(&ep->lock);
+	}
+
 send_events:
+	if (fatal_signal_pending(current)) {
+		/*
+		 * Always short-circuit for fatal signals to allow
+		 * threads to make a timely exit without the chance of
+		 * finding more events available and fetching
+		 * repeatedly.
+		 */
+		res = -EINTR;
+	}
 	/*
 	 * Try to transfer events to user space. In case we get 0 events and
 	 * there's still timeout left over, we go trying again in search of
@@ -1925,12 +1944,6 @@ send_events:
 	    !(res = ep_send_events(ep, events, maxevents)) && !timed_out)
 		goto fetch_events;
 
-	if (waiter) {
-		write_lock_irq(&ep->lock);
-		__remove_wait_queue(&ep->wq, &wait);
-		write_unlock_irq(&ep->lock);
-	}
-
 	return res;
 }
 
diff --git a/fs/exec.c b/fs/exec.c
index 06b4c550af5d..2c465119affc 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1317,6 +1317,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 	 */
 	set_mm_exe_file(bprm->mm, bprm->file);
 
+	would_dump(bprm, bprm->file);
+
 	/*
 	 * Release all of the old mmap stuff
 	 */
@@ -1876,8 +1878,6 @@ static int __do_execve_file(int fd, struct filename *filename,
 	if (retval < 0)
 		goto out;
 
-	would_dump(bprm, bprm->file);
-
 	retval = exec_binprm(bprm);
 	if (retval < 0)
 		goto out;
diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c
index 6a04cc02565a..6774a5a6ded8 100644
--- a/fs/exfat/balloc.c
+++ b/fs/exfat/balloc.c
@@ -91,7 +91,6 @@ static int exfat_allocate_bitmap(struct super_block *sb,
 		}
 	}
 
-	sbi->pbr_bh = NULL;
 	return 0;
 }
 
@@ -137,8 +136,6 @@ void exfat_free_bitmap(struct exfat_sb_info *sbi)
 {
 	int i;
 
-	brelse(sbi->pbr_bh);
-
 	for (i = 0; i < sbi->map_sectors; i++)
 		__brelse(sbi->vol_amap[i]);
 
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 67d4e46fb810..d67fb8a6f770 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -507,6 +507,7 @@ void exfat_msg(struct super_block *sb, const char *lv, const char *fmt, ...)
 		__printf(3, 4) __cold;
 void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts,
 		u8 tz, __le16 time, __le16 date, u8 time_ms);
+void exfat_truncate_atime(struct timespec64 *ts);
 void exfat_set_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts,
 		u8 *tz, __le16 *time, __le16 *date, u8 *time_ms);
 unsigned short exfat_calc_chksum_2byte(void *data, int len,
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 483f683757aa..c9db8eb0cfc3 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -273,6 +273,7 @@ int exfat_getattr(const struct path *path, struct kstat *stat,
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 
 	generic_fillattr(inode, stat);
+	exfat_truncate_atime(&stat->atime);
 	stat->result_mask |= STATX_BTIME;
 	stat->btime.tv_sec = ei->i_crtime.tv_sec;
 	stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
@@ -339,6 +340,7 @@ int exfat_setattr(struct dentry *dentry, struct iattr *attr)
 	}
 
 	setattr_copy(inode, attr);
+	exfat_truncate_atime(&inode->i_atime);
 	mark_inode_dirty(inode);
 
 out:
@@ -346,12 +348,13 @@ out:
 }
 
 const struct file_operations exfat_file_operations = {
-	.llseek      = generic_file_llseek,
-	.read_iter   = generic_file_read_iter,
-	.write_iter  = generic_file_write_iter,
-	.mmap        = generic_file_mmap,
-	.fsync       = generic_file_fsync,
-	.splice_read = generic_file_splice_read,
+	.llseek		= generic_file_llseek,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
+	.mmap		= generic_file_mmap,
+	.fsync		= generic_file_fsync,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
 };
 
 const struct inode_operations exfat_file_inode_operations = {
diff --git a/fs/exfat/misc.c b/fs/exfat/misc.c
index 14a3300848f6..ebd2cbe3cbc1 100644
--- a/fs/exfat/misc.c
+++ b/fs/exfat/misc.c
@@ -88,7 +88,8 @@ void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts,
 	if (time_ms) {
 		ts->tv_sec += time_ms / 100;
 		ts->tv_nsec = (time_ms % 100) * 10 * NSEC_PER_MSEC;
-	}
+	} else
+		ts->tv_nsec = 0;
 
 	if (tz & EXFAT_TZ_VALID)
 		/* Adjust timezone to UTC0. */
@@ -124,6 +125,17 @@ void exfat_set_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts,
 	*tz = EXFAT_TZ_VALID;
 }
 
+/*
+ * The timestamp for access_time has double seconds granularity.
+ * (There is no 10msIncrement field for access_time unlike create/modify_time)
+ * atime also has only a 2-second resolution.
+ */
+void exfat_truncate_atime(struct timespec64 *ts)
+{
+	ts->tv_sec = round_down(ts->tv_sec, 2);
+	ts->tv_nsec = 0;
+}
+
 unsigned short exfat_calc_chksum_2byte(void *data, int len,
 		unsigned short chksum, int type)
 {
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index a8681d91f569..a2659a8a68a1 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -595,6 +595,7 @@ static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	inode_inc_iversion(inode);
 	inode->i_mtime = inode->i_atime = inode->i_ctime =
 		EXFAT_I(inode)->i_crtime = current_time(inode);
+	exfat_truncate_atime(&inode->i_atime);
 	/* timestamp is already written, so mark_inode_dirty() is unneeded. */
 
 	d_instantiate(dentry, inode);
@@ -691,6 +692,7 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
 			exfat_fs_error(sb,
 				"non-zero size file starts with zero cluster (size : %llu, p_dir : %u, entry : 0x%08x)",
 				i_size_read(dir), ei->dir.dir, ei->entry);
+			kfree(es);
 			return -EIO;
 		}
 
@@ -854,6 +856,7 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry)
 
 	inode_inc_iversion(dir);
 	dir->i_mtime = dir->i_atime = current_time(dir);
+	exfat_truncate_atime(&dir->i_atime);
 	if (IS_DIRSYNC(dir))
 		exfat_sync_inode(dir);
 	else
@@ -861,6 +864,7 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry)
 
 	clear_nlink(inode);
 	inode->i_mtime = inode->i_atime = current_time(inode);
+	exfat_truncate_atime(&inode->i_atime);
 	exfat_unhash_inode(inode);
 	exfat_d_version_set(dentry, inode_query_iversion(dir));
 unlock:
@@ -903,6 +907,7 @@ static int exfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode_inc_iversion(inode);
 	inode->i_mtime = inode->i_atime = inode->i_ctime =
 		EXFAT_I(inode)->i_crtime = current_time(inode);
+	exfat_truncate_atime(&inode->i_atime);
 	/* timestamp is already written, so mark_inode_dirty() is unneeded. */
 
 	d_instantiate(dentry, inode);
@@ -1019,6 +1024,7 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 
 	inode_inc_iversion(dir);
 	dir->i_mtime = dir->i_atime = current_time(dir);
+	exfat_truncate_atime(&dir->i_atime);
 	if (IS_DIRSYNC(dir))
 		exfat_sync_inode(dir);
 	else
@@ -1027,6 +1033,7 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry)
 
 	clear_nlink(inode);
 	inode->i_mtime = inode->i_atime = current_time(inode);
+	exfat_truncate_atime(&inode->i_atime);
 	exfat_unhash_inode(inode);
 	exfat_d_version_set(dentry, inode_query_iversion(dir));
 unlock:
@@ -1387,6 +1394,7 @@ static int exfat_rename(struct inode *old_dir, struct dentry *old_dentry,
 	inode_inc_iversion(new_dir);
 	new_dir->i_ctime = new_dir->i_mtime = new_dir->i_atime =
 		EXFAT_I(new_dir)->i_crtime = current_time(new_dir);
+	exfat_truncate_atime(&new_dir->i_atime);
 	if (IS_DIRSYNC(new_dir))
 		exfat_sync_inode(new_dir);
 	else
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index 16ed202ef527..a846ff555656 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -49,6 +49,7 @@ static void exfat_put_super(struct super_block *sb)
 		sync_blockdev(sb->s_bdev);
 	exfat_set_vol_flags(sb, VOL_CLEAN);
 	exfat_free_bitmap(sbi);
+	brelse(sbi->pbr_bh);
 	mutex_unlock(&sbi->s_lock);
 
 	call_rcu(&sbi->rcu, exfat_delayed_free);
@@ -100,7 +101,7 @@ static int exfat_statfs(struct dentry *dentry, struct kstatfs *buf)
 int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flag)
 {
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
-	struct pbr64 *bpb;
+	struct pbr64 *bpb = (struct pbr64 *)sbi->pbr_bh->b_data;
 	bool sync = 0;
 
 	/* flags are not changed */
@@ -115,15 +116,6 @@ int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flag)
 	if (sb_rdonly(sb))
 		return 0;
 
-	if (!sbi->pbr_bh) {
-		sbi->pbr_bh = sb_bread(sb, 0);
-		if (!sbi->pbr_bh) {
-			exfat_msg(sb, KERN_ERR, "failed to read boot sector");
-			return -ENOMEM;
-		}
-	}
-
-	bpb = (struct pbr64 *)sbi->pbr_bh->b_data;
 	bpb->bsx.vol_flags = cpu_to_le16(new_flag);
 
 	if (new_flag == VOL_DIRTY && !buffer_dirty(sbi->pbr_bh))
@@ -159,7 +151,6 @@ static int exfat_show_options(struct seq_file *m, struct dentry *root)
 		seq_puts(m, ",iocharset=utf8");
 	else if (sbi->nls_io)
 		seq_printf(m, ",iocharset=%s", sbi->nls_io->charset);
-	seq_printf(m, ",bps=%ld", sb->s_blocksize);
 	if (opts->errors == EXFAT_ERRORS_CONT)
 		seq_puts(m, ",errors=continue");
 	else if (opts->errors == EXFAT_ERRORS_PANIC)
@@ -212,6 +203,12 @@ enum {
 	Opt_errors,
 	Opt_discard,
 	Opt_time_offset,
+
+	/* Deprecated options */
+	Opt_utf8,
+	Opt_debug,
+	Opt_namecase,
+	Opt_codepage,
 };
 
 static const struct constant_table exfat_param_enums[] = {
@@ -232,6 +229,14 @@ static const struct fs_parameter_spec exfat_parameters[] = {
 	fsparam_enum("errors",			Opt_errors, exfat_param_enums),
 	fsparam_flag("discard",			Opt_discard),
 	fsparam_s32("time_offset",		Opt_time_offset),
+	__fsparam(NULL, "utf8",			Opt_utf8, fs_param_deprecated,
+		  NULL),
+	__fsparam(NULL, "debug",		Opt_debug, fs_param_deprecated,
+		  NULL),
+	__fsparam(fs_param_is_u32, "namecase",	Opt_namecase,
+		  fs_param_deprecated, NULL),
+	__fsparam(fs_param_is_u32, "codepage",	Opt_codepage,
+		  fs_param_deprecated, NULL),
 	{}
 };
 
@@ -287,6 +292,11 @@ static int exfat_parse_param(struct fs_context *fc, struct fs_parameter *param)
 			return -EINVAL;
 		opts->time_offset = result.int_32;
 		break;
+	case Opt_utf8:
+	case Opt_debug:
+	case Opt_namecase:
+	case Opt_codepage:
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -351,14 +361,15 @@ static int exfat_read_root(struct inode *inode)
 	exfat_save_attr(inode, ATTR_SUBDIR);
 	inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
 		current_time(inode);
+	exfat_truncate_atime(&inode->i_atime);
 	exfat_cache_init_inode(inode);
 	return 0;
 }
 
-static struct pbr *exfat_read_pbr_with_logical_sector(struct super_block *sb,
-		struct buffer_head **prev_bh)
+static struct pbr *exfat_read_pbr_with_logical_sector(struct super_block *sb)
 {
-	struct pbr *p_pbr = (struct pbr *) (*prev_bh)->b_data;
+	struct exfat_sb_info *sbi = EXFAT_SB(sb);
+	struct pbr *p_pbr = (struct pbr *) (sbi->pbr_bh)->b_data;
 	unsigned short logical_sect = 0;
 
 	logical_sect = 1 << p_pbr->bsx.f64.sect_size_bits;
@@ -378,26 +389,23 @@ static struct pbr *exfat_read_pbr_with_logical_sector(struct super_block *sb,
 	}
 
 	if (logical_sect > sb->s_blocksize) {
-		struct buffer_head *bh = NULL;
-
-		__brelse(*prev_bh);
-		*prev_bh = NULL;
+		brelse(sbi->pbr_bh);
+		sbi->pbr_bh = NULL;
 
 		if (!sb_set_blocksize(sb, logical_sect)) {
 			exfat_msg(sb, KERN_ERR,
 				"unable to set blocksize %u", logical_sect);
 			return NULL;
 		}
-		bh = sb_bread(sb, 0);
-		if (!bh) {
+		sbi->pbr_bh = sb_bread(sb, 0);
+		if (!sbi->pbr_bh) {
 			exfat_msg(sb, KERN_ERR,
 				"unable to read boot sector (logical sector size = %lu)",
 				sb->s_blocksize);
 			return NULL;
 		}
 
-		*prev_bh = bh;
-		p_pbr = (struct pbr *) bh->b_data;
+		p_pbr = (struct pbr *)sbi->pbr_bh->b_data;
 	}
 	return p_pbr;
 }
@@ -408,21 +416,20 @@ static int __exfat_fill_super(struct super_block *sb)
 	int ret;
 	struct pbr *p_pbr;
 	struct pbr64 *p_bpb;
-	struct buffer_head *bh;
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 
 	/* set block size to read super block */
 	sb_min_blocksize(sb, 512);
 
 	/* read boot sector */
-	bh = sb_bread(sb, 0);
-	if (!bh) {
+	sbi->pbr_bh = sb_bread(sb, 0);
+	if (!sbi->pbr_bh) {
 		exfat_msg(sb, KERN_ERR, "unable to read boot sector");
 		return -EIO;
 	}
 
 	/* PRB is read */
-	p_pbr = (struct pbr *)bh->b_data;
+	p_pbr = (struct pbr *)sbi->pbr_bh->b_data;
 
 	/* check the validity of PBR */
 	if (le16_to_cpu((p_pbr->signature)) != PBR_SIGNATURE) {
@@ -433,7 +440,7 @@ static int __exfat_fill_super(struct super_block *sb)
 
 
 	/* check logical sector size */
-	p_pbr = exfat_read_pbr_with_logical_sector(sb, &bh);
+	p_pbr = exfat_read_pbr_with_logical_sector(sb);
 	if (!p_pbr) {
 		ret = -EIO;
 		goto free_bh;
@@ -514,7 +521,7 @@ free_alloc_bitmap:
 free_upcase_table:
 	exfat_free_upcase_table(sbi);
 free_bh:
-	brelse(bh);
+	brelse(sbi->pbr_bh);
 	return ret;
 }
 
@@ -531,17 +538,18 @@ static int exfat_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (opts->discard) {
 		struct request_queue *q = bdev_get_queue(sb->s_bdev);
 
-		if (!blk_queue_discard(q))
+		if (!blk_queue_discard(q)) {
 			exfat_msg(sb, KERN_WARNING,
 				"mounting with \"discard\" option, but the device does not support discard");
-		opts->discard = 0;
+			opts->discard = 0;
+		}
 	}
 
 	sb->s_flags |= SB_NODIRATIME;
 	sb->s_magic = EXFAT_SUPER_MAGIC;
 	sb->s_op = &exfat_sops;
 
-	sb->s_time_gran = 1;
+	sb->s_time_gran = 10 * NSEC_PER_MSEC;
 	sb->s_time_min = EXFAT_MIN_TIMESTAMP_SECS;
 	sb->s_time_max = EXFAT_MAX_TIMESTAMP_SECS;
 
@@ -605,6 +613,7 @@ put_inode:
 free_table:
 	exfat_free_upcase_table(sbi);
 	exfat_free_bitmap(sbi);
+	brelse(sbi->pbr_bh);
 
 check_nls_io:
 	unload_nls(sbi->nls_io);
@@ -717,6 +726,7 @@ static void __exit exit_exfat_fs(void)
 module_init(init_exfat_fs);
 module_exit(exit_exfat_fs);
 
+MODULE_ALIAS_FS("exfat");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("exFAT filesystem support");
 MODULE_AUTHOR("Samsung Electronics Co., Ltd.");
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 0e0a4d6209c7..a32e5f7b5385 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -410,7 +410,7 @@ verified:
  * Read the bitmap for a given block_group,and validate the
  * bits for block/inode/inode tables are set in the bitmaps
  *
- * Return buffer_head on success or NULL in case of failure.
+ * Return buffer_head on success or an ERR_PTR in case of failure.
  */
 struct buffer_head *
 ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
@@ -502,7 +502,7 @@ out:
 	return ERR_PTR(err);
 }
 
-/* Returns 0 on success, 1 on error */
+/* Returns 0 on success, -errno on error */
 int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
 			   struct buffer_head *bh)
 {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 91eb4381cae5..3147bb0cf82a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -722,7 +722,7 @@ enum {
 #define EXT4_MAX_BLOCK_FILE_PHYS	0xFFFFFFFF
 
 /* Max logical block we can support */
-#define EXT4_MAX_LOGICAL_BLOCK		0xFFFFFFFF
+#define EXT4_MAX_LOGICAL_BLOCK		0xFFFFFFFE
 
 /*
  * Structure of an inode on the disk
@@ -1357,11 +1357,9 @@ struct ext4_super_block {
  */
 #define EXT4_MF_MNTDIR_SAMPLED		0x0001
 #define EXT4_MF_FS_ABORTED		0x0002	/* Fatal error detected */
-#define EXT4_MF_TEST_DUMMY_ENCRYPTION	0x0004
 
 #ifdef CONFIG_FS_ENCRYPTION
-#define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely((sbi)->s_mount_flags & \
-						EXT4_MF_TEST_DUMMY_ENCRYPTION))
+#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_ctx.ctx != NULL)
 #else
 #define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
 #endif
@@ -1551,6 +1549,9 @@ struct ext4_sb_info {
 	struct ratelimit_state s_warning_ratelimit_state;
 	struct ratelimit_state s_msg_ratelimit_state;
 
+	/* Encryption context for '-o test_dummy_encryption' */
+	struct fscrypt_dummy_context s_dummy_enc_ctx;
+
 	/*
 	 * Barrier between writepages ops and changing any inode's JOURNAL_DATA
 	 * or EXTENTS flag.
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 7f16e1af8d5c..0c76cdd44d90 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -338,9 +338,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 		if (inode && inode_needs_sync(inode)) {
 			sync_dirty_buffer(bh);
 			if (buffer_req(bh) && !buffer_uptodate(bh)) {
-				struct ext4_super_block *es;
-
-				es = EXT4_SB(inode->i_sb)->s_es;
 				ext4_error_inode_err(inode, where, line,
 						     bh->b_blocknr, EIO,
 					"IO error syncing itable block");
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 031752cfb6f7..2b4b94542e34 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3374,8 +3374,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		(unsigned long long)map->m_lblk, map_len);
 
 	sbi = EXT4_SB(inode->i_sb);
-	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
-		inode->i_sb->s_blocksize_bits;
+	eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1)
+			>> inode->i_sb->s_blocksize_bits;
 	if (eof_block < map->m_lblk + map_len)
 		eof_block = map->m_lblk + map_len;
 
@@ -3627,8 +3627,8 @@ static int ext4_split_convert_extents(handle_t *handle,
 		  __func__, inode->i_ino,
 		  (unsigned long long)map->m_lblk, map->m_len);
 
-	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
-		inode->i_sb->s_blocksize_bits;
+	eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1)
+			>> inode->i_sb->s_blocksize_bits;
 	if (eof_block < map->m_lblk + map->m_len)
 		eof_block = map->m_lblk + map->m_len;
 	/*
@@ -4832,6 +4832,28 @@ static const struct iomap_ops ext4_iomap_xattr_ops = {
 	.iomap_begin		= ext4_iomap_xattr_begin,
 };
 
+static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len)
+{
+	u64 maxbytes;
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		maxbytes = inode->i_sb->s_maxbytes;
+	else
+		maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
+
+	if (*len == 0)
+		return -EINVAL;
+	if (start > maxbytes)
+		return -EFBIG;
+
+	/*
+	 * Shrink request scope to what the fs can actually handle.
+	 */
+	if (*len > maxbytes || (maxbytes - *len) < start)
+		*len = maxbytes - start;
+	return 0;
+}
+
 static int _ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			__u64 start, __u64 len, bool from_es_cache)
 {
@@ -4852,6 +4874,15 @@ static int _ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (fiemap_check_flags(fieinfo, ext4_fiemap_flags))
 		return -EBADR;
 
+	/*
+	 * For bitmap files the maximum size limit could be smaller than
+	 * s_maxbytes, so check len here manually instead of just relying on the
+	 * generic check.
+	 */
+	error = ext4_fiemap_check_ranges(inode, start, &len);
+	if (error)
+		return error;
+
 	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
 		fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR;
 		error = iomap_fiemap(inode, fieinfo, start, len,
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index b420c9dc444d..4b8c9a9bdf0c 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -113,7 +113,7 @@ verified:
  * Read the inode allocation bitmap for a given block_group, reading
  * into the specified slot in the superblock's bitmap cache.
  *
- * Return buffer_head of bitmap on success or NULL.
+ * Return buffer_head of bitmap on success, or an ERR_PTR on error.
  */
 static struct buffer_head *
 ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
@@ -662,7 +662,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
  * block has been written back to disk.  (Yes, these values are
  * somewhat arbitrary...)
  */
-#define RECENTCY_MIN	5
+#define RECENTCY_MIN	60
 #define RECENTCY_DIRTY	300
 
 static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e416096fc081..2a4aae6acdcb 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1973,7 +1973,7 @@ static int ext4_writepage(struct page *page,
 	bool keep_towrite = false;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
-		ext4_invalidatepage(page, 0, PAGE_SIZE);
+		inode->i_mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE);
 		unlock_page(page);
 		return -EIO;
 	}
@@ -4364,7 +4364,7 @@ make_io:
 			if (end > table)
 				end = table;
 			while (b <= end)
-				sb_breadahead(sb, b++);
+				sb_breadahead_unmovable(sb, b++);
 		}
 
 		/*
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bfc1281fc4cb..0746532ba463 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -733,29 +733,6 @@ static void ext4_fill_fsxattr(struct inode *inode, struct fsxattr *fa)
 		fa->fsx_projid = from_kprojid(&init_user_ns, ei->i_projid);
 }
 
-/* copied from fs/ioctl.c */
-static int fiemap_check_ranges(struct super_block *sb,
-			       u64 start, u64 len, u64 *new_len)
-{
-	u64 maxbytes = (u64) sb->s_maxbytes;
-
-	*new_len = len;
-
-	if (len == 0)
-		return -EINVAL;
-
-	if (start > maxbytes)
-		return -EFBIG;
-
-	/*
-	 * Shrink request scope to what the fs can actually handle.
-	 */
-	if (len > maxbytes || (maxbytes - len) < start)
-		*new_len = maxbytes - start;
-
-	return 0;
-}
-
 /* So that the fiemap access checks can't overflow on 32 bit machines. */
 #define FIEMAP_MAX_EXTENTS	(UINT_MAX / sizeof(struct fiemap_extent))
 
@@ -765,8 +742,6 @@ static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg)
 	struct fiemap __user *ufiemap = (struct fiemap __user *) arg;
 	struct fiemap_extent_info fieinfo = { 0, };
 	struct inode *inode = file_inode(filp);
-	struct super_block *sb = inode->i_sb;
-	u64 len;
 	int error;
 
 	if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap)))
@@ -775,11 +750,6 @@ static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg)
 	if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
 		return -EINVAL;
 
-	error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
-				    &len);
-	if (error)
-		return error;
-
 	fieinfo.fi_flags = fiemap.fm_flags;
 	fieinfo.fi_extents_max = fiemap.fm_extent_count;
 	fieinfo.fi_extents_start = ufiemap->fm_extents;
@@ -792,7 +762,8 @@ static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg)
 	if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
 		filemap_write_and_wait(inode->i_mapping);
 
-	error = ext4_get_es_cache(inode, &fieinfo, fiemap.fm_start, len);
+	error = ext4_get_es_cache(inode, &fieinfo, fiemap.fm_start,
+			fiemap.fm_length);
 	fiemap.fm_flags = fieinfo.fi_flags;
 	fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
 	if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap)))
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 87c85be4c12e..30d5d97548c4 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1943,7 +1943,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 	int free;
 
 	free = e4b->bd_info->bb_free;
-	BUG_ON(free <= 0);
+	if (WARN_ON(free <= 0))
+		return;
 
 	i = e4b->bd_info->bb_first_free;
 
@@ -1966,7 +1967,8 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 		}
 
 		mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex);
-		BUG_ON(ex.fe_len <= 0);
+		if (WARN_ON(ex.fe_len <= 0))
+			break;
 		if (free < ex.fe_len) {
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9728e7b0e84f..4a3d21972011 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -596,7 +596,6 @@ void __ext4_error_file(struct file *file, const char *function,
 {
 	va_list args;
 	struct va_format vaf;
-	struct ext4_super_block *es;
 	struct inode *inode = file_inode(file);
 	char pathname[80], *path;
 
@@ -604,7 +603,6 @@ void __ext4_error_file(struct file *file, const char *function,
 		return;
 
 	trace_ext4_error(inode->i_sb, function, line);
-	es = EXT4_SB(inode->i_sb)->s_es;
 	if (ext4_error_ratelimit(inode->i_sb)) {
 		path = file_path(file, pathname, sizeof(pathname));
 		if (IS_ERR(path))
@@ -1108,6 +1106,7 @@ static void ext4_put_super(struct super_block *sb)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->s_blockgroup_lock);
 	fs_put_dax(sbi->s_daxdev);
+	fscrypt_free_dummy_context(&sbi->s_dummy_enc_ctx);
 #ifdef CONFIG_UNICODE
 	utf8_unload(sbi->s_encoding);
 #endif
@@ -1391,9 +1390,10 @@ retry:
 	return res;
 }
 
-static bool ext4_dummy_context(struct inode *inode)
+static const union fscrypt_context *
+ext4_get_dummy_context(struct super_block *sb)
 {
-	return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
+	return EXT4_SB(sb)->s_dummy_enc_ctx.ctx;
 }
 
 static bool ext4_has_stable_inodes(struct super_block *sb)
@@ -1412,7 +1412,7 @@ static const struct fscrypt_operations ext4_cryptops = {
 	.key_prefix		= "ext4:",
 	.get_context		= ext4_get_context,
 	.set_context		= ext4_set_context,
-	.dummy_context		= ext4_dummy_context,
+	.get_dummy_context	= ext4_get_dummy_context,
 	.empty_dir		= ext4_empty_dir,
 	.max_namelen		= EXT4_NAME_LEN,
 	.has_stable_inodes	= ext4_has_stable_inodes,
@@ -1607,6 +1607,7 @@ static const match_table_t tokens = {
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
+	{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
 	{Opt_nombcache, "nombcache"},
 	{Opt_nombcache, "no_mbcache"},	/* for backward compatibility */
@@ -1818,7 +1819,7 @@ static const struct mount_opts {
 	{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
 	{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
 	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
-	{Opt_test_dummy_encryption, 0, MOPT_GTE0},
+	{Opt_test_dummy_encryption, 0, MOPT_STRING},
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
 	{Opt_err, 0, 0}
 };
@@ -1853,6 +1854,48 @@ static int ext4_sb_read_encoding(const struct ext4_super_block *es,
 }
 #endif
 
+static int ext4_set_test_dummy_encryption(struct super_block *sb,
+					  const char *opt,
+					  const substring_t *arg,
+					  bool is_remount)
+{
+#ifdef CONFIG_FS_ENCRYPTION
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int err;
+
+	/*
+	 * This mount option is just for testing, and it's not worthwhile to
+	 * implement the extra complexity (e.g. RCU protection) that would be
+	 * needed to allow it to be set or changed during remount.  We do allow
+	 * it to be specified during remount, but only if there is no change.
+	 */
+	if (is_remount && !sbi->s_dummy_enc_ctx.ctx) {
+		ext4_msg(sb, KERN_WARNING,
+			 "Can't set test_dummy_encryption on remount");
+		return -1;
+	}
+	err = fscrypt_set_test_dummy_encryption(sb, arg, &sbi->s_dummy_enc_ctx);
+	if (err) {
+		if (err == -EEXIST)
+			ext4_msg(sb, KERN_WARNING,
+				 "Can't change test_dummy_encryption on remount");
+		else if (err == -EINVAL)
+			ext4_msg(sb, KERN_WARNING,
+				 "Value of option \"%s\" is unrecognized", opt);
+		else
+			ext4_msg(sb, KERN_WARNING,
+				 "Error processing option \"%s\" [%d]",
+				 opt, err);
+		return -1;
+	}
+	ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled");
+#else
+	ext4_msg(sb, KERN_WARNING,
+		 "Test dummy encryption mount option ignored");
+#endif
+	return 1;
+}
+
 static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			    substring_t *args, unsigned long *journal_devnum,
 			    unsigned int *journal_ioprio, int is_remount)
@@ -2049,14 +2092,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		*journal_ioprio =
 			IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
 	} else if (token == Opt_test_dummy_encryption) {
-#ifdef CONFIG_FS_ENCRYPTION
-		sbi->s_mount_flags |= EXT4_MF_TEST_DUMMY_ENCRYPTION;
-		ext4_msg(sb, KERN_WARNING,
-			 "Test dummy encryption mode enabled");
-#else
-		ext4_msg(sb, KERN_WARNING,
-			 "Test dummy encryption mount option ignored");
-#endif
+		return ext4_set_test_dummy_encryption(sb, opt, &args[0],
+						      is_remount);
 	} else if (m->flags & MOPT_DATAJ) {
 		if (is_remount) {
 			if (!sbi->s_journal)
@@ -2313,8 +2350,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb);
 	if (test_opt(sb, DATA_ERR_ABORT))
 		SEQ_OPTS_PUTS("data_err=abort");
-	if (DUMMY_ENCRYPTION_ENABLED(sbi))
-		SEQ_OPTS_PUTS("test_dummy_encryption");
+
+	fscrypt_show_test_dummy_encryption(seq, sep, sb);
 
 	ext4_show_quota_options(seq, sb);
 	return 0;
@@ -4340,7 +4377,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/* Pre-read the descriptors into the buffer cache */
 	for (i = 0; i < db_count; i++) {
 		block = descriptor_loc(sb, logical_sb_block, i);
-		sb_breadahead(sb, block);
+		sb_breadahead_unmovable(sb, block);
 	}
 
 	for (i = 0; i < db_count; i++) {
@@ -4782,6 +4819,7 @@ failed_mount:
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(get_qf_name(sb, sbi, i));
 #endif
+	fscrypt_free_dummy_context(&sbi->s_dummy_enc_ctx);
 	ext4_blkdev_remove(sbi);
 	brelse(bh);
 out_fail:
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 04bfaf63752c..6c9fc9e21c13 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -293,6 +293,7 @@ EXT4_ATTR_FEATURE(batched_discard);
 EXT4_ATTR_FEATURE(meta_bg_resize);
 #ifdef CONFIG_FS_ENCRYPTION
 EXT4_ATTR_FEATURE(encryption);
+EXT4_ATTR_FEATURE(test_dummy_encryption_v2);
 #endif
 #ifdef CONFIG_UNICODE
 EXT4_ATTR_FEATURE(casefold);
@@ -308,6 +309,7 @@ static struct attribute *ext4_feat_attrs[] = {
 	ATTR_LIST(meta_bg_resize),
 #ifdef CONFIG_FS_ENCRYPTION
 	ATTR_LIST(encryption),
+	ATTR_LIST(test_dummy_encryption_v2),
 #endif
 #ifdef CONFIG_UNICODE
 	ATTR_LIST(casefold),
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ba470d5687fe..157eec348970 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -138,7 +138,7 @@ struct f2fs_mount_info {
 	int fsync_mode;			/* fsync policy */
 	int fs_mode;			/* fs mode: LFS or ADAPTIVE */
 	int bggc_mode;			/* bggc mode: off, on or sync */
-	bool test_dummy_encryption;	/* test dummy encryption */
+	struct fscrypt_dummy_context dummy_enc_ctx; /* test dummy encryption */
 	block_t unusable_cap;		/* Amount of space allowed to be
 					 * unusable when disabling checkpoint
 					 */
@@ -1259,7 +1259,7 @@ enum fsync_mode {
 
 #ifdef CONFIG_FS_ENCRYPTION
 #define DUMMY_ENCRYPTION_ENABLED(sbi) \
-			(unlikely(F2FS_OPTION(sbi).test_dummy_encryption))
+	(unlikely(F2FS_OPTION(sbi).dummy_enc_ctx.ctx != NULL))
 #else
 #define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
 #endif
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index 5bc4dcd8fc03..8c4ea5003ef8 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -12,7 +12,6 @@
 #include <linux/types.h>
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
-#include <linux/cryptohash.h>
 #include <linux/pagemap.h>
 #include <linux/unicode.h>
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f2dfc21c6abb..8a9955902d84 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -202,6 +202,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_whint, "whint_mode=%s"},
 	{Opt_alloc, "alloc_mode=%s"},
 	{Opt_fsync, "fsync_mode=%s"},
+	{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
 	{Opt_checkpoint_disable, "checkpoint=disable"},
 	{Opt_checkpoint_disable_cap, "checkpoint=disable:%u"},
@@ -394,7 +395,52 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi)
 }
 #endif
 
-static int parse_options(struct super_block *sb, char *options)
+static int f2fs_set_test_dummy_encryption(struct super_block *sb,
+					  const char *opt,
+					  const substring_t *arg,
+					  bool is_remount)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+#ifdef CONFIG_FS_ENCRYPTION
+	int err;
+
+	if (!f2fs_sb_has_encrypt(sbi)) {
+		f2fs_err(sbi, "Encrypt feature is off");
+		return -EINVAL;
+	}
+
+	/*
+	 * This mount option is just for testing, and it's not worthwhile to
+	 * implement the extra complexity (e.g. RCU protection) that would be
+	 * needed to allow it to be set or changed during remount.  We do allow
+	 * it to be specified during remount, but only if there is no change.
+	 */
+	if (is_remount && !F2FS_OPTION(sbi).dummy_enc_ctx.ctx) {
+		f2fs_warn(sbi, "Can't set test_dummy_encryption on remount");
+		return -EINVAL;
+	}
+	err = fscrypt_set_test_dummy_encryption(
+		sb, arg, &F2FS_OPTION(sbi).dummy_enc_ctx);
+	if (err) {
+		if (err == -EEXIST)
+			f2fs_warn(sbi,
+				  "Can't change test_dummy_encryption on remount");
+		else if (err == -EINVAL)
+			f2fs_warn(sbi, "Value of option \"%s\" is unrecognized",
+				  opt);
+		else
+			f2fs_warn(sbi, "Error processing option \"%s\" [%d]",
+				  opt, err);
+		return -EINVAL;
+	}
+	f2fs_warn(sbi, "Test dummy encryption mode enabled");
+#else
+	f2fs_warn(sbi, "Test dummy encryption mount option ignored");
+#endif
+	return 0;
+}
+
+static int parse_options(struct super_block *sb, char *options, bool is_remount)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	substring_t args[MAX_OPT_ARGS];
@@ -403,9 +449,7 @@ static int parse_options(struct super_block *sb, char *options)
 	int arg = 0, ext_cnt;
 	kuid_t uid;
 	kgid_t gid;
-#ifdef CONFIG_QUOTA
 	int ret;
-#endif
 
 	if (!options)
 		return 0;
@@ -778,17 +822,10 @@ static int parse_options(struct super_block *sb, char *options)
 			kvfree(name);
 			break;
 		case Opt_test_dummy_encryption:
-#ifdef CONFIG_FS_ENCRYPTION
-			if (!f2fs_sb_has_encrypt(sbi)) {
-				f2fs_err(sbi, "Encrypt feature is off");
-				return -EINVAL;
-			}
-
-			F2FS_OPTION(sbi).test_dummy_encryption = true;
-			f2fs_info(sbi, "Test dummy encryption mode enabled");
-#else
-			f2fs_info(sbi, "Test dummy encryption mount option ignored");
-#endif
+			ret = f2fs_set_test_dummy_encryption(sb, p, &args[0],
+							     is_remount);
+			if (ret)
+				return ret;
 			break;
 		case Opt_checkpoint_disable_cap_perc:
 			if (args->from && match_int(args, &arg))
@@ -1213,6 +1250,7 @@ static void f2fs_put_super(struct super_block *sb)
 	for (i = 0; i < MAXQUOTAS; i++)
 		kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
 #endif
+	fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
 	destroy_percpu_info(sbi);
 	for (i = 0; i < NR_PAGE_TYPE; i++)
 		kvfree(sbi->write_io[i]);
@@ -1543,10 +1581,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_printf(seq, ",whint_mode=%s", "user-based");
 	else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS)
 		seq_printf(seq, ",whint_mode=%s", "fs-based");
-#ifdef CONFIG_FS_ENCRYPTION
-	if (F2FS_OPTION(sbi).test_dummy_encryption)
-		seq_puts(seq, ",test_dummy_encryption");
-#endif
+
+	fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb);
 
 	if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_DEFAULT)
 		seq_printf(seq, ",alloc_mode=%s", "default");
@@ -1575,7 +1611,6 @@ static void default_options(struct f2fs_sb_info *sbi)
 	F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
 	F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT;
 	F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX;
-	F2FS_OPTION(sbi).test_dummy_encryption = false;
 	F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
 	F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID);
 	F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZ4;
@@ -1734,7 +1769,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	default_options(sbi);
 
 	/* parse mount options */
-	err = parse_options(sb, data);
+	err = parse_options(sb, data, true);
 	if (err)
 		goto restore_opts;
 	checkpoint_changed =
@@ -2410,9 +2445,10 @@ static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
 				ctx, len, fs_data, XATTR_CREATE);
 }
 
-static bool f2fs_dummy_context(struct inode *inode)
+static const union fscrypt_context *
+f2fs_get_dummy_context(struct super_block *sb)
 {
-	return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode));
+	return F2FS_OPTION(F2FS_SB(sb)).dummy_enc_ctx.ctx;
 }
 
 static bool f2fs_has_stable_inodes(struct super_block *sb)
@@ -2431,7 +2467,7 @@ static const struct fscrypt_operations f2fs_cryptops = {
 	.key_prefix		= "f2fs:",
 	.get_context		= f2fs_get_context,
 	.set_context		= f2fs_set_context,
-	.dummy_context		= f2fs_dummy_context,
+	.get_dummy_context	= f2fs_get_dummy_context,
 	.empty_dir		= f2fs_empty_dir,
 	.max_namelen		= F2FS_NAME_LEN,
 	.has_stable_inodes	= f2fs_has_stable_inodes,
@@ -3366,7 +3402,7 @@ try_onemore:
 		goto free_sb_buf;
 	}
 
-	err = parse_options(sb, options);
+	err = parse_options(sb, options, false);
 	if (err)
 		goto free_options;
 
@@ -3769,6 +3805,7 @@ free_options:
 	for (i = 0; i < MAXQUOTAS; i++)
 		kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
 #endif
+	fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
 	kvfree(options);
 free_sb_buf:
 	kvfree(raw_super);
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index e3bbbef9b4f0..3162f46b3c9b 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -446,6 +446,7 @@ enum feat_id {
 	FEAT_SB_CHECKSUM,
 	FEAT_CASEFOLD,
 	FEAT_COMPRESSION,
+	FEAT_TEST_DUMMY_ENCRYPTION_V2,
 };
 
 static ssize_t f2fs_feature_show(struct f2fs_attr *a,
@@ -466,6 +467,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a,
 	case FEAT_SB_CHECKSUM:
 	case FEAT_CASEFOLD:
 	case FEAT_COMPRESSION:
+	case FEAT_TEST_DUMMY_ENCRYPTION_V2:
 		return sprintf(buf, "supported\n");
 	}
 	return 0;
@@ -563,6 +565,7 @@ F2FS_GENERAL_RO_ATTR(avg_vblocks);
 
 #ifdef CONFIG_FS_ENCRYPTION
 F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
+F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2, FEAT_TEST_DUMMY_ENCRYPTION_V2);
 #endif
 #ifdef CONFIG_BLK_DEV_ZONED
 F2FS_FEATURE_RO_ATTR(block_zoned, FEAT_BLKZONED);
@@ -647,6 +650,7 @@ ATTRIBUTE_GROUPS(f2fs);
 static struct attribute *f2fs_feat_attrs[] = {
 #ifdef CONFIG_FS_ENCRYPTION
 	ATTR_LIST(encryption),
+	ATTR_LIST(test_dummy_encryption_v2),
 #endif
 #ifdef CONFIG_BLK_DEV_ZONED
 	ATTR_LIST(block_zoned),
diff --git a/fs/file.c b/fs/file.c
index c8a4e4c86e55..abb8b7081d7a 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -70,7 +70,7 @@ static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
  */
 static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
 {
-	unsigned int cpy, set;
+	size_t cpy, set;
 
 	BUG_ON(nfdt->max_fds < ofdt->max_fds);
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 936a8ec6b48e..6306eaae378b 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -528,10 +528,12 @@ lower_metapath:
 
 		/* Advance in metadata tree. */
 		(mp->mp_list[hgt])++;
-		if (mp->mp_list[hgt] >= sdp->sd_inptrs) {
-			if (!hgt)
+		if (hgt) {
+			if (mp->mp_list[hgt] >= sdp->sd_inptrs)
+				goto lower_metapath;
+		} else {
+			if (mp->mp_list[hgt] >= sdp->sd_diptrs)
 				break;
-			goto lower_metapath;
 		}
 
 fill_up_metapath:
@@ -876,10 +878,9 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
 					ret = -ENOENT;
 					goto unlock;
 				} else {
-					/* report a hole */
 					iomap->offset = pos;
 					iomap->length = length;
-					goto do_alloc;
+					goto hole_found;
 				}
 			}
 			iomap->length = size;
@@ -933,8 +934,6 @@ unlock:
 	return ret;
 
 do_alloc:
-	iomap->addr = IOMAP_NULL_ADDR;
-	iomap->type = IOMAP_HOLE;
 	if (flags & IOMAP_REPORT) {
 		if (pos >= size)
 			ret = -ENOENT;
@@ -956,6 +955,9 @@ do_alloc:
 		if (pos < size && height == ip->i_height)
 			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
 	}
+hole_found:
+	iomap->addr = IOMAP_NULL_ADDR;
+	iomap->type = IOMAP_HOLE;
 	goto out;
 }
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 29f9b6684b74..bf70e3b14938 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -613,7 +613,7 @@ __acquires(&gl->gl_lockref.lock)
 				fs_err(sdp, "Error %d syncing glock \n", ret);
 				gfs2_dump_glock(NULL, gl, true);
 			}
-			return;
+			goto skip_inval;
 		}
 	}
 	if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) {
@@ -633,6 +633,7 @@ __acquires(&gl->gl_lockref.lock)
 		clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
 	}
 
+skip_inval:
 	gfs2_glock_hold(gl);
 	/*
 	 * Check for an error encountered since we called go_sync and go_inval.
@@ -722,9 +723,6 @@ __acquires(&gl->gl_lockref.lock)
 			goto out_unlock;
 		if (nonblock)
 			goto out_sched;
-		smp_mb();
-		if (atomic_read(&gl->gl_revokes) != 0)
-			goto out_sched;
 		set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
 		GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE);
 		gl->gl_target = gl->gl_demote_state;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 70b2d3a1e866..5acd3ce30759 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -622,7 +622,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 				error = finish_no_open(file, NULL);
 		}
 		gfs2_glock_dq_uninit(ghs);
-		return error;
+		goto fail;
 	} else if (error != -ENOENT) {
 		goto fail_gunlock;
 	}
@@ -764,9 +764,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		error = finish_open(file, dentry, gfs2_open_common);
 	}
 	gfs2_glock_dq_uninit(ghs);
+	gfs2_qa_put(ip);
 	gfs2_glock_dq_uninit(ghs + 1);
 	clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
 	gfs2_glock_put(io_gl);
+	gfs2_qa_put(dip);
 	return error;
 
 fail_gunlock3:
@@ -776,7 +778,6 @@ fail_gunlock2:
 	clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
 	gfs2_glock_put(io_gl);
 fail_free_inode:
-	gfs2_qa_put(ip);
 	if (ip->i_gl) {
 		glock_clear_object(ip->i_gl, ip);
 		gfs2_glock_put(ip->i_gl);
@@ -1005,7 +1006,7 @@ out_gunlock:
 out_child:
 	gfs2_glock_dq(ghs);
 out_parent:
-	gfs2_qa_put(ip);
+	gfs2_qa_put(dip);
 	gfs2_holder_uninit(ghs);
 	gfs2_holder_uninit(ghs + 1);
 	return error;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 3a75843ae580..0644e58c6191 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -669,13 +669,13 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 	struct buffer_head *bh = bd->bd_bh;
 	struct gfs2_glock *gl = bd->bd_gl;
 
+	sdp->sd_log_num_revoke++;
+	if (atomic_inc_return(&gl->gl_revokes) == 1)
+		gfs2_glock_hold(gl);
 	bh->b_private = NULL;
 	bd->bd_blkno = bh->b_blocknr;
 	gfs2_remove_from_ail(bd); /* drops ref on bh */
 	bd->bd_bh = NULL;
-	sdp->sd_log_num_revoke++;
-	if (atomic_inc_return(&gl->gl_revokes) == 1)
-		gfs2_glock_hold(gl);
 	set_bit(GLF_LFLUSH, &gl->gl_flags);
 	list_add(&bd->bd_list, &sdp->sd_log_revokes);
 }
@@ -1131,6 +1131,10 @@ int gfs2_logd(void *data)
 
 	while (!kthread_should_stop()) {
 
+		if (gfs2_withdrawn(sdp)) {
+			msleep_interruptible(HZ);
+			continue;
+		}
 		/* Check for errors writing to the journal */
 		if (sdp->sd_log_error) {
 			gfs2_lm(sdp,
@@ -1139,6 +1143,7 @@ int gfs2_logd(void *data)
 				"prevent further damage.\n",
 				sdp->sd_fsname, sdp->sd_log_error);
 			gfs2_withdraw(sdp);
+			continue;
 		}
 
 		did_flush = false;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 5ea96757afc4..cb2a11b458c6 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -263,7 +263,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno,
 	struct super_block *sb = sdp->sd_vfs;
 	struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 
-	bio->bi_iter.bi_sector = blkno << (sb->s_blocksize_bits - 9);
+	bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift;
 	bio_set_dev(bio, sb->s_bdev);
 	bio->bi_end_io = end_io;
 	bio->bi_private = sdp;
@@ -509,12 +509,12 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
 	unsigned int bsize = sdp->sd_sb.sb_bsize, off;
 	unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift;
 	unsigned int shift = PAGE_SHIFT - bsize_shift;
-	unsigned int readahead_blocks = BIO_MAX_PAGES << shift;
+	unsigned int max_blocks = 2 * 1024 * 1024 >> bsize_shift;
 	struct gfs2_journal_extent *je;
 	int sz, ret = 0;
 	struct bio *bio = NULL;
 	struct page *page = NULL;
-	bool bio_chained = false, done = false;
+	bool done = false;
 	errseq_t since;
 
 	memset(head, 0, sizeof(*head));
@@ -537,30 +537,30 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
 				off = 0;
 			}
 
-			if (!bio || (bio_chained && !off)) {
-				/* start new bio */
-			} else {
-				sz = bio_add_page(bio, page, bsize, off);
-				if (sz == bsize)
-					goto block_added;
+			if (bio && (off || block < blocks_submitted + max_blocks)) {
+				sector_t sector = dblock << sdp->sd_fsb2bb_shift;
+
+				if (bio_end_sector(bio) == sector) {
+					sz = bio_add_page(bio, page, bsize, off);
+					if (sz == bsize)
+						goto block_added;
+				}
 				if (off) {
 					unsigned int blocks =
 						(PAGE_SIZE - off) >> bsize_shift;
 
 					bio = gfs2_chain_bio(bio, blocks);
-					bio_chained = true;
 					goto add_block_to_new_bio;
 				}
 			}
 
 			if (bio) {
-				blocks_submitted = block + 1;
+				blocks_submitted = block;
 				submit_bio(bio);
 			}
 
 			bio = gfs2_log_alloc_bio(sdp, dblock, gfs2_end_log_read);
 			bio->bi_opf = REQ_OP_READ;
-			bio_chained = false;
 add_block_to_new_bio:
 			sz = bio_add_page(bio, page, bsize, off);
 			BUG_ON(sz != bsize);
@@ -568,7 +568,7 @@ block_added:
 			off += bsize;
 			if (off == PAGE_SIZE)
 				page = NULL;
-			if (blocks_submitted < blocks_read + readahead_blocks) {
+			if (blocks_submitted <= blocks_read + max_blocks) {
 				/* Keep at least one bio in flight */
 				continue;
 			}
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 4b72abcf83b2..9856cc2e0795 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -252,7 +252,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	int num = 0;
 
 	if (unlikely(gfs2_withdrawn(sdp)) &&
-	    (!sdp->sd_jdesc || (blkno != sdp->sd_jdesc->jd_no_addr))) {
+	    (!sdp->sd_jdesc || gl != sdp->sd_jinode_gl)) {
 		*bhp = NULL;
 		return -EIO;
 	}
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index cc0c4b5800be..8259fef3f986 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1051,8 +1051,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 	u32 x;
 	int error = 0;
 
-	if (capable(CAP_SYS_RESOURCE) ||
-	    sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
 		return 0;
 
 	error = gfs2_quota_hold(ip, uid, gid);
@@ -1125,7 +1124,7 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
 	int found;
 
 	if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags))
-		goto out;
+		return;
 
 	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
 		struct gfs2_quota_data *qd;
@@ -1162,7 +1161,6 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
 			qd_unlock(qda[x]);
 	}
 
-out:
 	gfs2_quota_unhold(ip);
 }
 
@@ -1210,9 +1208,6 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid,
 	if (!test_bit(GIF_QD_LOCKED, &ip->i_flags))
 		return 0;
 
-        if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
-                return 0;
-
 	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
 		qd = ip->i_qadata->qa_qd[x];
 
@@ -1270,7 +1265,9 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
 	if (ip->i_diskflags & GFS2_DIF_SYSTEM)
 		return;
 
-	BUG_ON(ip->i_qadata->qa_ref <= 0);
+	if (gfs2_assert_withdraw(sdp, ip->i_qadata &&
+				 ip->i_qadata->qa_ref > 0))
+		return;
 	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
 		qd = ip->i_qadata->qa_qd[x];
 
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 7f9ca8ef40fc..21ada332d555 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -44,7 +44,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip,
 	int ret;
 
 	ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */
-	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+	if (capable(CAP_SYS_RESOURCE) ||
+	    sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
 		return 0;
 	ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
 	if (ret)
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 37fc41632aa2..956fced0a8ec 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1404,7 +1404,6 @@ out:
 	if (ip->i_qadata)
 		gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0);
 	gfs2_rs_delete(ip, NULL);
-	gfs2_qa_put(ip);
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
 	gfs2_dir_hash_inval(ip);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 9b64d40ab379..aa087a5675af 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -119,6 +119,12 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
 	if (!sb_rdonly(sdp->sd_vfs))
 		ret = gfs2_make_fs_ro(sdp);
 
+	if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */
+		if (!ret)
+			ret = -EIO;
+		clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
+		goto skip_recovery;
+	}
 	/*
 	 * Drop the glock for our journal so another node can recover it.
 	 */
@@ -159,10 +165,6 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
 		wait_on_bit(&gl->gl_flags, GLF_FREEING, TASK_UNINTERRUPTIBLE);
 	}
 
-	if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */
-		clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
-		goto skip_recovery;
-	}
 	/*
 	 * Dequeue the "live" glock, but keep a reference so it's never freed.
 	 */
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5190bfb6a665..bb25e3997d41 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -357,7 +357,6 @@ struct io_timeout_data {
 	struct hrtimer			timer;
 	struct timespec64		ts;
 	enum hrtimer_mode		mode;
-	u32				seq_offset;
 };
 
 struct io_accept {
@@ -385,7 +384,7 @@ struct io_timeout {
 	struct file			*file;
 	u64				addr;
 	int				flags;
-	unsigned			count;
+	u32				count;
 };
 
 struct io_rw {
@@ -508,6 +507,7 @@ enum {
 	REQ_F_FORCE_ASYNC_BIT	= IOSQE_ASYNC_BIT,
 	REQ_F_BUFFER_SELECT_BIT	= IOSQE_BUFFER_SELECT_BIT,
 
+	REQ_F_LINK_HEAD_BIT,
 	REQ_F_LINK_NEXT_BIT,
 	REQ_F_FAIL_LINK_BIT,
 	REQ_F_INFLIGHT_BIT,
@@ -524,6 +524,7 @@ enum {
 	REQ_F_OVERFLOW_BIT,
 	REQ_F_POLLED_BIT,
 	REQ_F_BUFFER_SELECTED_BIT,
+	REQ_F_NO_FILE_TABLE_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -543,6 +544,8 @@ enum {
 	/* IOSQE_BUFFER_SELECT */
 	REQ_F_BUFFER_SELECT	= BIT(REQ_F_BUFFER_SELECT_BIT),
 
+	/* head of a link */
+	REQ_F_LINK_HEAD		= BIT(REQ_F_LINK_HEAD_BIT),
 	/* already grabbed next link */
 	REQ_F_LINK_NEXT		= BIT(REQ_F_LINK_NEXT_BIT),
 	/* fail rest of links */
@@ -575,6 +578,8 @@ enum {
 	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
 	/* buffer already selected */
 	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
+	/* doesn't need file table for this request */
+	REQ_F_NO_FILE_TABLE	= BIT(REQ_F_NO_FILE_TABLE_BIT),
 };
 
 struct async_poll {
@@ -614,6 +619,8 @@ struct io_kiocb {
 	bool				needs_fixed_file;
 	u8				opcode;
 
+	u16				buf_index;
+
 	struct io_ring_ctx	*ctx;
 	struct list_head	list;
 	unsigned int		flags;
@@ -675,8 +682,6 @@ struct io_op_def {
 	unsigned		needs_mm : 1;
 	/* needs req->file assigned */
 	unsigned		needs_file : 1;
-	/* needs req->file assigned IFF fd is >= 0 */
-	unsigned		fd_non_neg : 1;
 	/* hash wq insertion if file is a regular file */
 	unsigned		hash_reg_file : 1;
 	/* unbound wq insertion if file is a non-regular file */
@@ -779,8 +784,6 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 	},
 	[IORING_OP_OPENAT] = {
-		.needs_file		= 1,
-		.fd_non_neg		= 1,
 		.file_table		= 1,
 		.needs_fs		= 1,
 	},
@@ -794,9 +797,8 @@ static const struct io_op_def io_op_defs[] = {
 	},
 	[IORING_OP_STATX] = {
 		.needs_mm		= 1,
-		.needs_file		= 1,
-		.fd_non_neg		= 1,
 		.needs_fs		= 1,
+		.file_table		= 1,
 	},
 	[IORING_OP_READ] = {
 		.needs_mm		= 1,
@@ -831,8 +833,6 @@ static const struct io_op_def io_op_defs[] = {
 		.buffer_select		= 1,
 	},
 	[IORING_OP_OPENAT2] = {
-		.needs_file		= 1,
-		.fd_non_neg		= 1,
 		.file_table		= 1,
 		.needs_fs		= 1,
 	},
@@ -926,6 +926,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 		goto err;
 
 	ctx->flags = p->flags;
+	init_waitqueue_head(&ctx->sqo_wait);
 	init_waitqueue_head(&ctx->cq_wait);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	init_completion(&ctx->completions[0]);
@@ -955,8 +956,8 @@ static inline bool __req_need_defer(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 
-	return req->sequence != ctx->cached_cq_tail + ctx->cached_sq_dropped
-					+ atomic_read(&ctx->cached_cq_overflow);
+	return req->sequence != ctx->cached_cq_tail
+				+ atomic_read(&ctx->cached_cq_overflow);
 }
 
 static inline bool req_need_defer(struct io_kiocb *req)
@@ -1289,7 +1290,7 @@ static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx)
 	struct io_kiocb *req;
 
 	req = ctx->fallback_req;
-	if (!test_and_set_bit_lock(0, (unsigned long *) ctx->fallback_req))
+	if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req))
 		return req;
 
 	return NULL;
@@ -1376,7 +1377,7 @@ static void __io_free_req(struct io_kiocb *req)
 	if (likely(!io_is_fallback_req(req)))
 		kmem_cache_free(req_cachep, req);
 	else
-		clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req);
+		clear_bit_unlock(0, (unsigned long *) &req->ctx->fallback_req);
 }
 
 struct req_batch {
@@ -1396,10 +1397,6 @@ static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
 		for (i = 0; i < rb->to_free; i++) {
 			struct io_kiocb *req = rb->reqs[i];
 
-			if (req->flags & REQ_F_FIXED_FILE) {
-				req->file = NULL;
-				percpu_ref_put(req->fixed_file_refs);
-			}
 			if (req->flags & REQ_F_INFLIGHT)
 				inflight++;
 			__io_req_aux_free(req);
@@ -1437,7 +1434,7 @@ static bool io_link_cancel_timeout(struct io_kiocb *req)
 	if (ret != -1) {
 		io_cqring_fill_event(req, -ECANCELED);
 		io_commit_cqring(ctx);
-		req->flags &= ~REQ_F_LINK;
+		req->flags &= ~REQ_F_LINK_HEAD;
 		io_put_req(req);
 		return true;
 	}
@@ -1473,7 +1470,7 @@ static void io_req_link_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
 
 		list_del_init(&req->link_list);
 		if (!list_empty(&nxt->link_list))
-			nxt->flags |= REQ_F_LINK;
+			nxt->flags |= REQ_F_LINK_HEAD;
 		*nxtptr = nxt;
 		break;
 	}
@@ -1484,7 +1481,7 @@ static void io_req_link_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
 }
 
 /*
- * Called if REQ_F_LINK is set, and we fail the head request
+ * Called if REQ_F_LINK_HEAD is set, and we fail the head request
  */
 static void io_fail_links(struct io_kiocb *req)
 {
@@ -1517,7 +1514,7 @@ static void io_fail_links(struct io_kiocb *req)
 
 static void io_req_find_next(struct io_kiocb *req, struct io_kiocb **nxt)
 {
-	if (likely(!(req->flags & REQ_F_LINK)))
+	if (likely(!(req->flags & REQ_F_LINK_HEAD)))
 		return;
 
 	/*
@@ -1669,10 +1666,10 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
 
 static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
 {
-	if ((req->flags & REQ_F_LINK) || io_is_fallback_req(req))
+	if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req))
 		return false;
 
-	if (!(req->flags & REQ_F_FIXED_FILE) || req->io)
+	if (req->file || req->io)
 		rb->need_iter++;
 
 	rb->reqs[rb->to_free++] = req;
@@ -2032,7 +2029,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd)
  * any file. For now, just ensure that anything potentially problematic is done
  * inline.
  */
-static bool io_file_supports_async(struct file *file)
+static bool io_file_supports_async(struct file *file, int rw)
 {
 	umode_t mode = file_inode(file)->i_mode;
 
@@ -2041,7 +2038,13 @@ static bool io_file_supports_async(struct file *file)
 	if (S_ISREG(mode) && file->f_op != &io_uring_fops)
 		return true;
 
-	return false;
+	if (!(file->f_mode & FMODE_NOWAIT))
+		return false;
+
+	if (rw == READ)
+		return file->f_op->read_iter != NULL;
+
+	return file->f_op->write_iter != NULL;
 }
 
 static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
@@ -2100,9 +2103,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 	req->rw.addr = READ_ONCE(sqe->addr);
 	req->rw.len = READ_ONCE(sqe->len);
-	/* we own ->private, reuse it for the buffer index  / buffer ID */
-	req->rw.kiocb.private = (void *) (unsigned long)
-					READ_ONCE(sqe->buf_index);
+	req->buf_index = READ_ONCE(sqe->buf_index);
 	return 0;
 }
 
@@ -2145,7 +2146,7 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
 	struct io_ring_ctx *ctx = req->ctx;
 	size_t len = req->rw.len;
 	struct io_mapped_ubuf *imu;
-	unsigned index, buf_index;
+	u16 index, buf_index;
 	size_t offset;
 	u64 buf_addr;
 
@@ -2153,7 +2154,7 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
 	if (unlikely(!ctx->user_bufs))
 		return -EFAULT;
 
-	buf_index = (unsigned long) req->rw.kiocb.private;
+	buf_index = req->buf_index;
 	if (unlikely(buf_index >= ctx->nr_user_bufs))
 		return -EFAULT;
 
@@ -2269,10 +2270,10 @@ static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
 					bool needs_lock)
 {
 	struct io_buffer *kbuf;
-	int bgid;
+	u16 bgid;
 
 	kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
-	bgid = (int) (unsigned long) req->rw.kiocb.private;
+	bgid = req->buf_index;
 	kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock);
 	if (IS_ERR(kbuf))
 		return kbuf;
@@ -2363,7 +2364,7 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 	}
 
 	/* buffer index only valid with fixed read/write, or buffer select  */
-	if (req->rw.kiocb.private && !(req->flags & REQ_F_BUFFER_SELECT))
+	if (req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT))
 		return -EINVAL;
 
 	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
@@ -2562,14 +2563,14 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
 
 	req->result = 0;
 	io_size = ret;
-	if (req->flags & REQ_F_LINK)
+	if (req->flags & REQ_F_LINK_HEAD)
 		req->result = io_size;
 
 	/*
 	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
 	 * we know to async punt it even if it was opened O_NONBLOCK
 	 */
-	if (force_nonblock && !io_file_supports_async(req->file))
+	if (force_nonblock && !io_file_supports_async(req->file, READ))
 		goto copy_iov;
 
 	iov_count = iov_iter_count(&iter);
@@ -2592,7 +2593,8 @@ copy_iov:
 			if (ret)
 				goto out_free;
 			/* any defer here is final, must blocking retry */
-			if (!(req->flags & REQ_F_NOWAIT))
+			if (!(req->flags & REQ_F_NOWAIT) &&
+			    !file_can_poll(req->file))
 				req->flags |= REQ_F_MUST_PUNT;
 			return -EAGAIN;
 		}
@@ -2653,14 +2655,14 @@ static int io_write(struct io_kiocb *req, bool force_nonblock)
 
 	req->result = 0;
 	io_size = ret;
-	if (req->flags & REQ_F_LINK)
+	if (req->flags & REQ_F_LINK_HEAD)
 		req->result = io_size;
 
 	/*
 	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
 	 * we know to async punt it even if it was opened O_NONBLOCK
 	 */
-	if (force_nonblock && !io_file_supports_async(req->file))
+	if (force_nonblock && !io_file_supports_async(req->file, WRITE))
 		goto copy_iov;
 
 	/* file path doesn't support NOWAIT for non-direct_IO */
@@ -2714,7 +2716,8 @@ copy_iov:
 			if (ret)
 				goto out_free;
 			/* any defer here is final, must blocking retry */
-			req->flags |= REQ_F_MUST_PUNT;
+			if (!file_can_poll(req->file))
+				req->flags |= REQ_F_MUST_PUNT;
 			return -EAGAIN;
 		}
 	}
@@ -2754,15 +2757,6 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static bool io_splice_punt(struct file *file)
-{
-	if (get_pipe_info(file))
-		return false;
-	if (!io_file_supports_async(file))
-		return true;
-	return !(file->f_mode & O_NONBLOCK);
-}
-
 static int io_splice(struct io_kiocb *req, bool force_nonblock)
 {
 	struct io_splice *sp = &req->splice;
@@ -2770,19 +2764,16 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock)
 	struct file *out = sp->file_out;
 	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
 	loff_t *poff_in, *poff_out;
-	long ret;
+	long ret = 0;
 
-	if (force_nonblock) {
-		if (io_splice_punt(in) || io_splice_punt(out))
-			return -EAGAIN;
-		flags |= SPLICE_F_NONBLOCK;
-	}
+	if (force_nonblock)
+		return -EAGAIN;
 
 	poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
 	poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
-	ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
-	if (force_nonblock && ret == -EAGAIN)
-		return -EAGAIN;
+
+	if (sp->len)
+		ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
 
 	io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
 	req->flags &= ~REQ_F_NEED_CLEANUP;
@@ -3353,8 +3344,12 @@ static int io_statx(struct io_kiocb *req, bool force_nonblock)
 	struct kstat stat;
 	int ret;
 
-	if (force_nonblock)
+	if (force_nonblock) {
+		/* only need file table for an actual valid fd */
+		if (ctx->dfd == -1 || ctx->dfd == AT_FDCWD)
+			req->flags |= REQ_F_NO_FILE_TABLE;
 		return -EAGAIN;
+	}
 
 	if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->how.flags))
 		return -EINVAL;
@@ -3500,7 +3495,7 @@ static void io_sync_file_range_finish(struct io_wq_work **workptr)
 	if (io_req_cancelled(req))
 		return;
 	__io_sync_file_range(req);
-	io_put_req(req); /* put submission ref */
+	io_steal_work(req, workptr);
 }
 
 static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock)
@@ -4140,12 +4135,14 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 	req->result = mask;
 	init_task_work(&req->task_work, func);
 	/*
-	 * If this fails, then the task is exiting. Punt to one of the io-wq
-	 * threads to ensure the work gets run, we can't always rely on exit
-	 * cancelation taking care of this.
+	 * If this fails, then the task is exiting. When a task exits, the
+	 * work gets canceled, so just cancel this request as well instead
+	 * of executing it. We can't safely execute it anyway, as we may not
+	 * have the needed state needed for it anyway.
 	 */
 	ret = task_work_add(tsk, &req->task_work, true);
 	if (unlikely(ret)) {
+		WRITE_ONCE(poll->canceled, true);
 		tsk = io_wq_get_task(req->ctx->io_wq);
 		task_work_add(tsk, &req->task_work, true);
 	}
@@ -4153,25 +4150,62 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 	return 1;
 }
 
+static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll)
+	__acquires(&req->ctx->completion_lock)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+
+	if (!req->result && !READ_ONCE(poll->canceled)) {
+		struct poll_table_struct pt = { ._key = poll->events };
+
+		req->result = vfs_poll(req->file, &pt) & poll->events;
+	}
+
+	spin_lock_irq(&ctx->completion_lock);
+	if (!req->result && !READ_ONCE(poll->canceled)) {
+		add_wait_queue(poll->head, &poll->wait);
+		return true;
+	}
+
+	return false;
+}
+
 static void io_async_task_func(struct callback_head *cb)
 {
 	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
 	struct async_poll *apoll = req->apoll;
 	struct io_ring_ctx *ctx = req->ctx;
+	bool canceled;
 
 	trace_io_uring_task_run(req->ctx, req->opcode, req->user_data);
 
-	WARN_ON_ONCE(!list_empty(&req->apoll->poll.wait.entry));
+	if (io_poll_rewait(req, &apoll->poll)) {
+		spin_unlock_irq(&ctx->completion_lock);
+		return;
+	}
 
-	if (hash_hashed(&req->hash_node)) {
-		spin_lock_irq(&ctx->completion_lock);
+	if (hash_hashed(&req->hash_node))
 		hash_del(&req->hash_node);
-		spin_unlock_irq(&ctx->completion_lock);
+
+	canceled = READ_ONCE(apoll->poll.canceled);
+	if (canceled) {
+		io_cqring_fill_event(req, -ECANCELED);
+		io_commit_cqring(ctx);
 	}
 
+	spin_unlock_irq(&ctx->completion_lock);
+
 	/* restore ->work in case we need to retry again */
 	memcpy(&req->work, &apoll->work, sizeof(req->work));
 
+	if (canceled) {
+		kfree(apoll);
+		io_cqring_ev_posted(ctx);
+		req_set_fail_links(req);
+		io_double_put_req(req);
+		return;
+	}
+
 	__set_current_state(TASK_RUNNING);
 	mutex_lock(&ctx->uring_lock);
 	__io_queue_sqe(req, NULL);
@@ -4315,11 +4349,13 @@ static bool __io_poll_remove_one(struct io_kiocb *req,
 
 static bool io_poll_remove_one(struct io_kiocb *req)
 {
+	struct async_poll *apoll = NULL;
 	bool do_complete;
 
 	if (req->opcode == IORING_OP_POLL_ADD) {
 		do_complete = __io_poll_remove_one(req, &req->poll);
 	} else {
+		apoll = req->apoll;
 		/* non-poll requests have submit ref still */
 		do_complete = __io_poll_remove_one(req, &req->apoll->poll);
 		if (do_complete)
@@ -4328,6 +4364,14 @@ static bool io_poll_remove_one(struct io_kiocb *req)
 
 	hash_del(&req->hash_node);
 
+	if (do_complete && apoll) {
+		/*
+		 * restore ->work because we need to call io_req_work_drop_env.
+		 */
+		memcpy(&req->work, &apoll->work, sizeof(req->work));
+		kfree(apoll);
+	}
+
 	if (do_complete) {
 		io_cqring_fill_event(req, -ECANCELED);
 		io_commit_cqring(req->ctx);
@@ -4342,7 +4386,7 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx)
 {
 	struct hlist_node *tmp;
 	struct io_kiocb *req;
-	int i;
+	int posted = 0, i;
 
 	spin_lock_irq(&ctx->completion_lock);
 	for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
@@ -4350,11 +4394,12 @@ static void io_poll_remove_all(struct io_ring_ctx *ctx)
 
 		list = &ctx->cancel_hash[i];
 		hlist_for_each_entry_safe(req, tmp, list, hash_node)
-			io_poll_remove_one(req);
+			posted += io_poll_remove_one(req);
 	}
 	spin_unlock_irq(&ctx->completion_lock);
 
-	io_cqring_ev_posted(ctx);
+	if (posted)
+		io_cqring_ev_posted(ctx);
 }
 
 static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr)
@@ -4423,18 +4468,11 @@ static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt)
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_poll_iocb *poll = &req->poll;
 
-	if (!req->result && !READ_ONCE(poll->canceled)) {
-		struct poll_table_struct pt = { ._key = poll->events };
-
-		req->result = vfs_poll(req->file, &pt) & poll->events;
-	}
-
-	spin_lock_irq(&ctx->completion_lock);
-	if (!req->result && !READ_ONCE(poll->canceled)) {
-		add_wait_queue(poll->head, &poll->wait);
+	if (io_poll_rewait(req, poll)) {
 		spin_unlock_irq(&ctx->completion_lock);
 		return;
 	}
+
 	hash_del(&req->hash_node);
 	io_poll_complete(req, req->result, 0);
 	req->flags |= REQ_F_COMP_LOCKED;
@@ -4665,11 +4703,12 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 static int io_timeout(struct io_kiocb *req)
 {
-	unsigned count;
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_timeout_data *data;
 	struct list_head *entry;
 	unsigned span = 0;
+	u32 count = req->timeout.count;
+	u32 seq = req->sequence;
 
 	data = &req->io->timeout;
 
@@ -4678,7 +4717,6 @@ static int io_timeout(struct io_kiocb *req)
 	 * timeout event to be satisfied. If it isn't set, then this is
 	 * a pure timeout request, sequence isn't used.
 	 */
-	count = req->timeout.count;
 	if (!count) {
 		req->flags |= REQ_F_TIMEOUT_NOSEQ;
 		spin_lock_irq(&ctx->completion_lock);
@@ -4686,8 +4724,7 @@ static int io_timeout(struct io_kiocb *req)
 		goto add;
 	}
 
-	req->sequence = ctx->cached_sq_head + count - 1;
-	data->seq_offset = count;
+	req->sequence = seq + count;
 
 	/*
 	 * Insertion sort, ensuring the first entry in the list is always
@@ -4696,26 +4733,26 @@ static int io_timeout(struct io_kiocb *req)
 	spin_lock_irq(&ctx->completion_lock);
 	list_for_each_prev(entry, &ctx->timeout_list) {
 		struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, list);
-		unsigned nxt_sq_head;
+		unsigned nxt_seq;
 		long long tmp, tmp_nxt;
-		u32 nxt_offset = nxt->io->timeout.seq_offset;
+		u32 nxt_offset = nxt->timeout.count;
 
 		if (nxt->flags & REQ_F_TIMEOUT_NOSEQ)
 			continue;
 
 		/*
-		 * Since cached_sq_head + count - 1 can overflow, use type long
+		 * Since seq + count can overflow, use type long
 		 * long to store it.
 		 */
-		tmp = (long long)ctx->cached_sq_head + count - 1;
-		nxt_sq_head = nxt->sequence - nxt_offset + 1;
-		tmp_nxt = (long long)nxt_sq_head + nxt_offset - 1;
+		tmp = (long long)seq + count;
+		nxt_seq = nxt->sequence - nxt_offset;
+		tmp_nxt = (long long)nxt_seq + nxt_offset;
 
 		/*
 		 * cached_sq_head may overflow, and it will never overflow twice
 		 * once there is some timeout req still be valid.
 		 */
-		if (ctx->cached_sq_head < nxt_sq_head)
+		if (seq < nxt_seq)
 			tmp += UINT_MAX;
 
 		if (tmp > tmp_nxt)
@@ -4973,15 +5010,16 @@ static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	int ret;
 
 	/* Still need defer if there is pending req in defer list. */
-	if (!req_need_defer(req) && list_empty(&ctx->defer_list))
+	if (!req_need_defer(req) && list_empty_careful(&ctx->defer_list))
 		return 0;
 
-	if (!req->io && io_alloc_async_ctx(req))
-		return -EAGAIN;
-
-	ret = io_req_defer_prep(req, sqe);
-	if (ret < 0)
-		return ret;
+	if (!req->io) {
+		if (io_alloc_async_ctx(req))
+			return -EAGAIN;
+		ret = io_req_defer_prep(req, sqe);
+		if (ret < 0)
+			return ret;
+	}
 
 	spin_lock_irq(&ctx->completion_lock);
 	if (!req_need_defer(req) && list_empty(&ctx->defer_list)) {
@@ -5268,7 +5306,8 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if (ret)
 		return ret;
 
-	if (ctx->flags & IORING_SETUP_IOPOLL) {
+	/* If the op doesn't have a file, we're not polling for it */
+	if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) {
 		const bool in_async = io_wq_current_is_worker();
 
 		if (req->result == -EAGAIN)
@@ -5322,15 +5361,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
 	io_steal_work(req, workptr);
 }
 
-static int io_req_needs_file(struct io_kiocb *req, int fd)
-{
-	if (!io_op_defs[req->opcode].needs_file)
-		return 0;
-	if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg)
-		return 0;
-	return 1;
-}
-
 static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
 					      int index)
 {
@@ -5368,14 +5398,11 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
 }
 
 static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
-			   int fd, unsigned int flags)
+			   int fd)
 {
 	bool fixed;
 
-	if (!io_req_needs_file(req, fd))
-		return 0;
-
-	fixed = (flags & IOSQE_FIXED_FILE);
+	fixed = (req->flags & REQ_F_FIXED_FILE) != 0;
 	if (unlikely(!fixed && req->needs_fixed_file))
 		return -EBADF;
 
@@ -5387,7 +5414,7 @@ static int io_grab_files(struct io_kiocb *req)
 	int ret = -EBADF;
 	struct io_ring_ctx *ctx = req->ctx;
 
-	if (req->work.files)
+	if (req->work.files || (req->flags & REQ_F_NO_FILE_TABLE))
 		return 0;
 	if (!ctx->ring_file)
 		return -EBADF;
@@ -5476,7 +5503,7 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
 {
 	struct io_kiocb *nxt;
 
-	if (!(req->flags & REQ_F_LINK))
+	if (!(req->flags & REQ_F_LINK_HEAD))
 		return NULL;
 	/* for polled retry, if flag is set, we already went through here */
 	if (req->flags & REQ_F_POLLED)
@@ -5581,9 +5608,15 @@ fail_req:
 			io_double_put_req(req);
 		}
 	} else if (req->flags & REQ_F_FORCE_ASYNC) {
-		ret = io_req_defer_prep(req, sqe);
-		if (unlikely(ret < 0))
-			goto fail_req;
+		if (!req->io) {
+			ret = -EAGAIN;
+			if (io_alloc_async_ctx(req))
+				goto fail_req;
+			ret = io_req_defer_prep(req, sqe);
+			if (unlikely(ret < 0))
+				goto fail_req;
+		}
+
 		/*
 		 * Never try inline submit of IOSQE_ASYNC is set, go straight
 		 * to async execution.
@@ -5604,54 +5637,11 @@ static inline void io_queue_link_head(struct io_kiocb *req)
 		io_queue_sqe(req, NULL);
 }
 
-#define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK|	\
-				IOSQE_IO_HARDLINK | IOSQE_ASYNC | \
-				IOSQE_BUFFER_SELECT)
-
-static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+static int io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			  struct io_submit_state *state, struct io_kiocb **link)
 {
 	struct io_ring_ctx *ctx = req->ctx;
-	unsigned int sqe_flags;
-	int ret, id, fd;
-
-	sqe_flags = READ_ONCE(sqe->flags);
-
-	/* enforce forwards compatibility on users */
-	if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) {
-		ret = -EINVAL;
-		goto err_req;
-	}
-
-	if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
-	    !io_op_defs[req->opcode].buffer_select) {
-		ret = -EOPNOTSUPP;
-		goto err_req;
-	}
-
-	id = READ_ONCE(sqe->personality);
-	if (id) {
-		req->work.creds = idr_find(&ctx->personality_idr, id);
-		if (unlikely(!req->work.creds)) {
-			ret = -EINVAL;
-			goto err_req;
-		}
-		get_cred(req->work.creds);
-	}
-
-	/* same numerical values with corresponding REQ_F_*, safe to copy */
-	req->flags |= sqe_flags & (IOSQE_IO_DRAIN | IOSQE_IO_HARDLINK |
-					IOSQE_ASYNC | IOSQE_FIXED_FILE |
-					IOSQE_BUFFER_SELECT);
-
-	fd = READ_ONCE(sqe->fd);
-	ret = io_req_set_file(state, req, fd, sqe_flags);
-	if (unlikely(ret)) {
-err_req:
-		io_cqring_add_event(req, ret);
-		io_double_put_req(req);
-		return false;
-	}
+	int ret;
 
 	/*
 	 * If we already have a head request, queue this one for async
@@ -5670,42 +5660,39 @@ err_req:
 		 * next after the link request. The last one is done via
 		 * drain_next flag to persist the effect across calls.
 		 */
-		if (sqe_flags & IOSQE_IO_DRAIN) {
+		if (req->flags & REQ_F_IO_DRAIN) {
 			head->flags |= REQ_F_IO_DRAIN;
 			ctx->drain_next = 1;
 		}
-		if (io_alloc_async_ctx(req)) {
-			ret = -EAGAIN;
-			goto err_req;
-		}
+		if (io_alloc_async_ctx(req))
+			return -EAGAIN;
 
 		ret = io_req_defer_prep(req, sqe);
 		if (ret) {
 			/* fail even hard links since we don't submit */
 			head->flags |= REQ_F_FAIL_LINK;
-			goto err_req;
+			return ret;
 		}
 		trace_io_uring_link(ctx, req, head);
 		list_add_tail(&req->link_list, &head->link_list);
 
 		/* last request of a link, enqueue the link */
-		if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK))) {
+		if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) {
 			io_queue_link_head(head);
 			*link = NULL;
 		}
 	} else {
 		if (unlikely(ctx->drain_next)) {
 			req->flags |= REQ_F_IO_DRAIN;
-			req->ctx->drain_next = 0;
+			ctx->drain_next = 0;
 		}
-		if (sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) {
-			req->flags |= REQ_F_LINK;
+		if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
+			req->flags |= REQ_F_LINK_HEAD;
 			INIT_LIST_HEAD(&req->link_list);
 
-			if (io_alloc_async_ctx(req)) {
-				ret = -EAGAIN;
-				goto err_req;
-			}
+			if (io_alloc_async_ctx(req))
+				return -EAGAIN;
+
 			ret = io_req_defer_prep(req, sqe);
 			if (ret)
 				req->flags |= REQ_F_FAIL_LINK;
@@ -5715,7 +5702,7 @@ err_req:
 		}
 	}
 
-	return true;
+	return 0;
 }
 
 /*
@@ -5789,15 +5776,23 @@ static inline void io_consume_sqe(struct io_ring_ctx *ctx)
 	ctx->cached_sq_head++;
 }
 
-static void io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			const struct io_uring_sqe *sqe)
+#define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK|	\
+				IOSQE_IO_HARDLINK | IOSQE_ASYNC | \
+				IOSQE_BUFFER_SELECT)
+
+static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
+		       const struct io_uring_sqe *sqe,
+		       struct io_submit_state *state, bool async)
 {
+	unsigned int sqe_flags;
+	int id;
+
 	/*
 	 * All io need record the previous position, if LINK vs DARIN,
 	 * it can be used to mark the position of the first IO in the
 	 * link list.
 	 */
-	req->sequence = ctx->cached_sq_head;
+	req->sequence = ctx->cached_sq_head - ctx->cached_sq_dropped;
 	req->opcode = READ_ONCE(sqe->opcode);
 	req->user_data = READ_ONCE(sqe->user_data);
 	req->io = NULL;
@@ -5808,17 +5803,52 @@ static void io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	refcount_set(&req->refs, 2);
 	req->task = NULL;
 	req->result = 0;
+	req->needs_fixed_file = async;
 	INIT_IO_WORK(&req->work, io_wq_submit_work);
+
+	if (unlikely(req->opcode >= IORING_OP_LAST))
+		return -EINVAL;
+
+	if (io_op_defs[req->opcode].needs_mm && !current->mm) {
+		if (unlikely(!mmget_not_zero(ctx->sqo_mm)))
+			return -EFAULT;
+		use_mm(ctx->sqo_mm);
+	}
+
+	sqe_flags = READ_ONCE(sqe->flags);
+	/* enforce forwards compatibility on users */
+	if (unlikely(sqe_flags & ~SQE_VALID_FLAGS))
+		return -EINVAL;
+
+	if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
+	    !io_op_defs[req->opcode].buffer_select)
+		return -EOPNOTSUPP;
+
+	id = READ_ONCE(sqe->personality);
+	if (id) {
+		req->work.creds = idr_find(&ctx->personality_idr, id);
+		if (unlikely(!req->work.creds))
+			return -EINVAL;
+		get_cred(req->work.creds);
+	}
+
+	/* same numerical values with corresponding REQ_F_*, safe to copy */
+	req->flags |= sqe_flags & (IOSQE_IO_DRAIN | IOSQE_IO_HARDLINK |
+					IOSQE_ASYNC | IOSQE_FIXED_FILE |
+					IOSQE_BUFFER_SELECT | IOSQE_IO_LINK);
+
+	if (!io_op_defs[req->opcode].needs_file)
+		return 0;
+
+	return io_req_set_file(state, req, READ_ONCE(sqe->fd));
 }
 
 static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
-			  struct file *ring_file, int ring_fd,
-			  struct mm_struct **mm, bool async)
+			  struct file *ring_file, int ring_fd, bool async)
 {
 	struct io_submit_state state, *statep = NULL;
 	struct io_kiocb *link = NULL;
 	int i, submitted = 0;
-	bool mm_fault = false;
 
 	/* if we have a backlog and couldn't flush it all, return BUSY */
 	if (test_bit(0, &ctx->sq_check_overflow)) {
@@ -5858,34 +5888,23 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 			break;
 		}
 
-		io_init_req(ctx, req, sqe);
+		err = io_init_req(ctx, req, sqe, statep, async);
 		io_consume_sqe(ctx);
 		/* will complete beyond this point, count as submitted */
 		submitted++;
 
-		if (unlikely(req->opcode >= IORING_OP_LAST)) {
-			err = -EINVAL;
+		if (unlikely(err)) {
 fail_req:
 			io_cqring_add_event(req, err);
 			io_double_put_req(req);
 			break;
 		}
 
-		if (io_op_defs[req->opcode].needs_mm && !*mm) {
-			mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm);
-			if (unlikely(mm_fault)) {
-				err = -EFAULT;
-				goto fail_req;
-			}
-			use_mm(ctx->sqo_mm);
-			*mm = ctx->sqo_mm;
-		}
-
-		req->needs_fixed_file = async;
 		trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data,
 						true, async);
-		if (!io_submit_sqe(req, sqe, statep, &link))
-			break;
+		err = io_submit_sqe(req, sqe, statep, &link);
+		if (err)
+			goto fail_req;
 	}
 
 	if (unlikely(submitted != nr)) {
@@ -5904,10 +5923,19 @@ fail_req:
 	return submitted;
 }
 
+static inline void io_sq_thread_drop_mm(struct io_ring_ctx *ctx)
+{
+	struct mm_struct *mm = current->mm;
+
+	if (mm) {
+		unuse_mm(mm);
+		mmput(mm);
+	}
+}
+
 static int io_sq_thread(void *data)
 {
 	struct io_ring_ctx *ctx = data;
-	struct mm_struct *cur_mm = NULL;
 	const struct cred *old_cred;
 	mm_segment_t old_fs;
 	DEFINE_WAIT(wait);
@@ -5948,11 +5976,7 @@ static int io_sq_thread(void *data)
 			 * adding ourselves to the waitqueue, as the unuse/drop
 			 * may sleep.
 			 */
-			if (cur_mm) {
-				unuse_mm(cur_mm);
-				mmput(cur_mm);
-				cur_mm = NULL;
-			}
+			io_sq_thread_drop_mm(ctx);
 
 			/*
 			 * We're polling. If we're within the defined idle
@@ -6008,6 +6032,7 @@ static int io_sq_thread(void *data)
 				finish_wait(&ctx->sqo_wait, &wait);
 
 				ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+				ret = 0;
 				continue;
 			}
 			finish_wait(&ctx->sqo_wait, &wait);
@@ -6016,7 +6041,7 @@ static int io_sq_thread(void *data)
 		}
 
 		mutex_lock(&ctx->uring_lock);
-		ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true);
+		ret = io_submit_sqes(ctx, to_submit, NULL, -1, true);
 		mutex_unlock(&ctx->uring_lock);
 		timeout = jiffies + ctx->sq_thread_idle;
 	}
@@ -6025,10 +6050,7 @@ static int io_sq_thread(void *data)
 		task_work_run();
 
 	set_fs(old_fs);
-	if (cur_mm) {
-		unuse_mm(cur_mm);
-		mmput(cur_mm);
-	}
+	io_sq_thread_drop_mm(ctx);
 	revert_creds(old_cred);
 
 	kthread_parkme();
@@ -6824,7 +6846,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 {
 	int ret;
 
-	init_waitqueue_head(&ctx->sqo_wait);
 	mmgrab(current->mm);
 	ctx->sqo_mm = current->mm;
 
@@ -7299,7 +7320,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 	 * it could cause shutdown to hang.
 	 */
 	while (ctx->sqo_thread && !wq_has_sleeper(&ctx->sqo_wait))
-		cpu_relax();
+		cond_resched();
 
 	io_kill_timeouts(ctx);
 	io_poll_remove_all(ctx);
@@ -7328,11 +7349,9 @@ static int io_uring_release(struct inode *inode, struct file *file)
 static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 				  struct files_struct *files)
 {
-	struct io_kiocb *req;
-	DEFINE_WAIT(wait);
-
 	while (!list_empty_careful(&ctx->inflight_list)) {
-		struct io_kiocb *cancel_req = NULL;
+		struct io_kiocb *cancel_req = NULL, *req;
+		DEFINE_WAIT(wait);
 
 		spin_lock_irq(&ctx->inflight_lock);
 		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
@@ -7372,6 +7391,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 			 */
 			if (refcount_sub_and_test(2, &cancel_req->refs)) {
 				io_put_req(cancel_req);
+				finish_wait(&ctx->inflight_wait, &wait);
 				continue;
 			}
 		}
@@ -7379,8 +7399,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 		io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
 		io_put_req(cancel_req);
 		schedule();
+		finish_wait(&ctx->inflight_wait, &wait);
 	}
-	finish_wait(&ctx->inflight_wait, &wait);
 }
 
 static int io_uring_flush(struct file *file, void *data)
@@ -7509,13 +7529,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			wake_up(&ctx->sqo_wait);
 		submitted = to_submit;
 	} else if (to_submit) {
-		struct mm_struct *cur_mm;
-
 		mutex_lock(&ctx->uring_lock);
-		/* already have mm, so io_submit_sqes() won't try to grab it */
-		cur_mm = ctx->sqo_mm;
-		submitted = io_submit_sqes(ctx, to_submit, f.file, fd,
-					   &cur_mm, false);
+		submitted = io_submit_sqes(ctx, to_submit, f.file, fd, false);
 		mutex_unlock(&ctx->uring_lock);
 
 		if (submitted != to_submit)
@@ -7734,7 +7749,8 @@ err:
 	return ret;
 }
 
-static int io_uring_create(unsigned entries, struct io_uring_params *p)
+static int io_uring_create(unsigned entries, struct io_uring_params *p,
+			   struct io_uring_params __user *params)
 {
 	struct user_struct *user = NULL;
 	struct io_ring_ctx *ctx;
@@ -7826,6 +7842,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
 	p->cq_off.cqes = offsetof(struct io_rings, cqes);
 
+	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
+			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
+			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
+
+	if (copy_to_user(params, p, sizeof(*p))) {
+		ret = -EFAULT;
+		goto err;
+	}
 	/*
 	 * Install ring fd as the very last thing, so we don't risk someone
 	 * having closed it before we finish setup
@@ -7834,9 +7858,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	if (ret < 0)
 		goto err;
 
-	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
-			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
-			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
 	trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
 	return ret;
 err:
@@ -7852,7 +7873,6 @@ err:
 static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 {
 	struct io_uring_params p;
-	long ret;
 	int i;
 
 	if (copy_from_user(&p, params, sizeof(p)))
@@ -7867,14 +7887,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ))
 		return -EINVAL;
 
-	ret = io_uring_create(entries, &p);
-	if (ret < 0)
-		return ret;
-
-	if (copy_to_user(params, &p, sizeof(p)))
-		return -EFAULT;
-
-	return ret;
+	return  io_uring_create(entries, &p, params);
 }
 
 SYSCALL_DEFINE2(io_uring_setup, u32, entries,
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 282d45be6f45..5e80b40bc1b5 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -55,6 +55,7 @@ EXPORT_SYMBOL(vfs_ioctl);
 static int ioctl_fibmap(struct file *filp, int __user *p)
 {
 	struct inode *inode = file_inode(filp);
+	struct super_block *sb = inode->i_sb;
 	int error, ur_block;
 	sector_t block;
 
@@ -71,6 +72,13 @@ static int ioctl_fibmap(struct file *filp, int __user *p)
 	block = ur_block;
 	error = bmap(inode, &block);
 
+	if (block > INT_MAX) {
+		error = -ERANGE;
+		pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n",
+				    current->comm, task_pid_nr(current),
+				    sb->s_id, filp);
+	}
+
 	if (error)
 		ur_block = 0;
 	else
diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c
index bccf305ea9ce..d55e8f491a5e 100644
--- a/fs/iomap/fiemap.c
+++ b/fs/iomap/fiemap.c
@@ -117,10 +117,7 @@ iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length,
 
 	if (iomap->type == IOMAP_MAPPED) {
 		addr = (pos - iomap->offset + iomap->addr) >> inode->i_blkbits;
-		if (addr > INT_MAX)
-			WARN(1, "would truncate bmap result\n");
-		else
-			*bno = addr;
+		*bno = addr;
 	}
 	return 0;
 }
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 1abf126c2df4..a60df88efc40 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -118,8 +118,6 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int
 
 	nfss->fscache_key = NULL;
 	nfss->fscache = NULL;
-	if (!(nfss->options & NFS_OPTION_FSCACHE))
-		return;
 	if (!uniq) {
 		uniq = "";
 		ulen = 1;
@@ -188,7 +186,8 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int
 	/* create a cache index for looking up filehandles */
 	nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
 					       &nfs_fscache_super_index_def,
-					       key, sizeof(*key) + ulen,
+					       &key->key,
+					       sizeof(key->key) + ulen,
 					       NULL, 0,
 					       nfss, 0, true);
 	dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
@@ -226,6 +225,19 @@ void nfs_fscache_release_super_cookie(struct super_block *sb)
 	}
 }
 
+static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata,
+				  struct nfs_inode *nfsi)
+{
+	memset(auxdata, 0, sizeof(*auxdata));
+	auxdata->mtime_sec  = nfsi->vfs_inode.i_mtime.tv_sec;
+	auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata->ctime_sec  = nfsi->vfs_inode.i_ctime.tv_sec;
+	auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+
+	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+		auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+}
+
 /*
  * Initialise the per-inode cache cookie pointer for an NFS inode.
  */
@@ -239,14 +251,7 @@ void nfs_fscache_init_inode(struct inode *inode)
 	if (!(nfss->fscache && S_ISREG(inode->i_mode)))
 		return;
 
-	memset(&auxdata, 0, sizeof(auxdata));
-	auxdata.mtime_sec  = nfsi->vfs_inode.i_mtime.tv_sec;
-	auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
-	auxdata.ctime_sec  = nfsi->vfs_inode.i_ctime.tv_sec;
-	auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
-
-	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
-		auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+	nfs_fscache_update_auxdata(&auxdata, nfsi);
 
 	nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache,
 					       &nfs_fscache_inode_object_def,
@@ -266,11 +271,7 @@ void nfs_fscache_clear_inode(struct inode *inode)
 
 	dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);
 
-	memset(&auxdata, 0, sizeof(auxdata));
-	auxdata.mtime_sec  = nfsi->vfs_inode.i_mtime.tv_sec;
-	auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
-	auxdata.ctime_sec  = nfsi->vfs_inode.i_ctime.tv_sec;
-	auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+	nfs_fscache_update_auxdata(&auxdata, nfsi);
 	fscache_relinquish_cookie(cookie, &auxdata, false);
 	nfsi->fscache = NULL;
 }
@@ -310,11 +311,7 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp)
 	if (!fscache_cookie_valid(cookie))
 		return;
 
-	memset(&auxdata, 0, sizeof(auxdata));
-	auxdata.mtime_sec  = nfsi->vfs_inode.i_mtime.tv_sec;
-	auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
-	auxdata.ctime_sec  = nfsi->vfs_inode.i_ctime.tv_sec;
-	auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+	nfs_fscache_update_auxdata(&auxdata, nfsi);
 
 	if (inode_is_open_for_write(inode)) {
 		dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 35c8cb2d7637..dda5c3e65d8d 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -30,6 +30,7 @@
 #define encode_dirpath_sz	(1 + XDR_QUADLEN(MNTPATHLEN))
 #define MNT_status_sz		(1)
 #define MNT_fhandle_sz		XDR_QUADLEN(NFS2_FHSIZE)
+#define MNT_fhandlev3_sz	XDR_QUADLEN(NFS3_FHSIZE)
 #define MNT_authflav3_sz	(1 + NFS_MAX_SECFLAVORS)
 
 /*
@@ -37,7 +38,7 @@
  */
 #define MNT_enc_dirpath_sz	encode_dirpath_sz
 #define MNT_dec_mountres_sz	(MNT_status_sz + MNT_fhandle_sz)
-#define MNT_dec_mountres3_sz	(MNT_status_sz + MNT_fhandle_sz + \
+#define MNT_dec_mountres3_sz	(MNT_status_sz + MNT_fhandlev3_sz + \
 				 MNT_authflav3_sz)
 
 /*
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index c5c3fc6e6c60..26c94b32d6f4 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -253,37 +253,45 @@ int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 
 int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
-	struct posix_acl *alloc = NULL, *dfacl = NULL;
+	struct posix_acl *orig = acl, *dfacl = NULL, *alloc;
 	int status;
 
 	if (S_ISDIR(inode->i_mode)) {
 		switch(type) {
 		case ACL_TYPE_ACCESS:
-			alloc = dfacl = get_acl(inode, ACL_TYPE_DEFAULT);
+			alloc = get_acl(inode, ACL_TYPE_DEFAULT);
 			if (IS_ERR(alloc))
 				goto fail;
+			dfacl = alloc;
 			break;
 
 		case ACL_TYPE_DEFAULT:
-			dfacl = acl;
-			alloc = acl = get_acl(inode, ACL_TYPE_ACCESS);
+			alloc = get_acl(inode, ACL_TYPE_ACCESS);
 			if (IS_ERR(alloc))
 				goto fail;
+			dfacl = acl;
+			acl = alloc;
 			break;
 		}
 	}
 
 	if (acl == NULL) {
-		alloc = acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+		alloc = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
 		if (IS_ERR(alloc))
 			goto fail;
+		acl = alloc;
 	}
 	status = __nfs3_proc_setacls(inode, acl, dfacl);
-	posix_acl_release(alloc);
+out:
+	if (acl != orig)
+		posix_acl_release(acl);
+	if (dfacl != orig)
+		posix_acl_release(dfacl);
 	return status;
 
 fail:
-	return PTR_ERR(alloc);
+	status = PTR_ERR(alloc);
+	goto out;
 }
 
 const struct xattr_handler *nfs3_xattr_handlers[] = {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 512afb1c7867..9056f3dd380e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6347,7 +6347,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 		.rpc_client = server->client,
 		.rpc_message = &msg,
 		.callback_ops = &nfs4_delegreturn_ops,
-		.flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | RPC_TASK_TIMEOUT,
+		.flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT,
 	};
 	int status = 0;
 
@@ -7891,6 +7891,7 @@ static void
 nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp;
+	struct nfs41_bind_conn_to_session_res *res = task->tk_msg.rpc_resp;
 	struct nfs_client *clp = args->client;
 
 	switch (task->tk_status) {
@@ -7899,6 +7900,12 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 		nfs4_schedule_session_recovery(clp->cl_session,
 				task->tk_status);
 	}
+	if (args->dir == NFS4_CDFC4_FORE_OR_BOTH &&
+			res->dir != NFS4_CDFS4_BOTH) {
+		rpc_task_close_connection(task);
+		if (args->retries++ < MAX_BIND_CONN_TO_SESSION_RETRIES)
+			rpc_restart_call(task);
+	}
 }
 
 static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
@@ -7921,6 +7928,7 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
 	struct nfs41_bind_conn_to_session_args args = {
 		.client = clp,
 		.dir = NFS4_CDFC4_FORE_OR_BOTH,
+		.retries = 0,
 	};
 	struct nfs41_bind_conn_to_session_res res;
 	struct rpc_message msg = {
@@ -9191,8 +9199,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
 	nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0);
 
 	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task))
-		return ERR_CAST(task);
+
 	status = rpc_wait_for_completion_task(task);
 	if (status != 0)
 		goto out;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index ac93715c05a4..a8dc25ce48bb 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -734,9 +734,9 @@ nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner)
 		state = new;
 		state->owner = owner;
 		atomic_inc(&owner->so_count);
-		list_add_rcu(&state->inode_states, &nfsi->open_states);
 		ihold(inode);
 		state->inode = inode;
+		list_add_rcu(&state->inode_states, &nfsi->open_states);
 		spin_unlock(&inode->i_lock);
 		/* Note: The reclaim code dictates that we add stateless
 		 * and read-only stateids to the end of the list */
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index f61f96603df7..6ca421cbe19c 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -752,7 +752,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
 		.callback_ops = call_ops,
 		.callback_data = hdr,
 		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | flags,
+		.flags = RPC_TASK_ASYNC | flags,
 	};
 
 	hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
@@ -950,7 +950,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
 					hdr->cred,
 					NFS_PROTO(hdr->inode),
 					desc->pg_rpc_callops,
-					desc->pg_ioflags, 0);
+					desc->pg_ioflags,
+					RPC_TASK_CRED_NOREF);
 	return ret;
 }
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index f2dc35c22964..dd2e14f5875d 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1332,13 +1332,15 @@ _pnfs_return_layout(struct inode *ino)
 			!valid_layout) {
 		spin_unlock(&ino->i_lock);
 		dprintk("NFS: %s no layout segments to return\n", __func__);
-		goto out_put_layout_hdr;
+		goto out_wait_layoutreturn;
 	}
 
 	send = pnfs_prepare_layoutreturn(lo, &stateid, &cred, NULL);
 	spin_unlock(&ino->i_lock);
 	if (send)
 		status = pnfs_send_layoutreturn(lo, &stateid, &cred, IOMODE_ANY, true);
+out_wait_layoutreturn:
+	wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, TASK_UNINTERRUPTIBLE);
 out_put_layout_hdr:
 	pnfs_free_lseg_list(&tmp_list);
 	pnfs_put_layout_hdr(lo);
@@ -1456,18 +1458,15 @@ retry:
 	/* lo ref dropped in pnfs_roc_release() */
 	layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &lc_cred, &iomode);
 	/* If the creds don't match, we can't compound the layoutreturn */
-	if (!layoutreturn)
+	if (!layoutreturn || cred_fscmp(cred, lc_cred) != 0)
 		goto out_noroc;
-	if (cred_fscmp(cred, lc_cred) != 0)
-		goto out_noroc_put_cred;
 
 	roc = layoutreturn;
 	pnfs_init_layoutreturn_args(args, lo, &stateid, iomode);
 	res->lrs_present = 0;
 	layoutreturn = false;
-
-out_noroc_put_cred:
 	put_cred(lc_cred);
+
 out_noroc:
 	spin_unlock(&ino->i_lock);
 	rcu_read_unlock();
@@ -2023,6 +2022,7 @@ lookup_again:
 			goto lookup_again;
 		}
 
+		spin_unlock(&ino->i_lock);
 		first = true;
 		status = nfs4_select_rw_stateid(ctx->state,
 					iomode == IOMODE_RW ? FMODE_WRITE : FMODE_READ,
@@ -2032,12 +2032,12 @@ lookup_again:
 			trace_pnfs_update_layout(ino, pos, count,
 					iomode, lo, lseg,
 					PNFS_UPDATE_LAYOUT_INVALID_OPEN);
-			spin_unlock(&ino->i_lock);
 			nfs4_schedule_stateid_recovery(server, ctx->state);
 			pnfs_clear_first_layoutget(lo);
 			pnfs_put_layout_hdr(lo);
 			goto lookup_again;
 		}
+		spin_lock(&ino->i_lock);
 	} else {
 		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
 	}
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index e7ddbce48321..679767ac258d 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -536,7 +536,8 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 			nfs_init_commit(data, NULL, NULL, cinfo);
 			nfs_initiate_commit(NFS_CLIENT(inode), data,
 					    NFS_PROTO(data->inode),
-					    data->mds_ops, how, 0);
+					    data->mds_ops, how,
+					    RPC_TASK_CRED_NOREF);
 		} else {
 			nfs_init_commit(data, NULL, data->lseg, cinfo);
 			initiate_commit(data, how);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 59ef3b13ccca..7a70287f21a2 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -185,7 +185,7 @@ static int __nfs_list_for_each_server(struct list_head *head,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, head, client_link) {
-		if (!nfs_sb_active(server->super))
+		if (!(server->super && nfs_sb_active(server->super)))
 			continue;
 		rcu_read_unlock();
 		if (last)
@@ -1189,7 +1189,6 @@ static void nfs_get_cache_cookie(struct super_block *sb,
 			uniq = ctx->fscache_uniq;
 			ulen = strlen(ctx->fscache_uniq);
 		}
-		return;
 	}
 
 	nfs_fscache_get_super_cookie(sb, uniq, ulen);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index df4b87c30ac9..1e767f779c49 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1695,7 +1695,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 		.callback_ops = call_ops,
 		.callback_data = data,
 		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | flags,
+		.flags = RPC_TASK_ASYNC | flags,
 		.priority = priority,
 	};
 	/* Set up the initial task struct.  */
@@ -1813,7 +1813,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 	nfs_init_commit(data, head, NULL, cinfo);
 	atomic_inc(&cinfo->mds->rpcs_out);
 	return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
-				   data->mds_ops, how, 0);
+				   data->mds_ops, how, RPC_TASK_CRED_NOREF);
 }
 
 /*
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index c3b11a715082..5cf91322de0f 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1312,6 +1312,7 @@ nfsd4_run_cb_work(struct work_struct *work)
 		container_of(work, struct nfsd4_callback, cb_work);
 	struct nfs4_client *clp = cb->cb_clp;
 	struct rpc_clnt *clnt;
+	int flags;
 
 	if (cb->cb_need_restart) {
 		cb->cb_need_restart = false;
@@ -1340,7 +1341,8 @@ nfsd4_run_cb_work(struct work_struct *work)
 	}
 
 	cb->cb_msg.rpc_cred = clp->cl_cb_cred;
-	rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
+	flags = clp->cl_minorversion ? RPC_TASK_NOCONNECT : RPC_TASK_SOFTCONN;
+	rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | flags,
 			cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb);
 }
 
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index a8fb18609146..9e40dfecf1b1 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -127,16 +127,8 @@ nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
  		goto out;
 	}
 
-	{
-		SHASH_DESC_ON_STACK(desc, tfm);
-
-		desc->tfm = tfm;
-
-		status = crypto_shash_digest(desc, clname->data, clname->len,
-					     cksum.data);
-		shash_desc_zero(desc);
-	}
-
+	status = crypto_shash_tfm_digest(tfm, clname->data, clname->len,
+					 cksum.data);
 	if (status)
 		goto out;
 
@@ -1148,7 +1140,6 @@ nfsd4_cld_create_v2(struct nfs4_client *clp)
 	struct crypto_shash *tfm = cn->cn_tfm;
 	struct xdr_netobj cksum;
 	char *principal = NULL;
-	SHASH_DESC_ON_STACK(desc, tfm);
 
 	/* Don't upcall if it's already stored */
 	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
@@ -1170,16 +1161,14 @@ nfsd4_cld_create_v2(struct nfs4_client *clp)
 	else if (clp->cl_cred.cr_principal)
 		principal = clp->cl_cred.cr_principal;
 	if (principal) {
-		desc->tfm = tfm;
 		cksum.len = crypto_shash_digestsize(tfm);
 		cksum.data = kmalloc(cksum.len, GFP_KERNEL);
 		if (cksum.data == NULL) {
 			ret = -ENOMEM;
 			goto out;
 		}
-		ret = crypto_shash_digest(desc, principal, strlen(principal),
-					  cksum.data);
-		shash_desc_zero(desc);
+		ret = crypto_shash_tfm_digest(tfm, principal, strlen(principal),
+					      cksum.data);
 		if (ret) {
 			kfree(cksum.data);
 			goto out;
@@ -1343,7 +1332,6 @@ nfsd4_cld_check_v2(struct nfs4_client *clp)
 	struct crypto_shash *tfm = cn->cn_tfm;
 	struct xdr_netobj cksum;
 	char *principal = NULL;
-	SHASH_DESC_ON_STACK(desc, tfm);
 
 	/* did we already find that this client is stable? */
 	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
@@ -1381,14 +1369,12 @@ found:
 			principal = clp->cl_cred.cr_principal;
 		if (principal == NULL)
 			return -ENOENT;
-		desc->tfm = tfm;
 		cksum.len = crypto_shash_digestsize(tfm);
 		cksum.data = kmalloc(cksum.len, GFP_KERNEL);
 		if (cksum.data == NULL)
 			return -ENOENT;
-		status = crypto_shash_digest(desc, principal, strlen(principal),
-					     cksum.data);
-		shash_desc_zero(desc);
+		status = crypto_shash_tfm_digest(tfm, principal,
+						 strlen(principal), cksum.data);
 		if (status) {
 			kfree(cksum.data);
 			return -ENOENT;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e32ecedece0f..c107caa56525 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -267,6 +267,8 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 	if (!nbl) {
 		nbl= kmalloc(sizeof(*nbl), GFP_KERNEL);
 		if (nbl) {
+			INIT_LIST_HEAD(&nbl->nbl_list);
+			INIT_LIST_HEAD(&nbl->nbl_lru);
 			fh_copy_shallow(&nbl->nbl_fh, fh);
 			locks_init_lock(&nbl->nbl_lock);
 			nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client,
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 5435a40f82be..c18459cea6f4 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -520,7 +520,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 	BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
 	BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19);
 
 	mask = fanotify_group_event_mask(group, iter_info, mask, data,
 					 data_type);
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 8e4f1ace467c..1de77f1a600b 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -275,7 +275,6 @@ static ssize_t dlmfs_file_write(struct file *filp,
 				loff_t *ppos)
 {
 	int bytes_left;
-	ssize_t writelen;
 	char *lvb_buf;
 	struct inode *inode = file_inode(filp);
 
@@ -285,32 +284,30 @@ static ssize_t dlmfs_file_write(struct file *filp,
 	if (*ppos >= i_size_read(inode))
 		return -ENOSPC;
 
+	/* don't write past the lvb */
+	if (count > i_size_read(inode) - *ppos)
+		count = i_size_read(inode) - *ppos;
+
 	if (!count)
 		return 0;
 
 	if (!access_ok(buf, count))
 		return -EFAULT;
 
-	/* don't write past the lvb */
-	if ((count + *ppos) > i_size_read(inode))
-		writelen = i_size_read(inode) - *ppos;
-	else
-		writelen = count - *ppos;
-
-	lvb_buf = kmalloc(writelen, GFP_NOFS);
+	lvb_buf = kmalloc(count, GFP_NOFS);
 	if (!lvb_buf)
 		return -ENOMEM;
 
-	bytes_left = copy_from_user(lvb_buf, buf, writelen);
-	writelen -= bytes_left;
-	if (writelen)
-		user_dlm_write_lvb(inode, lvb_buf, writelen);
+	bytes_left = copy_from_user(lvb_buf, buf, count);
+	count -= bytes_left;
+	if (count)
+		user_dlm_write_lvb(inode, lvb_buf, count);
 
 	kfree(lvb_buf);
 
-	*ppos = *ppos + writelen;
-	mlog(0, "wrote %zd bytes\n", writelen);
-	return writelen;
+	*ppos = *ppos + count;
+	mlog(0, "wrote %zu bytes\n", count);
+	return count;
 }
 
 static void dlmfs_init_once(void *foo)
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index 475c61f53f0f..ed5c1078919c 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -783,6 +783,9 @@ static struct ovl_fh *ovl_fid_to_fh(struct fid *fid, int buflen, int fh_type)
 	if (fh_type != OVL_FILEID_V0)
 		return ERR_PTR(-EINVAL);
 
+	if (buflen <= OVL_FH_WIRE_OFFSET)
+		return ERR_PTR(-EINVAL);
+
 	fh = kzalloc(buflen, GFP_KERNEL);
 	if (!fh)
 		return ERR_PTR(-ENOMEM);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index b0d42ece4d7c..981f11ec51bc 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -58,6 +58,24 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 		if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
 			attr->ia_valid &= ~ATTR_MODE;
 
+		/*
+		 * We might have to translate ovl file into real file object
+		 * once use cases emerge.  For now, simply don't let underlying
+		 * filesystem rely on attr->ia_file
+		 */
+		attr->ia_valid &= ~ATTR_FILE;
+
+		/*
+		 * If open(O_TRUNC) is done, VFS calls ->setattr with ATTR_OPEN
+		 * set.  Overlayfs does not pass O_TRUNC flag to underlying
+		 * filesystem during open -> do not pass ATTR_OPEN.  This
+		 * disables optimization in fuse which assumes open(O_TRUNC)
+		 * already set file size to 0.  But we never passed O_TRUNC to
+		 * fuse.  So by clearing ATTR_OPEN, fuse will be forced to send
+		 * setattr request to server.
+		 */
+		attr->ia_valid &= ~ATTR_OPEN;
+
 		inode_lock(upperdentry->d_inode);
 		old_cred = ovl_override_creds(dentry->d_sb);
 		err = notify_change(upperdentry, attr, NULL);
diff --git a/fs/pnode.c b/fs/pnode.c
index 49f6d7ff2139..1106137c747a 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -261,14 +261,13 @@ static int propagate_one(struct mount *m)
 	child = copy_tree(last_source, last_source->mnt.mnt_root, type);
 	if (IS_ERR(child))
 		return PTR_ERR(child);
+	read_seqlock_excl(&mount_lock);
 	mnt_set_mountpoint(m, mp, child);
+	if (m->mnt_master != dest_master)
+		SET_MNT_MARK(m->mnt_master);
+	read_sequnlock_excl(&mount_lock);
 	last_dest = m;
 	last_source = child;
-	if (m->mnt_master != dest_master) {
-		read_seqlock_excl(&mount_lock);
-		SET_MNT_MARK(m->mnt_master);
-		read_sequnlock_excl(&mount_lock);
-	}
 	hlist_add_head(&child->mnt_hash, list);
 	return count_mounts(m->mnt_ns, child);
 }
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 6042b646ab27..eb2255e95f62 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1573,6 +1573,7 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf,
 	noffsets = 0;
 	for (pos = kbuf; pos; pos = next_line) {
 		struct proc_timens_offset *off = &offsets[noffsets];
+		char clock[10];
 		int err;
 
 		/* Find the end of line and ensure we don't look past it */
@@ -1584,10 +1585,21 @@ static ssize_t timens_offsets_write(struct file *file, const char __user *buf,
 				next_line = NULL;
 		}
 
-		err = sscanf(pos, "%u %lld %lu", &off->clockid,
+		err = sscanf(pos, "%9s %lld %lu", clock,
 				&off->val.tv_sec, &off->val.tv_nsec);
 		if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC)
 			goto out;
+
+		clock[sizeof(clock) - 1] = 0;
+		if (strcmp(clock, "monotonic") == 0 ||
+		    strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0)
+			off->clockid = CLOCK_MONOTONIC;
+		else if (strcmp(clock, "boottime") == 0 ||
+			 strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0)
+			off->clockid = CLOCK_BOOTTIME;
+		else
+			goto out;
+
 		noffsets++;
 		if (noffsets == ARRAY_SIZE(offsets)) {
 			if (next_line)
@@ -3274,7 +3286,6 @@ static const struct inode_operations proc_tgid_base_inode_operations = {
 void proc_flush_pid(struct pid *pid)
 {
 	proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock);
-	put_pid(pid);
 }
 
 static struct dentry *proc_pid_instantiate(struct dentry * dentry,
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 8c1f1bb1a5ce..09cd51c8d23d 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -103,6 +103,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "SUnreclaim:     ", sunreclaim);
 	seq_printf(m, "KernelStack:    %8lu kB\n",
 		   global_zone_page_state(NR_KERNEL_STACK_KB));
+#ifdef CONFIG_SHADOW_CALL_STACK
+	seq_printf(m, "ShadowCallStack:%8lu kB\n",
+		   global_zone_page_state(NR_KERNEL_SCS_KB));
+#endif
 	show_val_kb(m, "PageTables:     ",
 		    global_zone_page_state(NR_PAGETABLE));
 
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 2633f10446c3..cdbe9293ea55 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -196,6 +196,13 @@ static void proc_kill_sb(struct super_block *sb)
 	if (ns->proc_thread_self)
 		dput(ns->proc_thread_self);
 	kill_anon_super(sb);
+
+	/* Make the pid namespace safe for the next mount of proc */
+	ns->proc_self = NULL;
+	ns->proc_thread_self = NULL;
+	ns->pid_gid = GLOBAL_ROOT_GID;
+	ns->hide_pid = 0;
+
 	put_pid_ns(ns);
 }
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 8d382d4ec067..10a6d472397f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -622,9 +622,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_GROWSDOWN)]	= "gd",
 		[ilog2(VM_PFNMAP)]	= "pf",
 		[ilog2(VM_DENYWRITE)]	= "dw",
-#ifdef CONFIG_X86_INTEL_MPX
-		[ilog2(VM_MPX)]		= "mp",
-#endif
 		[ilog2(VM_LOCKED)]	= "lo",
 		[ilog2(VM_IO)]		= "io",
 		[ilog2(VM_SEQ_READ)]	= "sr",
@@ -638,6 +635,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_ARCH_1)]	= "ar",
 		[ilog2(VM_WIPEONFORK)]	= "wf",
 		[ilog2(VM_DONTDUMP)]	= "dd",
+#ifdef CONFIG_ARM64_BTI
+		[ilog2(VM_ARM64_BTI)]	= "bt",
+#endif
 #ifdef CONFIG_MEM_SOFT_DIRTY
 		[ilog2(VM_SOFTDIRTY)]	= "sd",
 #endif
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 7dc800cce354..c663202da8de 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -266,7 +266,8 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst,
 		if (start < offset + dump->size) {
 			tsz = min(offset + (u64)dump->size - start, (u64)size);
 			buf = dump->buf + start - offset;
-			if (remap_vmalloc_range_partial(vma, dst, buf, tsz)) {
+			if (remap_vmalloc_range_partial(vma, dst, buf, 0,
+							tsz)) {
 				ret = -EFAULT;
 				goto out_unlock;
 			}
@@ -624,7 +625,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
 		kaddr = elfnotes_buf + start - elfcorebuf_sz - vmcoredd_orig_sz;
 		if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
-						kaddr, tsz))
+						kaddr, 0, tsz))
 			goto fail;
 
 		size -= tsz;
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index 8f0369aad22a..e16a49ebfe54 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -153,3 +153,112 @@ config PSTORE_RAM
 	  "ramoops.ko".
 
 	  For more information, see Documentation/admin-guide/ramoops.rst.
+
+config PSTORE_ZONE
+	tristate
+	depends on PSTORE
+	help
+	  The common layer for pstore/blk (and pstore/ram in the future)
+	  to manage storage in zones.
+
+config PSTORE_BLK
+	tristate "Log panic/oops to a block device"
+	depends on PSTORE
+	depends on BLOCK
+	select PSTORE_ZONE
+	default n
+	help
+	  This enables panic and oops message to be logged to a block dev
+	  where it can be read back at some later point.
+
+	  For more information, see Documentation/admin-guide/pstore-blk.rst
+
+	  If unsure, say N.
+
+config PSTORE_BLK_BLKDEV
+	string "block device identifier"
+	depends on PSTORE_BLK
+	default ""
+	help
+	  Which block device should be used for pstore/blk.
+
+	  It accepts the following variants:
+	  1) <hex_major><hex_minor> device number in hexadecimal representation,
+	     with no leading 0x, for example b302.
+	  2) /dev/<disk_name> represents the device name of disk
+	  3) /dev/<disk_name><decimal> represents the device name and number
+	     of partition - device number of disk plus the partition number
+	  4) /dev/<disk_name>p<decimal> - same as the above, this form is
+	     used when disk name of partitioned disk ends with a digit.
+	  5) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
+	     unique id of a partition if the partition table provides it.
+	     The UUID may be either an EFI/GPT UUID, or refer to an MSDOS
+	     partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero-
+	     filled hex representation of the 32-bit "NT disk signature", and PP
+	     is a zero-filled hex representation of the 1-based partition number.
+	  6) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation
+	     to a partition with a known unique id.
+	  7) <major>:<minor> major and minor number of the device separated by
+	     a colon.
+
+	  NOTE that, both Kconfig and module parameters can configure
+	  pstore/blk, but module parameters have priority over Kconfig.
+
+config PSTORE_BLK_KMSG_SIZE
+	int "Size in Kbytes of kmsg dump log to store"
+	depends on PSTORE_BLK
+	default 64
+	help
+	  This just sets size of kmsg dump (oops, panic, etc) log for
+	  pstore/blk. The size is in KB and must be a multiple of 4.
+
+	  NOTE that, both Kconfig and module parameters can configure
+	  pstore/blk, but module parameters have priority over Kconfig.
+
+config PSTORE_BLK_MAX_REASON
+	int "Maximum kmsg dump reason to store"
+	depends on PSTORE_BLK
+	default 2
+	help
+	  The maximum reason for kmsg dumps to store. The default is
+	  2 (KMSG_DUMP_OOPS), see include/linux/kmsg_dump.h's
+	  enum kmsg_dump_reason for more details.
+
+	  NOTE that, both Kconfig and module parameters can configure
+	  pstore/blk, but module parameters have priority over Kconfig.
+
+config PSTORE_BLK_PMSG_SIZE
+	int "Size in Kbytes of pmsg to store"
+	depends on PSTORE_BLK
+	depends on PSTORE_PMSG
+	default 64
+	help
+	  This just sets size of pmsg (pmsg_size) for pstore/blk. The size is
+	  in KB and must be a multiple of 4.
+
+	  NOTE that, both Kconfig and module parameters can configure
+	  pstore/blk, but module parameters have priority over Kconfig.
+
+config PSTORE_BLK_CONSOLE_SIZE
+	int "Size in Kbytes of console log to store"
+	depends on PSTORE_BLK
+	depends on PSTORE_CONSOLE
+	default 64
+	help
+	  This just sets size of console log (console_size) to store via
+	  pstore/blk. The size is in KB and must be a multiple of 4.
+
+	  NOTE that, both Kconfig and module parameters can configure
+	  pstore/blk, but module parameters have priority over Kconfig.
+
+config PSTORE_BLK_FTRACE_SIZE
+	int "Size in Kbytes of ftrace log to store"
+	depends on PSTORE_BLK
+	depends on PSTORE_FTRACE
+	default 64
+	help
+	  This just sets size of ftrace log (ftrace_size) for pstore/blk. The
+	  size is in KB and must be a multiple of 4.
+
+	  NOTE that, both Kconfig and module parameters can configure
+	  pstore/blk, but module parameters have priority over Kconfig.
diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile
index 967b5891f325..c270467aeece 100644
--- a/fs/pstore/Makefile
+++ b/fs/pstore/Makefile
@@ -12,3 +12,9 @@ pstore-$(CONFIG_PSTORE_PMSG)	+= pmsg.o
 
 ramoops-objs += ram.o ram_core.o
 obj-$(CONFIG_PSTORE_RAM)	+= ramoops.o
+
+pstore_zone-objs += zone.o
+obj-$(CONFIG_PSTORE_ZONE)	+= pstore_zone.o
+
+pstore_blk-objs += blk.o
+obj-$(CONFIG_PSTORE_BLK)	+= pstore_blk.o
diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c
new file mode 100644
index 000000000000..fcd5563dde06
--- /dev/null
+++ b/fs/pstore/blk.c
@@ -0,0 +1,517 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implements pstore backend driver that write to block (or non-block) storage
+ * devices, using the pstore/zone API.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include "../../block/blk.h"
+#include <linux/blkdev.h>
+#include <linux/string.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/pstore_blk.h>
+#include <linux/mount.h>
+#include <linux/uio.h>
+
+static long kmsg_size = CONFIG_PSTORE_BLK_KMSG_SIZE;
+module_param(kmsg_size, long, 0400);
+MODULE_PARM_DESC(kmsg_size, "kmsg dump record size in kbytes");
+
+static int max_reason = CONFIG_PSTORE_BLK_MAX_REASON;
+module_param(max_reason, int, 0400);
+MODULE_PARM_DESC(max_reason,
+		 "maximum reason for kmsg dump (default 2: Oops and Panic)");
+
+#if IS_ENABLED(CONFIG_PSTORE_PMSG)
+static long pmsg_size = CONFIG_PSTORE_BLK_PMSG_SIZE;
+#else
+static long pmsg_size = -1;
+#endif
+module_param(pmsg_size, long, 0400);
+MODULE_PARM_DESC(pmsg_size, "pmsg size in kbytes");
+
+#if IS_ENABLED(CONFIG_PSTORE_CONSOLE)
+static long console_size = CONFIG_PSTORE_BLK_CONSOLE_SIZE;
+#else
+static long console_size = -1;
+#endif
+module_param(console_size, long, 0400);
+MODULE_PARM_DESC(console_size, "console size in kbytes");
+
+#if IS_ENABLED(CONFIG_PSTORE_FTRACE)
+static long ftrace_size = CONFIG_PSTORE_BLK_FTRACE_SIZE;
+#else
+static long ftrace_size = -1;
+#endif
+module_param(ftrace_size, long, 0400);
+MODULE_PARM_DESC(ftrace_size, "ftrace size in kbytes");
+
+static bool best_effort;
+module_param(best_effort, bool, 0400);
+MODULE_PARM_DESC(best_effort, "use best effort to write (i.e. do not require storage driver pstore support, default: off)");
+
+/*
+ * blkdev - the block device to use for pstore storage
+ *
+ * Usually, this will be a partition of a block device.
+ *
+ * blkdev accepts the following variants:
+ * 1) <hex_major><hex_minor> device number in hexadecimal representation,
+ *    with no leading 0x, for example b302.
+ * 2) /dev/<disk_name> represents the device number of disk
+ * 3) /dev/<disk_name><decimal> represents the device number
+ *    of partition - device number of disk plus the partition number
+ * 4) /dev/<disk_name>p<decimal> - same as the above, that form is
+ *    used when disk name of partitioned disk ends on a digit.
+ * 5) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
+ *    unique id of a partition if the partition table provides it.
+ *    The UUID may be either an EFI/GPT UUID, or refer to an MSDOS
+ *    partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero-
+ *    filled hex representation of the 32-bit "NT disk signature", and PP
+ *    is a zero-filled hex representation of the 1-based partition number.
+ * 6) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to
+ *    a partition with a known unique id.
+ * 7) <major>:<minor> major and minor number of the device separated by
+ *    a colon.
+ */
+static char blkdev[80] = CONFIG_PSTORE_BLK_BLKDEV;
+module_param_string(blkdev, blkdev, 80, 0400);
+MODULE_PARM_DESC(blkdev, "block device for pstore storage");
+
+/*
+ * All globals must only be accessed under the pstore_blk_lock
+ * during the register/unregister functions.
+ */
+static DEFINE_MUTEX(pstore_blk_lock);
+static struct block_device *psblk_bdev;
+static struct pstore_zone_info *pstore_zone_info;
+static pstore_blk_panic_write_op blkdev_panic_write;
+
+struct bdev_info {
+	dev_t devt;
+	sector_t nr_sects;
+	sector_t start_sect;
+};
+
+#define check_size(name, alignsize) ({				\
+	long _##name_ = (name);					\
+	_##name_ = _##name_ <= 0 ? 0 : (_##name_ * 1024);	\
+	if (_##name_ & ((alignsize) - 1)) {			\
+		pr_info(#name " must align to %d\n",		\
+				(alignsize));			\
+		_##name_ = ALIGN(name, (alignsize));		\
+	}							\
+	_##name_;						\
+})
+
+static int __register_pstore_device(struct pstore_device_info *dev)
+{
+	int ret;
+
+	lockdep_assert_held(&pstore_blk_lock);
+
+	if (!dev || !dev->total_size || !dev->read || !dev->write)
+		return -EINVAL;
+
+	/* someone already registered before */
+	if (pstore_zone_info)
+		return -EBUSY;
+
+	pstore_zone_info = kzalloc(sizeof(struct pstore_zone_info), GFP_KERNEL);
+	if (!pstore_zone_info)
+		return -ENOMEM;
+
+	/* zero means not limit on which backends to attempt to store. */
+	if (!dev->flags)
+		dev->flags = UINT_MAX;
+
+#define verify_size(name, alignsize, enabled) {				\
+		long _##name_;						\
+		if (enabled)						\
+			_##name_ = check_size(name, alignsize);		\
+		else							\
+			_##name_ = 0;					\
+		name = _##name_ / 1024;					\
+		pstore_zone_info->name = _##name_;			\
+	}
+
+	verify_size(kmsg_size, 4096, dev->flags & PSTORE_FLAGS_DMESG);
+	verify_size(pmsg_size, 4096, dev->flags & PSTORE_FLAGS_PMSG);
+	verify_size(console_size, 4096, dev->flags & PSTORE_FLAGS_CONSOLE);
+	verify_size(ftrace_size, 4096, dev->flags & PSTORE_FLAGS_FTRACE);
+#undef verify_size
+
+	pstore_zone_info->total_size = dev->total_size;
+	pstore_zone_info->max_reason = max_reason;
+	pstore_zone_info->read = dev->read;
+	pstore_zone_info->write = dev->write;
+	pstore_zone_info->erase = dev->erase;
+	pstore_zone_info->panic_write = dev->panic_write;
+	pstore_zone_info->name = KBUILD_MODNAME;
+	pstore_zone_info->owner = THIS_MODULE;
+
+	ret = register_pstore_zone(pstore_zone_info);
+	if (ret) {
+		kfree(pstore_zone_info);
+		pstore_zone_info = NULL;
+	}
+	return ret;
+}
+/**
+ * register_pstore_device() - register non-block device to pstore/blk
+ *
+ * @dev: non-block device information
+ *
+ * Return:
+ * * 0		- OK
+ * * Others	- something error.
+ */
+int register_pstore_device(struct pstore_device_info *dev)
+{
+	int ret;
+
+	mutex_lock(&pstore_blk_lock);
+	ret = __register_pstore_device(dev);
+	mutex_unlock(&pstore_blk_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_pstore_device);
+
+static void __unregister_pstore_device(struct pstore_device_info *dev)
+{
+	lockdep_assert_held(&pstore_blk_lock);
+	if (pstore_zone_info && pstore_zone_info->read == dev->read) {
+		unregister_pstore_zone(pstore_zone_info);
+		kfree(pstore_zone_info);
+		pstore_zone_info = NULL;
+	}
+}
+
+/**
+ * unregister_pstore_device() - unregister non-block device from pstore/blk
+ *
+ * @dev: non-block device information
+ */
+void unregister_pstore_device(struct pstore_device_info *dev)
+{
+	mutex_lock(&pstore_blk_lock);
+	__unregister_pstore_device(dev);
+	mutex_unlock(&pstore_blk_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_pstore_device);
+
+/**
+ * psblk_get_bdev() - open block device
+ *
+ * @holder:	Exclusive holder identifier
+ * @info:	Information about bdev to fill in
+ *
+ * Return: pointer to block device on success and others on error.
+ *
+ * On success, the returned block_device has reference count of one.
+ */
+static struct block_device *psblk_get_bdev(void *holder,
+					   struct bdev_info *info)
+{
+	struct block_device *bdev = ERR_PTR(-ENODEV);
+	fmode_t mode = FMODE_READ | FMODE_WRITE;
+	sector_t nr_sects;
+
+	lockdep_assert_held(&pstore_blk_lock);
+
+	if (pstore_zone_info)
+		return ERR_PTR(-EBUSY);
+
+	if (!blkdev[0])
+		return ERR_PTR(-ENODEV);
+
+	if (holder)
+		mode |= FMODE_EXCL;
+	bdev = blkdev_get_by_path(blkdev, mode, holder);
+	if (IS_ERR(bdev)) {
+		dev_t devt;
+
+		devt = name_to_dev_t(blkdev);
+		if (devt == 0)
+			return ERR_PTR(-ENODEV);
+		bdev = blkdev_get_by_dev(devt, mode, holder);
+		if (IS_ERR(bdev))
+			return bdev;
+	}
+
+	nr_sects = part_nr_sects_read(bdev->bd_part);
+	if (!nr_sects) {
+		pr_err("not enough space for '%s'\n", blkdev);
+		blkdev_put(bdev, mode);
+		return ERR_PTR(-ENOSPC);
+	}
+
+	if (info) {
+		info->devt = bdev->bd_dev;
+		info->nr_sects = nr_sects;
+		info->start_sect = get_start_sect(bdev);
+	}
+
+	return bdev;
+}
+
+static void psblk_put_bdev(struct block_device *bdev, void *holder)
+{
+	fmode_t mode = FMODE_READ | FMODE_WRITE;
+
+	lockdep_assert_held(&pstore_blk_lock);
+
+	if (!bdev)
+		return;
+
+	if (holder)
+		mode |= FMODE_EXCL;
+	blkdev_put(bdev, mode);
+}
+
+static ssize_t psblk_generic_blk_read(char *buf, size_t bytes, loff_t pos)
+{
+	struct block_device *bdev = psblk_bdev;
+	struct file file;
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	struct kvec iov = {.iov_base = buf, .iov_len = bytes};
+
+	if (!bdev)
+		return -ENODEV;
+
+	memset(&file, 0, sizeof(struct file));
+	file.f_mapping = bdev->bd_inode->i_mapping;
+	file.f_flags = O_DSYNC | __O_SYNC | O_NOATIME;
+	file.f_inode = bdev->bd_inode;
+	file_ra_state_init(&file.f_ra, file.f_mapping);
+
+	init_sync_kiocb(&kiocb, &file);
+	kiocb.ki_pos = pos;
+	iov_iter_kvec(&iter, READ, &iov, 1, bytes);
+
+	return generic_file_read_iter(&kiocb, &iter);
+}
+
+static ssize_t psblk_generic_blk_write(const char *buf, size_t bytes,
+		loff_t pos)
+{
+	struct block_device *bdev = psblk_bdev;
+	struct iov_iter iter;
+	struct kiocb kiocb;
+	struct file file;
+	ssize_t ret;
+	struct kvec iov = {.iov_base = (void *)buf, .iov_len = bytes};
+
+	if (!bdev)
+		return -ENODEV;
+
+	/* Console/Ftrace backend may handle buffer until flush dirty zones */
+	if (in_interrupt() || irqs_disabled())
+		return -EBUSY;
+
+	memset(&file, 0, sizeof(struct file));
+	file.f_mapping = bdev->bd_inode->i_mapping;
+	file.f_flags = O_DSYNC | __O_SYNC | O_NOATIME;
+	file.f_inode = bdev->bd_inode;
+
+	init_sync_kiocb(&kiocb, &file);
+	kiocb.ki_pos = pos;
+	iov_iter_kvec(&iter, WRITE, &iov, 1, bytes);
+
+	inode_lock(bdev->bd_inode);
+	ret = generic_write_checks(&kiocb, &iter);
+	if (ret > 0)
+		ret = generic_perform_write(&file, &iter, pos);
+	inode_unlock(bdev->bd_inode);
+
+	if (likely(ret > 0)) {
+		const struct file_operations f_op = {.fsync = blkdev_fsync};
+
+		file.f_op = &f_op;
+		kiocb.ki_pos += ret;
+		ret = generic_write_sync(&kiocb, ret);
+	}
+	return ret;
+}
+
+static ssize_t psblk_blk_panic_write(const char *buf, size_t size,
+		loff_t off)
+{
+	int ret;
+
+	if (!blkdev_panic_write)
+		return -EOPNOTSUPP;
+
+	/* size and off must align to SECTOR_SIZE for block device */
+	ret = blkdev_panic_write(buf, off >> SECTOR_SHIFT,
+			size >> SECTOR_SHIFT);
+	/* try next zone */
+	if (ret == -ENOMSG)
+		return ret;
+	return ret ? -EIO : size;
+}
+
+static int __register_pstore_blk(struct pstore_blk_info *info)
+{
+	char bdev_name[BDEVNAME_SIZE];
+	struct block_device *bdev;
+	struct pstore_device_info dev;
+	struct bdev_info binfo;
+	void *holder = blkdev;
+	int ret = -ENODEV;
+
+	lockdep_assert_held(&pstore_blk_lock);
+
+	/* hold bdev exclusively */
+	memset(&binfo, 0, sizeof(binfo));
+	bdev = psblk_get_bdev(holder, &binfo);
+	if (IS_ERR(bdev)) {
+		pr_err("failed to open '%s'!\n", blkdev);
+		return PTR_ERR(bdev);
+	}
+
+	/* only allow driver matching the @blkdev */
+	if (!binfo.devt || (!best_effort &&
+			    MAJOR(binfo.devt) != info->major)) {
+		pr_debug("invalid major %u (expect %u)\n",
+				info->major, MAJOR(binfo.devt));
+		ret = -ENODEV;
+		goto err_put_bdev;
+	}
+
+	/* psblk_bdev must be assigned before register to pstore/blk */
+	psblk_bdev = bdev;
+	blkdev_panic_write = info->panic_write;
+
+	/* Copy back block device details. */
+	info->devt = binfo.devt;
+	info->nr_sects = binfo.nr_sects;
+	info->start_sect = binfo.start_sect;
+
+	memset(&dev, 0, sizeof(dev));
+	dev.total_size = info->nr_sects << SECTOR_SHIFT;
+	dev.flags = info->flags;
+	dev.read = psblk_generic_blk_read;
+	dev.write = psblk_generic_blk_write;
+	dev.erase = NULL;
+	dev.panic_write = info->panic_write ? psblk_blk_panic_write : NULL;
+
+	ret = __register_pstore_device(&dev);
+	if (ret)
+		goto err_put_bdev;
+
+	bdevname(bdev, bdev_name);
+	pr_info("attached %s%s\n", bdev_name,
+		info->panic_write ? "" : " (no dedicated panic_write!)");
+	return 0;
+
+err_put_bdev:
+	psblk_bdev = NULL;
+	blkdev_panic_write = NULL;
+	psblk_put_bdev(bdev, holder);
+	return ret;
+}
+
+/**
+ * register_pstore_blk() - register block device to pstore/blk
+ *
+ * @info: details on the desired block device interface
+ *
+ * Return:
+ * * 0		- OK
+ * * Others	- something error.
+ */
+int register_pstore_blk(struct pstore_blk_info *info)
+{
+	int ret;
+
+	mutex_lock(&pstore_blk_lock);
+	ret = __register_pstore_blk(info);
+	mutex_unlock(&pstore_blk_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_pstore_blk);
+
+static void __unregister_pstore_blk(unsigned int major)
+{
+	struct pstore_device_info dev = { .read = psblk_generic_blk_read };
+	void *holder = blkdev;
+
+	lockdep_assert_held(&pstore_blk_lock);
+	if (psblk_bdev && MAJOR(psblk_bdev->bd_dev) == major) {
+		__unregister_pstore_device(&dev);
+		psblk_put_bdev(psblk_bdev, holder);
+		blkdev_panic_write = NULL;
+		psblk_bdev = NULL;
+	}
+}
+
+/**
+ * unregister_pstore_blk() - unregister block device from pstore/blk
+ *
+ * @major: the major device number of device
+ */
+void unregister_pstore_blk(unsigned int major)
+{
+	mutex_lock(&pstore_blk_lock);
+	__unregister_pstore_blk(major);
+	mutex_unlock(&pstore_blk_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_pstore_blk);
+
+/* get information of pstore/blk */
+int pstore_blk_get_config(struct pstore_blk_config *info)
+{
+	strncpy(info->device, blkdev, 80);
+	info->max_reason = max_reason;
+	info->kmsg_size = check_size(kmsg_size, 4096);
+	info->pmsg_size = check_size(pmsg_size, 4096);
+	info->ftrace_size = check_size(ftrace_size, 4096);
+	info->console_size = check_size(console_size, 4096);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pstore_blk_get_config);
+
+static int __init pstore_blk_init(void)
+{
+	struct pstore_blk_info info = { };
+	int ret = 0;
+
+	mutex_lock(&pstore_blk_lock);
+	if (!pstore_zone_info && best_effort && blkdev[0])
+		ret = __register_pstore_blk(&info);
+	mutex_unlock(&pstore_blk_lock);
+
+	return ret;
+}
+late_initcall(pstore_blk_init);
+
+static void __exit pstore_blk_exit(void)
+{
+	mutex_lock(&pstore_blk_lock);
+	if (psblk_bdev)
+		__unregister_pstore_blk(MAJOR(psblk_bdev->bd_dev));
+	else {
+		struct pstore_device_info dev = { };
+
+		if (pstore_zone_info)
+			dev.read = pstore_zone_info->read;
+		__unregister_pstore_device(&dev);
+	}
+	mutex_unlock(&pstore_blk_lock);
+}
+module_exit(pstore_blk_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("WeiXiong Liao <liaoweixiong@allwinnertech.com>");
+MODULE_AUTHOR("Kees Cook <keescook@chromium.org>");
+MODULE_DESCRIPTION("pstore backend for block devices");
diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c
index bfbfc2698070..5c0450701293 100644
--- a/fs/pstore/ftrace.c
+++ b/fs/pstore/ftrace.c
@@ -16,6 +16,7 @@
 #include <linux/debugfs.h>
 #include <linux/err.h>
 #include <linux/cache.h>
+#include <linux/slab.h>
 #include <asm/barrier.h>
 #include "internal.h"
 
@@ -132,3 +133,56 @@ void pstore_unregister_ftrace(void)
 
 	debugfs_remove_recursive(pstore_ftrace_dir);
 }
+
+ssize_t pstore_ftrace_combine_log(char **dest_log, size_t *dest_log_size,
+				  const char *src_log, size_t src_log_size)
+{
+	size_t dest_size, src_size, total, dest_off, src_off;
+	size_t dest_idx = 0, src_idx = 0, merged_idx = 0;
+	void *merged_buf;
+	struct pstore_ftrace_record *drec, *srec, *mrec;
+	size_t record_size = sizeof(struct pstore_ftrace_record);
+
+	dest_off = *dest_log_size % record_size;
+	dest_size = *dest_log_size - dest_off;
+
+	src_off = src_log_size % record_size;
+	src_size = src_log_size - src_off;
+
+	total = dest_size + src_size;
+	merged_buf = kmalloc(total, GFP_KERNEL);
+	if (!merged_buf)
+		return -ENOMEM;
+
+	drec = (struct pstore_ftrace_record *)(*dest_log + dest_off);
+	srec = (struct pstore_ftrace_record *)(src_log + src_off);
+	mrec = (struct pstore_ftrace_record *)(merged_buf);
+
+	while (dest_size > 0 && src_size > 0) {
+		if (pstore_ftrace_read_timestamp(&drec[dest_idx]) <
+		    pstore_ftrace_read_timestamp(&srec[src_idx])) {
+			mrec[merged_idx++] = drec[dest_idx++];
+			dest_size -= record_size;
+		} else {
+			mrec[merged_idx++] = srec[src_idx++];
+			src_size -= record_size;
+		}
+	}
+
+	while (dest_size > 0) {
+		mrec[merged_idx++] = drec[dest_idx++];
+		dest_size -= record_size;
+	}
+
+	while (src_size > 0) {
+		mrec[merged_idx++] = srec[src_idx++];
+		src_size -= record_size;
+	}
+
+	kfree(*dest_log);
+	*dest_log = merged_buf;
+	*dest_log_size = total;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pstore_ftrace_combine_log);
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index d99b5d39aa90..c331efe8de95 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -22,18 +22,21 @@
 #include <linux/magic.h>
 #include <linux/pstore.h>
 #include <linux/slab.h>
-#include <linux/spinlock.h>
 #include <linux/uaccess.h>
 
 #include "internal.h"
 
 #define	PSTORE_NAMELEN	64
 
-static DEFINE_SPINLOCK(allpstore_lock);
-static LIST_HEAD(allpstore);
+static DEFINE_MUTEX(records_list_lock);
+static LIST_HEAD(records_list);
+
+static DEFINE_MUTEX(pstore_sb_lock);
+static struct super_block *pstore_sb;
 
 struct pstore_private {
 	struct list_head list;
+	struct dentry *dentry;
 	struct pstore_record *record;
 	size_t total_size;
 };
@@ -178,10 +181,22 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct pstore_private *p = d_inode(dentry)->i_private;
 	struct pstore_record *record = p->record;
+	int rc = 0;
 
 	if (!record->psi->erase)
 		return -EPERM;
 
+	/* Make sure we can't race while removing this file. */
+	mutex_lock(&records_list_lock);
+	if (!list_empty(&p->list))
+		list_del_init(&p->list);
+	else
+		rc = -ENOENT;
+	p->dentry = NULL;
+	mutex_unlock(&records_list_lock);
+	if (rc)
+		return rc;
+
 	mutex_lock(&record->psi->read_mutex);
 	record->psi->erase(record);
 	mutex_unlock(&record->psi->read_mutex);
@@ -192,15 +207,9 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry)
 static void pstore_evict_inode(struct inode *inode)
 {
 	struct pstore_private	*p = inode->i_private;
-	unsigned long		flags;
 
 	clear_inode(inode);
-	if (p) {
-		spin_lock_irqsave(&allpstore_lock, flags);
-		list_del(&p->list);
-		spin_unlock_irqrestore(&allpstore_lock, flags);
-		free_pstore_private(p);
-	}
+	free_pstore_private(p);
 }
 
 static const struct inode_operations pstore_dir_inode_operations = {
@@ -278,11 +287,54 @@ static const struct super_operations pstore_ops = {
 	.show_options	= pstore_show_options,
 };
 
-static struct super_block *pstore_sb;
+static struct dentry *psinfo_lock_root(void)
+{
+	struct dentry *root;
 
-bool pstore_is_mounted(void)
+	mutex_lock(&pstore_sb_lock);
+	/*
+	 * Having no backend is fine -- no records appear.
+	 * Not being mounted is fine -- nothing to do.
+	 */
+	if (!psinfo || !pstore_sb) {
+		mutex_unlock(&pstore_sb_lock);
+		return NULL;
+	}
+
+	root = pstore_sb->s_root;
+	inode_lock(d_inode(root));
+	mutex_unlock(&pstore_sb_lock);
+
+	return root;
+}
+
+int pstore_put_backend_records(struct pstore_info *psi)
 {
-	return pstore_sb != NULL;
+	struct pstore_private *pos, *tmp;
+	struct dentry *root;
+	int rc = 0;
+
+	root = psinfo_lock_root();
+	if (!root)
+		return 0;
+
+	mutex_lock(&records_list_lock);
+	list_for_each_entry_safe(pos, tmp, &records_list, list) {
+		if (pos->record->psi == psi) {
+			list_del_init(&pos->list);
+			rc = simple_unlink(d_inode(root), pos->dentry);
+			if (WARN_ON(rc))
+				break;
+			d_drop(pos->dentry);
+			dput(pos->dentry);
+			pos->dentry = NULL;
+		}
+	}
+	mutex_unlock(&records_list_lock);
+
+	inode_unlock(d_inode(root));
+
+	return rc;
 }
 
 /*
@@ -297,23 +349,20 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record)
 	int			rc = 0;
 	char			name[PSTORE_NAMELEN];
 	struct pstore_private	*private, *pos;
-	unsigned long		flags;
 	size_t			size = record->size + record->ecc_notice_size;
 
-	WARN_ON(!inode_is_locked(d_inode(root)));
+	if (WARN_ON(!inode_is_locked(d_inode(root))))
+		return -EINVAL;
 
-	spin_lock_irqsave(&allpstore_lock, flags);
-	list_for_each_entry(pos, &allpstore, list) {
+	rc = -EEXIST;
+	/* Skip records that are already present in the filesystem. */
+	mutex_lock(&records_list_lock);
+	list_for_each_entry(pos, &records_list, list) {
 		if (pos->record->type == record->type &&
 		    pos->record->id == record->id &&
-		    pos->record->psi == record->psi) {
-			rc = -EEXIST;
-			break;
-		}
+		    pos->record->psi == record->psi)
+			goto fail;
 	}
-	spin_unlock_irqrestore(&allpstore_lock, flags);
-	if (rc)
-		return rc;
 
 	rc = -ENOMEM;
 	inode = pstore_get_inode(root->d_sb);
@@ -334,6 +383,7 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record)
 	if (!dentry)
 		goto fail_private;
 
+	private->dentry = dentry;
 	private->record = record;
 	inode->i_size = private->total_size = size;
 	inode->i_private = private;
@@ -343,9 +393,8 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record)
 
 	d_add(dentry, inode);
 
-	spin_lock_irqsave(&allpstore_lock, flags);
-	list_add(&private->list, &allpstore);
-	spin_unlock_irqrestore(&allpstore_lock, flags);
+	list_add(&private->list, &records_list);
+	mutex_unlock(&records_list_lock);
 
 	return 0;
 
@@ -353,8 +402,8 @@ fail_private:
 	free_pstore_private(private);
 fail_inode:
 	iput(inode);
-
 fail:
+	mutex_unlock(&records_list_lock);
 	return rc;
 }
 
@@ -366,16 +415,13 @@ fail:
  */
 void pstore_get_records(int quiet)
 {
-	struct pstore_info *psi = psinfo;
 	struct dentry *root;
 
-	if (!psi || !pstore_sb)
+	root = psinfo_lock_root();
+	if (!root)
 		return;
 
-	root = pstore_sb->s_root;
-
-	inode_lock(d_inode(root));
-	pstore_get_backend_records(psi, root, quiet);
+	pstore_get_backend_records(psinfo, root, quiet);
 	inode_unlock(d_inode(root));
 }
 
@@ -383,8 +429,6 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct inode *inode;
 
-	pstore_sb = sb;
-
 	sb->s_maxbytes		= MAX_LFS_FILESIZE;
 	sb->s_blocksize		= PAGE_SIZE;
 	sb->s_blocksize_bits	= PAGE_SHIFT;
@@ -405,6 +449,10 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sb->s_root)
 		return -ENOMEM;
 
+	mutex_lock(&pstore_sb_lock);
+	pstore_sb = sb;
+	mutex_unlock(&pstore_sb_lock);
+
 	pstore_get_records(0);
 
 	return 0;
@@ -418,8 +466,17 @@ static struct dentry *pstore_mount(struct file_system_type *fs_type,
 
 static void pstore_kill_sb(struct super_block *sb)
 {
+	mutex_lock(&pstore_sb_lock);
+	WARN_ON(pstore_sb != sb);
+
 	kill_litter_super(sb);
 	pstore_sb = NULL;
+
+	mutex_lock(&records_list_lock);
+	INIT_LIST_HEAD(&records_list);
+	mutex_unlock(&records_list_lock);
+
+	mutex_unlock(&pstore_sb_lock);
 }
 
 static struct file_system_type pstore_fs_type = {
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index 7062ea4bc57c..7fb219042f13 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -12,9 +12,18 @@ extern unsigned long kmsg_bytes;
 #ifdef CONFIG_PSTORE_FTRACE
 extern void pstore_register_ftrace(void);
 extern void pstore_unregister_ftrace(void);
+ssize_t pstore_ftrace_combine_log(char **dest_log, size_t *dest_log_size,
+				  const char *src_log, size_t src_log_size);
 #else
 static inline void pstore_register_ftrace(void) {}
 static inline void pstore_unregister_ftrace(void) {}
+static inline ssize_t
+pstore_ftrace_combine_log(char **dest_log, size_t *dest_log_size,
+			  const char *src_log, size_t src_log_size)
+{
+	*dest_log_size = 0;
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_PSTORE_PMSG
@@ -31,9 +40,9 @@ extern void	pstore_set_kmsg_bytes(int);
 extern void	pstore_get_records(int);
 extern void	pstore_get_backend_records(struct pstore_info *psi,
 					   struct dentry *root, int quiet);
+extern int	pstore_put_backend_records(struct pstore_info *psi);
 extern int	pstore_mkfile(struct dentry *root,
 			      struct pstore_record *record);
-extern bool	pstore_is_mounted(void);
 extern void	pstore_record_init(struct pstore_record *record,
 				   struct pstore_info *psi);
 
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 408277ee3cdb..a9e297eefdff 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -44,7 +44,7 @@ static int pstore_update_ms = -1;
 module_param_named(update_ms, pstore_update_ms, int, 0600);
 MODULE_PARM_DESC(update_ms, "milliseconds before pstore updates its content "
 		 "(default is -1, which means runtime updates are disabled; "
-		 "enabling this option is not safe, it may lead to further "
+		 "enabling this option may not be safe; it may lead to further "
 		 "corruption on Oopses)");
 
 /* Names should be in the same order as the enum pstore_type_id */
@@ -69,19 +69,25 @@ static void pstore_dowork(struct work_struct *);
 static DECLARE_WORK(pstore_work, pstore_dowork);
 
 /*
- * pstore_lock just protects "psinfo" during
- * calls to pstore_register()
+ * psinfo_lock protects "psinfo" during calls to
+ * pstore_register(), pstore_unregister(), and
+ * the filesystem mount/unmount routines.
  */
-static DEFINE_SPINLOCK(pstore_lock);
+static DEFINE_MUTEX(psinfo_lock);
 struct pstore_info *psinfo;
 
 static char *backend;
+module_param(backend, charp, 0444);
+MODULE_PARM_DESC(backend, "specific backend to use");
+
 static char *compress =
 #ifdef CONFIG_PSTORE_COMPRESS_DEFAULT
 		CONFIG_PSTORE_COMPRESS_DEFAULT;
 #else
 		NULL;
 #endif
+module_param(compress, charp, 0444);
+MODULE_PARM_DESC(compress, "compression to use");
 
 /* Compression parameters */
 static struct crypto_comp *tfm;
@@ -129,24 +135,12 @@ enum pstore_type_id pstore_name_to_type(const char *name)
 }
 EXPORT_SYMBOL_GPL(pstore_name_to_type);
 
-static const char *get_reason_str(enum kmsg_dump_reason reason)
+static void pstore_timer_kick(void)
 {
-	switch (reason) {
-	case KMSG_DUMP_PANIC:
-		return "Panic";
-	case KMSG_DUMP_OOPS:
-		return "Oops";
-	case KMSG_DUMP_EMERG:
-		return "Emergency";
-	case KMSG_DUMP_RESTART:
-		return "Restart";
-	case KMSG_DUMP_HALT:
-		return "Halt";
-	case KMSG_DUMP_POWEROFF:
-		return "Poweroff";
-	default:
-		return "Unknown";
-	}
+	if (pstore_update_ms < 0)
+		return;
+
+	mod_timer(&pstore_timer, jiffies + msecs_to_jiffies(pstore_update_ms));
 }
 
 /*
@@ -393,7 +387,7 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 	unsigned int	part = 1;
 	int		ret;
 
-	why = get_reason_str(reason);
+	why = kmsg_dump_reason_str(reason);
 
 	if (down_trylock(&psinfo->buf_lock)) {
 		/* Failed to acquire lock: give up if we cannot wait. */
@@ -459,8 +453,10 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 		}
 
 		ret = psinfo->write(&record);
-		if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted())
+		if (ret == 0 && reason == KMSG_DUMP_OOPS) {
 			pstore_new_entry = 1;
+			pstore_timer_kick();
+		}
 
 		total += record.size;
 		part++;
@@ -503,14 +499,20 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
 }
 
 static struct console pstore_console = {
-	.name	= "pstore",
 	.write	= pstore_console_write,
-	.flags	= CON_PRINTBUFFER | CON_ENABLED | CON_ANYTIME,
 	.index	= -1,
 };
 
 static void pstore_register_console(void)
 {
+	/* Show which backend is going to get console writes. */
+	strscpy(pstore_console.name, psinfo->name,
+		sizeof(pstore_console.name));
+	/*
+	 * Always initialize flags here since prior unregister_console()
+	 * calls may have changed settings (specifically CON_ENABLED).
+	 */
+	pstore_console.flags = CON_PRINTBUFFER | CON_ENABLED | CON_ANYTIME;
 	register_console(&pstore_console);
 }
 
@@ -555,8 +557,6 @@ out:
  */
 int pstore_register(struct pstore_info *psi)
 {
-	struct module *owner = psi->owner;
-
 	if (backend && strcmp(backend, psi->name)) {
 		pr_warn("ignoring unexpected backend '%s'\n", psi->name);
 		return -EPERM;
@@ -576,11 +576,11 @@ int pstore_register(struct pstore_info *psi)
 		return -EINVAL;
 	}
 
-	spin_lock(&pstore_lock);
+	mutex_lock(&psinfo_lock);
 	if (psinfo) {
 		pr_warn("backend '%s' already loaded: ignoring '%s'\n",
 			psinfo->name, psi->name);
-		spin_unlock(&pstore_lock);
+		mutex_unlock(&psinfo_lock);
 		return -EBUSY;
 	}
 
@@ -589,21 +589,16 @@ int pstore_register(struct pstore_info *psi)
 	psinfo = psi;
 	mutex_init(&psinfo->read_mutex);
 	sema_init(&psinfo->buf_lock, 1);
-	spin_unlock(&pstore_lock);
-
-	if (owner && !try_module_get(owner)) {
-		psinfo = NULL;
-		return -EINVAL;
-	}
 
 	if (psi->flags & PSTORE_FLAGS_DMESG)
 		allocate_buf_for_compression();
 
-	if (pstore_is_mounted())
-		pstore_get_records(0);
+	pstore_get_records(0);
 
-	if (psi->flags & PSTORE_FLAGS_DMESG)
+	if (psi->flags & PSTORE_FLAGS_DMESG) {
+		pstore_dumper.max_reason = psinfo->max_reason;
 		pstore_register_kmsg();
+	}
 	if (psi->flags & PSTORE_FLAGS_CONSOLE)
 		pstore_register_console();
 	if (psi->flags & PSTORE_FLAGS_FTRACE)
@@ -612,33 +607,36 @@ int pstore_register(struct pstore_info *psi)
 		pstore_register_pmsg();
 
 	/* Start watching for new records, if desired. */
-	if (pstore_update_ms >= 0) {
-		pstore_timer.expires = jiffies +
-			msecs_to_jiffies(pstore_update_ms);
-		add_timer(&pstore_timer);
-	}
+	pstore_timer_kick();
 
 	/*
 	 * Update the module parameter backend, so it is visible
 	 * through /sys/module/pstore/parameters/backend
 	 */
-	backend = psi->name;
+	backend = kstrdup(psi->name, GFP_KERNEL);
 
 	pr_info("Registered %s as persistent store backend\n", psi->name);
 
-	module_put(owner);
-
+	mutex_unlock(&psinfo_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pstore_register);
 
 void pstore_unregister(struct pstore_info *psi)
 {
-	/* Stop timer and make sure all work has finished. */
-	pstore_update_ms = -1;
-	del_timer_sync(&pstore_timer);
-	flush_work(&pstore_work);
+	/* It's okay to unregister nothing. */
+	if (!psi)
+		return;
+
+	mutex_lock(&psinfo_lock);
+
+	/* Only one backend can be registered at a time. */
+	if (WARN_ON(psi != psinfo)) {
+		mutex_unlock(&psinfo_lock);
+		return;
+	}
 
+	/* Unregister all callbacks. */
 	if (psi->flags & PSTORE_FLAGS_PMSG)
 		pstore_unregister_pmsg();
 	if (psi->flags & PSTORE_FLAGS_FTRACE)
@@ -648,10 +646,19 @@ void pstore_unregister(struct pstore_info *psi)
 	if (psi->flags & PSTORE_FLAGS_DMESG)
 		pstore_unregister_kmsg();
 
+	/* Stop timer and make sure all work has finished. */
+	del_timer_sync(&pstore_timer);
+	flush_work(&pstore_work);
+
+	/* Remove all backend records from filesystem tree. */
+	pstore_put_backend_records(psi);
+
 	free_buf_for_compression();
 
 	psinfo = NULL;
+	kfree(backend);
 	backend = NULL;
+	mutex_unlock(&psinfo_lock);
 }
 EXPORT_SYMBOL_GPL(pstore_unregister);
 
@@ -788,9 +795,7 @@ static void pstore_timefunc(struct timer_list *unused)
 		schedule_work(&pstore_work);
 	}
 
-	if (pstore_update_ms >= 0)
-		mod_timer(&pstore_timer,
-			  jiffies + msecs_to_jiffies(pstore_update_ms));
+	pstore_timer_kick();
 }
 
 static void __init pstore_choose_compression(void)
@@ -835,11 +840,5 @@ static void __exit pstore_exit(void)
 }
 module_exit(pstore_exit)
 
-module_param(compress, charp, 0444);
-MODULE_PARM_DESC(compress, "Pstore compression to use");
-
-module_param(backend, charp, 0444);
-MODULE_PARM_DESC(backend, "Pstore backend to use");
-
 MODULE_AUTHOR("Tony Luck <tony.luck@intel.com>");
 MODULE_LICENSE("GPL");
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 795622190c01..ca6d8a867285 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -21,6 +21,7 @@
 #include <linux/pstore_ram.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include "internal.h"
 
 #define RAMOOPS_KERNMSG_HDR "===="
 #define MIN_MEM_SIZE 4096UL
@@ -53,22 +54,27 @@ MODULE_PARM_DESC(mem_size,
 		"size of reserved RAM used to store oops/panic logs");
 
 static unsigned int mem_type;
-module_param(mem_type, uint, 0600);
+module_param(mem_type, uint, 0400);
 MODULE_PARM_DESC(mem_type,
 		"set to 1 to try to use unbuffered memory (default 0)");
 
-static int dump_oops = 1;
-module_param(dump_oops, int, 0600);
-MODULE_PARM_DESC(dump_oops,
-		"set to 1 to dump oopses, 0 to only dump panics (default 1)");
+static int ramoops_max_reason = -1;
+module_param_named(max_reason, ramoops_max_reason, int, 0400);
+MODULE_PARM_DESC(max_reason,
+		 "maximum reason for kmsg dump (default 2: Oops and Panic) ");
 
 static int ramoops_ecc;
-module_param_named(ecc, ramoops_ecc, int, 0600);
+module_param_named(ecc, ramoops_ecc, int, 0400);
 MODULE_PARM_DESC(ramoops_ecc,
 		"if non-zero, the option enables ECC support and specifies "
 		"ECC buffer size in bytes (1 is a special value, means 16 "
 		"bytes ECC)");
 
+static int ramoops_dump_oops = -1;
+module_param_named(dump_oops, ramoops_dump_oops, int, 0400);
+MODULE_PARM_DESC(dump_oops,
+		 "(deprecated: use max_reason instead) set to 1 to dump oopses & panics, 0 to only dump panics");
+
 struct ramoops_context {
 	struct persistent_ram_zone **dprzs;	/* Oops dump zones */
 	struct persistent_ram_zone *cprz;	/* Console zone */
@@ -81,7 +87,6 @@ struct ramoops_context {
 	size_t console_size;
 	size_t ftrace_size;
 	size_t pmsg_size;
-	int dump_oops;
 	u32 flags;
 	struct persistent_ram_ecc_info ecc_info;
 	unsigned int max_dump_cnt;
@@ -168,58 +173,6 @@ static bool prz_ok(struct persistent_ram_zone *prz)
 			   persistent_ram_ecc_string(prz, NULL, 0));
 }
 
-static ssize_t ftrace_log_combine(struct persistent_ram_zone *dest,
-				  struct persistent_ram_zone *src)
-{
-	size_t dest_size, src_size, total, dest_off, src_off;
-	size_t dest_idx = 0, src_idx = 0, merged_idx = 0;
-	void *merged_buf;
-	struct pstore_ftrace_record *drec, *srec, *mrec;
-	size_t record_size = sizeof(struct pstore_ftrace_record);
-
-	dest_off = dest->old_log_size % record_size;
-	dest_size = dest->old_log_size - dest_off;
-
-	src_off = src->old_log_size % record_size;
-	src_size = src->old_log_size - src_off;
-
-	total = dest_size + src_size;
-	merged_buf = kmalloc(total, GFP_KERNEL);
-	if (!merged_buf)
-		return -ENOMEM;
-
-	drec = (struct pstore_ftrace_record *)(dest->old_log + dest_off);
-	srec = (struct pstore_ftrace_record *)(src->old_log + src_off);
-	mrec = (struct pstore_ftrace_record *)(merged_buf);
-
-	while (dest_size > 0 && src_size > 0) {
-		if (pstore_ftrace_read_timestamp(&drec[dest_idx]) <
-		    pstore_ftrace_read_timestamp(&srec[src_idx])) {
-			mrec[merged_idx++] = drec[dest_idx++];
-			dest_size -= record_size;
-		} else {
-			mrec[merged_idx++] = srec[src_idx++];
-			src_size -= record_size;
-		}
-	}
-
-	while (dest_size > 0) {
-		mrec[merged_idx++] = drec[dest_idx++];
-		dest_size -= record_size;
-	}
-
-	while (src_size > 0) {
-		mrec[merged_idx++] = srec[src_idx++];
-		src_size -= record_size;
-	}
-
-	kfree(dest->old_log);
-	dest->old_log = merged_buf;
-	dest->old_log_size = total;
-
-	return 0;
-}
-
 static ssize_t ramoops_pstore_read(struct pstore_record *record)
 {
 	ssize_t size = 0;
@@ -291,7 +244,12 @@ static ssize_t ramoops_pstore_read(struct pstore_record *record)
 				tmp_prz->corrected_bytes +=
 						prz_next->corrected_bytes;
 				tmp_prz->bad_blocks += prz_next->bad_blocks;
-				size = ftrace_log_combine(tmp_prz, prz_next);
+
+				size = pstore_ftrace_combine_log(
+						&tmp_prz->old_log,
+						&tmp_prz->old_log_size,
+						prz_next->old_log,
+						prz_next->old_log_size);
 				if (size)
 					goto out;
 			}
@@ -382,16 +340,14 @@ static int notrace ramoops_pstore_write(struct pstore_record *record)
 		return -EINVAL;
 
 	/*
-	 * Out of the various dmesg dump types, ramoops is currently designed
-	 * to only store crash logs, rather than storing general kernel logs.
+	 * We could filter on record->reason here if we wanted to (which
+	 * would duplicate what happened before the "max_reason" setting
+	 * was added), but that would defeat the purpose of a system
+	 * changing printk.always_kmsg_dump, so instead log everything that
+	 * the kmsg dumper sends us, since it should be doing the filtering
+	 * based on the combination of printk.always_kmsg_dump and our
+	 * requested "max_reason".
 	 */
-	if (record->reason != KMSG_DUMP_OOPS &&
-	    record->reason != KMSG_DUMP_PANIC)
-		return -EINVAL;
-
-	/* Skip Oopes when configured to do so. */
-	if (record->reason == KMSG_DUMP_OOPS && !cxt->dump_oops)
-		return -EINVAL;
 
 	/*
 	 * Explicitly only take the first part of any new crash.
@@ -644,19 +600,25 @@ static int ramoops_init_prz(const char *name,
 	return 0;
 }
 
-static int ramoops_parse_dt_size(struct platform_device *pdev,
-				 const char *propname, u32 *value)
+/* Read a u32 from a dt property and make sure it's safe for an int. */
+static int ramoops_parse_dt_u32(struct platform_device *pdev,
+				const char *propname,
+				u32 default_value, u32 *value)
 {
 	u32 val32 = 0;
 	int ret;
 
 	ret = of_property_read_u32(pdev->dev.of_node, propname, &val32);
-	if (ret < 0 && ret != -EINVAL) {
+	if (ret == -EINVAL) {
+		/* field is missing, use default value. */
+		val32 = default_value;
+	} else if (ret < 0) {
 		dev_err(&pdev->dev, "failed to parse property %s: %d\n",
 			propname, ret);
 		return ret;
 	}
 
+	/* Sanity check our results. */
 	if (val32 > INT_MAX) {
 		dev_err(&pdev->dev, "%s %u > INT_MAX\n", propname, val32);
 		return -EOVERFLOW;
@@ -687,23 +649,32 @@ static int ramoops_parse_dt(struct platform_device *pdev,
 	pdata->mem_size = resource_size(res);
 	pdata->mem_address = res->start;
 	pdata->mem_type = of_property_read_bool(of_node, "unbuffered");
-	pdata->dump_oops = !of_property_read_bool(of_node, "no-dump-oops");
-
-#define parse_size(name, field) {					\
-		ret = ramoops_parse_dt_size(pdev, name, &value);	\
+	/*
+	 * Setting "no-dump-oops" is deprecated and will be ignored if
+	 * "max_reason" is also specified.
+	 */
+	if (of_property_read_bool(of_node, "no-dump-oops"))
+		pdata->max_reason = KMSG_DUMP_PANIC;
+	else
+		pdata->max_reason = KMSG_DUMP_OOPS;
+
+#define parse_u32(name, field, default_value) {				\
+		ret = ramoops_parse_dt_u32(pdev, name, default_value,	\
+					    &value);			\
 		if (ret < 0)						\
 			return ret;					\
 		field = value;						\
 	}
 
-	parse_size("record-size", pdata->record_size);
-	parse_size("console-size", pdata->console_size);
-	parse_size("ftrace-size", pdata->ftrace_size);
-	parse_size("pmsg-size", pdata->pmsg_size);
-	parse_size("ecc-size", pdata->ecc_info.ecc_size);
-	parse_size("flags", pdata->flags);
+	parse_u32("record-size", pdata->record_size, 0);
+	parse_u32("console-size", pdata->console_size, 0);
+	parse_u32("ftrace-size", pdata->ftrace_size, 0);
+	parse_u32("pmsg-size", pdata->pmsg_size, 0);
+	parse_u32("ecc-size", pdata->ecc_info.ecc_size, 0);
+	parse_u32("flags", pdata->flags, 0);
+	parse_u32("max-reason", pdata->max_reason, pdata->max_reason);
 
-#undef parse_size
+#undef parse_u32
 
 	/*
 	 * Some old Chromebooks relied on the kernel setting the
@@ -785,7 +756,6 @@ static int ramoops_probe(struct platform_device *pdev)
 	cxt->console_size = pdata->console_size;
 	cxt->ftrace_size = pdata->ftrace_size;
 	cxt->pmsg_size = pdata->pmsg_size;
-	cxt->dump_oops = pdata->dump_oops;
 	cxt->flags = pdata->flags;
 	cxt->ecc_info = pdata->ecc_info;
 
@@ -828,8 +798,10 @@ static int ramoops_probe(struct platform_device *pdev)
 	 * the single region size is how to check.
 	 */
 	cxt->pstore.flags = 0;
-	if (cxt->max_dump_cnt)
+	if (cxt->max_dump_cnt) {
 		cxt->pstore.flags |= PSTORE_FLAGS_DMESG;
+		cxt->pstore.max_reason = pdata->max_reason;
+	}
 	if (cxt->console_size)
 		cxt->pstore.flags |= PSTORE_FLAGS_CONSOLE;
 	if (cxt->max_ftrace_cnt)
@@ -865,7 +837,7 @@ static int ramoops_probe(struct platform_device *pdev)
 	mem_size = pdata->mem_size;
 	mem_address = pdata->mem_address;
 	record_size = pdata->record_size;
-	dump_oops = pdata->dump_oops;
+	ramoops_max_reason = pdata->max_reason;
 	ramoops_console_size = pdata->console_size;
 	ramoops_pmsg_size = pdata->pmsg_size;
 	ramoops_ftrace_size = pdata->ftrace_size;
@@ -948,7 +920,16 @@ static void __init ramoops_register_dummy(void)
 	pdata.console_size = ramoops_console_size;
 	pdata.ftrace_size = ramoops_ftrace_size;
 	pdata.pmsg_size = ramoops_pmsg_size;
-	pdata.dump_oops = dump_oops;
+	/* If "max_reason" is set, its value has priority over "dump_oops". */
+	if (ramoops_max_reason >= 0)
+		pdata.max_reason = ramoops_max_reason;
+	/* Otherwise, if "dump_oops" is set, parse it into "max_reason". */
+	else if (ramoops_dump_oops != -1)
+		pdata.max_reason = ramoops_dump_oops ? KMSG_DUMP_OOPS
+						     : KMSG_DUMP_PANIC;
+	/* And if neither are explicitly set, use the default. */
+	else
+		pdata.max_reason = KMSG_DUMP_OOPS;
 	pdata.flags = RAMOOPS_FLAG_FTRACE_PER_CPU;
 
 	/*
diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c
new file mode 100644
index 000000000000..819428dfa32f
--- /dev/null
+++ b/fs/pstore/zone.c
@@ -0,0 +1,1465 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Provide a pstore intermediate backend, organized into kernel memory
+ * allocated zones that are then mapped and flushed into a single
+ * contiguous region on a storage backend of some kind (block, mtd, etc).
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/mount.h>
+#include <linux/printk.h>
+#include <linux/fs.h>
+#include <linux/pstore_zone.h>
+#include <linux/kdev_t.h>
+#include <linux/device.h>
+#include <linux/namei.h>
+#include <linux/fcntl.h>
+#include <linux/uio.h>
+#include <linux/writeback.h>
+#include "internal.h"
+
+/**
+ * struct psz_head - header of zone to flush to storage
+ *
+ * @sig: signature to indicate header (PSZ_SIG xor PSZONE-type value)
+ * @datalen: length of data in @data
+ * @start: offset into @data where the beginning of the stored bytes begin
+ * @data: zone data.
+ */
+struct psz_buffer {
+#define PSZ_SIG (0x43474244) /* DBGC */
+	uint32_t sig;
+	atomic_t datalen;
+	atomic_t start;
+	uint8_t data[];
+};
+
+/**
+ * struct psz_kmsg_header - kmsg dump-specific header to flush to storage
+ *
+ * @magic: magic num for kmsg dump header
+ * @time: kmsg dump trigger time
+ * @compressed: whether conpressed
+ * @counter: kmsg dump counter
+ * @reason: the kmsg dump reason (e.g. oops, panic, etc)
+ * @data: pointer to log data
+ *
+ * This is a sub-header for a kmsg dump, trailing after &psz_buffer.
+ */
+struct psz_kmsg_header {
+#define PSTORE_KMSG_HEADER_MAGIC 0x4dfc3ae5 /* Just a random number */
+	uint32_t magic;
+	struct timespec64 time;
+	bool compressed;
+	uint32_t counter;
+	enum kmsg_dump_reason reason;
+	uint8_t data[];
+};
+
+/**
+ * struct pstore_zone - single stored buffer
+ *
+ * @off: zone offset of storage
+ * @type: front-end type for this zone
+ * @name: front-end name for this zone
+ * @buffer: pointer to data buffer managed by this zone
+ * @oldbuf: pointer to old data buffer
+ * @buffer_size: bytes in @buffer->data
+ * @should_recover: whether this zone should recover from storage
+ * @dirty: whether the data in @buffer dirty
+ *
+ * zone structure in memory.
+ */
+struct pstore_zone {
+	loff_t off;
+	const char *name;
+	enum pstore_type_id type;
+
+	struct psz_buffer *buffer;
+	struct psz_buffer *oldbuf;
+	size_t buffer_size;
+	bool should_recover;
+	atomic_t dirty;
+};
+
+/**
+ * struct psz_context - all about running state of pstore/zone
+ *
+ * @kpszs: kmsg dump storage zones
+ * @ppsz: pmsg storage zone
+ * @cpsz: console storage zone
+ * @fpszs: ftrace storage zones
+ * @kmsg_max_cnt: max count of @kpszs
+ * @kmsg_read_cnt: counter of total read kmsg dumps
+ * @kmsg_write_cnt: counter of total kmsg dump writes
+ * @pmsg_read_cnt: counter of total read pmsg zone
+ * @console_read_cnt: counter of total read console zone
+ * @ftrace_max_cnt: max count of @fpszs
+ * @ftrace_read_cnt: counter of max read ftrace zone
+ * @oops_counter: counter of oops dumps
+ * @panic_counter: counter of panic dumps
+ * @recovered: whether finished recovering data from storage
+ * @on_panic: whether panic is happening
+ * @pstore_zone_info_lock: lock to @pstore_zone_info
+ * @pstore_zone_info: information from backend
+ * @pstore: structure for pstore
+ */
+struct psz_context {
+	struct pstore_zone **kpszs;
+	struct pstore_zone *ppsz;
+	struct pstore_zone *cpsz;
+	struct pstore_zone **fpszs;
+	unsigned int kmsg_max_cnt;
+	unsigned int kmsg_read_cnt;
+	unsigned int kmsg_write_cnt;
+	unsigned int pmsg_read_cnt;
+	unsigned int console_read_cnt;
+	unsigned int ftrace_max_cnt;
+	unsigned int ftrace_read_cnt;
+	/*
+	 * These counters should be calculated during recovery.
+	 * It records the oops/panic times after crashes rather than boots.
+	 */
+	unsigned int oops_counter;
+	unsigned int panic_counter;
+	atomic_t recovered;
+	atomic_t on_panic;
+
+	/*
+	 * pstore_zone_info_lock protects this entire structure during calls
+	 * to register_pstore_zone()/unregister_pstore_zone().
+	 */
+	struct mutex pstore_zone_info_lock;
+	struct pstore_zone_info *pstore_zone_info;
+	struct pstore_info pstore;
+};
+static struct psz_context pstore_zone_cxt;
+
+static void psz_flush_all_dirty_zones(struct work_struct *);
+static DECLARE_DELAYED_WORK(psz_cleaner, psz_flush_all_dirty_zones);
+
+/**
+ * enum psz_flush_mode - flush mode for psz_zone_write()
+ *
+ * @FLUSH_NONE: do not flush to storage but update data on memory
+ * @FLUSH_PART: just flush part of data including meta data to storage
+ * @FLUSH_META: just flush meta data of zone to storage
+ * @FLUSH_ALL: flush all of zone
+ */
+enum psz_flush_mode {
+	FLUSH_NONE = 0,
+	FLUSH_PART,
+	FLUSH_META,
+	FLUSH_ALL,
+};
+
+static inline int buffer_datalen(struct pstore_zone *zone)
+{
+	return atomic_read(&zone->buffer->datalen);
+}
+
+static inline int buffer_start(struct pstore_zone *zone)
+{
+	return atomic_read(&zone->buffer->start);
+}
+
+static inline bool is_on_panic(void)
+{
+	return atomic_read(&pstore_zone_cxt.on_panic);
+}
+
+static ssize_t psz_zone_read_buffer(struct pstore_zone *zone, char *buf,
+		size_t len, unsigned long off)
+{
+	if (!buf || !zone || !zone->buffer)
+		return -EINVAL;
+	if (off > zone->buffer_size)
+		return -EINVAL;
+	len = min_t(size_t, len, zone->buffer_size - off);
+	memcpy(buf, zone->buffer->data + off, len);
+	return len;
+}
+
+static int psz_zone_read_oldbuf(struct pstore_zone *zone, char *buf,
+		size_t len, unsigned long off)
+{
+	if (!buf || !zone || !zone->oldbuf)
+		return -EINVAL;
+	if (off > zone->buffer_size)
+		return -EINVAL;
+	len = min_t(size_t, len, zone->buffer_size - off);
+	memcpy(buf, zone->oldbuf->data + off, len);
+	return 0;
+}
+
+static int psz_zone_write(struct pstore_zone *zone,
+		enum psz_flush_mode flush_mode, const char *buf,
+		size_t len, unsigned long off)
+{
+	struct pstore_zone_info *info = pstore_zone_cxt.pstore_zone_info;
+	ssize_t wcnt = 0;
+	ssize_t (*writeop)(const char *buf, size_t bytes, loff_t pos);
+	size_t wlen;
+
+	if (off > zone->buffer_size)
+		return -EINVAL;
+
+	wlen = min_t(size_t, len, zone->buffer_size - off);
+	if (buf && wlen) {
+		memcpy(zone->buffer->data + off, buf, wlen);
+		atomic_set(&zone->buffer->datalen, wlen + off);
+	}
+
+	/* avoid to damage old records */
+	if (!is_on_panic() && !atomic_read(&pstore_zone_cxt.recovered))
+		goto dirty;
+
+	writeop = is_on_panic() ? info->panic_write : info->write;
+	if (!writeop)
+		goto dirty;
+
+	switch (flush_mode) {
+	case FLUSH_NONE:
+		if (unlikely(buf && wlen))
+			goto dirty;
+		return 0;
+	case FLUSH_PART:
+		wcnt = writeop((const char *)zone->buffer->data + off, wlen,
+				zone->off + sizeof(*zone->buffer) + off);
+		if (wcnt != wlen)
+			goto dirty;
+		fallthrough;
+	case FLUSH_META:
+		wlen = sizeof(struct psz_buffer);
+		wcnt = writeop((const char *)zone->buffer, wlen, zone->off);
+		if (wcnt != wlen)
+			goto dirty;
+		break;
+	case FLUSH_ALL:
+		wlen = zone->buffer_size + sizeof(*zone->buffer);
+		wcnt = writeop((const char *)zone->buffer, wlen, zone->off);
+		if (wcnt != wlen)
+			goto dirty;
+		break;
+	}
+
+	return 0;
+dirty:
+	/* no need to mark dirty if going to try next zone */
+	if (wcnt == -ENOMSG)
+		return -ENOMSG;
+	atomic_set(&zone->dirty, true);
+	/* flush dirty zones nicely */
+	if (wcnt == -EBUSY && !is_on_panic())
+		schedule_delayed_work(&psz_cleaner, msecs_to_jiffies(500));
+	return -EBUSY;
+}
+
+static int psz_flush_dirty_zone(struct pstore_zone *zone)
+{
+	int ret;
+
+	if (unlikely(!zone))
+		return -EINVAL;
+
+	if (unlikely(!atomic_read(&pstore_zone_cxt.recovered)))
+		return -EBUSY;
+
+	if (!atomic_xchg(&zone->dirty, false))
+		return 0;
+
+	ret = psz_zone_write(zone, FLUSH_ALL, NULL, 0, 0);
+	if (ret)
+		atomic_set(&zone->dirty, true);
+	return ret;
+}
+
+static int psz_flush_dirty_zones(struct pstore_zone **zones, unsigned int cnt)
+{
+	int i, ret;
+	struct pstore_zone *zone;
+
+	if (!zones)
+		return -EINVAL;
+
+	for (i = 0; i < cnt; i++) {
+		zone = zones[i];
+		if (!zone)
+			return -EINVAL;
+		ret = psz_flush_dirty_zone(zone);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int psz_move_zone(struct pstore_zone *old, struct pstore_zone *new)
+{
+	const char *data = (const char *)old->buffer->data;
+	int ret;
+
+	ret = psz_zone_write(new, FLUSH_ALL, data, buffer_datalen(old), 0);
+	if (ret) {
+		atomic_set(&new->buffer->datalen, 0);
+		atomic_set(&new->dirty, false);
+		return ret;
+	}
+	atomic_set(&old->buffer->datalen, 0);
+	return 0;
+}
+
+static void psz_flush_all_dirty_zones(struct work_struct *work)
+{
+	struct psz_context *cxt = &pstore_zone_cxt;
+	int ret = 0;
+
+	if (cxt->ppsz)
+		ret |= psz_flush_dirty_zone(cxt->ppsz);
+	if (cxt->cpsz)
+		ret |= psz_flush_dirty_zone(cxt->cpsz);
+	if (cxt->kpszs)
+		ret |= psz_flush_dirty_zones(cxt->kpszs, cxt->kmsg_max_cnt);
+	if (cxt->fpszs)
+		ret |= psz_flush_dirty_zones(cxt->fpszs, cxt->ftrace_max_cnt);
+	if (ret && cxt->pstore_zone_info)
+		schedule_delayed_work(&psz_cleaner, msecs_to_jiffies(1000));
+}
+
+static int psz_kmsg_recover_data(struct psz_context *cxt)
+{
+	struct pstore_zone_info *info = cxt->pstore_zone_info;
+	struct pstore_zone *zone = NULL;
+	struct psz_buffer *buf;
+	unsigned long i;
+	ssize_t rcnt;
+
+	if (!info->read)
+		return -EINVAL;
+
+	for (i = 0; i < cxt->kmsg_max_cnt; i++) {
+		zone = cxt->kpszs[i];
+		if (unlikely(!zone))
+			return -EINVAL;
+		if (atomic_read(&zone->dirty)) {
+			unsigned int wcnt = cxt->kmsg_write_cnt;
+			struct pstore_zone *new = cxt->kpszs[wcnt];
+			int ret;
+
+			ret = psz_move_zone(zone, new);
+			if (ret) {
+				pr_err("move zone from %lu to %d failed\n",
+						i, wcnt);
+				return ret;
+			}
+			cxt->kmsg_write_cnt = (wcnt + 1) % cxt->kmsg_max_cnt;
+		}
+		if (!zone->should_recover)
+			continue;
+		buf = zone->buffer;
+		rcnt = info->read((char *)buf, zone->buffer_size + sizeof(*buf),
+				zone->off);
+		if (rcnt != zone->buffer_size + sizeof(*buf))
+			return (int)rcnt < 0 ? (int)rcnt : -EIO;
+	}
+	return 0;
+}
+
+static int psz_kmsg_recover_meta(struct psz_context *cxt)
+{
+	struct pstore_zone_info *info = cxt->pstore_zone_info;
+	struct pstore_zone *zone;
+	size_t rcnt, len;
+	struct psz_buffer *buf;
+	struct psz_kmsg_header *hdr;
+	struct timespec64 time = { };
+	unsigned long i;
+	/*
+	 * Recover may on panic, we can't allocate any memory by kmalloc.
+	 * So, we use local array instead.
+	 */
+	char buffer_header[sizeof(*buf) + sizeof(*hdr)] = {0};
+
+	if (!info->read)
+		return -EINVAL;
+
+	len = sizeof(*buf) + sizeof(*hdr);
+	buf = (struct psz_buffer *)buffer_header;
+	for (i = 0; i < cxt->kmsg_max_cnt; i++) {
+		zone = cxt->kpszs[i];
+		if (unlikely(!zone))
+			return -EINVAL;
+
+		rcnt = info->read((char *)buf, len, zone->off);
+		if (rcnt == -ENOMSG) {
+			pr_debug("%s with id %lu may be broken, skip\n",
+					zone->name, i);
+			continue;
+		} else if (rcnt != len) {
+			pr_err("read %s with id %lu failed\n", zone->name, i);
+			return (int)rcnt < 0 ? (int)rcnt : -EIO;
+		}
+
+		if (buf->sig != zone->buffer->sig) {
+			pr_debug("no valid data in kmsg dump zone %lu\n", i);
+			continue;
+		}
+
+		if (zone->buffer_size < atomic_read(&buf->datalen)) {
+			pr_info("found overtop zone: %s: id %lu, off %lld, size %zu\n",
+					zone->name, i, zone->off,
+					zone->buffer_size);
+			continue;
+		}
+
+		hdr = (struct psz_kmsg_header *)buf->data;
+		if (hdr->magic != PSTORE_KMSG_HEADER_MAGIC) {
+			pr_info("found invalid zone: %s: id %lu, off %lld, size %zu\n",
+					zone->name, i, zone->off,
+					zone->buffer_size);
+			continue;
+		}
+
+		/*
+		 * we get the newest zone, and the next one must be the oldest
+		 * or unused zone, because we do write one by one like a circle.
+		 */
+		if (hdr->time.tv_sec >= time.tv_sec) {
+			time.tv_sec = hdr->time.tv_sec;
+			cxt->kmsg_write_cnt = (i + 1) % cxt->kmsg_max_cnt;
+		}
+
+		if (hdr->reason == KMSG_DUMP_OOPS)
+			cxt->oops_counter =
+				max(cxt->oops_counter, hdr->counter);
+		else if (hdr->reason == KMSG_DUMP_PANIC)
+			cxt->panic_counter =
+				max(cxt->panic_counter, hdr->counter);
+
+		if (!atomic_read(&buf->datalen)) {
+			pr_debug("found erased zone: %s: id %lu, off %lld, size %zu, datalen %d\n",
+					zone->name, i, zone->off,
+					zone->buffer_size,
+					atomic_read(&buf->datalen));
+			continue;
+		}
+
+		if (!is_on_panic())
+			zone->should_recover = true;
+		pr_debug("found nice zone: %s: id %lu, off %lld, size %zu, datalen %d\n",
+				zone->name, i, zone->off,
+				zone->buffer_size, atomic_read(&buf->datalen));
+	}
+
+	return 0;
+}
+
+static int psz_kmsg_recover(struct psz_context *cxt)
+{
+	int ret;
+
+	if (!cxt->kpszs)
+		return 0;
+
+	ret = psz_kmsg_recover_meta(cxt);
+	if (ret)
+		goto recover_fail;
+
+	ret = psz_kmsg_recover_data(cxt);
+	if (ret)
+		goto recover_fail;
+
+	return 0;
+recover_fail:
+	pr_debug("psz_recover_kmsg failed\n");
+	return ret;
+}
+
+static int psz_recover_zone(struct psz_context *cxt, struct pstore_zone *zone)
+{
+	struct pstore_zone_info *info = cxt->pstore_zone_info;
+	struct psz_buffer *oldbuf, tmpbuf;
+	int ret = 0;
+	char *buf;
+	ssize_t rcnt, len, start, off;
+
+	if (!zone || zone->oldbuf)
+		return 0;
+
+	if (is_on_panic()) {
+		/* save data as much as possible */
+		psz_flush_dirty_zone(zone);
+		return 0;
+	}
+
+	if (unlikely(!info->read))
+		return -EINVAL;
+
+	len = sizeof(struct psz_buffer);
+	rcnt = info->read((char *)&tmpbuf, len, zone->off);
+	if (rcnt != len) {
+		pr_debug("read zone %s failed\n", zone->name);
+		return (int)rcnt < 0 ? (int)rcnt : -EIO;
+	}
+
+	if (tmpbuf.sig != zone->buffer->sig) {
+		pr_debug("no valid data in zone %s\n", zone->name);
+		return 0;
+	}
+
+	if (zone->buffer_size < atomic_read(&tmpbuf.datalen) ||
+		zone->buffer_size < atomic_read(&tmpbuf.start)) {
+		pr_info("found overtop zone: %s: off %lld, size %zu\n",
+				zone->name, zone->off, zone->buffer_size);
+		/* just keep going */
+		return 0;
+	}
+
+	if (!atomic_read(&tmpbuf.datalen)) {
+		pr_debug("found erased zone: %s: off %lld, size %zu, datalen %d\n",
+				zone->name, zone->off, zone->buffer_size,
+				atomic_read(&tmpbuf.datalen));
+		return 0;
+	}
+
+	pr_debug("found nice zone: %s: off %lld, size %zu, datalen %d\n",
+			zone->name, zone->off, zone->buffer_size,
+			atomic_read(&tmpbuf.datalen));
+
+	len = atomic_read(&tmpbuf.datalen) + sizeof(*oldbuf);
+	oldbuf = kzalloc(len, GFP_KERNEL);
+	if (!oldbuf)
+		return -ENOMEM;
+
+	memcpy(oldbuf, &tmpbuf, sizeof(*oldbuf));
+	buf = (char *)oldbuf + sizeof(*oldbuf);
+	len = atomic_read(&oldbuf->datalen);
+	start = atomic_read(&oldbuf->start);
+	off = zone->off + sizeof(*oldbuf);
+
+	/* get part of data */
+	rcnt = info->read(buf, len - start, off + start);
+	if (rcnt != len - start) {
+		pr_err("read zone %s failed\n", zone->name);
+		ret = (int)rcnt < 0 ? (int)rcnt : -EIO;
+		goto free_oldbuf;
+	}
+
+	/* get the rest of data */
+	rcnt = info->read(buf + len - start, start, off);
+	if (rcnt != start) {
+		pr_err("read zone %s failed\n", zone->name);
+		ret = (int)rcnt < 0 ? (int)rcnt : -EIO;
+		goto free_oldbuf;
+	}
+
+	zone->oldbuf = oldbuf;
+	psz_flush_dirty_zone(zone);
+	return 0;
+
+free_oldbuf:
+	kfree(oldbuf);
+	return ret;
+}
+
+static int psz_recover_zones(struct psz_context *cxt,
+		struct pstore_zone **zones, unsigned int cnt)
+{
+	int ret;
+	unsigned int i;
+	struct pstore_zone *zone;
+
+	if (!zones)
+		return 0;
+
+	for (i = 0; i < cnt; i++) {
+		zone = zones[i];
+		if (unlikely(!zone))
+			continue;
+		ret = psz_recover_zone(cxt, zone);
+		if (ret)
+			goto recover_fail;
+	}
+
+	return 0;
+recover_fail:
+	pr_debug("recover %s[%u] failed\n", zone->name, i);
+	return ret;
+}
+
+/**
+ * psz_recovery() - recover data from storage
+ * @cxt: the context of pstore/zone
+ *
+ * recovery means reading data back from storage after rebooting
+ *
+ * Return: 0 on success, others on failure.
+ */
+static inline int psz_recovery(struct psz_context *cxt)
+{
+	int ret;
+
+	if (atomic_read(&cxt->recovered))
+		return 0;
+
+	ret = psz_kmsg_recover(cxt);
+	if (ret)
+		goto out;
+
+	ret = psz_recover_zone(cxt, cxt->ppsz);
+	if (ret)
+		goto out;
+
+	ret = psz_recover_zone(cxt, cxt->cpsz);
+	if (ret)
+		goto out;
+
+	ret = psz_recover_zones(cxt, cxt->fpszs, cxt->ftrace_max_cnt);
+
+out:
+	if (unlikely(ret))
+		pr_err("recover failed\n");
+	else {
+		pr_debug("recover end!\n");
+		atomic_set(&cxt->recovered, 1);
+	}
+	return ret;
+}
+
+static int psz_pstore_open(struct pstore_info *psi)
+{
+	struct psz_context *cxt = psi->data;
+
+	cxt->kmsg_read_cnt = 0;
+	cxt->pmsg_read_cnt = 0;
+	cxt->console_read_cnt = 0;
+	cxt->ftrace_read_cnt = 0;
+	return 0;
+}
+
+static inline bool psz_old_ok(struct pstore_zone *zone)
+{
+	if (zone && zone->oldbuf && atomic_read(&zone->oldbuf->datalen))
+		return true;
+	return false;
+}
+
+static inline bool psz_ok(struct pstore_zone *zone)
+{
+	if (zone && zone->buffer && buffer_datalen(zone))
+		return true;
+	return false;
+}
+
+static inline int psz_kmsg_erase(struct psz_context *cxt,
+		struct pstore_zone *zone, struct pstore_record *record)
+{
+	struct psz_buffer *buffer = zone->buffer;
+	struct psz_kmsg_header *hdr =
+		(struct psz_kmsg_header *)buffer->data;
+	size_t size;
+
+	if (unlikely(!psz_ok(zone)))
+		return 0;
+
+	/* this zone is already updated, no need to erase */
+	if (record->count != hdr->counter)
+		return 0;
+
+	size = buffer_datalen(zone) + sizeof(*zone->buffer);
+	atomic_set(&zone->buffer->datalen, 0);
+	if (cxt->pstore_zone_info->erase)
+		return cxt->pstore_zone_info->erase(size, zone->off);
+	else
+		return psz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+}
+
+static inline int psz_record_erase(struct psz_context *cxt,
+		struct pstore_zone *zone)
+{
+	if (unlikely(!psz_old_ok(zone)))
+		return 0;
+
+	kfree(zone->oldbuf);
+	zone->oldbuf = NULL;
+	/*
+	 * if there are new data in zone buffer, that means the old data
+	 * are already invalid. It is no need to flush 0 (erase) to
+	 * block device.
+	 */
+	if (!buffer_datalen(zone))
+		return psz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+	psz_flush_dirty_zone(zone);
+	return 0;
+}
+
+static int psz_pstore_erase(struct pstore_record *record)
+{
+	struct psz_context *cxt = record->psi->data;
+
+	switch (record->type) {
+	case PSTORE_TYPE_DMESG:
+		if (record->id >= cxt->kmsg_max_cnt)
+			return -EINVAL;
+		return psz_kmsg_erase(cxt, cxt->kpszs[record->id], record);
+	case PSTORE_TYPE_PMSG:
+		return psz_record_erase(cxt, cxt->ppsz);
+	case PSTORE_TYPE_CONSOLE:
+		return psz_record_erase(cxt, cxt->cpsz);
+	case PSTORE_TYPE_FTRACE:
+		if (record->id >= cxt->ftrace_max_cnt)
+			return -EINVAL;
+		return psz_record_erase(cxt, cxt->fpszs[record->id]);
+	default: return -EINVAL;
+	}
+}
+
+static void psz_write_kmsg_hdr(struct pstore_zone *zone,
+		struct pstore_record *record)
+{
+	struct psz_context *cxt = record->psi->data;
+	struct psz_buffer *buffer = zone->buffer;
+	struct psz_kmsg_header *hdr =
+		(struct psz_kmsg_header *)buffer->data;
+
+	hdr->magic = PSTORE_KMSG_HEADER_MAGIC;
+	hdr->compressed = record->compressed;
+	hdr->time.tv_sec = record->time.tv_sec;
+	hdr->time.tv_nsec = record->time.tv_nsec;
+	hdr->reason = record->reason;
+	if (hdr->reason == KMSG_DUMP_OOPS)
+		hdr->counter = ++cxt->oops_counter;
+	else if (hdr->reason == KMSG_DUMP_PANIC)
+		hdr->counter = ++cxt->panic_counter;
+	else
+		hdr->counter = 0;
+}
+
+/*
+ * In case zone is broken, which may occur to MTD device, we try each zones,
+ * start at cxt->kmsg_write_cnt.
+ */
+static inline int notrace psz_kmsg_write_record(struct psz_context *cxt,
+		struct pstore_record *record)
+{
+	size_t size, hlen;
+	struct pstore_zone *zone;
+	unsigned int i;
+
+	for (i = 0; i < cxt->kmsg_max_cnt; i++) {
+		unsigned int zonenum, len;
+		int ret;
+
+		zonenum = (cxt->kmsg_write_cnt + i) % cxt->kmsg_max_cnt;
+		zone = cxt->kpszs[zonenum];
+		if (unlikely(!zone))
+			return -ENOSPC;
+
+		/* avoid destroying old data, allocate a new one */
+		len = zone->buffer_size + sizeof(*zone->buffer);
+		zone->oldbuf = zone->buffer;
+		zone->buffer = kzalloc(len, GFP_KERNEL);
+		if (!zone->buffer) {
+			zone->buffer = zone->oldbuf;
+			return -ENOMEM;
+		}
+		zone->buffer->sig = zone->oldbuf->sig;
+
+		pr_debug("write %s to zone id %d\n", zone->name, zonenum);
+		psz_write_kmsg_hdr(zone, record);
+		hlen = sizeof(struct psz_kmsg_header);
+		size = min_t(size_t, record->size, zone->buffer_size - hlen);
+		ret = psz_zone_write(zone, FLUSH_ALL, record->buf, size, hlen);
+		if (likely(!ret || ret != -ENOMSG)) {
+			cxt->kmsg_write_cnt = zonenum + 1;
+			cxt->kmsg_write_cnt %= cxt->kmsg_max_cnt;
+			/* no need to try next zone, free last zone buffer */
+			kfree(zone->oldbuf);
+			zone->oldbuf = NULL;
+			return ret;
+		}
+
+		pr_debug("zone %u may be broken, try next dmesg zone\n",
+				zonenum);
+		kfree(zone->buffer);
+		zone->buffer = zone->oldbuf;
+		zone->oldbuf = NULL;
+	}
+
+	return -EBUSY;
+}
+
+static int notrace psz_kmsg_write(struct psz_context *cxt,
+		struct pstore_record *record)
+{
+	int ret;
+
+	/*
+	 * Explicitly only take the first part of any new crash.
+	 * If our buffer is larger than kmsg_bytes, this can never happen,
+	 * and if our buffer is smaller than kmsg_bytes, we don't want the
+	 * report split across multiple records.
+	 */
+	if (record->part != 1)
+		return -ENOSPC;
+
+	if (!cxt->kpszs)
+		return -ENOSPC;
+
+	ret = psz_kmsg_write_record(cxt, record);
+	if (!ret && is_on_panic()) {
+		/* ensure all data are flushed to storage when panic */
+		pr_debug("try to flush other dirty zones\n");
+		psz_flush_all_dirty_zones(NULL);
+	}
+
+	/* always return 0 as we had handled it on buffer */
+	return 0;
+}
+
+static int notrace psz_record_write(struct pstore_zone *zone,
+		struct pstore_record *record)
+{
+	size_t start, rem;
+	bool is_full_data = false;
+	char *buf;
+	int cnt;
+
+	if (!zone || !record)
+		return -ENOSPC;
+
+	if (atomic_read(&zone->buffer->datalen) >= zone->buffer_size)
+		is_full_data = true;
+
+	cnt = record->size;
+	buf = record->buf;
+	if (unlikely(cnt > zone->buffer_size)) {
+		buf += cnt - zone->buffer_size;
+		cnt = zone->buffer_size;
+	}
+
+	start = buffer_start(zone);
+	rem = zone->buffer_size - start;
+	if (unlikely(rem < cnt)) {
+		psz_zone_write(zone, FLUSH_PART, buf, rem, start);
+		buf += rem;
+		cnt -= rem;
+		start = 0;
+		is_full_data = true;
+	}
+
+	atomic_set(&zone->buffer->start, cnt + start);
+	psz_zone_write(zone, FLUSH_PART, buf, cnt, start);
+
+	/**
+	 * psz_zone_write will set datalen as start + cnt.
+	 * It work if actual data length lesser than buffer size.
+	 * If data length greater than buffer size, pmsg will rewrite to
+	 * beginning of zone, which make buffer->datalen wrongly.
+	 * So we should reset datalen as buffer size once actual data length
+	 * greater than buffer size.
+	 */
+	if (is_full_data) {
+		atomic_set(&zone->buffer->datalen, zone->buffer_size);
+		psz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+	}
+	return 0;
+}
+
+static int notrace psz_pstore_write(struct pstore_record *record)
+{
+	struct psz_context *cxt = record->psi->data;
+
+	if (record->type == PSTORE_TYPE_DMESG &&
+			record->reason == KMSG_DUMP_PANIC)
+		atomic_set(&cxt->on_panic, 1);
+
+	/*
+	 * if on panic, do not write except panic records
+	 * Fix case that panic_write prints log which wakes up console backend.
+	 */
+	if (is_on_panic() && record->type != PSTORE_TYPE_DMESG)
+		return -EBUSY;
+
+	switch (record->type) {
+	case PSTORE_TYPE_DMESG:
+		return psz_kmsg_write(cxt, record);
+	case PSTORE_TYPE_CONSOLE:
+		return psz_record_write(cxt->cpsz, record);
+	case PSTORE_TYPE_PMSG:
+		return psz_record_write(cxt->ppsz, record);
+	case PSTORE_TYPE_FTRACE: {
+		int zonenum = smp_processor_id();
+
+		if (!cxt->fpszs)
+			return -ENOSPC;
+		return psz_record_write(cxt->fpszs[zonenum], record);
+	}
+	default:
+		return -EINVAL;
+	}
+}
+
+static struct pstore_zone *psz_read_next_zone(struct psz_context *cxt)
+{
+	struct pstore_zone *zone = NULL;
+
+	while (cxt->kmsg_read_cnt < cxt->kmsg_max_cnt) {
+		zone = cxt->kpszs[cxt->kmsg_read_cnt++];
+		if (psz_ok(zone))
+			return zone;
+	}
+
+	if (cxt->ftrace_read_cnt < cxt->ftrace_max_cnt)
+		/*
+		 * No need psz_old_ok(). Let psz_ftrace_read() do so for
+		 * combination. psz_ftrace_read() should traverse over
+		 * all zones in case of some zone without data.
+		 */
+		return cxt->fpszs[cxt->ftrace_read_cnt++];
+
+	if (cxt->pmsg_read_cnt == 0) {
+		cxt->pmsg_read_cnt++;
+		zone = cxt->ppsz;
+		if (psz_old_ok(zone))
+			return zone;
+	}
+
+	if (cxt->console_read_cnt == 0) {
+		cxt->console_read_cnt++;
+		zone = cxt->cpsz;
+		if (psz_old_ok(zone))
+			return zone;
+	}
+
+	return NULL;
+}
+
+static int psz_kmsg_read_hdr(struct pstore_zone *zone,
+		struct pstore_record *record)
+{
+	struct psz_buffer *buffer = zone->buffer;
+	struct psz_kmsg_header *hdr =
+		(struct psz_kmsg_header *)buffer->data;
+
+	if (hdr->magic != PSTORE_KMSG_HEADER_MAGIC)
+		return -EINVAL;
+	record->compressed = hdr->compressed;
+	record->time.tv_sec = hdr->time.tv_sec;
+	record->time.tv_nsec = hdr->time.tv_nsec;
+	record->reason = hdr->reason;
+	record->count = hdr->counter;
+	return 0;
+}
+
+static ssize_t psz_kmsg_read(struct pstore_zone *zone,
+		struct pstore_record *record)
+{
+	ssize_t size, hlen = 0;
+
+	size = buffer_datalen(zone);
+	/* Clear and skip this kmsg dump record if it has no valid header */
+	if (psz_kmsg_read_hdr(zone, record)) {
+		atomic_set(&zone->buffer->datalen, 0);
+		atomic_set(&zone->dirty, 0);
+		return -ENOMSG;
+	}
+	size -= sizeof(struct psz_kmsg_header);
+
+	if (!record->compressed) {
+		char *buf = kasprintf(GFP_KERNEL, "%s: Total %d times\n",
+				      kmsg_dump_reason_str(record->reason),
+				      record->count);
+		hlen = strlen(buf);
+		record->buf = krealloc(buf, hlen + size, GFP_KERNEL);
+		if (!record->buf) {
+			kfree(buf);
+			return -ENOMEM;
+		}
+	} else {
+		record->buf = kmalloc(size, GFP_KERNEL);
+		if (!record->buf)
+			return -ENOMEM;
+	}
+
+	size = psz_zone_read_buffer(zone, record->buf + hlen, size,
+			sizeof(struct psz_kmsg_header));
+	if (unlikely(size < 0)) {
+		kfree(record->buf);
+		return -ENOMSG;
+	}
+
+	return size + hlen;
+}
+
+/* try to combine all ftrace zones */
+static ssize_t psz_ftrace_read(struct pstore_zone *zone,
+		struct pstore_record *record)
+{
+	struct psz_context *cxt;
+	struct psz_buffer *buf;
+	int ret;
+
+	if (!zone || !record)
+		return -ENOSPC;
+
+	if (!psz_old_ok(zone))
+		goto out;
+
+	buf = (struct psz_buffer *)zone->oldbuf;
+	if (!buf)
+		return -ENOMSG;
+
+	ret = pstore_ftrace_combine_log(&record->buf, &record->size,
+			(char *)buf->data, atomic_read(&buf->datalen));
+	if (unlikely(ret))
+		return ret;
+
+out:
+	cxt = record->psi->data;
+	if (cxt->ftrace_read_cnt < cxt->ftrace_max_cnt)
+		/* then, read next ftrace zone */
+		return -ENOMSG;
+	record->id = 0;
+	return record->size ? record->size : -ENOMSG;
+}
+
+static ssize_t psz_record_read(struct pstore_zone *zone,
+		struct pstore_record *record)
+{
+	size_t len;
+	struct psz_buffer *buf;
+
+	if (!zone || !record)
+		return -ENOSPC;
+
+	buf = (struct psz_buffer *)zone->oldbuf;
+	if (!buf)
+		return -ENOMSG;
+
+	len = atomic_read(&buf->datalen);
+	record->buf = kmalloc(len, GFP_KERNEL);
+	if (!record->buf)
+		return -ENOMEM;
+
+	if (unlikely(psz_zone_read_oldbuf(zone, record->buf, len, 0))) {
+		kfree(record->buf);
+		return -ENOMSG;
+	}
+
+	return len;
+}
+
+static ssize_t psz_pstore_read(struct pstore_record *record)
+{
+	struct psz_context *cxt = record->psi->data;
+	ssize_t (*readop)(struct pstore_zone *zone,
+			struct pstore_record *record);
+	struct pstore_zone *zone;
+	ssize_t ret;
+
+	/* before read, we must recover from storage */
+	ret = psz_recovery(cxt);
+	if (ret)
+		return ret;
+
+next_zone:
+	zone = psz_read_next_zone(cxt);
+	if (!zone)
+		return 0;
+
+	record->type = zone->type;
+	switch (record->type) {
+	case PSTORE_TYPE_DMESG:
+		readop = psz_kmsg_read;
+		record->id = cxt->kmsg_read_cnt - 1;
+		break;
+	case PSTORE_TYPE_FTRACE:
+		readop = psz_ftrace_read;
+		break;
+	case PSTORE_TYPE_CONSOLE:
+		fallthrough;
+	case PSTORE_TYPE_PMSG:
+		readop = psz_record_read;
+		break;
+	default:
+		goto next_zone;
+	}
+
+	ret = readop(zone, record);
+	if (ret == -ENOMSG)
+		goto next_zone;
+	return ret;
+}
+
+static struct psz_context pstore_zone_cxt = {
+	.pstore_zone_info_lock =
+		__MUTEX_INITIALIZER(pstore_zone_cxt.pstore_zone_info_lock),
+	.recovered = ATOMIC_INIT(0),
+	.on_panic = ATOMIC_INIT(0),
+	.pstore = {
+		.owner = THIS_MODULE,
+		.open = psz_pstore_open,
+		.read = psz_pstore_read,
+		.write = psz_pstore_write,
+		.erase = psz_pstore_erase,
+	},
+};
+
+static void psz_free_zone(struct pstore_zone **pszone)
+{
+	struct pstore_zone *zone = *pszone;
+
+	if (!zone)
+		return;
+
+	kfree(zone->buffer);
+	kfree(zone);
+	*pszone = NULL;
+}
+
+static void psz_free_zones(struct pstore_zone ***pszones, unsigned int *cnt)
+{
+	struct pstore_zone **zones = *pszones;
+
+	if (!zones)
+		return;
+
+	while (*cnt > 0) {
+		(*cnt)--;
+		psz_free_zone(&(zones[*cnt]));
+	}
+	kfree(zones);
+	*pszones = NULL;
+}
+
+static void psz_free_all_zones(struct psz_context *cxt)
+{
+	if (cxt->kpszs)
+		psz_free_zones(&cxt->kpszs, &cxt->kmsg_max_cnt);
+	if (cxt->ppsz)
+		psz_free_zone(&cxt->ppsz);
+	if (cxt->cpsz)
+		psz_free_zone(&cxt->cpsz);
+	if (cxt->fpszs)
+		psz_free_zones(&cxt->fpszs, &cxt->ftrace_max_cnt);
+}
+
+static struct pstore_zone *psz_init_zone(enum pstore_type_id type,
+		loff_t *off, size_t size)
+{
+	struct pstore_zone_info *info = pstore_zone_cxt.pstore_zone_info;
+	struct pstore_zone *zone;
+	const char *name = pstore_type_to_name(type);
+
+	if (!size)
+		return NULL;
+
+	if (*off + size > info->total_size) {
+		pr_err("no room for %s (0x%zx@0x%llx over 0x%lx)\n",
+			name, size, *off, info->total_size);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	zone = kzalloc(sizeof(struct pstore_zone), GFP_KERNEL);
+	if (!zone)
+		return ERR_PTR(-ENOMEM);
+
+	zone->buffer = kmalloc(size, GFP_KERNEL);
+	if (!zone->buffer) {
+		kfree(zone);
+		return ERR_PTR(-ENOMEM);
+	}
+	memset(zone->buffer, 0xFF, size);
+	zone->off = *off;
+	zone->name = name;
+	zone->type = type;
+	zone->buffer_size = size - sizeof(struct psz_buffer);
+	zone->buffer->sig = type ^ PSZ_SIG;
+	zone->oldbuf = NULL;
+	atomic_set(&zone->dirty, 0);
+	atomic_set(&zone->buffer->datalen, 0);
+	atomic_set(&zone->buffer->start, 0);
+
+	*off += size;
+
+	pr_debug("pszone %s: off 0x%llx, %zu header, %zu data\n", zone->name,
+			zone->off, sizeof(*zone->buffer), zone->buffer_size);
+	return zone;
+}
+
+static struct pstore_zone **psz_init_zones(enum pstore_type_id type,
+	loff_t *off, size_t total_size, ssize_t record_size,
+	unsigned int *cnt)
+{
+	struct pstore_zone_info *info = pstore_zone_cxt.pstore_zone_info;
+	struct pstore_zone **zones, *zone;
+	const char *name = pstore_type_to_name(type);
+	int c, i;
+
+	*cnt = 0;
+	if (!total_size || !record_size)
+		return NULL;
+
+	if (*off + total_size > info->total_size) {
+		pr_err("no room for zones %s (0x%zx@0x%llx over 0x%lx)\n",
+			name, total_size, *off, info->total_size);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	c = total_size / record_size;
+	zones = kcalloc(c, sizeof(*zones), GFP_KERNEL);
+	if (!zones) {
+		pr_err("allocate for zones %s failed\n", name);
+		return ERR_PTR(-ENOMEM);
+	}
+	memset(zones, 0, c * sizeof(*zones));
+
+	for (i = 0; i < c; i++) {
+		zone = psz_init_zone(type, off, record_size);
+		if (!zone || IS_ERR(zone)) {
+			pr_err("initialize zones %s failed\n", name);
+			psz_free_zones(&zones, &i);
+			return (void *)zone;
+		}
+		zones[i] = zone;
+	}
+
+	*cnt = c;
+	return zones;
+}
+
+static int psz_alloc_zones(struct psz_context *cxt)
+{
+	struct pstore_zone_info *info = cxt->pstore_zone_info;
+	loff_t off = 0;
+	int err;
+	size_t off_size = 0;
+
+	off_size += info->pmsg_size;
+	cxt->ppsz = psz_init_zone(PSTORE_TYPE_PMSG, &off, info->pmsg_size);
+	if (IS_ERR(cxt->ppsz)) {
+		err = PTR_ERR(cxt->ppsz);
+		cxt->ppsz = NULL;
+		goto free_out;
+	}
+
+	off_size += info->console_size;
+	cxt->cpsz = psz_init_zone(PSTORE_TYPE_CONSOLE, &off,
+			info->console_size);
+	if (IS_ERR(cxt->cpsz)) {
+		err = PTR_ERR(cxt->cpsz);
+		cxt->cpsz = NULL;
+		goto free_out;
+	}
+
+	off_size += info->ftrace_size;
+	cxt->fpszs = psz_init_zones(PSTORE_TYPE_FTRACE, &off,
+			info->ftrace_size,
+			info->ftrace_size / nr_cpu_ids,
+			&cxt->ftrace_max_cnt);
+	if (IS_ERR(cxt->fpszs)) {
+		err = PTR_ERR(cxt->fpszs);
+		cxt->fpszs = NULL;
+		goto free_out;
+	}
+
+	cxt->kpszs = psz_init_zones(PSTORE_TYPE_DMESG, &off,
+			info->total_size - off_size,
+			info->kmsg_size, &cxt->kmsg_max_cnt);
+	if (IS_ERR(cxt->kpszs)) {
+		err = PTR_ERR(cxt->kpszs);
+		cxt->kpszs = NULL;
+		goto free_out;
+	}
+
+	return 0;
+free_out:
+	psz_free_all_zones(cxt);
+	return err;
+}
+
+/**
+ * register_pstore_zone() - register to pstore/zone
+ *
+ * @info: back-end driver information. See &struct pstore_zone_info.
+ *
+ * Only one back-end at one time.
+ *
+ * Return: 0 on success, others on failure.
+ */
+int register_pstore_zone(struct pstore_zone_info *info)
+{
+	int err = -EINVAL;
+	struct psz_context *cxt = &pstore_zone_cxt;
+
+	if (info->total_size < 4096) {
+		pr_warn("total_size must be >= 4096\n");
+		return -EINVAL;
+	}
+
+	if (!info->kmsg_size && !info->pmsg_size && !info->console_size &&
+	    !info->ftrace_size) {
+		pr_warn("at least one record size must be non-zero\n");
+		return -EINVAL;
+	}
+
+	if (!info->name || !info->name[0])
+		return -EINVAL;
+
+#define check_size(name, size) {					\
+		if (info->name > 0 && info->name < (size)) {		\
+			pr_err(#name " must be over %d\n", (size));	\
+			return -EINVAL;					\
+		}							\
+		if (info->name & (size - 1)) {				\
+			pr_err(#name " must be a multiple of %d\n",	\
+					(size));			\
+			return -EINVAL;					\
+		}							\
+	}
+
+	check_size(total_size, 4096);
+	check_size(kmsg_size, SECTOR_SIZE);
+	check_size(pmsg_size, SECTOR_SIZE);
+	check_size(console_size, SECTOR_SIZE);
+	check_size(ftrace_size, SECTOR_SIZE);
+
+#undef check_size
+
+	/*
+	 * the @read and @write must be applied.
+	 * if no @read, pstore may mount failed.
+	 * if no @write, pstore do not support to remove record file.
+	 */
+	if (!info->read || !info->write) {
+		pr_err("no valid general read/write interface\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&cxt->pstore_zone_info_lock);
+	if (cxt->pstore_zone_info) {
+		pr_warn("'%s' already loaded: ignoring '%s'\n",
+				cxt->pstore_zone_info->name, info->name);
+		mutex_unlock(&cxt->pstore_zone_info_lock);
+		return -EBUSY;
+	}
+	cxt->pstore_zone_info = info;
+
+	pr_debug("register %s with properties:\n", info->name);
+	pr_debug("\ttotal size : %ld Bytes\n", info->total_size);
+	pr_debug("\tkmsg size : %ld Bytes\n", info->kmsg_size);
+	pr_debug("\tpmsg size : %ld Bytes\n", info->pmsg_size);
+	pr_debug("\tconsole size : %ld Bytes\n", info->console_size);
+	pr_debug("\tftrace size : %ld Bytes\n", info->ftrace_size);
+
+	err = psz_alloc_zones(cxt);
+	if (err) {
+		pr_err("alloc zones failed\n");
+		goto fail_out;
+	}
+
+	if (info->kmsg_size) {
+		cxt->pstore.bufsize = cxt->kpszs[0]->buffer_size -
+			sizeof(struct psz_kmsg_header);
+		cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL);
+		if (!cxt->pstore.buf) {
+			err = -ENOMEM;
+			goto fail_free;
+		}
+	}
+	cxt->pstore.data = cxt;
+
+	pr_info("registered %s as backend for", info->name);
+	cxt->pstore.max_reason = info->max_reason;
+	cxt->pstore.name = info->name;
+	if (info->kmsg_size) {
+		cxt->pstore.flags |= PSTORE_FLAGS_DMESG;
+		pr_cont(" kmsg(%s",
+			kmsg_dump_reason_str(cxt->pstore.max_reason));
+		if (cxt->pstore_zone_info->panic_write)
+			pr_cont(",panic_write");
+		pr_cont(")");
+	}
+	if (info->pmsg_size) {
+		cxt->pstore.flags |= PSTORE_FLAGS_PMSG;
+		pr_cont(" pmsg");
+	}
+	if (info->console_size) {
+		cxt->pstore.flags |= PSTORE_FLAGS_CONSOLE;
+		pr_cont(" console");
+	}
+	if (info->ftrace_size) {
+		cxt->pstore.flags |= PSTORE_FLAGS_FTRACE;
+		pr_cont(" ftrace");
+	}
+	pr_cont("\n");
+
+	err = pstore_register(&cxt->pstore);
+	if (err) {
+		pr_err("registering with pstore failed\n");
+		goto fail_free;
+	}
+	mutex_unlock(&pstore_zone_cxt.pstore_zone_info_lock);
+
+	return 0;
+
+fail_free:
+	kfree(cxt->pstore.buf);
+	cxt->pstore.buf = NULL;
+	cxt->pstore.bufsize = 0;
+	psz_free_all_zones(cxt);
+fail_out:
+	pstore_zone_cxt.pstore_zone_info = NULL;
+	mutex_unlock(&pstore_zone_cxt.pstore_zone_info_lock);
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_pstore_zone);
+
+/**
+ * unregister_pstore_zone() - unregister to pstore/zone
+ *
+ * @info: back-end driver information. See struct pstore_zone_info.
+ */
+void unregister_pstore_zone(struct pstore_zone_info *info)
+{
+	struct psz_context *cxt = &pstore_zone_cxt;
+
+	mutex_lock(&cxt->pstore_zone_info_lock);
+	if (!cxt->pstore_zone_info) {
+		mutex_unlock(&cxt->pstore_zone_info_lock);
+		return;
+	}
+
+	/* Stop incoming writes from pstore. */
+	pstore_unregister(&cxt->pstore);
+
+	/* Flush any pending writes. */
+	psz_flush_all_dirty_zones(NULL);
+	flush_delayed_work(&psz_cleaner);
+
+	/* Clean up allocations. */
+	kfree(cxt->pstore.buf);
+	cxt->pstore.buf = NULL;
+	cxt->pstore.bufsize = 0;
+	cxt->pstore_zone_info = NULL;
+
+	psz_free_all_zones(cxt);
+
+	/* Clear counters and zone state. */
+	cxt->oops_counter = 0;
+	cxt->panic_counter = 0;
+	atomic_set(&cxt->recovered, 0);
+	atomic_set(&cxt->on_panic, 0);
+
+	mutex_unlock(&cxt->pstore_zone_info_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_pstore_zone);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("WeiXiong Liao <liaoweixiong@allwinnertech.com>");
+MODULE_AUTHOR("Kees Cook <keescook@chromium.org>");
+MODULE_DESCRIPTION("Storage Manager for pstore/blk");
diff --git a/fs/splice.c b/fs/splice.c
index 4735defc46ee..4e53efbd621d 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1118,6 +1118,10 @@ long do_splice(struct file *in, loff_t __user *off_in,
 	loff_t offset;
 	long ret;
 
+	if (unlikely(!(in->f_mode & FMODE_READ) ||
+		     !(out->f_mode & FMODE_WRITE)))
+		return -EBADF;
+
 	ipipe = get_pipe_info(in);
 	opipe = get_pipe_info(out);
 
@@ -1125,12 +1129,6 @@ long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_in || off_out)
 			return -ESPIPE;
 
-		if (!(in->f_mode & FMODE_READ))
-			return -EBADF;
-
-		if (!(out->f_mode & FMODE_WRITE))
-			return -EBADF;
-
 		/* Splicing to self would be fun, but... */
 		if (ipipe == opipe)
 			return -EINVAL;
@@ -1153,9 +1151,6 @@ long do_splice(struct file *in, loff_t __user *off_in,
 			offset = out->f_pos;
 		}
 
-		if (unlikely(!(out->f_mode & FMODE_WRITE)))
-			return -EBADF;
-
 		if (unlikely(out->f_flags & O_APPEND))
 			return -EINVAL;
 
@@ -1440,15 +1435,11 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 	error = -EBADF;
 	in = fdget(fd_in);
 	if (in.file) {
-		if (in.file->f_mode & FMODE_READ) {
-			out = fdget(fd_out);
-			if (out.file) {
-				if (out.file->f_mode & FMODE_WRITE)
-					error = do_splice(in.file, off_in,
-							  out.file, off_out,
-							  len, flags);
-				fdput(out);
-			}
+		out = fdget(fd_out);
+		if (out.file) {
+			error = do_splice(in.file, off_in, out.file, off_out,
+					  len, flags);
+			fdput(out);
 		}
 		fdput(in);
 	}
@@ -1503,7 +1494,7 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 	 * Check pipe occupancy without the inode lock first. This function
 	 * is speculative anyways, so missing one is ok.
 	 */
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+	if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage))
 		return 0;
 
 	ret = 0;
@@ -1770,6 +1761,10 @@ static long do_tee(struct file *in, struct file *out, size_t len,
 	struct pipe_inode_info *opipe = get_pipe_info(out);
 	int ret = -EINVAL;
 
+	if (unlikely(!(in->f_mode & FMODE_READ) ||
+		     !(out->f_mode & FMODE_WRITE)))
+		return -EBADF;
+
 	/*
 	 * Duplicate the contents of ipipe to opipe without actually
 	 * copying the data.
@@ -1795,7 +1790,7 @@ static long do_tee(struct file *in, struct file *out, size_t len,
 
 SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 {
-	struct fd in;
+	struct fd in, out;
 	int error;
 
 	if (unlikely(flags & ~SPLICE_F_ALL))
@@ -1807,14 +1802,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 	error = -EBADF;
 	in = fdget(fdin);
 	if (in.file) {
-		if (in.file->f_mode & FMODE_READ) {
-			struct fd out = fdget(fdout);
-			if (out.file) {
-				if (out.file->f_mode & FMODE_WRITE)
-					error = do_tee(in.file, out.file,
-							len, flags);
-				fdput(out);
-			}
+		out = fdget(fdout);
+		if (out.file) {
+			error = do_tee(in.file, out.file, len, flags);
+			fdput(out);
 		}
  		fdput(in);
  	}
diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c
index 2a2a2d106440..e206ebfe003c 100644
--- a/fs/squashfs/decompressor_multi_percpu.c
+++ b/fs/squashfs/decompressor_multi_percpu.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/percpu.h>
 #include <linux/buffer_head.h>
+#include <linux/local_lock.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -20,7 +21,8 @@
  */
 
 struct squashfs_stream {
-	void		*stream;
+	void			*stream;
+	local_lock_t	lock;
 };
 
 void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
@@ -41,6 +43,7 @@ void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
 			err = PTR_ERR(stream->stream);
 			goto out;
 		}
+		local_lock_init(&stream->lock);
 	}
 
 	kfree(comp_opts);
@@ -75,12 +78,16 @@ void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
 int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
 	int b, int offset, int length, struct squashfs_page_actor *output)
 {
-	struct squashfs_stream __percpu *percpu =
-			(struct squashfs_stream __percpu *) msblk->stream;
-	struct squashfs_stream *stream = get_cpu_ptr(percpu);
-	int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
-		offset, length, output);
-	put_cpu_ptr(stream);
+	struct squashfs_stream *stream;
+	int res;
+
+	local_lock(&msblk->stream->lock);
+	stream = this_cpu_ptr(msblk->stream);
+
+	res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+			offset, length, output);
+
+	local_unlock(&msblk->stream->lock);
 
 	if (res < 0)
 		ERROR("%s decompression failed, data probably corrupt\n",
diff --git a/fs/super.c b/fs/super.c
index cd352530eca9..a288cd60d2ae 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1302,8 +1302,8 @@ int get_tree_bdev(struct fs_context *fc,
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
 	if (bdev->bd_fsfreeze_count > 0) {
 		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		blkdev_put(bdev, mode);
 		warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
+		blkdev_put(bdev, mode);
 		return -EBUSY;
 	}
 
diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c
index 8cdbd53d780c..cc5c0abfd536 100644
--- a/fs/ubifs/auth.c
+++ b/fs/ubifs/auth.c
@@ -31,15 +31,9 @@ int __ubifs_node_calc_hash(const struct ubifs_info *c, const void *node,
 			    u8 *hash)
 {
 	const struct ubifs_ch *ch = node;
-	SHASH_DESC_ON_STACK(shash, c->hash_tfm);
-	int err;
-
-	shash->tfm = c->hash_tfm;
 
-	err = crypto_shash_digest(shash, node, le32_to_cpu(ch->len), hash);
-	if (err < 0)
-		return err;
-	return 0;
+	return crypto_shash_tfm_digest(c->hash_tfm, node, le32_to_cpu(ch->len),
+				       hash);
 }
 
 /**
@@ -53,15 +47,7 @@ int __ubifs_node_calc_hash(const struct ubifs_info *c, const void *node,
 static int ubifs_hash_calc_hmac(const struct ubifs_info *c, const u8 *hash,
 				 u8 *hmac)
 {
-	SHASH_DESC_ON_STACK(shash, c->hmac_tfm);
-	int err;
-
-	shash->tfm = c->hmac_tfm;
-
-	err = crypto_shash_digest(shash, hash, c->hash_len, hmac);
-	if (err < 0)
-		return err;
-	return 0;
+	return crypto_shash_tfm_digest(c->hmac_tfm, hash, c->hash_len, hmac);
 }
 
 /**
@@ -79,13 +65,9 @@ int ubifs_prepare_auth_node(struct ubifs_info *c, void *node,
 			     struct shash_desc *inhash)
 {
 	struct ubifs_auth_node *auth = node;
-	u8 *hash;
+	u8 hash[UBIFS_HASH_ARR_SZ];
 	int err;
 
-	hash = kmalloc(crypto_shash_descsize(c->hash_tfm), GFP_NOFS);
-	if (!hash)
-		return -ENOMEM;
-
 	{
 		SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm);
 
@@ -94,21 +76,16 @@ int ubifs_prepare_auth_node(struct ubifs_info *c, void *node,
 
 		err = crypto_shash_final(hash_desc, hash);
 		if (err)
-			goto out;
+			return err;
 	}
 
 	err = ubifs_hash_calc_hmac(c, hash, auth->hmac);
 	if (err)
-		goto out;
+		return err;
 
 	auth->ch.node_type = UBIFS_AUTH_NODE;
 	ubifs_prepare_node(c, auth, ubifs_auth_node_sz(c), 0);
-
-	err = 0;
-out:
-	kfree(hash);
-
-	return err;
+	return 0;
 }
 
 static struct shash_desc *ubifs_get_desc(const struct ubifs_info *c,
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 743928efffc1..49fe062ce45e 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1375,7 +1375,6 @@ int ubifs_update_time(struct inode *inode, struct timespec64 *time,
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
 	struct ubifs_budget_req req = { .dirtied_ino = 1,
 			.dirtied_ino_d = ALIGN(ui->data_len, 8) };
-	int iflags = I_DIRTY_TIME;
 	int err, release;
 
 	if (!IS_ENABLED(CONFIG_UBIFS_ATIME_SUPPORT))
@@ -1393,11 +1392,8 @@ int ubifs_update_time(struct inode *inode, struct timespec64 *time,
 	if (flags & S_MTIME)
 		inode->i_mtime = *time;
 
-	if (!(inode->i_sb->s_flags & SB_LAZYTIME))
-		iflags |= I_DIRTY_SYNC;
-
 	release = ui->dirty;
-	__mark_inode_dirty(inode, iflags);
+	__mark_inode_dirty(inode, I_DIRTY_SYNC);
 	mutex_unlock(&ui->ui_mutex);
 	if (release)
 		ubifs_release_budget(c, &req);
diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c
index 52a85c01397e..911d0555b9f2 100644
--- a/fs/ubifs/master.c
+++ b/fs/ubifs/master.c
@@ -68,12 +68,9 @@ static int mst_node_check_hash(const struct ubifs_info *c,
 	u8 calc[UBIFS_MAX_HASH_LEN];
 	const void *node = mst;
 
-	SHASH_DESC_ON_STACK(shash, c->hash_tfm);
-
-	shash->tfm = c->hash_tfm;
-
-	crypto_shash_digest(shash, node + sizeof(struct ubifs_ch),
-			    UBIFS_MST_NODE_SZ - sizeof(struct ubifs_ch), calc);
+	crypto_shash_tfm_digest(c->hash_tfm, node + sizeof(struct ubifs_ch),
+				UBIFS_MST_NODE_SZ - sizeof(struct ubifs_ch),
+				calc);
 
 	if (ubifs_check_hash(c, expected, calc))
 		return -EPERM;
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index b28ac4dfb407..b69ffac7e415 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -558,7 +558,7 @@ static int is_last_bud(struct ubifs_info *c, struct ubifs_bud *bud)
 	return data == 0xFFFFFFFF;
 }
 
-/* authenticate_sleb_hash and authenticate_sleb_hmac are split out for stack usage */
+/* authenticate_sleb_hash is split out for stack usage */
 static int authenticate_sleb_hash(struct ubifs_info *c, struct shash_desc *log_hash, u8 *hash)
 {
 	SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm);
@@ -569,15 +569,6 @@ static int authenticate_sleb_hash(struct ubifs_info *c, struct shash_desc *log_h
 	return crypto_shash_final(hash_desc, hash);
 }
 
-static int authenticate_sleb_hmac(struct ubifs_info *c, u8 *hash, u8 *hmac)
-{
-	SHASH_DESC_ON_STACK(hmac_desc, c->hmac_tfm);
-
-	hmac_desc->tfm = c->hmac_tfm;
-
-	return crypto_shash_digest(hmac_desc, hash, c->hash_len, hmac);
-}
-
 /**
  * authenticate_sleb - authenticate one scan LEB
  * @c: UBIFS file-system description object
@@ -601,18 +592,12 @@ static int authenticate_sleb(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 	struct ubifs_scan_node *snod;
 	int n_nodes = 0;
 	int err;
-	u8 *hash, *hmac;
+	u8 hash[UBIFS_HASH_ARR_SZ];
+	u8 hmac[UBIFS_HMAC_ARR_SZ];
 
 	if (!ubifs_authenticated(c))
 		return sleb->nodes_cnt;
 
-	hash = kmalloc(crypto_shash_descsize(c->hash_tfm), GFP_NOFS);
-	hmac = kmalloc(c->hmac_desc_len, GFP_NOFS);
-	if (!hash || !hmac) {
-		err = -ENOMEM;
-		goto out;
-	}
-
 	list_for_each_entry(snod, &sleb->nodes, list) {
 
 		n_nodes++;
@@ -624,7 +609,8 @@ static int authenticate_sleb(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 			if (err)
 				goto out;
 
-			err = authenticate_sleb_hmac(c, hash, hmac);
+			err = crypto_shash_tfm_digest(c->hmac_tfm, hash,
+						      c->hash_len, hmac);
 			if (err)
 				goto out;
 
@@ -662,9 +648,6 @@ static int authenticate_sleb(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 		err = 0;
 	}
 out:
-	kfree(hash);
-	kfree(hmac);
-
 	return err ? err : n_nodes - n_not_auth;
 }
 
diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index 675e26989376..8fe03b4a0d2b 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -164,7 +164,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
 		goto fail_free;
 	}
 
-	err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id);
+	err = super_setup_bdi_name(sb, "vboxsf-%d", sbi->bdi_id);
 	if (err)
 		goto fail_free;
 
diff --git a/fs/verity/enable.c b/fs/verity/enable.c
index d98bea308fd7..5ab3bbec8108 100644
--- a/fs/verity/enable.c
+++ b/fs/verity/enable.c
@@ -329,6 +329,8 @@ rollback:
 
 /**
  * fsverity_ioctl_enable() - enable verity on a file
+ * @filp: file to enable verity on
+ * @uarg: user pointer to fsverity_enable_arg
  *
  * Enable fs-verity on a file.  See the "FS_IOC_ENABLE_VERITY" section of
  * Documentation/filesystems/fsverity.rst for the documentation.
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index 74768cf539da..e96d99d5145e 100644
--- a/fs/verity/fsverity_private.h
+++ b/fs/verity/fsverity_private.h
@@ -61,7 +61,7 @@ struct merkle_tree_params {
 	u64 level_start[FS_VERITY_MAX_LEVELS];
 };
 
-/**
+/*
  * fsverity_info - cached verity metadata for an inode
  *
  * When a verity file is first opened, an instance of this struct is allocated
@@ -134,7 +134,7 @@ void __init fsverity_check_hash_algs(void);
 
 /* init.c */
 
-extern void __printf(3, 4) __cold
+void __printf(3, 4) __cold
 fsverity_msg(const struct inode *inode, const char *level,
 	     const char *fmt, ...);
 
diff --git a/fs/verity/measure.c b/fs/verity/measure.c
index 05049b68c745..df409a5682ed 100644
--- a/fs/verity/measure.c
+++ b/fs/verity/measure.c
@@ -11,6 +11,8 @@
 
 /**
  * fsverity_ioctl_measure() - get a verity file's measurement
+ * @filp: file to get measurement of
+ * @_uarg: user pointer to fsverity_digest
  *
  * Retrieve the file measurement that the kernel is enforcing for reads from a
  * verity file.  See the "FS_IOC_MEASURE_VERITY" section of
diff --git a/fs/verity/open.c b/fs/verity/open.c
index c5fe6948e262..d007db0c9304 100644
--- a/fs/verity/open.c
+++ b/fs/verity/open.c
@@ -330,6 +330,7 @@ EXPORT_SYMBOL_GPL(fsverity_prepare_setattr);
 
 /**
  * fsverity_cleanup_inode() - free the inode's verity info, if present
+ * @inode: an inode being evicted
  *
  * Filesystems must call this on inode eviction to free ->i_verity_info.
  */
diff --git a/fs/verity/signature.c b/fs/verity/signature.c
index c8b255232de5..b14ed96387ec 100644
--- a/fs/verity/signature.c
+++ b/fs/verity/signature.c
@@ -28,6 +28,9 @@ static struct key *fsverity_keyring;
 
 /**
  * fsverity_verify_signature() - check a verity file's signature
+ * @vi: the file's fsverity_info
+ * @desc: the file's fsverity_descriptor
+ * @desc_size: size of @desc
  *
  * If the file's fs-verity descriptor includes a signature of the file
  * measurement, verify it against the certificates in the fs-verity keyring.
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
index e0cb62da3864..a8b68c6f663d 100644
--- a/fs/verity/verify.c
+++ b/fs/verity/verify.c
@@ -179,6 +179,7 @@ out:
 
 /**
  * fsverity_verify_page() - verify a data page
+ * @page: the page to verity
  *
  * Verify a page that has just been read from a verity file.  The page must be a
  * pagecache page that is still locked and not yet uptodate.
@@ -206,6 +207,7 @@ EXPORT_SYMBOL_GPL(fsverity_verify_page);
 #ifdef CONFIG_BLOCK
 /**
  * fsverity_verify_bio() - verify a 'read' bio that has just completed
+ * @bio: the bio to verify
  *
  * Verify a set of pages that have just been read from a verity file.  The pages
  * must be pagecache pages that are still locked and not yet uptodate.  Pages
@@ -264,6 +266,7 @@ EXPORT_SYMBOL_GPL(fsverity_verify_bio);
 
 /**
  * fsverity_enqueue_verify_work() - enqueue work on the fs-verity workqueue
+ * @work: the work to enqueue
  *
  * Enqueue verification work for asynchronous processing.
  */
diff --git a/fs/xattr.c b/fs/xattr.c
index e13265e65871..91608d9bfc6a 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -876,6 +876,9 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
 	struct simple_xattr *new_xattr = NULL;
 	int err = 0;
 
+	if (removed_size)
+		*removed_size = -1;
+
 	/* value == NULL means remove */
 	if (value) {
 		new_xattr = simple_xattr_alloc(value, size);
@@ -914,9 +917,6 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
 		list_add(&new_xattr->list, &xattrs->head);
 		xattr = NULL;
 	}
-
-	if (removed_size)
-		*removed_size = -1;
 out:
 	spin_unlock(&xattrs->lock);
 	if (xattr) {
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index a7be7a9e5c1a..8bf1d15be3f6 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -911,7 +911,12 @@ xfs_eofblocks_worker(
 {
 	struct xfs_mount *mp = container_of(to_delayed_work(work),
 				struct xfs_mount, m_eofblocks_work);
+
+	if (!sb_start_write_trylock(mp->m_super))
+		return;
 	xfs_icache_free_eofblocks(mp, NULL);
+	sb_end_write(mp->m_super);
+
 	xfs_queue_eofblocks(mp);
 }
 
@@ -938,7 +943,12 @@ xfs_cowblocks_worker(
 {
 	struct xfs_mount *mp = container_of(to_delayed_work(work),
 				struct xfs_mount, m_cowblocks_work);
+
+	if (!sb_start_write_trylock(mp->m_super))
+		return;
 	xfs_icache_free_cowblocks(mp, NULL);
+	sb_end_write(mp->m_super);
+
 	xfs_queue_cowblocks(mp);
 }
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index cdfb3cd9a25b..309958186d33 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -2363,7 +2363,10 @@ xfs_file_ioctl(
 		if (error)
 			return error;
 
-		return xfs_icache_free_eofblocks(mp, &keofb);
+		sb_start_write(mp->m_super);
+		error = xfs_icache_free_eofblocks(mp, &keofb);
+		sb_end_write(mp->m_super);
+		return error;
 	}
 
 	default:
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 50c43422fa17..b2e4598fdf7d 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -167,8 +167,12 @@ typedef struct xfs_mount {
 	struct xfs_kobj		m_error_meta_kobj;
 	struct xfs_error_cfg	m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX];
 	struct xstats		m_stats;	/* per-fs stats */
-	struct ratelimit_state	m_flush_inodes_ratelimit;
 
+	/*
+	 * Workqueue item so that we can coalesce multiple inode flush attempts
+	 * into a single flush.
+	 */
+	struct work_struct	m_flush_inodes_work;
 	struct workqueue_struct *m_buf_workqueue;
 	struct workqueue_struct	*m_unwritten_workqueue;
 	struct workqueue_struct	*m_cil_workqueue;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index b0ce04ffd3cd..107bf2a2f344 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1051,6 +1051,7 @@ xfs_reflink_remap_extent(
 		uirec.br_startblock = irec->br_startblock + rlen;
 		uirec.br_startoff = irec->br_startoff + rlen;
 		uirec.br_blockcount = unmap_len - rlen;
+		uirec.br_state = irec->br_state;
 		unmap_len = rlen;
 
 		/* If this isn't a real mapping, we're done. */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index abf06bf9c3f3..424bb9a2d532 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -516,6 +516,20 @@ xfs_destroy_mount_workqueues(
 	destroy_workqueue(mp->m_buf_workqueue);
 }
 
+static void
+xfs_flush_inodes_worker(
+	struct work_struct	*work)
+{
+	struct xfs_mount	*mp = container_of(work, struct xfs_mount,
+						   m_flush_inodes_work);
+	struct super_block	*sb = mp->m_super;
+
+	if (down_read_trylock(&sb->s_umount)) {
+		sync_inodes_sb(sb);
+		up_read(&sb->s_umount);
+	}
+}
+
 /*
  * Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK
  * or a page lock. We use sync_inodes_sb() here to ensure we block while waiting
@@ -526,15 +540,15 @@ void
 xfs_flush_inodes(
 	struct xfs_mount	*mp)
 {
-	struct super_block	*sb = mp->m_super;
-
-	if (!__ratelimit(&mp->m_flush_inodes_ratelimit))
+	/*
+	 * If flush_work() returns true then that means we waited for a flush
+	 * which was already in progress.  Don't bother running another scan.
+	 */
+	if (flush_work(&mp->m_flush_inodes_work))
 		return;
 
-	if (down_read_trylock(&sb->s_umount)) {
-		sync_inodes_sb(sb);
-		up_read(&sb->s_umount);
-	}
+	queue_work(mp->m_sync_workqueue, &mp->m_flush_inodes_work);
+	flush_work(&mp->m_flush_inodes_work);
 }
 
 /* Catch misguided souls that try to use this interface on XFS */
@@ -1369,17 +1383,6 @@ xfs_fc_fill_super(
 	if (error)
 		goto out_free_names;
 
-	/*
-	 * Cap the number of invocations of xfs_flush_inodes to 16 for every
-	 * quarter of a second.  The magic numbers here were determined by
-	 * observation neither to cause stalls in writeback when there are a
-	 * lot of IO threads and the fs is near ENOSPC, nor cause any fstest
-	 * regressions.  YMMV.
-	 */
-	ratelimit_state_init(&mp->m_flush_inodes_ratelimit, HZ / 4, 16);
-	ratelimit_set_flags(&mp->m_flush_inodes_ratelimit,
-			RATELIMIT_MSG_ON_RELEASE);
-
 	error = xfs_init_mount_workqueues(mp);
 	if (error)
 		goto out_close_devices;
@@ -1752,6 +1755,7 @@ static int xfs_init_fs_context(
 	spin_lock_init(&mp->m_perag_lock);
 	mutex_init(&mp->m_growlock);
 	atomic_set(&mp->m_active_trans, 0);
+	INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker);
 	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
 	INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker);
 	INIT_DELAYED_WORK(&mp->m_cowblocks_work, xfs_cowblocks_worker);
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 36341dfded70..44ec80e70518 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -56,6 +56,7 @@ mandatory-y += topology.h
 mandatory-y += trace_clock.h
 mandatory-y += uaccess.h
 mandatory-y += unaligned.h
+mandatory-y += vermagic.h
 mandatory-y += vga.h
 mandatory-y += word-at-a-time.h
 mandatory-y += xor.h
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index b3f1082cc435..1c4fd950f091 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -163,7 +163,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 	return nr_bank;
 }
 
-void hyperv_report_panic(struct pt_regs *regs, long err);
+void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
 void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
 bool hv_is_hyperv_initialized(void);
 bool hv_is_hibernation_supported(void);
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index d1779d442aa5..66397ed10acb 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -53,6 +53,9 @@ extern char __ctors_start[], __ctors_end[];
 /* Start and end of .opd section - used for function descriptors. */
 extern char __start_opd[], __end_opd[];
 
+/* Start and end of instrumentation protected text section */
+extern char __noinstr_text_start[], __noinstr_text_end[];
+
 extern __visible const void __nosave_begin, __nosave_end;
 
 /* Function descriptor handling (if any).  Override in asm/sections.h */
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 238873739550..5aa8705df87e 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -48,7 +48,7 @@
   #ifdef CONFIG_NEED_MULTIPLE_NODES
     #define cpumask_of_node(node)	((node) == 0 ? cpu_online_mask : cpu_none_mask)
   #else
-    #define cpumask_of_node(node)	((void)node, cpu_online_mask)
+    #define cpumask_of_node(node)	((void)(node), cpu_online_mask)
   #endif
 #endif
 #ifndef pcibus_to_node
diff --git a/include/asm-generic/vermagic.h b/include/asm-generic/vermagic.h
new file mode 100644
index 000000000000..084274a1219e
--- /dev/null
+++ b/include/asm-generic/vermagic.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_GENERIC_VERMAGIC_H
+#define _ASM_GENERIC_VERMAGIC_H
+
+#define MODULE_ARCH_VERMAGIC ""
+
+#endif /* _ASM_GENERIC_VERMAGIC_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 71e387a5fe90..db600ef218d7 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -541,6 +541,15 @@
 	__end_rodata = .;
 
 /*
+ * Non-instrumentable text section
+ */
+#define NOINSTR_TEXT							\
+		ALIGN_FUNCTION();					\
+		__noinstr_text_start = .;				\
+		*(.noinstr.text)					\
+		__noinstr_text_end = .;
+
+/*
  * .text section. Map to function alignment to avoid address changes
  * during second ld run in second ld pass when generating System.map
  *
@@ -551,6 +560,7 @@
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
 		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
+		NOINSTR_TEXT						\
 		*(.text..refcount)					\
 		*(.ref.text)						\
 	MEM_KEEP(init.text*)						\
diff --git a/include/crypto/acompress.h b/include/crypto/acompress.h
index d873f999b334..2b4d2b06ccbd 100644
--- a/include/crypto/acompress.h
+++ b/include/crypto/acompress.h
@@ -157,7 +157,7 @@ static inline int crypto_has_acomp(const char *alg_name, u32 type, u32 mask)
 {
 	type &= ~CRYPTO_ALG_TYPE_MASK;
 	type |= CRYPTO_ALG_TYPE_ACOMPRESS;
-	mask |= CRYPTO_ALG_TYPE_MASK;
+	mask |= CRYPTO_ALG_TYPE_ACOMPRESS_MASK;
 
 	return crypto_has_alg(alg_name, type, mask);
 }
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index e115f9215ed5..00a9cf98debe 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -125,6 +125,8 @@ int crypto_inst_setname(struct crypto_instance *inst, const char *name,
 void crypto_init_queue(struct crypto_queue *queue, unsigned int max_qlen);
 int crypto_enqueue_request(struct crypto_queue *queue,
 			   struct crypto_async_request *request);
+void crypto_enqueue_request_head(struct crypto_queue *queue,
+				 struct crypto_async_request *request);
 struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue);
 static inline unsigned int crypto_queue_len(struct crypto_queue *queue)
 {
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index 8c9af21efce1..c4165126937e 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -184,11 +184,7 @@ static inline size_t drbg_max_addtl(struct drbg_state *drbg)
 static inline size_t drbg_max_requests(struct drbg_state *drbg)
 {
 	/* SP800-90A requires 2**48 maximum requests before reseeding */
-#if (__BITS_PER_LONG == 32)
-	return SIZE_MAX;
-#else
-	return (1UL<<48);
-#endif
+	return (1<<20);
 }
 
 /*
diff --git a/include/crypto/engine.h b/include/crypto/engine.h
index e29cd67f93c7..3f06e40d063a 100644
--- a/include/crypto/engine.h
+++ b/include/crypto/engine.h
@@ -24,7 +24,9 @@
  * @idling: the engine is entering idle state
  * @busy: request pump is busy
  * @running: the engine is on working
- * @cur_req_prepared: current request is prepared
+ * @retry_support: indication that the hardware allows re-execution
+ * of a failed backlog request
+ * crypto-engine, in head position to keep order
  * @list: link with the global crypto engine list
  * @queue_lock: spinlock to syncronise access to request queue
  * @queue: the crypto queue of the engine
@@ -35,6 +37,8 @@
  * @unprepare_crypt_hardware: there are currently no more requests on the
  * queue so the subsystem notifies the driver that it may relax the
  * hardware by issuing this call
+ * @do_batch_requests: execute a batch of requests. Depends on multiple
+ * requests support.
  * @kworker: kthread worker struct for request pump
  * @pump_requests: work struct for scheduling work to the request pump
  * @priv_data: the engine private data
@@ -45,7 +49,8 @@ struct crypto_engine {
 	bool			idling;
 	bool			busy;
 	bool			running;
-	bool			cur_req_prepared;
+
+	bool			retry_support;
 
 	struct list_head	list;
 	spinlock_t		queue_lock;
@@ -56,6 +61,8 @@ struct crypto_engine {
 
 	int (*prepare_crypt_hardware)(struct crypto_engine *engine);
 	int (*unprepare_crypt_hardware)(struct crypto_engine *engine);
+	int (*do_batch_requests)(struct crypto_engine *engine);
+
 
 	struct kthread_worker           *kworker;
 	struct kthread_work             pump_requests;
@@ -102,6 +109,10 @@ void crypto_finalize_skcipher_request(struct crypto_engine *engine,
 int crypto_engine_start(struct crypto_engine *engine);
 int crypto_engine_stop(struct crypto_engine *engine);
 struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt);
+struct crypto_engine *crypto_engine_alloc_init_and_set(struct device *dev,
+						       bool retry_support,
+						       int (*cbk_do_batch)(struct crypto_engine *engine),
+						       bool rt, int qlen);
 int crypto_engine_exit(struct crypto_engine *engine);
 
 #endif /* _CRYPTO_ENGINE_H */
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index cee446c59497..4829d2367eda 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -856,6 +856,25 @@ int crypto_shash_digest(struct shash_desc *desc, const u8 *data,
 			unsigned int len, u8 *out);
 
 /**
+ * crypto_shash_tfm_digest() - calculate message digest for buffer
+ * @tfm: hash transformation object
+ * @data: see crypto_shash_update()
+ * @len: see crypto_shash_update()
+ * @out: see crypto_shash_final()
+ *
+ * This is a simplified version of crypto_shash_digest() for users who don't
+ * want to allocate their own hash descriptor (shash_desc).  Instead,
+ * crypto_shash_tfm_digest() takes a hash transformation object (crypto_shash)
+ * directly, and it allocates a hash descriptor on the stack internally.
+ * Note that this stack allocation may be fairly large.
+ *
+ * Context: Any context.
+ * Return: 0 on success; < 0 if an error occurred.
+ */
+int crypto_shash_tfm_digest(struct crypto_shash *tfm, const u8 *data,
+			    unsigned int len, u8 *out);
+
+/**
  * crypto_shash_export() - extract operational state for message digest
  * @desc: reference to the operational state handle whose state is exported
  * @out: output buffer of sufficient size that can hold the hash state
diff --git a/include/crypto/sha.h b/include/crypto/sha.h
index 5c2132c71900..10753ff71d46 100644
--- a/include/crypto/sha.h
+++ b/include/crypto/sha.h
@@ -114,6 +114,16 @@ extern int crypto_sha512_finup(struct shash_desc *desc, const u8 *data,
 			       unsigned int len, u8 *hash);
 
 /*
+ * An implementation of SHA-1's compression function.  Don't use in new code!
+ * You shouldn't be using SHA-1, and even if you *have* to use SHA-1, this isn't
+ * the correct way to hash something with SHA-1 (use crypto_shash instead).
+ */
+#define SHA1_DIGEST_WORDS	(SHA1_DIGEST_SIZE / 4)
+#define SHA1_WORKSPACE_WORDS	16
+void sha1_init(__u32 *buf);
+void sha1_transform(__u32 *digest, const char *data, __u32 *W);
+
+/*
  * Stand-alone implementation of the SHA256 algorithm. It is designed to
  * have as little dependencies as possible so it can be used in the
  * kexec_file purgatory. In other cases you should generally use the
@@ -123,7 +133,7 @@ extern int crypto_sha512_finup(struct shash_desc *desc, const u8 *data,
  * For details see lib/crypto/sha256.c
  */
 
-static inline int sha256_init(struct sha256_state *sctx)
+static inline void sha256_init(struct sha256_state *sctx)
 {
 	sctx->state[0] = SHA256_H0;
 	sctx->state[1] = SHA256_H1;
@@ -134,14 +144,11 @@ static inline int sha256_init(struct sha256_state *sctx)
 	sctx->state[6] = SHA256_H6;
 	sctx->state[7] = SHA256_H7;
 	sctx->count = 0;
-
-	return 0;
 }
-extern int sha256_update(struct sha256_state *sctx, const u8 *input,
-			 unsigned int length);
-extern int sha256_final(struct sha256_state *sctx, u8 *hash);
+void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len);
+void sha256_final(struct sha256_state *sctx, u8 *out);
 
-static inline int sha224_init(struct sha256_state *sctx)
+static inline void sha224_init(struct sha256_state *sctx)
 {
 	sctx->state[0] = SHA224_H0;
 	sctx->state[1] = SHA224_H1;
@@ -152,11 +159,8 @@ static inline int sha224_init(struct sha256_state *sctx)
 	sctx->state[6] = SHA224_H6;
 	sctx->state[7] = SHA224_H7;
 	sctx->count = 0;
-
-	return 0;
 }
-extern int sha224_update(struct sha256_state *sctx, const u8 *input,
-			 unsigned int length);
-extern int sha224_final(struct sha256_state *sctx, u8 *hash);
+void sha224_update(struct sha256_state *sctx, const u8 *data, unsigned int len);
+void sha224_final(struct sha256_state *sctx, u8 *out);
 
 #endif
diff --git a/include/crypto/sha256_base.h b/include/crypto/sha256_base.h
index cea60cff80bd..6ded110783ae 100644
--- a/include/crypto/sha256_base.h
+++ b/include/crypto/sha256_base.h
@@ -22,14 +22,16 @@ static inline int sha224_base_init(struct shash_desc *desc)
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	return sha224_init(sctx);
+	sha224_init(sctx);
+	return 0;
 }
 
 static inline int sha256_base_init(struct shash_desc *desc)
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	return sha256_init(sctx);
+	sha256_init(sctx);
+	return 0;
 }
 
 static inline int sha256_base_do_update(struct shash_desc *desc,
diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
index 99134d4f35eb..320f8112a0f8 100644
--- a/include/drm/drm_modes.h
+++ b/include/drm/drm_modes.h
@@ -48,7 +48,7 @@ struct videomode;
  * @MODE_HSYNC: hsync out of range
  * @MODE_VSYNC: vsync out of range
  * @MODE_H_ILLEGAL: mode has illegal horizontal timings
- * @MODE_V_ILLEGAL: mode has illegal horizontal timings
+ * @MODE_V_ILLEGAL: mode has illegal vertical timings
  * @MODE_BAD_WIDTH: requires an unsupported linepitch
  * @MODE_NOMODE: no mode with a matching name
  * @MODE_NO_INTERLACE: interlaced mode not supported
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 26f0ecf401ea..0bbfd647f5c6 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -65,6 +65,7 @@ struct amba_device {
 	struct device		dev;
 	struct resource		res;
 	struct clk		*pclk;
+	struct device_dma_parameters dma_parms;
 	unsigned int		periphid;
 	unsigned int		cid;
 	struct amba_cs_uci_id	uci;
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 59494df0f55b..56d6a5c6e353 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -5,12 +5,15 @@
 #ifndef __LINUX_ARM_SMCCC_H
 #define __LINUX_ARM_SMCCC_H
 
+#include <linux/init.h>
 #include <uapi/linux/const.h>
 
 /*
  * This file provides common defines for ARM SMC Calling Convention as
  * specified in
- * http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
+ * https://developer.arm.com/docs/den0028/latest
+ *
+ * This code is up-to-date with version DEN 0028 C
  */
 
 #define ARM_SMCCC_STD_CALL	        _AC(0,U)
@@ -56,6 +59,7 @@
 
 #define ARM_SMCCC_VERSION_1_0		0x10000
 #define ARM_SMCCC_VERSION_1_1		0x10001
+#define ARM_SMCCC_VERSION_1_2		0x10002
 
 #define ARM_SMCCC_VERSION_FUNC_ID					\
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
@@ -98,6 +102,19 @@ enum arm_smccc_conduit {
 enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void);
 
 /**
+ * arm_smccc_get_version()
+ *
+ * Returns the version to be used for SMCCCv1.1 or later.
+ *
+ * When SMCCCv1.1 or above is not present, returns SMCCCv1.0, but this
+ * does not imply the presence of firmware or a valid conduit. Caller
+ * handling SMCCCv1.0 must determine the conduit by other means.
+ */
+u32 arm_smccc_get_version(void);
+
+void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit);
+
+/**
  * struct arm_smccc_res - Result from SMC/HVC call
  * @a0-a3 result values from registers 0 to 3
  */
@@ -314,10 +331,14 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
  */
 #define arm_smccc_1_1_hvc(...)	__arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__)
 
-/* Return codes defined in ARM DEN 0070A */
+/*
+ * Return codes defined in ARM DEN 0070A
+ * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C
+ */
 #define SMCCC_RET_SUCCESS			0
 #define SMCCC_RET_NOT_SUPPORTED			-1
 #define SMCCC_RET_NOT_REQUIRED			-2
+#define SMCCC_RET_INVALID_PARAMETER		-3
 
 /*
  * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED.
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 4fc87dee005a..7367150f962a 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -54,7 +54,6 @@ enum wb_reason {
 	WB_REASON_SYNC,
 	WB_REASON_PERIODIC,
 	WB_REASON_LAPTOP_TIMER,
-	WB_REASON_FREE_MORE_MEM,
 	WB_REASON_FS_FREE_SPACE,
 	/*
 	 * There is no bdi forker thread any more and works are done
@@ -220,6 +219,7 @@ struct backing_dev_info {
 	wait_queue_head_t wb_waitq;
 
 	struct device *dev;
+	char dev_name[64];
 	struct device *owner;
 
 	struct timer_list laptop_mode_wb_timer;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f88197c1ffc2..c9ad5c3b7b4b 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -505,13 +505,6 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 				  (1 << WB_async_congested));
 }
 
-extern const char *bdi_unknown_name;
-
-static inline const char *bdi_dev_name(struct backing_dev_info *bdi)
-{
-	if (!bdi || !bdi->dev)
-		return bdi_unknown_name;
-	return dev_name(bdi->dev);
-}
+const char *bdi_dev_name(struct backing_dev_info *bdi);
 
 #endif	/* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index c1c0f9ea4e63..a0ee494a6329 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -319,7 +319,7 @@ struct bio_integrity_payload {
 	struct work_struct	bip_work;	/* I/O completion */
 
 	struct bio_vec		*bip_vec;
-	struct bio_vec		bip_inline_vecs[0];/* embedded bvec array */
+	struct bio_vec		bip_inline_vecs[];/* embedded bvec array */
 };
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index f389d7c724bd..b45148ba3291 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -173,7 +173,7 @@ struct blk_mq_hw_ctx {
 	 * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also
 	 * blk_mq_hw_ctx_size().
 	 */
-	struct srcu_struct	srcu[0];
+	struct srcu_struct	srcu[];
 };
 
 /**
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 70254ae11769..31eb92876be7 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -198,7 +198,7 @@ struct bio {
 	 * double allocations for a small number of bio_vecs. This member
 	 * MUST obviously be kept at the very end of the bio.
 	 */
-	struct bio_vec		bi_inline_vecs[0];
+	struct bio_vec		bi_inline_vecs[];
 };
 
 #define BIO_RESET_BYTES		offsetof(struct bio, bi_max_vecs)
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 6462c5447872..f4b77018c625 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -245,6 +245,7 @@
 #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN	(1 << 0)
 #define BCM54810_SHD_CLK_CTL			0x3
 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN		(1 << 9)
+#define BCM54810_SHD_SCR3_TRDDAPD		0x0100
 
 /* BCM54612E Registers */
 #define BCM54612E_EXP_SPARE0		(MII_BCM54XX_EXP_SEL_ETC + 0x34)
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index e0b020eaf32e..15b765a181b8 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -189,6 +189,8 @@ struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
 void __brelse(struct buffer_head *);
 void __bforget(struct buffer_head *);
 void __breadahead(struct block_device *, sector_t block, unsigned int size);
+void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size,
+		  gfp_t gfp);
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
 void invalidate_bh_lrus(void);
@@ -319,6 +321,12 @@ sb_breadahead(struct super_block *sb, sector_t block)
 	__breadahead(sb->s_bdev, block, sb->s_blocksize);
 }
 
+static inline void
+sb_breadahead_unmovable(struct super_block *sb, sector_t block)
+{
+	__breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0);
+}
+
 static inline struct buffer_head *
 sb_getblk(struct super_block *sb, sector_t block)
 {
diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h
index 511a37302fea..5fd627e9da19 100644
--- a/include/linux/can/dev/peak_canfd.h
+++ b/include/linux/can/dev/peak_canfd.h
@@ -189,7 +189,7 @@ struct __packed pucan_rx_msg {
 	u8	client;
 	__le16	flags;
 	__le32	can_id;
-	u8	d[0];
+	u8	d[];
 };
 
 /* uCAN error types */
@@ -266,7 +266,7 @@ struct __packed pucan_tx_msg {
 	u8	client;
 	__le16	flags;
 	__le32	can_id;
-	u8	d[0];
+	u8	d[];
 };
 
 /* build the cmd opcode_channel field with respect to the correct endianness */
diff --git a/include/linux/capability.h b/include/linux/capability.h
index ecce0f43c73a..027d7e4a853b 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -251,6 +251,10 @@ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct
 extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
 extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
 extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
+static inline bool perfmon_capable(void)
+{
+	return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN);
+}
 
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 333a6695a918..790c0c6b8552 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -42,3 +42,7 @@
  * compilers, like ICC.
  */
 #define barrier() __asm__ __volatile__("" : : : "memory")
+
+#if __has_feature(shadow_call_stack)
+# define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
+#endif
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 034b0a644efc..6325d64e3c3b 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -120,12 +120,65 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 /* Annotate a C jump table to allow objtool to follow the code flow */
 #define __annotate_jump_table __section(.rodata..c_jump_table)
 
+#ifdef CONFIG_DEBUG_ENTRY
+/* Begin/end of an instrumentation safe region */
+#define instrumentation_begin() ({					\
+	asm volatile("%c0:\n\t"						\
+		     ".pushsection .discard.instr_begin\n\t"		\
+		     ".long %c0b - .\n\t"				\
+		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+})
+
+/*
+ * Because instrumentation_{begin,end}() can nest, objtool validation considers
+ * _begin() a +1 and _end() a -1 and computes a sum over the instructions.
+ * When the value is greater than 0, we consider instrumentation allowed.
+ *
+ * There is a problem with code like:
+ *
+ * noinstr void foo()
+ * {
+ *	instrumentation_begin();
+ *	...
+ *	if (cond) {
+ *		instrumentation_begin();
+ *		...
+ *		instrumentation_end();
+ *	}
+ *	bar();
+ *	instrumentation_end();
+ * }
+ *
+ * If instrumentation_end() would be an empty label, like all the other
+ * annotations, the inner _end(), which is at the end of a conditional block,
+ * would land on the instruction after the block.
+ *
+ * If we then consider the sum of the !cond path, we'll see that the call to
+ * bar() is with a 0-value, even though, we meant it to happen with a positive
+ * value.
+ *
+ * To avoid this, have _end() be a NOP instruction, this ensures it will be
+ * part of the condition block and does not escape.
+ */
+#define instrumentation_end() ({					\
+	asm volatile("%c0: nop\n\t"					\
+		     ".pushsection .discard.instr_end\n\t"		\
+		     ".long %c0b - .\n\t"				\
+		     ".popsection\n\t" : : "i" (__COUNTER__));		\
+})
+#endif /* CONFIG_DEBUG_ENTRY */
+
 #else
 #define annotate_reachable()
 #define annotate_unreachable()
 #define __annotate_jump_table
 #endif
 
+#ifndef instrumentation_begin
+#define instrumentation_begin()		do { } while(0)
+#define instrumentation_end()		do { } while(0)
+#endif
+
 #ifndef ASM_UNREACHABLE
 # define ASM_UNREACHABLE
 #endif
@@ -356,4 +409,10 @@ static inline void *offset_to_ptr(const int *off)
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
+/*
+ * This is needed in functions which generate the stack canary, see
+ * arch/x86/kernel/smpboot.c::start_secondary() for an example.
+ */
+#define prevent_tail_call_optimization()	mb()
+
 #endif /* __LINUX_COMPILER_H */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index e970f97a7fcb..6fcf73200b67 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -118,6 +118,10 @@ struct ftrace_likely_data {
 #define notrace			__attribute__((__no_instrument_function__))
 #endif
 
+/* Section for code which can't be instrumented at all */
+#define noinstr								\
+	noinline notrace __attribute((__section__(".noinstr.text")))
+
 /*
  * it doesn't make sense on ARM (currently the only user of __naked)
  * to trace naked functions because then mcount is called without
@@ -193,6 +197,10 @@ struct ftrace_likely_data {
 # define randomized_struct_fields_end
 #endif
 
+#ifndef __noscs
+# define __noscs
+#endif
+
 #ifndef asm_volatile_goto
 #define asm_volatile_goto(x...) asm goto(x)
 #endif
diff --git a/include/linux/console.h b/include/linux/console.h
index 7a140f4e5d0c..75dd20650fbe 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -134,7 +134,7 @@ static inline int con_debug_leave(void)
  */
 
 #define CON_PRINTBUFFER	(1)
-#define CON_CONSDEV	(2) /* Last on the command line */
+#define CON_CONSDEV	(2) /* Preferred console, /dev/console */
 #define CON_ENABLED	(4)
 #define CON_BOOT	(8)
 #define CON_ANYTIME	(16) /* Safe to call when cpu is offline */
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 4f005d95ce88..8537e9282a65 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -521,6 +521,15 @@ struct cper_sec_pcie {
 	u8	aer_info[96];
 };
 
+/* Firmware Error Record Reference, UEFI v2.7 sec N.2.10  */
+struct cper_sec_fw_err_rec_ref {
+	u8 record_type;
+	u8 revision;
+	u8 reserved[6];
+	u64 record_identifier;
+	guid_t record_identifier_guid;
+};
+
 /* Reset to default packing */
 #pragma pack()
 
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index beaed2dc269e..52692587f7fe 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -144,18 +144,8 @@ static inline void get_online_cpus(void) { cpus_read_lock(); }
 static inline void put_online_cpus(void) { cpus_read_unlock(); }
 
 #ifdef CONFIG_PM_SLEEP_SMP
-int __freeze_secondary_cpus(int primary, bool suspend);
-static inline int freeze_secondary_cpus(int primary)
-{
-	return __freeze_secondary_cpus(primary, true);
-}
-
-static inline int disable_nonboot_cpus(void)
-{
-	return __freeze_secondary_cpus(0, false);
-}
-
-void enable_nonboot_cpus(void);
+extern int freeze_secondary_cpus(int primary);
+extern void thaw_secondary_cpus(void);
 
 static inline int suspend_disable_secondary_cpus(void)
 {
@@ -168,12 +158,11 @@ static inline int suspend_disable_secondary_cpus(void)
 }
 static inline void suspend_enable_secondary_cpus(void)
 {
-	return enable_nonboot_cpus();
+	return thaw_secondary_cpus();
 }
 
 #else /* !CONFIG_PM_SLEEP_SMP */
-static inline int disable_nonboot_cpus(void) { return 0; }
-static inline void enable_nonboot_cpus(void) {}
+static inline void thaw_secondary_cpus(void) {}
 static inline int suspend_disable_secondary_cpus(void) { return 0; }
 static inline void suspend_enable_secondary_cpus(void) { }
 #endif /* !CONFIG_PM_SLEEP_SMP */
diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h
index 02edeafcb2bf..be8aea04d023 100644
--- a/include/linux/cpu_rmap.h
+++ b/include/linux/cpu_rmap.h
@@ -28,7 +28,7 @@ struct cpu_rmap {
 	struct {
 		u16	index;
 		u16	dist;
-	}		near[0];
+	}		near[];
 };
 #define CPU_RMAP_DIST_INF 0xffff
 
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 4664fc1871de..bc156285d097 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -97,8 +97,6 @@ extern void unregister_oldmem_pfn_is_ram(void);
 static inline bool is_kdump_kernel(void) { return 0; }
 #endif /* CONFIG_CRASH_DUMP */
 
-extern unsigned long saved_max_pfn;
-
 /* Device Dump information to be filled by drivers */
 struct vmcoredd_data {
 	char dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Unique name of the dump */
diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h
deleted file mode 100644
index f6ba4c3e60d7..000000000000
--- a/include/linux/cryptohash.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __CRYPTOHASH_H
-#define __CRYPTOHASH_H
-
-#include <uapi/linux/types.h>
-
-#define SHA_DIGEST_WORDS 5
-#define SHA_MESSAGE_BYTES (512 /*bits*/ / 8)
-#define SHA_WORKSPACE_WORDS 16
-
-void sha_init(__u32 *buf);
-void sha_transform(__u32 *digest, const char *data, __u32 *W);
-
-#endif
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index a274d95fa66e..63cb3606dea7 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -103,8 +103,8 @@ void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent,
 		       u8 *value);
 void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent,
 			u16 *value);
-struct dentry *debugfs_create_u32(const char *name, umode_t mode,
-				  struct dentry *parent, u32 *value);
+void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent,
+			u32 *value);
 void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent,
 			u64 *value);
 struct dentry *debugfs_create_ulong(const char *name, umode_t mode,
@@ -250,12 +250,8 @@ static inline void debugfs_create_u8(const char *name, umode_t mode,
 static inline void debugfs_create_u16(const char *name, umode_t mode,
 				      struct dentry *parent, u16 *value) { }
 
-static inline struct dentry *debugfs_create_u32(const char *name, umode_t mode,
-						struct dentry *parent,
-						u32 *value)
-{
-	return ERR_PTR(-ENODEV);
-}
+static inline void debugfs_create_u32(const char *name, umode_t mode,
+				      struct dentry *parent, u32 *value) { }
 
 static inline void debugfs_create_u64(const char *name, umode_t mode,
 				      struct dentry *parent, u64 *value) { }
diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h
index fa35b52e0002..9a72214496e5 100644
--- a/include/linux/device_cgroup.h
+++ b/include/linux/device_cgroup.h
@@ -1,6 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/fs.h>
-#include <linux/bpf-cgroup.h>
 
 #define DEVCG_ACC_MKNOD 1
 #define DEVCG_ACC_READ  2
@@ -11,16 +10,10 @@
 #define DEVCG_DEV_CHAR  2
 #define DEVCG_DEV_ALL   4  /* this represents all devices */
 
-#ifdef CONFIG_CGROUP_DEVICE
-int devcgroup_check_permission(short type, u32 major, u32 minor,
-			       short access);
-#else
-static inline int devcgroup_check_permission(short type, u32 major, u32 minor,
-					     short access)
-{ return 0; }
-#endif
 
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
+int devcgroup_check_permission(short type, u32 major, u32 minor,
+			       short access);
 static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 {
 	short type, access = 0;
@@ -61,6 +54,9 @@ static inline int devcgroup_inode_mknod(int mode, dev_t dev)
 }
 
 #else
+static inline int devcgroup_check_permission(short type, u32 major, u32 minor,
+			       short access)
+{ return 0; }
 static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 { return 0; }
 static inline int devcgroup_inode_mknod(int mode, dev_t dev)
diff --git a/include/linux/digsig.h b/include/linux/digsig.h
index 594fc66a395a..2ace69e41088 100644
--- a/include/linux/digsig.h
+++ b/include/linux/digsig.h
@@ -29,7 +29,7 @@ struct pubkey_hdr {
 	uint32_t	timestamp;	/* key made, always 0 for now */
 	uint8_t		algo;
 	uint8_t		nmpi;
-	char		mpi[0];
+	char		mpi[];
 } __packed;
 
 struct signature_hdr {
@@ -39,7 +39,7 @@ struct signature_hdr {
 	uint8_t		hash;
 	uint8_t		keyid[8];
 	uint8_t		nmpi;
-	char		mpi[0];
+	char		mpi[];
 } __packed;
 
 #if defined(CONFIG_SIGNATURE) || defined(CONFIG_SIGNATURE_MODULE)
diff --git a/include/linux/dirent.h b/include/linux/dirent.h
index fc61f3cff72f..99002220cd45 100644
--- a/include/linux/dirent.h
+++ b/include/linux/dirent.h
@@ -7,7 +7,7 @@ struct linux_dirent64 {
 	s64		d_off;
 	unsigned short	d_reclen;
 	unsigned char	d_type;
-	char		d_name[0];
+	char		d_name[];
 };
 
 #endif
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 1ade486fc2bb..57bcef6f988a 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -329,13 +329,12 @@ struct dma_buf {
 
 /**
  * struct dma_buf_attach_ops - importer operations for an attachment
- * @move_notify: [optional] notification that the DMA-buf is moving
  *
  * Attachment operations implemented by the importer.
  */
 struct dma_buf_attach_ops {
 	/**
-	 * @move_notify
+	 * @move_notify: [optional] notification that the DMA-buf is moving
 	 *
 	 * If this callback is provided the framework can avoid pinning the
 	 * backing store while mappings exists.
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 21065c04c4ac..e1c03339918f 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -83,9 +83,9 @@ enum dma_transfer_direction {
 /**
  * Interleaved Transfer Request
  * ----------------------------
- * A chunk is collection of contiguous bytes to be transfered.
+ * A chunk is collection of contiguous bytes to be transferred.
  * The gap(in bytes) between two chunks is called inter-chunk-gap(ICG).
- * ICGs may or maynot change between chunks.
+ * ICGs may or may not change between chunks.
  * A FRAME is the smallest series of contiguous {chunk,icg} pairs,
  *  that when repeated an integral number of times, specifies the transfer.
  * A transfer template is specification of a Frame, the number of times
@@ -341,13 +341,11 @@ struct dma_chan {
  * @chan: driver channel device
  * @device: sysfs device
  * @dev_id: parent dma_device dev_id
- * @idr_ref: reference count to gate release of dma_device dev_id
  */
 struct dma_chan_dev {
 	struct dma_chan *chan;
 	struct device device;
 	int dev_id;
-	atomic_t *idr_ref;
 };
 
 /**
@@ -835,6 +833,8 @@ struct dma_device {
 	int dev_id;
 	struct device *dev;
 	struct module *owner;
+	struct ida chan_ida;
+	struct mutex chan_mutex;	/* to protect chan_ida */
 
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
@@ -1069,7 +1069,7 @@ static inline int dmaengine_terminate_all(struct dma_chan *chan)
  * dmaengine_synchronize() needs to be called before it is safe to free
  * any memory that is accessed by previously submitted descriptors or before
  * freeing any resources accessed from within the completion callback of any
- * perviously submitted descriptors.
+ * previously submitted descriptors.
  *
  * This function can be called from atomic context as well as from within a
  * complete callback of a descriptor submitted on the same channel.
@@ -1091,7 +1091,7 @@ static inline int dmaengine_terminate_async(struct dma_chan *chan)
  *
  * Synchronizes to the DMA channel termination to the current context. When this
  * function returns it is guaranteed that all transfers for previously issued
- * descriptors have stopped and and it is safe to free the memory assoicated
+ * descriptors have stopped and it is safe to free the memory associated
  * with them. Furthermore it is guaranteed that all complete callback functions
  * for a previously submitted descriptor have finished running and it is safe to
  * free resources accessed from within the complete callbacks.
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 251f1f783cdf..2c6495f72f79 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -39,6 +39,7 @@
 #define EFI_WRITE_PROTECTED	( 8 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_OUT_OF_RESOURCES	( 9 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_NOT_FOUND		(14 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_TIMEOUT		(18 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_ABORTED		(21 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_SECURITY_VIOLATION	(26 | (1UL << (BITS_PER_LONG-1)))
 
@@ -379,8 +380,8 @@ typedef union {
 
 typedef struct {
 	efi_guid_t guid;
-	const char *name;
 	unsigned long *ptr;
+	const char name[16];
 } efi_config_table_type_t;
 
 #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL)
@@ -426,6 +427,7 @@ typedef struct {
 	u32 tables;
 } efi_system_table_32_t;
 
+typedef union efi_simple_text_input_protocol efi_simple_text_input_protocol_t;
 typedef union efi_simple_text_output_protocol efi_simple_text_output_protocol_t;
 
 typedef union {
@@ -434,7 +436,7 @@ typedef union {
 		unsigned long fw_vendor;	/* physical addr of CHAR16 vendor string */
 		u32 fw_revision;
 		unsigned long con_in_handle;
-		unsigned long con_in;
+		efi_simple_text_input_protocol_t *con_in;
 		unsigned long con_out_handle;
 		efi_simple_text_output_protocol_t *con_out;
 		unsigned long stderr_handle;
@@ -1245,4 +1247,6 @@ struct linux_efi_memreserve {
 
 void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size);
 
+char *efi_systab_show_arch(char *str);
+
 #endif /* _LINUX_EFI_H */
diff --git a/include/linux/elf.h b/include/linux/elf.h
index e3649b3e970e..5d5b0321da0b 100644
--- a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_ELF_H
 #define _LINUX_ELF_H
 
+#include <linux/types.h>
 #include <asm/elf.h>
 #include <uapi/linux/elf.h>
 
@@ -21,6 +22,9 @@
 	SET_PERSONALITY(ex)
 #endif
 
+#define ELF32_GNU_PROPERTY_ALIGN	4
+#define ELF64_GNU_PROPERTY_ALIGN	8
+
 #if ELF_CLASS == ELFCLASS32
 
 extern Elf32_Dyn _DYNAMIC [];
@@ -31,6 +35,7 @@ extern Elf32_Dyn _DYNAMIC [];
 #define elf_addr_t	Elf32_Off
 #define Elf_Half	Elf32_Half
 #define Elf_Word	Elf32_Word
+#define ELF_GNU_PROPERTY_ALIGN	ELF32_GNU_PROPERTY_ALIGN
 
 #else
 
@@ -42,6 +47,7 @@ extern Elf64_Dyn _DYNAMIC [];
 #define elf_addr_t	Elf64_Off
 #define Elf_Half	Elf64_Half
 #define Elf_Word	Elf64_Word
+#define ELF_GNU_PROPERTY_ALIGN	ELF64_GNU_PROPERTY_ALIGN
 
 #endif
 
@@ -56,4 +62,41 @@ static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) {
 extern int elf_coredump_extra_notes_size(void);
 extern int elf_coredump_extra_notes_write(struct coredump_params *cprm);
 #endif
+
+/*
+ * NT_GNU_PROPERTY_TYPE_0 header:
+ * Keep this internal until/unless there is an agreed UAPI definition.
+ * pr_type values (GNU_PROPERTY_*) are public and defined in the UAPI header.
+ */
+struct gnu_property {
+	u32 pr_type;
+	u32 pr_datasz;
+};
+
+struct arch_elf_state;
+
+#ifndef CONFIG_ARCH_USE_GNU_PROPERTY
+static inline int arch_parse_elf_property(u32 type, const void *data,
+					  size_t datasz, bool compat,
+					  struct arch_elf_state *arch)
+{
+	return 0;
+}
+#else
+extern int arch_parse_elf_property(u32 type, const void *data, size_t datasz,
+				   bool compat, struct arch_elf_state *arch);
+#endif
+
+#ifdef CONFIG_ARCH_HAVE_ELF_PROT
+int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state,
+			 bool has_interp, bool is_interp);
+#else
+static inline int arch_elf_adjust_prot(int prot,
+				       const struct arch_elf_state *state,
+				       bool has_interp, bool is_interp)
+{
+	return prot;
+}
+#endif
+
 #endif /* _LINUX_ELF_H */
diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h
index 564e96f625ff..1c630e2c2756 100644
--- a/include/linux/enclosure.h
+++ b/include/linux/enclosure.h
@@ -101,7 +101,7 @@ struct enclosure_device {
 	struct device edev;
 	struct enclosure_component_callbacks *cb;
 	int components;
-	struct enclosure_component component[0];
+	struct enclosure_component component[];
 };
 
 static inline struct enclosure_device *
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index d249b88a4d5a..ade6486a3382 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -36,7 +36,7 @@ struct em_cap_state {
 struct em_perf_domain {
 	struct em_cap_state *table;
 	int nr_cap_states;
-	unsigned long cpus[0];
+	unsigned long cpus[];
 };
 
 #ifdef CONFIG_ENERGY_MODEL
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index c1d379bf6ee1..a23b26eab479 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -35,7 +35,7 @@ struct compat_ethtool_rxnfc {
 	compat_u64			data;
 	struct compat_ethtool_rx_flow_spec fs;
 	u32				rule_cnt;
-	u32				rule_locs[0];
+	u32				rule_locs[];
 };
 
 #endif /* CONFIG_COMPAT */
@@ -462,7 +462,7 @@ int ethtool_check_ops(const struct ethtool_ops *ops);
 
 struct ethtool_rx_flow_rule {
 	struct flow_rule	*rule;
-	unsigned long		priv[0];
+	unsigned long		priv[];
 };
 
 struct ethtool_rx_flow_spec_input {
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 3049a6c06d9e..b79fa9bb7359 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -47,8 +47,7 @@
  * Directory entry modification events - reported only to directory
  * where entry is modified and not to a watching parent.
  */
-#define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE | \
-				 FAN_DIR_MODIFY)
+#define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE)
 
 /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */
 #define FANOTIFY_INODE_EVENTS	(FANOTIFY_DIRENT_EVENTS | \
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 9b5aa5c483cc..ec45fd7992c9 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -16,11 +16,11 @@
 #include <linux/workqueue.h>
 #include <linux/sched.h>
 #include <linux/capability.h>
-#include <linux/cryptohash.h>
 #include <linux/set_memory.h>
 #include <linux/kallsyms.h>
 #include <linux/if_vlan.h>
 #include <linux/vmalloc.h>
+#include <crypto/sha.h>
 
 #include <net/sch_generic.h>
 
@@ -746,7 +746,7 @@ static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog)
 static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog)
 {
 	return round_up(bpf_prog_insn_size(prog) +
-			sizeof(__be64) + 1, SHA_MESSAGE_BYTES);
+			sizeof(__be64) + 1, SHA1_BLOCK_SIZE);
 }
 
 static inline unsigned int bpf_prog_size(unsigned int proglen)
diff --git a/include/linux/frame.h b/include/linux/frame.h
index 02d3ca2d9598..303cda600e56 100644
--- a/include/linux/frame.h
+++ b/include/linux/frame.h
@@ -15,9 +15,20 @@
 	static void __used __section(.discard.func_stack_frame_non_standard) \
 		*__func_stack_frame_non_standard_##func = func
 
+/*
+ * This macro indicates that the following intra-function call is valid.
+ * Any non-annotated intra-function call will cause objtool to issue a warning.
+ */
+#define ANNOTATE_INTRA_FUNCTION_CALL				\
+	999:							\
+	.pushsection .discard.intra_function_calls;		\
+	.long 999b;						\
+	.popsection;
+
 #else /* !CONFIG_STACK_VALIDATION */
 
 #define STACK_FRAME_NON_STANDARD(func)
+#define ANNOTATE_INTRA_FUNCTION_CALL
 
 #endif /* CONFIG_STACK_VALIDATION */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4f6f59b4f22a..45cc10cdf6dd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -983,7 +983,7 @@ struct file_handle {
 	__u32 handle_bytes;
 	int handle_type;
 	/* file identifier */
-	unsigned char f_handle[0];
+	unsigned char f_handle[];
 };
 
 static inline struct file *get_file(struct file *f)
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index e3c2d2a15525..2862ca5fea33 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -15,12 +15,15 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/parser.h>
 #include <linux/slab.h>
 #include <uapi/linux/fscrypt.h>
 
 #define FS_CRYPTO_BLOCK_SIZE		16
 
+union fscrypt_context;
 struct fscrypt_info;
+struct seq_file;
 
 struct fscrypt_str {
 	unsigned char *name;
@@ -56,10 +59,12 @@ struct fscrypt_name {
 struct fscrypt_operations {
 	unsigned int flags;
 	const char *key_prefix;
-	int (*get_context)(struct inode *, void *, size_t);
-	int (*set_context)(struct inode *, const void *, size_t, void *);
-	bool (*dummy_context)(struct inode *);
-	bool (*empty_dir)(struct inode *);
+	int (*get_context)(struct inode *inode, void *ctx, size_t len);
+	int (*set_context)(struct inode *inode, const void *ctx, size_t len,
+			   void *fs_data);
+	const union fscrypt_context *(*get_dummy_context)(
+		struct super_block *sb);
+	bool (*empty_dir)(struct inode *inode);
 	unsigned int max_namelen;
 	bool (*has_stable_inodes)(struct super_block *sb);
 	void (*get_ino_and_lblk_bits)(struct super_block *sb,
@@ -75,6 +80,7 @@ static inline bool fscrypt_has_encryption_key(const struct inode *inode)
 /**
  * fscrypt_needs_contents_encryption() - check whether an inode needs
  *					 contents encryption
+ * @inode: the inode to check
  *
  * Return: %true iff the inode is an encrypted regular file and the kernel was
  * built with fscrypt support.
@@ -87,10 +93,12 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 	return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
 }
 
-static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
+static inline const union fscrypt_context *
+fscrypt_get_dummy_context(struct super_block *sb)
 {
-	return inode->i_sb->s_cop->dummy_context &&
-		inode->i_sb->s_cop->dummy_context(inode);
+	if (!sb->s_cop->get_dummy_context)
+		return NULL;
+	return sb->s_cop->get_dummy_context(sb);
 }
 
 /*
@@ -106,22 +114,21 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry)
 }
 
 /* crypto.c */
-extern void fscrypt_enqueue_decrypt_work(struct work_struct *);
-
-extern struct page *fscrypt_encrypt_pagecache_blocks(struct page *page,
-						     unsigned int len,
-						     unsigned int offs,
-						     gfp_t gfp_flags);
-extern int fscrypt_encrypt_block_inplace(const struct inode *inode,
-					 struct page *page, unsigned int len,
-					 unsigned int offs, u64 lblk_num,
-					 gfp_t gfp_flags);
-
-extern int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len,
-					    unsigned int offs);
-extern int fscrypt_decrypt_block_inplace(const struct inode *inode,
-					 struct page *page, unsigned int len,
-					 unsigned int offs, u64 lblk_num);
+void fscrypt_enqueue_decrypt_work(struct work_struct *);
+
+struct page *fscrypt_encrypt_pagecache_blocks(struct page *page,
+					      unsigned int len,
+					      unsigned int offs,
+					      gfp_t gfp_flags);
+int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page,
+				  unsigned int len, unsigned int offs,
+				  u64 lblk_num, gfp_t gfp_flags);
+
+int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len,
+				     unsigned int offs);
+int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page,
+				  unsigned int len, unsigned int offs,
+				  u64 lblk_num);
 
 static inline bool fscrypt_is_bounce_page(struct page *page)
 {
@@ -133,78 +140,90 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page)
 	return (struct page *)page_private(bounce_page);
 }
 
-extern void fscrypt_free_bounce_page(struct page *bounce_page);
+void fscrypt_free_bounce_page(struct page *bounce_page);
 
 /* policy.c */
-extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
-extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
-extern int fscrypt_ioctl_get_policy_ex(struct file *, void __user *);
-extern int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
-extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
-extern int fscrypt_inherit_context(struct inode *, struct inode *,
-					void *, bool);
+int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg);
+int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg);
+int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg);
+int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
+int fscrypt_has_permitted_context(struct inode *parent, struct inode *child);
+int fscrypt_inherit_context(struct inode *parent, struct inode *child,
+			    void *fs_data, bool preload);
+
+struct fscrypt_dummy_context {
+	const union fscrypt_context *ctx;
+};
+
+int fscrypt_set_test_dummy_encryption(struct super_block *sb,
+				      const substring_t *arg,
+				      struct fscrypt_dummy_context *dummy_ctx);
+void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
+					struct super_block *sb);
+static inline void
+fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx)
+{
+	kfree(dummy_ctx->ctx);
+	dummy_ctx->ctx = NULL;
+}
+
 /* keyring.c */
-extern void fscrypt_sb_free(struct super_block *sb);
-extern int fscrypt_ioctl_add_key(struct file *filp, void __user *arg);
-extern int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg);
-extern int fscrypt_ioctl_remove_key_all_users(struct file *filp,
-					      void __user *arg);
-extern int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg);
+void fscrypt_sb_free(struct super_block *sb);
+int fscrypt_ioctl_add_key(struct file *filp, void __user *arg);
+int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg);
+int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg);
+int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg);
 
 /* keysetup.c */
-extern int fscrypt_get_encryption_info(struct inode *);
-extern void fscrypt_put_encryption_info(struct inode *);
-extern void fscrypt_free_inode(struct inode *);
-extern int fscrypt_drop_inode(struct inode *inode);
+int fscrypt_get_encryption_info(struct inode *inode);
+void fscrypt_put_encryption_info(struct inode *inode);
+void fscrypt_free_inode(struct inode *inode);
+int fscrypt_drop_inode(struct inode *inode);
 
 /* fname.c */
-extern int fscrypt_setup_filename(struct inode *, const struct qstr *,
-				int lookup, struct fscrypt_name *);
+int fscrypt_setup_filename(struct inode *inode, const struct qstr *iname,
+			   int lookup, struct fscrypt_name *fname);
 
 static inline void fscrypt_free_filename(struct fscrypt_name *fname)
 {
 	kfree(fname->crypto_buf.name);
 }
 
-extern int fscrypt_fname_alloc_buffer(const struct inode *, u32,
-				struct fscrypt_str *);
-extern void fscrypt_fname_free_buffer(struct fscrypt_str *);
-extern int fscrypt_fname_disk_to_usr(const struct inode *inode,
-				     u32 hash, u32 minor_hash,
-				     const struct fscrypt_str *iname,
-				     struct fscrypt_str *oname);
-extern bool fscrypt_match_name(const struct fscrypt_name *fname,
-			       const u8 *de_name, u32 de_name_len);
-extern u64 fscrypt_fname_siphash(const struct inode *dir,
-				 const struct qstr *name);
+int fscrypt_fname_alloc_buffer(const struct inode *inode, u32 max_encrypted_len,
+			       struct fscrypt_str *crypto_str);
+void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str);
+int fscrypt_fname_disk_to_usr(const struct inode *inode,
+			      u32 hash, u32 minor_hash,
+			      const struct fscrypt_str *iname,
+			      struct fscrypt_str *oname);
+bool fscrypt_match_name(const struct fscrypt_name *fname,
+			const u8 *de_name, u32 de_name_len);
+u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name);
 
 /* bio.c */
-extern void fscrypt_decrypt_bio(struct bio *);
-extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t,
-				 unsigned int);
+void fscrypt_decrypt_bio(struct bio *bio);
+int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
+			  sector_t pblk, unsigned int len);
 
 /* hooks.c */
-extern int fscrypt_file_open(struct inode *inode, struct file *filp);
-extern int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
-				  struct dentry *dentry);
-extern int __fscrypt_prepare_rename(struct inode *old_dir,
-				    struct dentry *old_dentry,
-				    struct inode *new_dir,
-				    struct dentry *new_dentry,
-				    unsigned int flags);
-extern int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
-				    struct fscrypt_name *fname);
-extern int fscrypt_prepare_setflags(struct inode *inode,
-				    unsigned int oldflags, unsigned int flags);
-extern int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
-				     unsigned int max_len,
-				     struct fscrypt_str *disk_link);
-extern int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
-				     unsigned int len,
-				     struct fscrypt_str *disk_link);
-extern const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
-				       unsigned int max_size,
-				       struct delayed_call *done);
+int fscrypt_file_open(struct inode *inode, struct file *filp);
+int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
+			   struct dentry *dentry);
+int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
+			     struct inode *new_dir, struct dentry *new_dentry,
+			     unsigned int flags);
+int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
+			     struct fscrypt_name *fname);
+int fscrypt_prepare_setflags(struct inode *inode,
+			     unsigned int oldflags, unsigned int flags);
+int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
+			      unsigned int max_len,
+			      struct fscrypt_str *disk_link);
+int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
+			      unsigned int len, struct fscrypt_str *disk_link);
+const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
+				unsigned int max_size,
+				struct delayed_call *done);
 static inline void fscrypt_set_ops(struct super_block *sb,
 				   const struct fscrypt_operations *s_cop)
 {
@@ -222,9 +241,10 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 	return false;
 }
 
-static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
+static inline const union fscrypt_context *
+fscrypt_get_dummy_context(struct super_block *sb)
 {
-	return false;
+	return NULL;
 }
 
 static inline void fscrypt_handle_d_move(struct dentry *dentry)
@@ -319,6 +339,20 @@ static inline int fscrypt_inherit_context(struct inode *parent,
 	return -EOPNOTSUPP;
 }
 
+struct fscrypt_dummy_context {
+};
+
+static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq,
+						      char sep,
+						      struct super_block *sb)
+{
+}
+
+static inline void
+fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx)
+{
+}
+
 /* keyring.c */
 static inline void fscrypt_sb_free(struct super_block *sb)
 {
@@ -504,7 +538,7 @@ static inline void fscrypt_set_ops(struct super_block *sb,
 #endif	/* !CONFIG_FS_ENCRYPTION */
 
 /**
- * fscrypt_require_key - require an inode's encryption key
+ * fscrypt_require_key() - require an inode's encryption key
  * @inode: the inode we need the key for
  *
  * If the inode is encrypted, set up its encryption key if not already done.
@@ -530,7 +564,8 @@ static inline int fscrypt_require_key(struct inode *inode)
 }
 
 /**
- * fscrypt_prepare_link - prepare to link an inode into a possibly-encrypted directory
+ * fscrypt_prepare_link() - prepare to link an inode into a possibly-encrypted
+ *			    directory
  * @old_dentry: an existing dentry for the inode being linked
  * @dir: the target directory
  * @dentry: negative dentry for the target filename
@@ -557,7 +592,8 @@ static inline int fscrypt_prepare_link(struct dentry *old_dentry,
 }
 
 /**
- * fscrypt_prepare_rename - prepare for a rename between possibly-encrypted directories
+ * fscrypt_prepare_rename() - prepare for a rename between possibly-encrypted
+ *			      directories
  * @old_dir: source directory
  * @old_dentry: dentry for source file
  * @new_dir: target directory
@@ -590,7 +626,8 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir,
 }
 
 /**
- * fscrypt_prepare_lookup - prepare to lookup a name in a possibly-encrypted directory
+ * fscrypt_prepare_lookup() - prepare to lookup a name in a possibly-encrypted
+ *			      directory
  * @dir: directory being searched
  * @dentry: filename being looked up
  * @fname: (output) the name to use to search the on-disk directory
@@ -623,7 +660,8 @@ static inline int fscrypt_prepare_lookup(struct inode *dir,
 }
 
 /**
- * fscrypt_prepare_setattr - prepare to change a possibly-encrypted inode's attributes
+ * fscrypt_prepare_setattr() - prepare to change a possibly-encrypted inode's
+ *			       attributes
  * @dentry: dentry through which the inode is being changed
  * @attr: attributes to change
  *
@@ -648,7 +686,7 @@ static inline int fscrypt_prepare_setattr(struct dentry *dentry,
 }
 
 /**
- * fscrypt_prepare_symlink - prepare to create a possibly-encrypted symlink
+ * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink
  * @dir: directory in which the symlink is being created
  * @target: plaintext symlink target
  * @len: length of @target excluding null terminator
@@ -676,7 +714,7 @@ static inline int fscrypt_prepare_symlink(struct inode *dir,
 					  unsigned int max_len,
 					  struct fscrypt_str *disk_link)
 {
-	if (IS_ENCRYPTED(dir) || fscrypt_dummy_context_enabled(dir))
+	if (IS_ENCRYPTED(dir) || fscrypt_get_dummy_context(dir->i_sb) != NULL)
 		return __fscrypt_prepare_symlink(dir, len, max_len, disk_link);
 
 	disk_link->name = (unsigned char *)target;
@@ -687,7 +725,7 @@ static inline int fscrypt_prepare_symlink(struct inode *dir,
 }
 
 /**
- * fscrypt_encrypt_symlink - encrypt the symlink target if needed
+ * fscrypt_encrypt_symlink() - encrypt the symlink target if needed
  * @inode: symlink inode
  * @target: plaintext symlink target
  * @len: length of @target excluding null terminator
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
index ecc604e61d61..78201a6d35f6 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -121,23 +121,23 @@ static inline struct fsverity_info *fsverity_get_info(const struct inode *inode)
 
 /* enable.c */
 
-extern int fsverity_ioctl_enable(struct file *filp, const void __user *arg);
+int fsverity_ioctl_enable(struct file *filp, const void __user *arg);
 
 /* measure.c */
 
-extern int fsverity_ioctl_measure(struct file *filp, void __user *arg);
+int fsverity_ioctl_measure(struct file *filp, void __user *arg);
 
 /* open.c */
 
-extern int fsverity_file_open(struct inode *inode, struct file *filp);
-extern int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr);
-extern void fsverity_cleanup_inode(struct inode *inode);
+int fsverity_file_open(struct inode *inode, struct file *filp);
+int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr);
+void fsverity_cleanup_inode(struct inode *inode);
 
 /* verify.c */
 
-extern bool fsverity_verify_page(struct page *page);
-extern void fsverity_verify_bio(struct bio *bio);
-extern void fsverity_enqueue_verify_work(struct work_struct *work);
+bool fsverity_verify_page(struct page *page);
+void fsverity_verify_bio(struct bio *bio);
+void fsverity_enqueue_verify_work(struct work_struct *work);
 
 #else /* !CONFIG_FS_VERITY */
 
@@ -200,6 +200,7 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work)
 
 /**
  * fsverity_active() - do reads from the inode need to go through fs-verity?
+ * @inode: inode to check
  *
  * This checks whether ->i_verity_info has been set.
  *
@@ -207,6 +208,8 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work)
  * be verified or not.  Don't use IS_VERITY() for this purpose; it's subject to
  * a race condition where the file is being read concurrently with
  * FS_IOC_ENABLE_VERITY completing.  (S_VERITY is set before ->i_verity_info.)
+ *
+ * Return: true if reads need to go through fs-verity, otherwise false
  */
 static inline bool fsverity_active(const struct inode *inode)
 {
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index db95244a62d4..ab4bd15cbcdb 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -210,6 +210,29 @@ struct ftrace_ops {
 #endif
 };
 
+extern struct ftrace_ops __rcu *ftrace_ops_list;
+extern struct ftrace_ops ftrace_list_end;
+
+/*
+ * Traverse the ftrace_global_list, invoking all entries.  The reason that we
+ * can use rcu_dereference_raw_check() is that elements removed from this list
+ * are simply leaked, so there is no need to interact with a grace-period
+ * mechanism.  The rcu_dereference_raw_check() calls are needed to handle
+ * concurrent insertions into the ftrace_global_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
+#define do_for_each_ftrace_op(op, list)			\
+	op = rcu_dereference_raw_check(list);			\
+	do
+
+/*
+ * Optimized for just a single item in the list (as that is the normal case).
+ */
+#define while_for_each_ftrace_op(op)				\
+	while (likely(op = rcu_dereference_raw_check((op)->next)) &&	\
+	       unlikely((op) != &ftrace_list_end))
+
 /*
  * Type of the current tracing.
  */
diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h
index ccda97dc7f8b..0abd9a1d2852 100644
--- a/include/linux/ftrace_irq.h
+++ b/include/linux/ftrace_irq.h
@@ -2,15 +2,6 @@
 #ifndef _LINUX_FTRACE_IRQ_H
 #define _LINUX_FTRACE_IRQ_H
 
-
-#ifdef CONFIG_FTRACE_NMI_ENTER
-extern void arch_ftrace_nmi_enter(void);
-extern void arch_ftrace_nmi_exit(void);
-#else
-static inline void arch_ftrace_nmi_enter(void) { }
-static inline void arch_ftrace_nmi_exit(void) { }
-#endif
-
 #ifdef CONFIG_HWLAT_TRACER
 extern bool trace_hwlat_callback_enabled;
 extern void trace_hwlat_callback(bool enter);
@@ -22,12 +13,10 @@ static inline void ftrace_nmi_enter(void)
 	if (trace_hwlat_callback_enabled)
 		trace_hwlat_callback(true);
 #endif
-	arch_ftrace_nmi_enter();
 }
 
 static inline void ftrace_nmi_exit(void)
 {
-	arch_ftrace_nmi_exit();
 #ifdef CONFIG_HWLAT_TRACER
 	if (trace_hwlat_callback_enabled)
 		trace_hwlat_callback(false);
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 5b14a0f38124..0bd581003cd5 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -76,7 +76,7 @@ struct gen_pool_chunk {
 	void *owner;			/* private data to retrieve at alloc time */
 	unsigned long start_addr;	/* start address of memory chunk */
 	unsigned long end_addr;		/* end address of memory chunk (inclusive) */
-	unsigned long bits[0];		/* bitmap for allocating memory chunk */
+	unsigned long bits[];		/* bitmap for allocating memory chunk */
 };
 
 /*
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 7c8b82f69288..e07cf853aa16 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -2,31 +2,28 @@
 #ifndef LINUX_HARDIRQ_H
 #define LINUX_HARDIRQ_H
 
+#include <linux/context_tracking_state.h>
 #include <linux/preempt.h>
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
 #include <linux/vtime.h>
 #include <asm/hardirq.h>
 
-
 extern void synchronize_irq(unsigned int irq);
 extern bool synchronize_hardirq(unsigned int irq);
 
-#if defined(CONFIG_TINY_RCU)
-
-static inline void rcu_nmi_enter(void)
-{
-}
+#ifdef CONFIG_NO_HZ_FULL
+void __rcu_irq_enter_check_tick(void);
+#else
+static inline void __rcu_irq_enter_check_tick(void) { }
+#endif
 
-static inline void rcu_nmi_exit(void)
+static __always_inline void rcu_irq_enter_check_tick(void)
 {
+	if (context_tracking_enabled())
+		__rcu_irq_enter_check_tick();
 }
 
-#else
-extern void rcu_nmi_enter(void);
-extern void rcu_nmi_exit(void);
-#endif
-
 /*
  * It is safe to do non-atomic ops on ->hardirq_context,
  * because NMI handlers may not preempt and the ops are
@@ -65,14 +62,34 @@ extern void irq_exit(void);
 #define arch_nmi_exit()		do { } while (0)
 #endif
 
+#ifdef CONFIG_TINY_RCU
+static inline void rcu_nmi_enter(void) { }
+static inline void rcu_nmi_exit(void) { }
+#else
+extern void rcu_nmi_enter(void);
+extern void rcu_nmi_exit(void);
+#endif
+
+/*
+ * NMI vs Tracing
+ * --------------
+ *
+ * We must not land in a tracer until (or after) we've changed preempt_count
+ * such that in_nmi() becomes true. To that effect all NMI C entry points must
+ * be marked 'notrace' and call nmi_enter() as soon as possible.
+ */
+
+/*
+ * nmi_enter() can nest up to 15 times; see NMI_BITS.
+ */
 #define nmi_enter()						\
 	do {							\
 		arch_nmi_enter();				\
 		printk_nmi_enter();				\
 		lockdep_off();					\
 		ftrace_nmi_enter();				\
-		BUG_ON(in_nmi());				\
-		preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		BUG_ON(in_nmi() == NMI_MASK);			\
+		__preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		rcu_nmi_enter();				\
 		lockdep_hardirq_enter();			\
 	} while (0)
@@ -82,7 +99,7 @@ extern void irq_exit(void);
 		lockdep_hardirq_exit();				\
 		rcu_nmi_exit();					\
 		BUG_ON(!in_nmi());				\
-		preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		__preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		ftrace_nmi_exit();				\
 		lockdep_on();					\
 		printk_nmi_exit();				\
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 62d216ff1097..c230b4e70d75 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -17,9 +17,12 @@ enum host1x_class {
 	HOST1X_CLASS_GR3D = 0x60,
 };
 
+struct host1x;
 struct host1x_client;
 struct iommu_group;
 
+u64 host1x_get_dma_mask(struct host1x *host1x);
+
 /**
  * struct host1x_client_ops - host1x client operations
  * @init: host1x client initialization code
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 5e609f25878c..363d4a814aa1 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -436,6 +436,9 @@ devm_hwmon_device_register_with_info(struct device *dev,
 void hwmon_device_unregister(struct device *dev);
 void devm_hwmon_device_unregister(struct device *dev);
 
+int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type,
+		       u32 attr, int channel);
+
 /**
  * hwmon_is_bad_char - Is the char invalid in a hwmon name
  * @ch: the char to be considered
diff --git a/include/linux/i2c-mux.h b/include/linux/i2c-mux.h
index c5a977320f82..98ef73b7c8fd 100644
--- a/include/linux/i2c-mux.h
+++ b/include/linux/i2c-mux.h
@@ -29,7 +29,7 @@ struct i2c_mux_core {
 
 	int num_adapters;
 	int max_adapters;
-	struct i2c_adapter *adapter[0];
+	struct i2c_adapter *adapter[];
 };
 
 struct i2c_mux_core *i2c_mux_alloc(struct i2c_adapter *parent,
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 456fc17ecb1c..49d29054e657 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -2,7 +2,7 @@
 /*
  * i2c.h - definitions for the Linux i2c bus interface
  * Copyright (C) 1995-2000 Simon G. Vogl
- * Copyright (C) 2013-2019 Wolfram Sang <wsa@the-dreams.de>
+ * Copyright (C) 2013-2019 Wolfram Sang <wsa@kernel.org>
  *
  * With some changes from Kyösti Mälkki <kmalkki@cc.hut.fi> and
  * Frodo Looijaard <frodol@dds.nl>
@@ -461,12 +461,6 @@ i2c_new_scanned_device(struct i2c_adapter *adap,
 		       unsigned short const *addr_list,
 		       int (*probe)(struct i2c_adapter *adap, unsigned short addr));
 
-struct i2c_client *
-i2c_new_probed_device(struct i2c_adapter *adap,
-		       struct i2c_board_info *info,
-		       unsigned short const *addr_list,
-		       int (*probe)(struct i2c_adapter *adap, unsigned short addr));
-
 /* Common custom probe functions */
 int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr);
 
diff --git a/include/linux/idr.h b/include/linux/idr.h
index ac6e946b6767..3ade03e5c7af 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -171,7 +171,7 @@ static inline bool idr_is_empty(const struct idr *idr)
  */
 static inline void idr_preload_end(void)
 {
-	preempt_enable();
+	local_unlock(&radix_tree_preloads.lock);
 }
 
 /**
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 16268ef1cbcc..5d3e48d02033 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2047,7 +2047,7 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info)
 }
 
 /* HE Operation defines */
-#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK		0x00000003
+#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK		0x00000007
 #define IEEE80211_HE_OPERATION_TWT_REQUIRED			0x00000008
 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK		0x00003ff0
 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET		4
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index 463047d0190b..faa6586a5783 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -38,7 +38,7 @@ struct ip_sf_socklist {
 	unsigned int		sl_max;
 	unsigned int		sl_count;
 	struct rcu_head		rcu;
-	__be32			sl_addr[0];
+	__be32			sl_addr[];
 };
 
 #define IP_SFLSIZE(count)	(sizeof(struct ip_sf_socklist) + \
diff --git a/include/linux/ihex.h b/include/linux/ihex.h
index 98cb5ce0b0a0..b824877e6d1b 100644
--- a/include/linux/ihex.h
+++ b/include/linux/ihex.h
@@ -18,7 +18,7 @@
 struct ihex_binrec {
 	__be32 addr;
 	__be16 len;
-	uint8_t data[0];
+	uint8_t data[];
 } __attribute__((packed));
 
 static inline uint16_t ihex_binrec_size(const struct ihex_binrec *p)
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 17f56a070b20..25c87507a1fa 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -600,7 +600,7 @@ void iio_device_unregister(struct iio_dev *indio_dev);
  * 0 on success, negative error number on failure.
  */
 #define devm_iio_device_register(dev, indio_dev) \
-	__devm_iio_device_register((dev), (indio_dev), THIS_MODULE);
+	__devm_iio_device_register((dev), (indio_dev), THIS_MODULE)
 int __devm_iio_device_register(struct device *dev, struct iio_dev *indio_dev,
 			       struct module *this_mod);
 void devm_iio_device_unregister(struct device *dev, struct iio_dev *indio_dev);
diff --git a/include/linux/input/lm8333.h b/include/linux/input/lm8333.h
index 79f918c6e8c5..906da5fc06e0 100644
--- a/include/linux/input/lm8333.h
+++ b/include/linux/input/lm8333.h
@@ -1,6 +1,6 @@
 /*
  * public include for LM8333 keypad driver - same license as driver
- * Copyright (C) 2012 Wolfram Sang, Pengutronix <w.sang@pengutronix.de>
+ * Copyright (C) 2012 Wolfram Sang, Pengutronix <kernel@pengutronix.de>
  */
 
 #ifndef _LM8333_H
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 9315fbb87db3..8d5bc2c237d7 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -573,8 +573,6 @@ enum {
 #define IRQ_DEFAULT_INIT_FLAGS	ARCH_IRQ_INIT_FLAGS
 
 struct irqaction;
-extern int setup_irq(unsigned int irq, struct irqaction *new);
-extern void remove_irq(unsigned int irq, struct irqaction *act);
 extern int setup_percpu_irq(unsigned int irq, struct irqaction *new);
 extern void remove_percpu_irq(unsigned int irq, struct irqaction *act);
 
@@ -1043,7 +1041,7 @@ struct irq_chip_generic {
 	unsigned long		unused;
 	struct irq_domain	*domain;
 	struct list_head	list;
-	struct irq_chip_type	chip_types[0];
+	struct irq_chip_type	chip_types[];
 };
 
 /**
@@ -1079,7 +1077,7 @@ struct irq_domain_chip_generic {
 	unsigned int		irq_flags_to_clear;
 	unsigned int		irq_flags_to_set;
 	enum irq_gc_flags	gc_flags;
-	struct irq_chip_generic	*gc[0];
+	struct irq_chip_generic	*gc[];
 };
 
 /* Generic chip callback functions */
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 765d9b769b69..6c36b6cc3edf 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -243,6 +243,7 @@
 
 #define GICR_TYPER_PLPIS		(1U << 0)
 #define GICR_TYPER_VLPIS		(1U << 1)
+#define GICR_TYPER_DIRTY		(1U << 2)
 #define GICR_TYPER_DirectLPIS		(1U << 3)
 #define GICR_TYPER_LAST			(1U << 4)
 #define GICR_TYPER_RVPEID		(1U << 7)
@@ -686,6 +687,7 @@ struct rdists {
 	bool			has_vlpis;
 	bool			has_rvpeid;
 	bool			has_direct_lpi;
+	bool			has_vpend_valid_dirty;
 };
 
 struct irq_domain;
diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h
index 2e7a1e032c71..3378bcbe585e 100644
--- a/include/linux/kmsg_dump.h
+++ b/include/linux/kmsg_dump.h
@@ -25,9 +25,8 @@ enum kmsg_dump_reason {
 	KMSG_DUMP_PANIC,
 	KMSG_DUMP_OOPS,
 	KMSG_DUMP_EMERG,
-	KMSG_DUMP_RESTART,
-	KMSG_DUMP_HALT,
-	KMSG_DUMP_POWEROFF,
+	KMSG_DUMP_SHUTDOWN,
+	KMSG_DUMP_MAX
 };
 
 /**
@@ -71,6 +70,8 @@ void kmsg_dump_rewind(struct kmsg_dumper *dumper);
 int kmsg_dump_register(struct kmsg_dumper *dumper);
 
 int kmsg_dump_unregister(struct kmsg_dumper *dumper);
+
+const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason);
 #else
 static inline void kmsg_dump(enum kmsg_dump_reason reason)
 {
@@ -112,6 +113,11 @@ static inline int kmsg_dump_unregister(struct kmsg_dumper *dumper)
 {
 	return -EINVAL;
 }
+
+static inline const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason)
+{
+	return "Disabled";
+}
 #endif
 
 #endif /* _LINUX_KMSG_DUMP_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 6d58beb65454..131cc1527d68 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -813,8 +813,11 @@ void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
 
 bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
+				 struct kvm_vcpu *except,
 				 unsigned long *vcpu_bitmap, cpumask_var_t tmp);
 bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
+bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
+				      struct kvm_vcpu *except);
 bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req,
 				unsigned long *vcpu_bitmap);
 
@@ -1048,7 +1051,7 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn)
 			start = slot + 1;
 	}
 
-	if (gfn >= memslots[start].base_gfn &&
+	if (start < slots->used_slots && gfn >= memslots[start].base_gfn &&
 	    gfn < memslots[start].base_gfn + memslots[start].npages) {
 		atomic_set(&slots->lru_slot, start);
 		return &memslots[start];
diff --git a/include/linux/linear_range.h b/include/linux/linear_range.h
new file mode 100644
index 000000000000..17b5943727d5
--- /dev/null
+++ b/include/linux/linear_range.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2020 ROHM Semiconductors */
+
+#ifndef LINEAR_RANGE_H
+#define LINEAR_RANGE_H
+
+#include <linux/types.h>
+
+/**
+ * struct linear_range - table of selector - value pairs
+ *
+ * Define a lookup-table for range of values. Intended to help when looking
+ * for a register value matching certaing physical measure (like voltage).
+ * Usable when increment of one in register always results a constant increment
+ * of the physical measure (like voltage).
+ *
+ * @min:  Lowest value in range
+ * @min_sel: Lowest selector for range
+ * @max_sel: Highest selector for range
+ * @step: Value step size
+ */
+struct linear_range {
+	unsigned int min;
+	unsigned int min_sel;
+	unsigned int max_sel;
+	unsigned int step;
+};
+
+unsigned int linear_range_values_in_range(const struct linear_range *r);
+unsigned int linear_range_values_in_range_array(const struct linear_range *r,
+						int ranges);
+unsigned int linear_range_get_max_value(const struct linear_range *r);
+
+int linear_range_get_value(const struct linear_range *r, unsigned int selector,
+			   unsigned int *val);
+int linear_range_get_value_array(const struct linear_range *r, int ranges,
+				 unsigned int selector, unsigned int *val);
+int linear_range_get_selector_low(const struct linear_range *r,
+				  unsigned int val, unsigned int *selector,
+				  bool *found);
+int linear_range_get_selector_high(const struct linear_range *r,
+				   unsigned int val, unsigned int *selector,
+				   bool *found);
+int linear_range_get_selector_low_array(const struct linear_range *r,
+					int ranges, unsigned int val,
+					unsigned int *selector, bool *found);
+
+#endif
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index 9280209d1f62..d796ec20d114 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -105,7 +105,7 @@
 
 /* === DEPRECATED annotations === */
 
-#ifndef CONFIG_X86
+#ifndef CONFIG_ARCH_USE_SYM_ANNOTATIONS
 #ifndef GLOBAL
 /* deprecated, use SYM_DATA*, SYM_ENTRY, or similar */
 #define GLOBAL(name) \
@@ -118,10 +118,10 @@
 #define ENTRY(name) \
 	SYM_FUNC_START(name)
 #endif
-#endif /* CONFIG_X86 */
+#endif /* CONFIG_ARCH_USE_SYM_ANNOTATIONS */
 #endif /* LINKER_SCRIPT */
 
-#ifndef CONFIG_X86
+#ifndef CONFIG_ARCH_USE_SYM_ANNOTATIONS
 #ifndef WEAK
 /* deprecated, use SYM_FUNC_START_WEAK* */
 #define WEAK(name)	   \
@@ -143,7 +143,7 @@
 #define ENDPROC(name) \
 	SYM_FUNC_END(name)
 #endif
-#endif /* CONFIG_X86 */
+#endif /* CONFIG_ARCH_USE_SYM_ANNOTATIONS */
 
 /* === generic annotations === */
 
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index d5ceb2839a2d..9dcaa3e582c9 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -34,7 +34,7 @@ struct list_lru_one {
 struct list_lru_memcg {
 	struct rcu_head		rcu;
 	/* array of per cgroup lists, indexed by memcg_cache_id */
-	struct list_lru_one	*lru[0];
+	struct list_lru_one	*lru[];
 };
 
 struct list_lru_node {
diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h
new file mode 100644
index 000000000000..e55010fa7329
--- /dev/null
+++ b/include/linux/local_lock.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_LOCAL_LOCK_H
+#define _LINUX_LOCAL_LOCK_H
+
+#include <linux/local_lock_internal.h>
+
+/**
+ * local_lock_init - Runtime initialize a lock instance
+ */
+#define local_lock_init(lock)		__local_lock_init(lock)
+
+/**
+ * local_lock - Acquire a per CPU local lock
+ * @lock:	The lock variable
+ */
+#define local_lock(lock)		__local_lock(lock)
+
+/**
+ * local_lock_irq - Acquire a per CPU local lock and disable interrupts
+ * @lock:	The lock variable
+ */
+#define local_lock_irq(lock)		__local_lock_irq(lock)
+
+/**
+ * local_lock_irqsave - Acquire a per CPU local lock, save and disable
+ *			 interrupts
+ * @lock:	The lock variable
+ * @flags:	Storage for interrupt flags
+ */
+#define local_lock_irqsave(lock, flags)				\
+	__local_lock_irqsave(lock, flags)
+
+/**
+ * local_unlock - Release a per CPU local lock
+ * @lock:	The lock variable
+ */
+#define local_unlock(lock)		__local_unlock(lock)
+
+/**
+ * local_unlock_irq - Release a per CPU local lock and enable interrupts
+ * @lock:	The lock variable
+ */
+#define local_unlock_irq(lock)		__local_unlock_irq(lock)
+
+/**
+ * local_unlock_irqrestore - Release a per CPU local lock and restore
+ *			      interrupt flags
+ * @lock:	The lock variable
+ * @flags:      Interrupt flags to restore
+ */
+#define local_unlock_irqrestore(lock, flags)			\
+	__local_unlock_irqrestore(lock, flags)
+
+#endif
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
new file mode 100644
index 000000000000..4a8795b21d77
--- /dev/null
+++ b/include/linux/local_lock_internal.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_LOCAL_LOCK_H
+# error "Do not include directly, include linux/local_lock.h"
+#endif
+
+#include <linux/percpu-defs.h>
+#include <linux/lockdep.h>
+
+typedef struct {
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+	struct task_struct	*owner;
+#endif
+} local_lock_t;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define LL_DEP_MAP_INIT(lockname)			\
+	.dep_map = {					\
+		.name = #lockname,			\
+		.wait_type_inner = LD_WAIT_CONFIG,	\
+	}
+#else
+# define LL_DEP_MAP_INIT(lockname)
+#endif
+
+#define INIT_LOCAL_LOCK(lockname)	{ LL_DEP_MAP_INIT(lockname) }
+
+#define __local_lock_init(lock)					\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
+	lockdep_init_map_wait(&(lock)->dep_map, #lock, &__key, 0, LD_WAIT_CONFIG);\
+} while (0)
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static inline void local_lock_acquire(local_lock_t *l)
+{
+	lock_map_acquire(&l->dep_map);
+	DEBUG_LOCKS_WARN_ON(l->owner);
+	l->owner = current;
+}
+
+static inline void local_lock_release(local_lock_t *l)
+{
+	DEBUG_LOCKS_WARN_ON(l->owner != current);
+	l->owner = NULL;
+	lock_map_release(&l->dep_map);
+}
+
+#else /* CONFIG_DEBUG_LOCK_ALLOC */
+static inline void local_lock_acquire(local_lock_t *l) { }
+static inline void local_lock_release(local_lock_t *l) { }
+#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
+
+#define __local_lock(lock)					\
+	do {							\
+		preempt_disable();				\
+		local_lock_acquire(this_cpu_ptr(lock));		\
+	} while (0)
+
+#define __local_lock_irq(lock)					\
+	do {							\
+		local_irq_disable();				\
+		local_lock_acquire(this_cpu_ptr(lock));		\
+	} while (0)
+
+#define __local_lock_irqsave(lock, flags)			\
+	do {							\
+		local_irq_save(flags);				\
+		local_lock_acquire(this_cpu_ptr(lock));		\
+	} while (0)
+
+#define __local_unlock(lock)					\
+	do {							\
+		local_lock_release(this_cpu_ptr(lock));		\
+		preempt_enable();				\
+	} while (0)
+
+#define __local_unlock_irq(lock)				\
+	do {							\
+		local_lock_release(this_cpu_ptr(lock));		\
+		local_irq_enable();				\
+	} while (0)
+
+#define __local_unlock_irqrestore(lock, flags)			\
+	do {							\
+		local_lock_release(this_cpu_ptr(lock));		\
+		local_irq_restore(flags);			\
+	} while (0)
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 206774ac6946..8fce5c98a4b0 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -308,8 +308,27 @@ extern void lockdep_set_selftest_task(struct task_struct *task);
 
 extern void lockdep_init_task(struct task_struct *task);
 
-extern void lockdep_off(void);
-extern void lockdep_on(void);
+/*
+ * Split the recrursion counter in two to readily detect 'off' vs recursion.
+ */
+#define LOCKDEP_RECURSION_BITS	16
+#define LOCKDEP_OFF		(1U << LOCKDEP_RECURSION_BITS)
+#define LOCKDEP_RECURSION_MASK	(LOCKDEP_OFF - 1)
+
+/*
+ * lockdep_{off,on}() are macros to avoid tracing and kprobes; not inlines due
+ * to header dependencies.
+ */
+
+#define lockdep_off()					\
+do {							\
+	current->lockdep_recursion += LOCKDEP_OFF;	\
+} while (0)
+
+#define lockdep_on()					\
+do {							\
+	current->lockdep_recursion -= LOCKDEP_OFF;	\
+} while (0)
 
 extern void lockdep_register_key(struct lock_class_key *key);
 extern void lockdep_unregister_key(struct lock_class_key *key);
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 9cd4455528e5..5616b2567aa7 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -55,7 +55,7 @@ LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm)
 LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm)
 LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc,
 	 struct fs_context *src_sc)
-LSM_HOOK(int, 0, fs_context_parse_param, struct fs_context *fc,
+LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc,
 	 struct fs_parameter *param)
 LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb)
 LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb)
@@ -243,7 +243,7 @@ LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, char *name,
 	 char **value)
 LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size)
 LSM_HOOK(int, 0, ismaclabel, const char *name)
-LSM_HOOK(int, 0, secid_to_secctx, u32 secid, char **secdata,
+LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata,
 	 u32 *seclen)
 LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid)
 LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1b4150ff64be..977edd3b7bd8 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -106,7 +106,7 @@ struct lruvec_stat {
  */
 struct memcg_shrinker_map {
 	struct rcu_head rcu;
-	unsigned long map[0];
+	unsigned long map[];
 };
 
 /*
@@ -148,7 +148,7 @@ struct mem_cgroup_threshold_ary {
 	/* Size of entries[] */
 	unsigned int size;
 	/* Array of thresholds */
-	struct mem_cgroup_threshold entries[0];
+	struct mem_cgroup_threshold entries[];
 };
 
 struct mem_cgroup_thresholds {
@@ -783,6 +783,8 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg,
 		atomic_long_inc(&memcg->memory_events[event]);
 		cgroup_file_notify(&memcg->events_file);
 
+		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+			break;
 		if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
 			break;
 	} while ((memcg = parent_mem_cgroup(memcg)) &&
diff --git a/include/linux/mfd/gsc.h b/include/linux/mfd/gsc.h
new file mode 100644
index 000000000000..6bd639c285b4
--- /dev/null
+++ b/include/linux/mfd/gsc.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (C) 2020 Gateworks Corporation
+ */
+#ifndef __LINUX_MFD_GSC_H_
+#define __LINUX_MFD_GSC_H_
+
+#include <linux/regmap.h>
+
+/* Device Addresses */
+#define GSC_MISC	0x20
+#define GSC_UPDATE	0x21
+#define GSC_GPIO	0x23
+#define GSC_HWMON	0x29
+#define GSC_EEPROM0	0x50
+#define GSC_EEPROM1	0x51
+#define GSC_EEPROM2	0x52
+#define GSC_EEPROM3	0x53
+#define GSC_RTC		0x68
+
+/* Register offsets */
+enum {
+	GSC_CTRL_0	= 0x00,
+	GSC_CTRL_1	= 0x01,
+	GSC_TIME	= 0x02,
+	GSC_TIME_ADD	= 0x06,
+	GSC_IRQ_STATUS	= 0x0A,
+	GSC_IRQ_ENABLE	= 0x0B,
+	GSC_FW_CRC	= 0x0C,
+	GSC_FW_VER	= 0x0E,
+	GSC_WP		= 0x0F,
+};
+
+/* Bit definitions */
+#define GSC_CTRL_0_PB_HARD_RESET	0
+#define GSC_CTRL_0_PB_CLEAR_SECURE_KEY	1
+#define GSC_CTRL_0_PB_SOFT_POWER_DOWN	2
+#define GSC_CTRL_0_PB_BOOT_ALTERNATE	3
+#define GSC_CTRL_0_PERFORM_CRC		4
+#define GSC_CTRL_0_TAMPER_DETECT	5
+#define GSC_CTRL_0_SWITCH_HOLD		6
+
+#define GSC_CTRL_1_SLEEP_ENABLE		0
+#define GSC_CTRL_1_SLEEP_ACTIVATE	1
+#define GSC_CTRL_1_SLEEP_ADD		2
+#define GSC_CTRL_1_SLEEP_NOWAKEPB	3
+#define GSC_CTRL_1_WDT_TIME		4
+#define GSC_CTRL_1_WDT_ENABLE		5
+#define GSC_CTRL_1_SWITCH_BOOT_ENABLE	6
+#define GSC_CTRL_1_SWITCH_BOOT_CLEAR	7
+
+#define GSC_IRQ_PB			0
+#define GSC_IRQ_KEY_ERASED		1
+#define GSC_IRQ_EEPROM_WP		2
+#define GSC_IRQ_RESV			3
+#define GSC_IRQ_GPIO			4
+#define GSC_IRQ_TAMPER			5
+#define GSC_IRQ_WDT_TIMEOUT		6
+#define GSC_IRQ_SWITCH_HOLD		7
+
+int gsc_read(void *context, unsigned int reg, unsigned int *val);
+int gsc_write(void *context, unsigned int reg, unsigned int val);
+
+struct gsc_dev {
+	struct device *dev;
+
+	struct i2c_client *i2c;		/* 0x20: interrupt controller, WDT */
+	struct i2c_client *i2c_hwmon;	/* 0x29: hwmon, fan controller */
+
+	struct regmap *regmap;
+
+	unsigned int fwver;
+	unsigned short fwcrc;
+};
+
+#endif /* __LINUX_MFD_GSC_H_ */
diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h
index 061af220dcd3..79c020bd0c70 100644
--- a/include/linux/mfd/max8998.h
+++ b/include/linux/mfd/max8998.h
@@ -39,6 +39,7 @@ enum {
 	MAX8998_ENVICHG,
 	MAX8998_ESAFEOUT1,
 	MAX8998_ESAFEOUT2,
+	MAX8998_CHARGER,
 };
 
 /**
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index ad1996001965..3d7c3c26eeb9 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -53,9 +53,9 @@ enum mhi_callback {
  * @MHI_CHAIN: Linked transfer
  */
 enum mhi_flags {
-	MHI_EOB,
-	MHI_EOT,
-	MHI_CHAIN,
+	MHI_EOB = BIT(0),
+	MHI_EOT = BIT(1),
+	MHI_CHAIN = BIT(2),
 };
 
 /**
@@ -335,14 +335,15 @@ struct mhi_controller_config {
  * @syserr_worker: System error worker
  * @state_event: State change event
  * @status_cb: CB function to notify power states of the device (required)
- * @link_status: CB function to query link status of the device (required)
  * @wake_get: CB function to assert device wake (optional)
  * @wake_put: CB function to de-assert device wake (optional)
  * @wake_toggle: CB function to assert and de-assert device wake (optional)
  * @runtime_get: CB function to controller runtime resume (required)
- * @runtimet_put: CB function to decrement pm usage (required)
+ * @runtime_put: CB function to decrement pm usage (required)
  * @map_single: CB function to create TRE buffer
  * @unmap_single: CB function to destroy TRE buffer
+ * @read_reg: Read a MHI register via the physical link (required)
+ * @write_reg: Write a MHI register via the physical link (required)
  * @buffer_len: Bounce buffer length
  * @bounce_buf: Use of bounce buffer
  * @fbc_download: MHI host needs to do complete image transfer (optional)
@@ -417,7 +418,6 @@ struct mhi_controller {
 
 	void (*status_cb)(struct mhi_controller *mhi_cntrl,
 			  enum mhi_callback cb);
-	int (*link_status)(struct mhi_controller *mhi_cntrl);
 	void (*wake_get)(struct mhi_controller *mhi_cntrl, bool override);
 	void (*wake_put)(struct mhi_controller *mhi_cntrl, bool override);
 	void (*wake_toggle)(struct mhi_controller *mhi_cntrl);
@@ -427,6 +427,10 @@ struct mhi_controller {
 			  struct mhi_buf_info *buf);
 	void (*unmap_single)(struct mhi_controller *mhi_cntrl,
 			     struct mhi_buf_info *buf);
+	int (*read_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr,
+			u32 *out);
+	void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr,
+			  u32 val);
 
 	size_t buffer_len;
 	bool bounce_buf;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6f8f79ef829b..8397b6558dc7 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -213,6 +213,12 @@ enum mlx5_port_status {
 	MLX5_PORT_DOWN      = 2,
 };
 
+enum mlx5_cmdif_state {
+	MLX5_CMDIF_STATE_UNINITIALIZED,
+	MLX5_CMDIF_STATE_UP,
+	MLX5_CMDIF_STATE_DOWN,
+};
+
 struct mlx5_cmd_first {
 	__be32		data[4];
 };
@@ -258,6 +264,7 @@ struct mlx5_cmd_stats {
 struct mlx5_cmd {
 	struct mlx5_nb    nb;
 
+	enum mlx5_cmdif_state	state;
 	void	       *cmd_alloc_buf;
 	dma_addr_t	alloc_dma;
 	int		alloc_size;
@@ -284,6 +291,7 @@ struct mlx5_cmd {
 	struct semaphore sem;
 	struct semaphore pages_sem;
 	int	mode;
+	u16     allowed_opcode;
 	struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS];
 	struct dma_pool *pool;
 	struct mlx5_cmd_debug dbg;
@@ -743,6 +751,7 @@ struct mlx5_cmd_work_ent {
 	struct delayed_work	cb_timeout_work;
 	void		       *context;
 	int			idx;
+	struct completion	handling;
 	struct completion	done;
 	struct mlx5_cmd        *cmd;
 	struct work_struct	work;
@@ -874,10 +883,17 @@ mlx5_frag_buf_get_idx_last_contig_stride(struct mlx5_frag_buf_ctrl *fbc, u32 ix)
 	return min_t(u32, last_frag_stride_idx - fbc->strides_offset, fbc->sz_m1);
 }
 
+enum {
+	CMD_ALLOWED_OPCODE_ALL,
+};
+
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
+void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
+			enum mlx5_cmdif_state cmdif_state);
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
+void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode);
 
 struct mlx5_async_ctx {
 	struct mlx5_core_dev *dev;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1f2850465f59..3468dbb2cad1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -325,17 +325,13 @@ extern unsigned int kobjsize(const void *objp);
 #elif defined(CONFIG_SPARC64)
 # define VM_SPARC_ADI	VM_ARCH_1	/* Uses ADI tag for access control */
 # define VM_ARCH_CLEAR	VM_SPARC_ADI
+#elif defined(CONFIG_ARM64)
+# define VM_ARM64_BTI	VM_ARCH_1	/* BTI guarded page, a.k.a. GP bit */
+# define VM_ARCH_CLEAR	VM_ARM64_BTI
 #elif !defined(CONFIG_MMU)
 # define VM_MAPPED_COPY	VM_ARCH_1	/* T if mapped copy of data (nommu mmap) */
 #endif
 
-#if defined(CONFIG_X86_INTEL_MPX)
-/* MPX specific bounds table or bounds directory */
-# define VM_MPX		VM_HIGH_ARCH_4
-#else
-# define VM_MPX		VM_NONE
-#endif
-
 #ifndef VM_GROWSUP
 # define VM_GROWSUP	VM_NONE
 #endif
@@ -782,6 +778,11 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags)
 
 extern void kvfree(const void *addr);
 
+/*
+ * Mapcount of compound page as a whole, does not include mapped sub-pages.
+ *
+ * Must be called only for compound pages or any their tail sub-pages.
+ */
 static inline int compound_mapcount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
@@ -801,10 +802,16 @@ static inline void page_mapcount_reset(struct page *page)
 
 int __page_mapcount(struct page *page);
 
+/*
+ * Mapcount of 0-order page; when compound sub-page, includes
+ * compound_mapcount().
+ *
+ * Result is undefined for pages which cannot be mapped into userspace.
+ * For example SLAB or special types of pages. See function page_has_type().
+ * They use this place in struct page differently.
+ */
 static inline int page_mapcount(struct page *page)
 {
-	VM_BUG_ON_PAGE(PageSlab(page), page);
-
 	if (unlikely(PageCompound(page)))
 		return __page_mapcount(page);
 	return atomic_read(&page->_mapcount) + 1;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 1b9de7d220fb..acffc3bc6178 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -156,6 +156,9 @@ enum zone_stat_item {
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_KERNEL_STACK_KB,	/* measured in KiB */
+#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
+	NR_KERNEL_SCS_KB,	/* measured in KiB */
+#endif
 	/* Second 128 byte cacheline */
 	NR_BOUNCE,
 #if IS_ENABLED(CONFIG_ZSMALLOC)
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 4c2ddd0941a7..0754b8d71262 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -663,6 +663,7 @@ struct x86_cpu_id {
 	__u16 vendor;
 	__u16 family;
 	__u16 model;
+	__u16 steppings;
 	__u16 feature;	/* bit index */
 	kernel_ulong_t driver_data;
 };
@@ -671,6 +672,7 @@ struct x86_cpu_id {
 #define X86_VENDOR_ANY 0xffff
 #define X86_FAMILY_ANY 0
 #define X86_MODEL_ANY  0
+#define X86_STEPPING_ANY 0
 #define X86_FEATURE_ANY 0	/* Same as FPU, you can't test for that */
 
 /*
diff --git a/include/linux/module.h b/include/linux/module.h
index 1ad393e62bef..d849d06e4d44 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -458,6 +458,8 @@ struct module {
 	void __percpu *percpu;
 	unsigned int percpu_size;
 #endif
+	void *noinstr_text_start;
+	unsigned int noinstr_text_size;
 
 #ifdef CONFIG_TRACEPOINTS
 	unsigned int num_tracepoints;
@@ -489,6 +491,12 @@ struct module {
 	unsigned int num_ftrace_callsites;
 	unsigned long *ftrace_callsites;
 #endif
+#ifdef CONFIG_KPROBES
+	void *kprobes_text_start;
+	unsigned int kprobes_text_size;
+	unsigned long *kprobe_blacklist;
+	unsigned int num_kprobe_blacklist;
+#endif
 
 #ifdef CONFIG_LIVEPATCH
 	bool klp; /* Is this a livepatch module? */
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index ca92aea8a6bd..4fa67a8b2265 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -29,6 +29,11 @@ void *module_alloc(unsigned long size);
 /* Free memory returned from module_alloc. */
 void module_memfree(void *module_region);
 
+/* Determines if the section name is an init section (that is only used during
+ * module loading).
+ */
+bool module_init_section(const char *name);
+
 /* Determines if the section name is an exit section (that is only used during
  * module unloading)
  */
diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h
index fcc409de31a4..a28aa289afdc 100644
--- a/include/linux/netfilter/nf_conntrack_pptp.h
+++ b/include/linux/netfilter/nf_conntrack_pptp.h
@@ -10,7 +10,7 @@
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <uapi/linux/netfilter/nf_conntrack_tuple_common.h>
 
-extern const char *const pptp_msg_name[];
+const char *pptp_msg_name(u_int16_t msg);
 
 /* state of the control session */
 enum pptp_ctrlsess_state {
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 440230488025..e5f3e7d8d3d5 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1317,11 +1317,13 @@ struct nfs41_impl_id {
 	struct nfstime4			date;
 };
 
+#define MAX_BIND_CONN_TO_SESSION_RETRIES 3
 struct nfs41_bind_conn_to_session_args {
 	struct nfs_client		*client;
 	struct nfs4_sessionid		sessionid;
 	u32				dir;
 	bool				use_conn_in_rdma_mode;
+	int				retries;
 };
 
 struct nfs41_bind_conn_to_session_res {
diff --git a/include/linux/padata.h b/include/linux/padata.h
index a0d8b41850b2..693cae9bfe66 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -139,7 +139,8 @@ struct padata_shell {
 /**
  * struct padata_instance - The overall control structure.
  *
- * @node: Used by CPU hotplug.
+ * @cpu_online_node: Linkage for CPU online callback.
+ * @cpu_dead_node: Linkage for CPU offline callback.
  * @parallel_wq: The workqueue used for parallel work.
  * @serial_wq: The workqueue used for serial work.
  * @pslist: List of padata_shell objects attached to this instance.
@@ -150,7 +151,8 @@ struct padata_shell {
  * @flags: padata flags.
  */
 struct padata_instance {
-	struct hlist_node		 node;
+	struct hlist_node		cpu_online_node;
+	struct hlist_node		cpu_dead_node;
 	struct workqueue_struct		*parallel_wq;
 	struct workqueue_struct		*serial_wq;
 	struct list_head		pslist;
diff --git a/include/linux/parser.h b/include/linux/parser.h
index 12fc3482f5fc..89e2b23fb888 100644
--- a/include/linux/parser.h
+++ b/include/linux/parser.h
@@ -7,7 +7,8 @@
  * but could potentially be used anywhere else that simple option=arg
  * parsing is required.
  */
-
+#ifndef _LINUX_PARSER_H
+#define _LINUX_PARSER_H
 
 /* associates an integer enumerator with a pattern string. */
 struct match_token {
@@ -34,3 +35,5 @@ int match_hex(substring_t *, int *result);
 bool match_wildcard(const char *pattern, const char *str);
 size_t match_strlcpy(char *, const substring_t *, size_t);
 char *match_strdup(const substring_t *);
+
+#endif /* _LINUX_PARSER_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 9c3e7619c929..d7b610c4eebd 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -61,7 +61,7 @@ struct perf_guest_info_callbacks {
 
 struct perf_callchain_entry {
 	__u64				nr;
-	__u64				ip[0]; /* /proc/sys/kernel/perf_event_max_stack */
+	__u64				ip[]; /* /proc/sys/kernel/perf_event_max_stack */
 };
 
 struct perf_callchain_entry_ctx {
@@ -113,7 +113,7 @@ struct perf_raw_record {
 struct perf_branch_stack {
 	__u64				nr;
 	__u64				hw_idx;
-	struct perf_branch_entry	entries[0];
+	struct perf_branch_entry	entries[];
 };
 
 struct task_struct;
@@ -1305,7 +1305,7 @@ static inline int perf_is_paranoid(void)
 
 static inline int perf_allow_kernel(struct perf_event_attr *attr)
 {
-	if (sysctl_perf_event_paranoid > 1 && !capable(CAP_SYS_ADMIN))
+	if (sysctl_perf_event_paranoid > 1 && !perfmon_capable())
 		return -EACCES;
 
 	return security_perf_event_open(attr, PERF_SECURITY_KERNEL);
@@ -1313,7 +1313,7 @@ static inline int perf_allow_kernel(struct perf_event_attr *attr)
 
 static inline int perf_allow_cpu(struct perf_event_attr *attr)
 {
-	if (sysctl_perf_event_paranoid > 0 && !capable(CAP_SYS_ADMIN))
+	if (sysctl_perf_event_paranoid > 0 && !perfmon_capable())
 		return -EACCES;
 
 	return security_perf_event_open(attr, PERF_SECURITY_CPU);
@@ -1321,7 +1321,7 @@ static inline int perf_allow_cpu(struct perf_event_attr *attr)
 
 static inline int perf_allow_tracepoint(struct perf_event_attr *attr)
 {
-	if (sysctl_perf_event_paranoid > -1 && !capable(CAP_SYS_ADMIN))
+	if (sysctl_perf_event_paranoid > -1 && !perfmon_capable())
 		return -EPERM;
 
 	return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT);
diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h
index c588be843f61..0ecce6aa69d5 100644
--- a/include/linux/platform_data/cros_ec_sensorhub.h
+++ b/include/linux/platform_data/cros_ec_sensorhub.h
@@ -185,6 +185,7 @@ int cros_ec_sensorhub_register_push_data(struct cros_ec_sensorhub *sensorhub,
 void cros_ec_sensorhub_unregister_push_data(struct cros_ec_sensorhub *sensorhub,
 					    u8 sensor_num);
 
+int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub);
 int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub);
 void cros_ec_sensorhub_ring_remove(void *arg);
 int cros_ec_sensorhub_ring_fifo_enable(struct cros_ec_sensorhub *sensorhub,
diff --git a/include/linux/platform_data/gsc_hwmon.h b/include/linux/platform_data/gsc_hwmon.h
new file mode 100644
index 000000000000..ec1611aff863
--- /dev/null
+++ b/include/linux/platform_data/gsc_hwmon.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _GSC_HWMON_H
+#define _GSC_HWMON_H
+
+enum gsc_hwmon_mode {
+	mode_temperature,
+	mode_voltage,
+	mode_voltage_raw,
+	mode_max,
+};
+
+/**
+ * struct gsc_hwmon_channel - configuration parameters
+ * @reg:  I2C register offset
+ * @mode: channel mode
+ * @name: channel name
+ * @mvoffset: voltage offset
+ * @vdiv: voltage divider array (2 resistor values in milli-ohms)
+ */
+struct gsc_hwmon_channel {
+	unsigned int reg;
+	unsigned int mode;
+	const char *name;
+	unsigned int mvoffset;
+	unsigned int vdiv[2];
+};
+
+/**
+ * struct gsc_hwmon_platform_data - platform data for gsc_hwmon driver
+ * @channels:	pointer to array of gsc_hwmon_channel structures
+ *		describing channels
+ * @nchannels:	number of elements in @channels array
+ * @vreference: voltage reference (mV)
+ * @resolution: ADC bit resolution
+ * @fan_base: register base for FAN controller
+ */
+struct gsc_hwmon_platform_data {
+	const struct gsc_hwmon_channel *channels;
+	int nchannels;
+	unsigned int resolution;
+	unsigned int vreference;
+	unsigned int fan_base;
+};
+#endif
diff --git a/include/linux/platform_data/wilco-ec.h b/include/linux/platform_data/wilco-ec.h
index 25f46a939637..3e268e636b5b 100644
--- a/include/linux/platform_data/wilco-ec.h
+++ b/include/linux/platform_data/wilco-ec.h
@@ -83,7 +83,7 @@ struct wilco_ec_response {
 	u16 result;
 	u16 data_size;
 	u8 reserved[2];
-	u8 data[0];
+	u8 data[];
 } __packed;
 
 /**
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index bdc35753ef7c..77a2aada106d 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -25,6 +25,7 @@ struct platform_device {
 	bool		id_auto;
 	struct device	dev;
 	u64		platform_dma_mask;
+	struct device_dma_parameters dma_parms;
 	u32		num_resources;
 	struct resource	*resource;
 
diff --git a/include/linux/pnp.h b/include/linux/pnp.h
index b18dca67253d..c2a7cfbca713 100644
--- a/include/linux/pnp.h
+++ b/include/linux/pnp.h
@@ -220,10 +220,8 @@ struct pnp_card {
 #define global_to_pnp_card(n) list_entry(n, struct pnp_card, global_list)
 #define protocol_to_pnp_card(n) list_entry(n, struct pnp_card, protocol_list)
 #define to_pnp_card(n) container_of(n, struct pnp_card, dev)
-#define pnp_for_each_card(card) \
-	for((card) = global_to_pnp_card(pnp_cards.next); \
-	(card) != global_to_pnp_card(&pnp_cards); \
-	(card) = global_to_pnp_card((card)->global_list.next))
+#define pnp_for_each_card(card)	\
+	list_for_each_entry(card, &pnp_cards, global_list)
 
 struct pnp_card_link {
 	struct pnp_card *card;
@@ -276,14 +274,9 @@ struct pnp_dev {
 #define card_to_pnp_dev(n) list_entry(n, struct pnp_dev, card_list)
 #define protocol_to_pnp_dev(n) list_entry(n, struct pnp_dev, protocol_list)
 #define	to_pnp_dev(n) container_of(n, struct pnp_dev, dev)
-#define pnp_for_each_dev(dev) \
-	for((dev) = global_to_pnp_dev(pnp_global.next); \
-	(dev) != global_to_pnp_dev(&pnp_global); \
-	(dev) = global_to_pnp_dev((dev)->global_list.next))
-#define card_for_each_dev(card,dev) \
-	for((dev) = card_to_pnp_dev((card)->devices.next); \
-	(dev) != card_to_pnp_dev(&(card)->devices); \
-	(dev) = card_to_pnp_dev((dev)->card_list.next))
+#define pnp_for_each_dev(dev) list_for_each_entry(dev, &pnp_global, global_list)
+#define card_for_each_dev(card, dev)	\
+	list_for_each_entry(dev, &(card)->devices, card_list)
 #define pnp_dev_name(dev) (dev)->name
 
 static inline void *pnp_get_drvdata(struct pnp_dev *pdev)
@@ -437,14 +430,10 @@ struct pnp_protocol {
 };
 
 #define to_pnp_protocol(n) list_entry(n, struct pnp_protocol, protocol_list)
-#define protocol_for_each_card(protocol,card) \
-	for((card) = protocol_to_pnp_card((protocol)->cards.next); \
-	(card) != protocol_to_pnp_card(&(protocol)->cards); \
-	(card) = protocol_to_pnp_card((card)->protocol_list.next))
-#define protocol_for_each_dev(protocol,dev) \
-	for((dev) = protocol_to_pnp_dev((protocol)->devices.next); \
-	(dev) != protocol_to_pnp_dev(&(protocol)->devices); \
-	(dev) = protocol_to_pnp_dev((dev)->protocol_list.next))
+#define protocol_for_each_card(protocol, card)	\
+	list_for_each_entry(card, &(protocol)->cards, protocol_list)
+#define protocol_for_each_dev(protocol, dev)	\
+	list_for_each_entry(dev, &(protocol)->devices, protocol_list)
 
 extern struct bus_type pnp_bus_type;
 
diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h
index 540595a321a7..90797f1b421d 100644
--- a/include/linux/posix_acl.h
+++ b/include/linux/posix_acl.h
@@ -28,7 +28,7 @@ struct posix_acl {
 	refcount_t		a_refcount;
 	struct rcu_head		a_rcu;
 	unsigned int		a_count;
-	struct posix_acl_entry	a_entries[0];
+	struct posix_acl_entry	a_entries[];
 };
 
 #define FOREACH_ACL_ENTRY(pa, acl, pe) \
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index bc3f1aecaa19..7d9c1c0e149c 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -26,13 +26,13 @@
  *         PREEMPT_MASK:	0x000000ff
  *         SOFTIRQ_MASK:	0x0000ff00
  *         HARDIRQ_MASK:	0x000f0000
- *             NMI_MASK:	0x00100000
+ *             NMI_MASK:	0x00f00000
  * PREEMPT_NEED_RESCHED:	0x80000000
  */
 #define PREEMPT_BITS	8
 #define SOFTIRQ_BITS	8
 #define HARDIRQ_BITS	4
-#define NMI_BITS	1
+#define NMI_BITS	4
 
 #define PREEMPT_SHIFT	0
 #define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
diff --git a/include/linux/printk.h b/include/linux/printk.h
index ccea5d4a509e..15c8133b194f 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -472,8 +472,7 @@ extern int kptr_restrict;
 	printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_info_once(fmt, ...)					\
 	printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_cont_once(fmt, ...)					\
-	printk_once(KERN_CONT pr_fmt(fmt), ##__VA_ARGS__)
+/* no pr_cont_once, don't do that... */
 
 #if defined(DEBUG)
 #define pr_devel_once(fmt, ...)					\
diff --git a/include/linux/psci.h b/include/linux/psci.h
index a67712b73b6c..14ad9b9ebcd6 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -21,11 +21,6 @@ bool psci_power_state_is_valid(u32 state);
 int psci_set_osi_mode(void);
 bool psci_has_osi_support(void);
 
-enum smccc_version {
-	SMCCC_VERSION_1_0,
-	SMCCC_VERSION_1_1,
-};
-
 struct psci_operations {
 	u32 (*get_version)(void);
 	int (*cpu_suspend)(u32 state, unsigned long entry_point);
@@ -35,8 +30,6 @@ struct psci_operations {
 	int (*affinity_info)(unsigned long target_affinity,
 			unsigned long lowest_affinity_level);
 	int (*migrate_info_type)(void);
-	enum arm_smccc_conduit conduit;
-	enum smccc_version smccc_version;
 };
 
 extern struct psci_operations psci_ops;
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 5167bf2bfc75..7fbc8679145c 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -100,6 +100,8 @@ struct sev_data_init {
 	u32 tmr_len;			/* In */
 } __packed;
 
+#define SEV_INIT_FLAGS_SEV_ES	0x01
+
 /**
  * struct sev_data_pek_csr - PEK_CSR command parameters
  *
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index e779441e6d26..eb93a54cff31 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -96,6 +96,12 @@ struct pstore_record {
  *
  * @read_mutex:	serializes @open, @read, @close, and @erase callbacks
  * @flags:	bitfield of frontends the backend can accept writes for
+ * @max_reason:	Used when PSTORE_FLAGS_DMESG is set. Contains the
+ *		kmsg_dump_reason enum value. KMSG_DUMP_UNDEF means
+ *		"use existing kmsg_dump() filtering, based on the
+ *		printk.always_kmsg_dump boot param" (which is either
+ *		KMSG_DUMP_OOPS when false, or KMSG_DUMP_MAX when
+ *		true); see printk.always_kmsg_dump for more details.
  * @data:	backend-private pointer passed back during callbacks
  *
  * Callbacks:
@@ -170,7 +176,7 @@ struct pstore_record {
  */
 struct pstore_info {
 	struct module	*owner;
-	char		*name;
+	const char	*name;
 
 	struct semaphore buf_lock;
 	char		*buf;
@@ -179,6 +185,7 @@ struct pstore_info {
 	struct mutex	read_mutex;
 
 	int		flags;
+	int		max_reason;
 	void		*data;
 
 	int		(*open)(struct pstore_info *psi);
diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h
new file mode 100644
index 000000000000..61e914522b01
--- /dev/null
+++ b/include/linux/pstore_blk.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __PSTORE_BLK_H_
+#define __PSTORE_BLK_H_
+
+#include <linux/types.h>
+#include <linux/pstore.h>
+#include <linux/pstore_zone.h>
+
+/**
+ * typedef pstore_blk_panic_write_op - panic write operation to block device
+ *
+ * @buf: the data to write
+ * @start_sect: start sector to block device
+ * @sects: sectors count on buf
+ *
+ * Return: On success, zero should be returned. Others excluding -ENOMSG
+ * mean error. -ENOMSG means to try next zone.
+ *
+ * Panic write to block device must be aligned to SECTOR_SIZE.
+ */
+typedef int (*pstore_blk_panic_write_op)(const char *buf, sector_t start_sect,
+		sector_t sects);
+
+/**
+ * struct pstore_blk_info - pstore/blk registration details
+ *
+ * @major:	Which major device number to support with pstore/blk
+ * @flags:	The supported PSTORE_FLAGS_* from linux/pstore.h.
+ * @panic_write:The write operation only used for the panic case.
+ *		This can be NULL, but is recommended to avoid losing
+ *		crash data if the kernel's IO path or work queues are
+ *		broken during a panic.
+ * @devt:	The dev_t that pstore/blk has attached to.
+ * @nr_sects:	Number of sectors on @devt.
+ * @start_sect:	Starting sector on @devt.
+ */
+struct pstore_blk_info {
+	unsigned int major;
+	unsigned int flags;
+	pstore_blk_panic_write_op panic_write;
+
+	/* Filled in by pstore/blk after registration. */
+	dev_t devt;
+	sector_t nr_sects;
+	sector_t start_sect;
+};
+
+int  register_pstore_blk(struct pstore_blk_info *info);
+void unregister_pstore_blk(unsigned int major);
+
+/**
+ * struct pstore_device_info - back-end pstore/blk driver structure.
+ *
+ * @total_size: The total size in bytes pstore/blk can use. It must be greater
+ *		than 4096 and be multiple of 4096.
+ * @flags:	Refer to macro starting with PSTORE_FLAGS defined in
+ *		linux/pstore.h. It means what front-ends this device support.
+ *		Zero means all backends for compatible.
+ * @read:	The general read operation. Both of the function parameters
+ *		@size and @offset are relative value to bock device (not the
+ *		whole disk).
+ *		On success, the number of bytes should be returned, others
+ *		means error.
+ * @write:	The same as @read, but the following error number:
+ *		-EBUSY means try to write again later.
+ *		-ENOMSG means to try next zone.
+ * @erase:	The general erase operation for device with special removing
+ *		job. Both of the function parameters @size and @offset are
+ *		relative value to storage.
+ *		Return 0 on success and others on failure.
+ * @panic_write:The write operation only used for panic case. It's optional
+ *		if you do not care panic log. The parameters are relative
+ *		value to storage.
+ *		On success, the number of bytes should be returned, others
+ *		excluding -ENOMSG mean error. -ENOMSG means to try next zone.
+ */
+struct pstore_device_info {
+	unsigned long total_size;
+	unsigned int flags;
+	pstore_zone_read_op read;
+	pstore_zone_write_op write;
+	pstore_zone_erase_op erase;
+	pstore_zone_write_op panic_write;
+};
+
+int  register_pstore_device(struct pstore_device_info *dev);
+void unregister_pstore_device(struct pstore_device_info *dev);
+
+/**
+ * struct pstore_blk_config - the pstore_blk backend configuration
+ *
+ * @device:		Name of the desired block device
+ * @max_reason:		Maximum kmsg dump reason to store to block device
+ * @kmsg_size:		Total size of for kmsg dumps
+ * @pmsg_size:		Total size of the pmsg storage area
+ * @console_size:	Total size of the console storage area
+ * @ftrace_size:	Total size for ftrace logging data (for all CPUs)
+ */
+struct pstore_blk_config {
+	char device[80];
+	enum kmsg_dump_reason max_reason;
+	unsigned long kmsg_size;
+	unsigned long pmsg_size;
+	unsigned long console_size;
+	unsigned long ftrace_size;
+};
+
+/**
+ * pstore_blk_get_config - get a copy of the pstore_blk backend configuration
+ *
+ * @info:	The sturct pstore_blk_config to be filled in
+ *
+ * Failure returns negative error code, and success returns 0.
+ */
+int pstore_blk_get_config(struct pstore_blk_config *info);
+
+#endif
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 9cb9b9067298..9f16afec7290 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -133,7 +133,7 @@ struct ramoops_platform_data {
 	unsigned long	console_size;
 	unsigned long	ftrace_size;
 	unsigned long	pmsg_size;
-	int		dump_oops;
+	int		max_reason;
 	u32		flags;
 	struct persistent_ram_ecc_info ecc_info;
 };
diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h
new file mode 100644
index 000000000000..1e35eaa33e5e
--- /dev/null
+++ b/include/linux/pstore_zone.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __PSTORE_ZONE_H_
+#define __PSTORE_ZONE_H_
+
+#include <linux/types.h>
+
+typedef ssize_t (*pstore_zone_read_op)(char *, size_t, loff_t);
+typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t);
+typedef ssize_t (*pstore_zone_erase_op)(size_t, loff_t);
+/**
+ * struct pstore_zone_info - pstore/zone back-end driver structure
+ *
+ * @owner:	Module which is responsible for this back-end driver.
+ * @name:	Name of the back-end driver.
+ * @total_size: The total size in bytes pstore/zone can use. It must be greater
+ *		than 4096 and be multiple of 4096.
+ * @kmsg_size:	The size of oops/panic zone. Zero means disabled, otherwise,
+ *		it must be multiple of SECTOR_SIZE(512 Bytes).
+ * @max_reason: Maximum kmsg dump reason to store.
+ * @pmsg_size:	The size of pmsg zone which is the same as @kmsg_size.
+ * @console_size:The size of console zone which is the same as @kmsg_size.
+ * @ftrace_size:The size of ftrace zone which is the same as @kmsg_size.
+ * @read:	The general read operation. Both of the function parameters
+ *		@size and @offset are relative value to storage.
+ *		On success, the number of bytes should be returned, others
+ *		mean error.
+ * @write:	The same as @read, but the following error number:
+ *		-EBUSY means try to write again later.
+ *		-ENOMSG means to try next zone.
+ * @erase:	The general erase operation for device with special removing
+ *		job. Both of the function parameters @size and @offset are
+ *		relative value to storage.
+ *		Return 0 on success and others on failure.
+ * @panic_write:The write operation only used for panic case. It's optional
+ *		if you do not care panic log. The parameters are relative
+ *		value to storage.
+ *		On success, the number of bytes should be returned, others
+ *		excluding -ENOMSG mean error. -ENOMSG means to try next zone.
+ */
+struct pstore_zone_info {
+	struct module *owner;
+	const char *name;
+
+	unsigned long total_size;
+	unsigned long kmsg_size;
+	int max_reason;
+	unsigned long pmsg_size;
+	unsigned long console_size;
+	unsigned long ftrace_size;
+	pstore_zone_read_op read;
+	pstore_zone_write_op write;
+	pstore_zone_erase_op erase;
+	pstore_zone_write_op panic_write;
+};
+
+extern int register_pstore_zone(struct pstore_zone_info *info);
+extern void unregister_pstore_zone(struct pstore_zone_info *info);
+
+#endif
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 121a7eda4593..c602670bbffb 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -105,10 +105,10 @@ struct ptp_system_timestamp {
  *            parameter func: the desired function to use.
  *            parameter chan: the function channel index to use.
  *
- * @do_work:  Request driver to perform auxiliary (periodic) operations
- *	      Driver should return delay of the next auxiliary work scheduling
- *	      time (>=0) or negative value in case further scheduling
- *	      is not required.
+ * @do_aux_work:  Request driver to perform auxiliary (periodic) operations
+ *                Driver should return delay of the next auxiliary work
+ *                scheduling time (>=0) or negative value in case further
+ *                scheduling is not required.
  *
  * Drivers should embed their ptp_clock_info within a private
  * structure, obtaining a reference to it using container_of().
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 63e62372443a..c2a9f7c90727 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -16,11 +16,20 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/xarray.h>
+#include <linux/local_lock.h>
 
 /* Keep unconverted code working */
 #define radix_tree_root		xarray
 #define radix_tree_node		xa_node
 
+struct radix_tree_preload {
+	local_lock_t lock;
+	unsigned nr;
+	/* nodes->parent points to next preallocated node */
+	struct radix_tree_node *nodes;
+};
+DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads);
+
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
  * slot are interpreted:
@@ -245,7 +254,7 @@ int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag);
 
 static inline void radix_tree_preload_end(void)
 {
-	preempt_enable();
+	local_unlock(&radix_tree_preloads.lock);
 }
 
 void __rcu **idr_get_free(struct radix_tree_root *root,
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 8214cdc715f2..7375bb3da140 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -371,7 +371,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
  * @member:	the name of the list_head within the struct.
- * @cond...:	optional lockdep expression if called from non-RCU protection.
+ * @cond:	optional lockdep expression if called from non-RCU protection.
  *
  * This list-traversal primitive may safely run concurrently with
  * the _rcu list-mutation primitives such as list_add_rcu()
@@ -646,7 +646,7 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @pos:	the type * to use as a loop cursor.
  * @head:	the head for your list.
  * @member:	the name of the hlist_node within the struct.
- * @cond...:	optional lockdep expression if called from non-RCU protection.
+ * @cond:	optional lockdep expression if called from non-RCU protection.
  *
  * This list-traversal primitive may safely run concurrently with
  * the _rcu list-mutation primitives such as hlist_add_head_rcu()
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 2678a37c3169..659cbfa7581a 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -37,6 +37,7 @@
 /* Exported common interfaces */
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 void rcu_barrier_tasks(void);
+void rcu_barrier_tasks_rude(void);
 void synchronize_rcu(void);
 
 #ifdef CONFIG_PREEMPT_RCU
@@ -129,25 +130,57 @@ static inline void rcu_init_nohz(void) { }
  * Note a quasi-voluntary context switch for RCU-tasks's benefit.
  * This is a macro rather than an inline function to avoid #include hell.
  */
-#ifdef CONFIG_TASKS_RCU
-#define rcu_tasks_qs(t) \
-	do { \
-		if (READ_ONCE((t)->rcu_tasks_holdout)) \
-			WRITE_ONCE((t)->rcu_tasks_holdout, false); \
+#ifdef CONFIG_TASKS_RCU_GENERIC
+
+# ifdef CONFIG_TASKS_RCU
+# define rcu_tasks_classic_qs(t, preempt)				\
+	do {								\
+		if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout))	\
+			WRITE_ONCE((t)->rcu_tasks_holdout, false);	\
 	} while (0)
-#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t)
 void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
 void synchronize_rcu_tasks(void);
+# else
+# define rcu_tasks_classic_qs(t, preempt) do { } while (0)
+# define call_rcu_tasks call_rcu
+# define synchronize_rcu_tasks synchronize_rcu
+# endif
+
+# ifdef CONFIG_TASKS_RCU_TRACE
+# define rcu_tasks_trace_qs(t)						\
+	do {								\
+		if (!likely(READ_ONCE((t)->trc_reader_checked)) &&	\
+		    !unlikely(READ_ONCE((t)->trc_reader_nesting))) {	\
+			smp_store_release(&(t)->trc_reader_checked, true); \
+			smp_mb(); /* Readers partitioned by store. */	\
+		}							\
+	} while (0)
+# else
+# define rcu_tasks_trace_qs(t) do { } while (0)
+# endif
+
+#define rcu_tasks_qs(t, preempt)					\
+do {									\
+	rcu_tasks_classic_qs((t), (preempt));				\
+	rcu_tasks_trace_qs((t));					\
+} while (0)
+
+# ifdef CONFIG_TASKS_RUDE_RCU
+void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func);
+void synchronize_rcu_tasks_rude(void);
+# endif
+
+#define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false)
 void exit_tasks_rcu_start(void);
 void exit_tasks_rcu_finish(void);
-#else /* #ifdef CONFIG_TASKS_RCU */
-#define rcu_tasks_qs(t)	do { } while (0)
+#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
+#define rcu_tasks_qs(t, preempt) do { } while (0)
 #define rcu_note_voluntary_context_switch(t) do { } while (0)
 #define call_rcu_tasks call_rcu
 #define synchronize_rcu_tasks synchronize_rcu
 static inline void exit_tasks_rcu_start(void) { }
 static inline void exit_tasks_rcu_finish(void) { }
-#endif /* #else #ifdef CONFIG_TASKS_RCU */
+#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
 
 /**
  * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU
@@ -158,7 +191,7 @@ static inline void exit_tasks_rcu_finish(void) { }
  */
 #define cond_resched_tasks_rcu_qs() \
 do { \
-	rcu_tasks_qs(current); \
+	rcu_tasks_qs(current, false); \
 	cond_resched(); \
 } while (0)
 
diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
new file mode 100644
index 000000000000..4c25a41f8b27
--- /dev/null
+++ b/include/linux/rcupdate_trace.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Read-Copy Update mechanism for mutual exclusion, adapted for tracing.
+ *
+ * Copyright (C) 2020 Paul E. McKenney.
+ */
+
+#ifndef __LINUX_RCUPDATE_TRACE_H
+#define __LINUX_RCUPDATE_TRACE_H
+
+#include <linux/sched.h>
+#include <linux/rcupdate.h>
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+extern struct lockdep_map rcu_trace_lock_map;
+
+static inline int rcu_read_lock_trace_held(void)
+{
+	return lock_is_held(&rcu_trace_lock_map);
+}
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+static inline int rcu_read_lock_trace_held(void)
+{
+	return 1;
+}
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+
+void rcu_read_unlock_trace_special(struct task_struct *t, int nesting);
+
+/**
+ * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section
+ *
+ * When synchronize_rcu_trace() is invoked by one task, then that task
+ * is guaranteed to block until all other tasks exit their read-side
+ * critical sections.  Similarly, if call_rcu_trace() is invoked on one
+ * task while other tasks are within RCU read-side critical sections,
+ * invocation of the corresponding RCU callback is deferred until after
+ * the all the other tasks exit their critical sections.
+ *
+ * For more details, please see the documentation for rcu_read_lock().
+ */
+static inline void rcu_read_lock_trace(void)
+{
+	struct task_struct *t = current;
+
+	WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1);
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
+	    t->trc_reader_special.b.need_mb)
+		smp_mb(); // Pairs with update-side barriers
+	rcu_lock_acquire(&rcu_trace_lock_map);
+}
+
+/**
+ * rcu_read_unlock_trace - mark end of RCU-trace read-side critical section
+ *
+ * Pairs with a preceding call to rcu_read_lock_trace(), and nesting is
+ * allowed.  Invoking a rcu_read_unlock_trace() when there is no matching
+ * rcu_read_lock_trace() is verboten, and will result in lockdep complaints.
+ *
+ * For more details, please see the documentation for rcu_read_unlock().
+ */
+static inline void rcu_read_unlock_trace(void)
+{
+	int nesting;
+	struct task_struct *t = current;
+
+	rcu_lock_release(&rcu_trace_lock_map);
+	nesting = READ_ONCE(t->trc_reader_nesting) - 1;
+	if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
+		WRITE_ONCE(t->trc_reader_nesting, nesting);
+		return;  // We assume shallow reader nesting.
+	}
+	rcu_read_unlock_trace_special(t, nesting);
+}
+
+void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
+void synchronize_rcu_tasks_trace(void);
+void rcu_barrier_tasks_trace(void);
+
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+
+#endif /* __LINUX_RCUPDATE_TRACE_H */
diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h
index c0578ba23c1a..699b938358bf 100644
--- a/include/linux/rcupdate_wait.h
+++ b/include/linux/rcupdate_wait.h
@@ -31,4 +31,23 @@ do {									\
 
 #define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
 
+/**
+ * synchronize_rcu_mult - Wait concurrently for multiple grace periods
+ * @...: List of call_rcu() functions for different grace periods to wait on
+ *
+ * This macro waits concurrently for multiple types of RCU grace periods.
+ * For example, synchronize_rcu_mult(call_rcu, call_rcu_tasks) would wait
+ * on concurrent RCU and RCU-tasks grace periods.  Waiting on a given SRCU
+ * domain requires you to write a wrapper function for that SRCU domain's
+ * call_srcu() function, with this wrapper supplying the pointer to the
+ * corresponding srcu_struct.
+ *
+ * The first argument tells Tiny RCU's _wait_rcu_gp() not to
+ * bother waiting for RCU.  The reason for this is because anywhere
+ * synchronize_rcu_mult() can be called is automatically already a full
+ * grace period.
+ */
+#define synchronize_rcu_mult(...) \
+	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
+
 #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 045c28b71f4f..8512caeb7682 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -49,7 +49,7 @@ static inline void rcu_softirq_qs(void)
 #define rcu_note_context_switch(preempt) \
 	do { \
 		rcu_qs(); \
-		rcu_tasks_qs(current); \
+		rcu_tasks_qs(current, (preempt)); \
 	} while (0)
 
 static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
@@ -71,6 +71,8 @@ static inline void rcu_irq_enter(void) { }
 static inline void rcu_irq_exit_irqson(void) { }
 static inline void rcu_irq_enter_irqson(void) { }
 static inline void rcu_irq_exit(void) { }
+static inline void rcu_irq_exit_preempt(void) { }
+static inline void rcu_irq_exit_check_preempt(void) { }
 static inline void exit_rcu(void) { }
 static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
@@ -85,8 +87,10 @@ static inline void rcu_scheduler_starting(void) { }
 static inline void rcu_end_inkernel_boot(void) { }
 static inline bool rcu_inkernel_boot_has_ended(void) { return true; }
 static inline bool rcu_is_watching(void) { return true; }
+static inline bool __rcu_is_watching(void) { return true; }
 static inline void rcu_momentary_dyntick_idle(void) { }
 static inline void kfree_rcu_scheduler_running(void) { }
+static inline bool rcu_gp_might_be_stalled(void) { return false; }
 
 /* Avoid RCU read-side critical sections leaking across. */
 static inline void rcu_all_qs(void) { barrier(); }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 45f3f66bb04d..d5cc9d675987 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -39,6 +39,7 @@ void rcu_barrier(void);
 bool rcu_eqs_special_set(int cpu);
 void rcu_momentary_dyntick_idle(void);
 void kfree_rcu_scheduler_running(void);
+bool rcu_gp_might_be_stalled(void);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
 
@@ -46,9 +47,16 @@ void rcu_idle_enter(void);
 void rcu_idle_exit(void);
 void rcu_irq_enter(void);
 void rcu_irq_exit(void);
+void rcu_irq_exit_preempt(void);
 void rcu_irq_enter_irqson(void);
 void rcu_irq_exit_irqson(void);
 
+#ifdef CONFIG_PROVE_RCU
+void rcu_irq_exit_check_preempt(void);
+#else
+static inline void rcu_irq_exit_check_preempt(void) { }
+#endif
+
 void exit_rcu(void);
 
 void rcu_scheduler_starting(void);
@@ -56,6 +64,7 @@ extern int rcu_scheduler_active __read_mostly;
 void rcu_end_inkernel_boot(void);
 bool rcu_inkernel_boot_has_ended(void);
 bool rcu_is_watching(void);
+bool __rcu_is_watching(void);
 #ifndef CONFIG_PREEMPTION
 void rcu_all_qs(void);
 #endif
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 40b07168fd8e..cb666b9c6b6a 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -17,10 +17,12 @@
 #include <linux/err.h>
 #include <linux/bug.h>
 #include <linux/lockdep.h>
+#include <linux/iopoll.h>
 
 struct module;
 struct clk;
 struct device;
+struct device_node;
 struct i2c_client;
 struct i3c_device;
 struct irq_domain;
@@ -71,6 +73,13 @@ struct reg_sequence {
 	unsigned int delay_us;
 };
 
+#define REG_SEQ(_reg, _def, _delay_us) {		\
+				.reg = _reg,		\
+				.def = _def,		\
+				.delay_us = _delay_us,	\
+				}
+#define REG_SEQ0(_reg, _def)	REG_SEQ(_reg, _def, 0)
+
 #define	regmap_update_bits(map, reg, mask, val) \
 	regmap_update_bits_base(map, reg, mask, val, NULL, false, false)
 #define	regmap_update_bits_async(map, reg, mask, val)\
@@ -122,26 +131,10 @@ struct reg_sequence {
  */
 #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \
 ({ \
-	u64 __timeout_us = (timeout_us); \
-	unsigned long __sleep_us = (sleep_us); \
-	ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
-	int __ret; \
-	might_sleep_if(__sleep_us); \
-	for (;;) { \
-		__ret = regmap_read((map), (addr), &(val)); \
-		if (__ret) \
-			break; \
-		if (cond) \
-			break; \
-		if ((__timeout_us) && \
-		    ktime_compare(ktime_get(), __timeout) > 0) { \
-			__ret = regmap_read((map), (addr), &(val)); \
-			break; \
-		} \
-		if (__sleep_us) \
-			usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
-	} \
-	__ret ?: ((cond) ? 0 : -ETIMEDOUT); \
+	int __ret, __tmp; \
+	__tmp = read_poll_timeout(regmap_read, __ret, __ret || (cond), \
+			sleep_us, timeout_us, false, (map), (addr), &(val)); \
+	__ret ?: __tmp; \
 })
 
 /**
@@ -209,25 +202,10 @@ struct reg_sequence {
  */
 #define regmap_field_read_poll_timeout(field, val, cond, sleep_us, timeout_us) \
 ({ \
-	u64 __timeout_us = (timeout_us); \
-	unsigned long __sleep_us = (sleep_us); \
-	ktime_t timeout = ktime_add_us(ktime_get(), __timeout_us); \
-	int pollret; \
-	might_sleep_if(__sleep_us); \
-	for (;;) { \
-		pollret = regmap_field_read((field), &(val)); \
-		if (pollret) \
-			break; \
-		if (cond) \
-			break; \
-		if (__timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
-			pollret = regmap_field_read((field), &(val)); \
-			break; \
-		} \
-		if (__sleep_us) \
-			usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
-	} \
-	pollret ?: ((cond) ? 0 : -ETIMEDOUT); \
+	int __ret, __tmp; \
+	__tmp = read_poll_timeout(regmap_field_read, __ret, __ret || (cond), \
+			sleep_us, timeout_us, false, (field), &(val)); \
+	__ret ?: __tmp; \
 })
 
 #ifdef CONFIG_REGMAP
@@ -1111,6 +1089,21 @@ bool regmap_reg_in_ranges(unsigned int reg,
 			  const struct regmap_range *ranges,
 			  unsigned int nranges);
 
+static inline int regmap_set_bits(struct regmap *map,
+				  unsigned int reg, unsigned int bits)
+{
+	return regmap_update_bits_base(map, reg, bits, bits,
+				       NULL, false, false);
+}
+
+static inline int regmap_clear_bits(struct regmap *map,
+				    unsigned int reg, unsigned int bits)
+{
+	return regmap_update_bits_base(map, reg, bits, 0, NULL, false, false);
+}
+
+int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits);
+
 /**
  * struct reg_field - Description of an register field
  *
@@ -1134,6 +1127,14 @@ struct reg_field {
 				.msb = _msb,	\
 				}
 
+#define REG_FIELD_ID(_reg, _lsb, _msb, _size, _offset) {	\
+				.reg = _reg,			\
+				.lsb = _lsb,			\
+				.msb = _msb,			\
+				.id_size = _size,		\
+				.id_offset = _offset,		\
+				}
+
 struct regmap_field *regmap_field_alloc(struct regmap *regmap,
 		struct reg_field reg_field);
 void regmap_field_free(struct regmap_field *field);
@@ -1310,12 +1311,21 @@ struct regmap_irq_chip_data;
 int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
 			int irq_base, const struct regmap_irq_chip *chip,
 			struct regmap_irq_chip_data **data);
+int regmap_add_irq_chip_np(struct device_node *np, struct regmap *map, int irq,
+			   int irq_flags, int irq_base,
+			   const struct regmap_irq_chip *chip,
+			   struct regmap_irq_chip_data **data);
 void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data);
 
 int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
 			     int irq_flags, int irq_base,
 			     const struct regmap_irq_chip *chip,
 			     struct regmap_irq_chip_data **data);
+int devm_regmap_add_irq_chip_np(struct device *dev, struct device_node *np,
+				struct regmap *map, int irq, int irq_flags,
+				int irq_base,
+				const struct regmap_irq_chip *chip,
+				struct regmap_irq_chip_data **data);
 void devm_regmap_del_irq_chip(struct device *dev, int irq,
 			      struct regmap_irq_chip_data *data);
 
@@ -1410,6 +1420,27 @@ static inline int regmap_update_bits_base(struct regmap *map, unsigned int reg,
 	return -EINVAL;
 }
 
+static inline int regmap_set_bits(struct regmap *map,
+				  unsigned int reg, unsigned int bits)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_clear_bits(struct regmap *map,
+				    unsigned int reg, unsigned int bits)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
+static inline int regmap_test_bits(struct regmap *map,
+				   unsigned int reg, unsigned int bits)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
 static inline int regmap_field_update_bits_base(struct regmap_field *field,
 					unsigned int mask, unsigned int val,
 					bool *change, bool async, bool force)
diff --git a/include/linux/regulator/coupler.h b/include/linux/regulator/coupler.h
index 0212d6255e4e..5f86824bd117 100644
--- a/include/linux/regulator/coupler.h
+++ b/include/linux/regulator/coupler.h
@@ -62,6 +62,8 @@ int regulator_get_voltage_rdev(struct regulator_dev *rdev);
 int regulator_set_voltage_rdev(struct regulator_dev *rdev,
 			       int min_uV, int max_uV,
 			       suspend_state_t state);
+int regulator_do_balance_voltage(struct regulator_dev *rdev,
+				 suspend_state_t state, bool skip_coupled);
 #else
 static inline int regulator_coupler_register(struct regulator_coupler *coupler)
 {
@@ -92,6 +94,12 @@ static inline int regulator_set_voltage_rdev(struct regulator_dev *rdev,
 {
 	return -EINVAL;
 }
+static inline int regulator_do_balance_voltage(struct regulator_dev *rdev,
+					       suspend_state_t state,
+					       bool skip_coupled)
+{
+	return -EINVAL;
+}
 #endif
 
 #endif
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 29d920516e0b..7eb9fea8e482 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -13,6 +13,7 @@
 #define __LINUX_REGULATOR_DRIVER_H_
 
 #include <linux/device.h>
+#include <linux/linear_range.h>
 #include <linux/notifier.h>
 #include <linux/regulator/consumer.h>
 #include <linux/ww_mutex.h>
@@ -39,31 +40,13 @@ enum regulator_status {
 	REGULATOR_STATUS_UNDEFINED,
 };
 
-/**
- * struct regulator_linear_range - specify linear voltage ranges
- *
- * Specify a range of voltages for regulator_map_linear_range() and
- * regulator_list_linear_range().
- *
- * @min_uV:  Lowest voltage in range
- * @min_sel: Lowest selector for range
- * @max_sel: Highest selector for range
- * @uV_step: Step size
- */
-struct regulator_linear_range {
-	unsigned int min_uV;
-	unsigned int min_sel;
-	unsigned int max_sel;
-	unsigned int uV_step;
-};
-
-/* Initialize struct regulator_linear_range */
+/* Initialize struct linear_range for regulators */
 #define REGULATOR_LINEAR_RANGE(_min_uV, _min_sel, _max_sel, _step_uV)	\
 {									\
-	.min_uV		= _min_uV,					\
+	.min		= _min_uV,					\
 	.min_sel	= _min_sel,					\
 	.max_sel	= _max_sel,					\
-	.uV_step	= _step_uV,					\
+	.step		= _step_uV,					\
 }
 
 /**
@@ -348,7 +331,7 @@ struct regulator_desc {
 	unsigned int ramp_delay;
 	int min_dropout_uV;
 
-	const struct regulator_linear_range *linear_ranges;
+	const struct linear_range *linear_ranges;
 	const unsigned int *linear_range_selectors;
 
 	int n_linear_ranges;
diff --git a/include/linux/rio.h b/include/linux/rio.h
index 317bace5ac64..2cd637268b4f 100644
--- a/include/linux/rio.h
+++ b/include/linux/rio.h
@@ -100,7 +100,7 @@ struct rio_switch {
 	u32 port_ok;
 	struct rio_switch_ops *ops;
 	spinlock_t lock;
-	struct rio_dev *nextdev[0];
+	struct rio_dev *nextdev[];
 };
 
 /**
@@ -201,7 +201,7 @@ struct rio_dev {
 	u8 hopcount;
 	struct rio_dev *prev;
 	atomic_t state;
-	struct rio_switch rswitch[0];	/* RIO switch info */
+	struct rio_switch rswitch[];	/* RIO switch info */
 };
 
 #define rio_dev_g(n) list_entry(n, struct rio_dev, global_list)
diff --git a/include/linux/rslib.h b/include/linux/rslib.h
index 5974cedd008c..238bb85243d3 100644
--- a/include/linux/rslib.h
+++ b/include/linux/rslib.h
@@ -54,7 +54,7 @@ struct rs_codec {
  */
 struct rs_control {
 	struct rs_codec	*codec;
-	uint16_t	buffers[0];
+	uint16_t	buffers[];
 };
 
 /* General purpose RS codec, 8-bit data width, symbol width 1-15 bit  */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4418f5cb8324..57d0ed061ae4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -613,7 +613,7 @@ union rcu_special {
 		u8			blocked;
 		u8			need_qs;
 		u8			exp_hint; /* Hint for performance. */
-		u8			deferred_qs;
+		u8			need_mb; /* Readers need smp_mb(). */
 	} b; /* Bits. */
 	u32 s; /* Set of bits. */
 };
@@ -724,6 +724,14 @@ struct task_struct {
 	struct list_head		rcu_tasks_holdout_list;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
+#ifdef CONFIG_TASKS_TRACE_RCU
+	int				trc_reader_nesting;
+	int				trc_ipi_to_cpu;
+	union rcu_special		trc_reader_special;
+	bool				trc_reader_checked;
+	struct list_head		trc_holdout_list;
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+
 	struct sched_info		sched_info;
 
 	struct list_head		tasks;
@@ -1289,6 +1297,12 @@ struct task_struct {
 	unsigned long			prev_lowest_stack;
 #endif
 
+#ifdef CONFIG_X86_MCE
+	u64				mce_addr;
+	u64				mce_status;
+	struct callback_head		mce_kill_me;
+#endif
+
 	/*
 	 * New fields for task_struct should be added above here, so that
 	 * they are included in the randomized portion of task_struct.
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index af9319e4cfb9..95253ad792b0 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -142,7 +142,7 @@ struct sched_domain {
 	 * by attaching extra space to the end of the structure,
 	 * depending on how many CPUs the kernel has booted up with)
 	 */
-	unsigned long span[0];
+	unsigned long span[];
 };
 
 static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
diff --git a/include/linux/scs.h b/include/linux/scs.h
new file mode 100644
index 000000000000..6dec390cf154
--- /dev/null
+++ b/include/linux/scs.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shadow Call Stack support.
+ *
+ * Copyright (C) 2019 Google LLC
+ */
+
+#ifndef _LINUX_SCS_H
+#define _LINUX_SCS_H
+
+#include <linux/gfp.h>
+#include <linux/poison.h>
+#include <linux/sched.h>
+#include <linux/sizes.h>
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+
+/*
+ * In testing, 1 KiB shadow stack size (i.e. 128 stack frames on a 64-bit
+ * architecture) provided ~40% safety margin on stack usage while keeping
+ * memory allocation overhead reasonable.
+ */
+#define SCS_SIZE		SZ_1K
+#define GFP_SCS			(GFP_KERNEL | __GFP_ZERO)
+
+/* An illegal pointer value to mark the end of the shadow stack. */
+#define SCS_END_MAGIC		(0x5f6UL + POISON_POINTER_DELTA)
+
+/* Allocate a static per-CPU shadow stack */
+#define DEFINE_SCS(name)						\
+	DEFINE_PER_CPU(unsigned long [SCS_SIZE/sizeof(long)], name)	\
+
+#define task_scs(tsk)		(task_thread_info(tsk)->scs_base)
+#define task_scs_sp(tsk)	(task_thread_info(tsk)->scs_sp)
+
+void scs_init(void);
+int scs_prepare(struct task_struct *tsk, int node);
+void scs_release(struct task_struct *tsk);
+
+static inline void scs_task_reset(struct task_struct *tsk)
+{
+	/*
+	 * Reset the shadow stack to the base address in case the task
+	 * is reused.
+	 */
+	task_scs_sp(tsk) = task_scs(tsk);
+}
+
+static inline unsigned long *__scs_magic(void *s)
+{
+	return (unsigned long *)(s + SCS_SIZE) - 1;
+}
+
+static inline bool task_scs_end_corrupted(struct task_struct *tsk)
+{
+	unsigned long *magic = __scs_magic(task_scs(tsk));
+	unsigned long sz = task_scs_sp(tsk) - task_scs(tsk);
+
+	return sz >= SCS_SIZE - 1 || READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC;
+}
+
+#else /* CONFIG_SHADOW_CALL_STACK */
+
+static inline void scs_init(void) {}
+static inline void scs_task_reset(struct task_struct *tsk) {}
+static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; }
+static inline void scs_release(struct task_struct *tsk) {}
+static inline bool task_scs_end_corrupted(struct task_struct *tsk) { return false; }
+
+#endif /* CONFIG_SHADOW_CALL_STACK */
+
+#endif /* _LINUX_SCS_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3a2ac7072dbb..3000c526f552 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4162,7 +4162,7 @@ struct skb_ext {
 	refcount_t refcnt;
 	u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */
 	u8 chunks;		/* same */
-	char data[0] __aligned(8);
+	char data[] __aligned(8);
 };
 
 struct skb_ext *__skb_ext_alloc(void);
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 8a709f63c5e5..ad31c9fb7158 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -187,6 +187,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
 	dst->sg.data[which] = src->sg.data[which];
 	dst->sg.data[which].length  = size;
 	dst->sg.size		   += size;
+	src->sg.size		   -= size;
 	src->sg.data[which].length -= size;
 	src->sg.data[which].offset += size;
 }
diff --git a/include/linux/smp.h b/include/linux/smp.h
index cbc9162689d0..04019872c7bc 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -227,8 +227,8 @@ static inline int get_boot_cpu_id(void)
  */
 extern void arch_disable_smp_support(void);
 
-extern void arch_enable_nonboot_cpus_begin(void);
-extern void arch_enable_nonboot_cpus_end(void);
+extern void arch_thaw_secondary_cpus_begin(void);
+extern void arch_thaw_secondary_cpus_end(void);
 
 void smp_setup_processor_id(void);
 
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index fbafb353e9be..bd964c31d333 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -177,6 +177,8 @@ struct plat_stmmacenet_data {
 	struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
 	struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
 	void (*fix_mac_speed)(void *priv, unsigned int speed);
+	int (*serdes_powerup)(struct net_device *ndev, void *priv);
+	void (*serdes_powerdown)(struct net_device *ndev, void *priv);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);
 	struct mac_device_info *(*setup)(void *priv);
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index ca7e108248e2..02e7a5863d28 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -71,7 +71,13 @@ struct rpc_clnt {
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	struct dentry		*cl_debugfs;	/* debugfs directory */
 #endif
-	struct rpc_xprt_iter	cl_xpi;
+	/* cl_work is only needed after cl_xpi is no longer used,
+	 * and that are of similar size
+	 */
+	union {
+		struct rpc_xprt_iter	cl_xpi;
+		struct work_struct	cl_work;
+	};
 	const struct cred	*cl_cred;
 };
 
@@ -236,4 +242,9 @@ static inline int rpc_reply_expected(struct rpc_task *task)
 		(task->tk_msg.rpc_proc->p_decode != NULL);
 }
 
+static inline void rpc_task_close_connection(struct rpc_task *task)
+{
+	if (task->tk_xprt)
+		xprt_force_disconnect(task->tk_xprt);
+}
 #endif /* _LINUX_SUNRPC_CLNT_H */
diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h
index 48c1b1674cbf..bc07e51f20d1 100644
--- a/include/linux/sunrpc/gss_api.h
+++ b/include/linux/sunrpc/gss_api.h
@@ -21,6 +21,7 @@
 struct gss_ctx {
 	struct gss_api_mech	*mech_type;
 	void			*internal_ctx_id;
+	unsigned int		slack, align;
 };
 
 #define GSS_C_NO_BUFFER		((struct xdr_netobj) 0)
@@ -66,6 +67,7 @@ u32 gss_wrap(
 u32 gss_unwrap(
 		struct gss_ctx		*ctx_id,
 		int			offset,
+		int			len,
 		struct xdr_buf		*inbuf);
 u32 gss_delete_sec_context(
 		struct gss_ctx		**ctx_id);
@@ -126,6 +128,7 @@ struct gss_api_ops {
 	u32 (*gss_unwrap)(
 			struct gss_ctx		*ctx_id,
 			int			offset,
+			int			len,
 			struct xdr_buf		*buf);
 	void (*gss_delete_sec_context)(
 			void			*internal_ctx_id);
diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h
index c1d77dd8ed41..e8f8ffe7448b 100644
--- a/include/linux/sunrpc/gss_krb5.h
+++ b/include/linux/sunrpc/gss_krb5.h
@@ -83,7 +83,7 @@ struct gss_krb5_enctype {
 	u32 (*encrypt_v2) (struct krb5_ctx *kctx, u32 offset,
 			   struct xdr_buf *buf,
 			   struct page **pages); /* v2 encryption function */
-	u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset,
+	u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, u32 len,
 			   struct xdr_buf *buf, u32 *headskip,
 			   u32 *tailskip);	/* v2 decryption function */
 };
@@ -255,7 +255,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx_id, int offset,
 		struct xdr_buf *outbuf, struct page **pages);
 
 u32
-gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset,
+gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, int len,
 		struct xdr_buf *buf);
 
 
@@ -312,7 +312,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset,
 		     struct page **pages);
 
 u32
-gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset,
+gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len,
 		     struct xdr_buf *buf, u32 *plainoffset,
 		     u32 *plainlen);
 
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 78fe2ac6dc6c..cbcfbd0521e3 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -170,6 +170,7 @@ extern bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma);
 extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 				   struct svc_rdma_recv_ctxt *ctxt);
 extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma);
+extern void svc_rdma_release_rqst(struct svc_rqst *rqstp);
 extern int svc_rdma_recvfrom(struct svc_rqst *);
 
 /* svc_rdma_rw.c */
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 01bb41908c93..22c207b2425f 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -184,6 +184,7 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p)
 extern void xdr_shift_buf(struct xdr_buf *, size_t);
 extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *);
 extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int);
+extern void xdr_buf_trim(struct xdr_buf *, unsigned int);
 extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b835d8dbea0e..25181d2dd0b9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -275,7 +275,7 @@ struct swap_info_struct {
 					 */
 	struct work_struct discard_work; /* discard worker */
 	struct swap_cluster_list discard_clusters; /* discard clusters list */
-	struct plist_node avail_lists[0]; /*
+	struct plist_node avail_lists[]; /*
 					   * entries in swap_avail_heads, one
 					   * entry per node.
 					   * Must be last as the number of the
@@ -337,6 +337,7 @@ extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
+extern void lru_add_drain_cpu_zone(struct zone *zone);
 extern void lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_file_page(struct page *page);
diff --git a/include/linux/tboot.h b/include/linux/tboot.h
index 5424bc6feac8..c7e424766360 100644
--- a/include/linux/tboot.h
+++ b/include/linux/tboot.h
@@ -121,13 +121,7 @@ struct tboot {
 #define TBOOT_UUID	{0xff, 0x8d, 0x3c, 0x66, 0xb3, 0xe8, 0x82, 0x4b, 0xbf,\
 			 0xaa, 0x19, 0xea, 0x4d, 0x5, 0x7a, 0x8}
 
-extern struct tboot *tboot;
-
-static inline int tboot_enabled(void)
-{
-	return tboot != NULL;
-}
-
+bool tboot_enabled(void);
 extern void tboot_probe(void);
 extern void tboot_shutdown(u32 shutdown_type);
 extern struct acpi_table_header *tboot_get_dmar_table(
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 421c99c12291..4f8159e90ce1 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -78,47 +78,6 @@ struct tcp_sack_block {
 #define TCP_SACK_SEEN     (1 << 0)   /*1 = peer is SACK capable, */
 #define TCP_DSACK_SEEN    (1 << 2)   /*1 = DSACK was received from peer*/
 
-#if IS_ENABLED(CONFIG_MPTCP)
-struct mptcp_options_received {
-	u64	sndr_key;
-	u64	rcvr_key;
-	u64	data_ack;
-	u64	data_seq;
-	u32	subflow_seq;
-	u16	data_len;
-	u16	mp_capable : 1,
-		mp_join : 1,
-		dss : 1,
-		add_addr : 1,
-		rm_addr : 1,
-		family : 4,
-		echo : 1,
-		backup : 1;
-	u32	token;
-	u32	nonce;
-	u64	thmac;
-	u8	hmac[20];
-	u8	join_id;
-	u8	use_map:1,
-		dsn64:1,
-		data_fin:1,
-		use_ack:1,
-		ack64:1,
-		mpc_map:1,
-		__unused:2;
-	u8	addr_id;
-	u8	rm_id;
-	union {
-		struct in_addr	addr;
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-		struct in6_addr	addr6;
-#endif
-	};
-	u64	ahmac;
-	u16	port;
-};
-#endif
-
 struct tcp_options_received {
 /*	PAWS/RTTM data	*/
 	int	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
@@ -136,9 +95,6 @@ struct tcp_options_received {
 	u8	num_sacks;	/* Number of SACK blocks		*/
 	u16	user_mss;	/* mss requested by user in ioctl	*/
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
-#if IS_ENABLED(CONFIG_MPTCP)
-	struct mptcp_options_received	mptcp;
-#endif
 };
 
 static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
@@ -148,13 +104,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 #if IS_ENABLED(CONFIG_SMC)
 	rx_opt->smc_ok = 0;
 #endif
-#if IS_ENABLED(CONFIG_MPTCP)
-	rx_opt->mptcp.mp_capable = 0;
-	rx_opt->mptcp.mp_join = 0;
-	rx_opt->mptcp.add_addr = 0;
-	rx_opt->mptcp.rm_addr = 0;
-	rx_opt->mptcp.dss = 0;
-#endif
 }
 
 /* This is the max number of SACKS that we'll generate and process. It's safe
diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h
index eb6cbdf10e50..44a7f9169ac6 100644
--- a/include/linux/ti_wilink_st.h
+++ b/include/linux/ti_wilink_st.h
@@ -295,7 +295,7 @@ struct bts_header {
 	u32 magic;
 	u32 version;
 	u8 future[24];
-	u8 actions[0];
+	u8 actions[];
 } __attribute__ ((packed));
 
 /**
@@ -305,7 +305,7 @@ struct bts_header {
 struct bts_action {
 	u16 type;
 	u16 size;
-	u8 data[0];
+	u8 data[];
 } __attribute__ ((packed));
 
 struct bts_action_send {
@@ -315,7 +315,7 @@ struct bts_action_send {
 struct bts_action_wait {
 	u32 msec;
 	u32 size;
-	u8 data[0];
+	u8 data[];
 } __attribute__ ((packed));
 
 struct bts_action_delay {
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 6241f59e2d6f..629b66e6c161 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -89,7 +89,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp);
 #ifdef CONFIG_PREEMPTION
 #define torture_preempt_schedule() preempt_schedule()
 #else
-#define torture_preempt_schedule()
+#define torture_preempt_schedule()	do { } while (0)
 #endif
 
 #endif /* __LINUX_TORTURE_H */
diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h
index 131ea1bad458..4f8c90c93c29 100644
--- a/include/linux/tpm_eventlog.h
+++ b/include/linux/tpm_eventlog.h
@@ -28,7 +28,7 @@ struct tcpa_event {
 	u32 event_type;
 	u8 pcr_value[20];	/* SHA1 */
 	u32 event_size;
-	u8 event_data[0];
+	u8 event_data[];
 };
 
 enum tcpa_event_types {
@@ -55,7 +55,7 @@ enum tcpa_event_types {
 struct tcpa_pc_event {
 	u32 event_id;
 	u32 event_size;
-	u8 event_data[0];
+	u8 event_data[];
 };
 
 enum tcpa_pc_event_ids {
@@ -97,12 +97,12 @@ struct tcg_pcr_event {
 	u32 event_type;
 	u8 digest[20];
 	u32 event_size;
-	u8 event[0];
+	u8 event[];
 } __packed;
 
 struct tcg_event_field {
 	u32 event_size;
-	u8 event[0];
+	u8 event[];
 } __packed;
 
 struct tcg_pcr_event2_head {
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 1fb11daa5c53..a1fecf311621 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -156,8 +156,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * Note, the proto and args passed in includes "__data" as the first parameter.
  * The reason for this is to handle the "void" prototype. If a tracepoint
  * has a "void" prototype, then it is invalid to declare a function
- * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
- * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
+ * as "(void *, void)".
  */
 #define __DO_TRACE(tp, proto, args, cond, rcuidle)			\
 	do {								\
@@ -373,25 +372,6 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 # define __tracepoint_string
 #endif
 
-/*
- * The need for the DECLARE_TRACE_NOARGS() is to handle the prototype
- * (void). "void" is a special value in a function prototype and can
- * not be combined with other arguments. Since the DECLARE_TRACE()
- * macro adds a data element at the beginning of the prototype,
- * we need a way to differentiate "(void *data, proto)" from
- * "(void *data, void)". The second prototype is invalid.
- *
- * DECLARE_TRACE_NOARGS() passes "void" as the tracepoint prototype
- * and "void *__data" as the callback prototype.
- *
- * DECLARE_TRACE() passes "proto" as the tracepoint protoype and
- * "void *__data, proto" as the callback prototype.
- */
-#define DECLARE_TRACE_NOARGS(name)					\
-	__DECLARE_TRACE(name, void, ,					\
-			cpu_online(raw_smp_processor_id()),		\
-			void *__data, __data)
-
 #define DECLARE_TRACE(name, proto, args)				\
 	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),		\
 			cpu_online(raw_smp_processor_id()),		\
diff --git a/include/linux/tty.h b/include/linux/tty.h
index bd5fe0e907e8..a99e9b8e4e31 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -66,7 +66,7 @@ struct tty_buffer {
 	int read;
 	int flags;
 	/* Data points here */
-	unsigned long data[0];
+	unsigned long data[];
 };
 
 /* Values for .flags field of tty_buffer */
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 733acfb7ef84..5453af87a33e 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -164,7 +164,7 @@ struct vdpa_config_ops {
 	u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx);
 
 	/* Device ops */
-	u16 (*get_vq_align)(struct vdpa_device *vdev);
+	u32 (*get_vq_align)(struct vdpa_device *vdev);
 	u64 (*get_features)(struct vdpa_device *vdev);
 	int (*set_features)(struct vdpa_device *vdev, u64 features);
 	void (*set_config_cb)(struct vdpa_device *vdev,
diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h
index 9aced11e9000..dc236577b92f 100644
--- a/include/linux/vermagic.h
+++ b/include/linux/vermagic.h
@@ -1,5 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VERMAGIC_H
+#define _LINUX_VERMAGIC_H
+
 #include <generated/utsrelease.h>
+#include <asm/vermagic.h>
 
 /* Simply sanity version stamp for modules. */
 #ifdef CONFIG_SMP
@@ -24,9 +28,6 @@
 #else
 #define MODULE_VERMAGIC_MODVERSIONS ""
 #endif
-#ifndef MODULE_ARCH_VERMAGIC
-#define MODULE_ARCH_VERMAGIC ""
-#endif
 #ifdef RANDSTRUCT_PLUGIN
 #include <generated/randomize_layout_hash.h>
 #define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED
@@ -41,3 +42,4 @@
 	MODULE_ARCH_VERMAGIC						\
 	MODULE_RANDSTRUCT_PLUGIN
 
+#endif /* _LINUX_VERMAGIC_H */
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 15f906e4a748..a493eac08393 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -9,7 +9,6 @@
 #include <linux/device.h>
 #include <linux/mod_devicetable.h>
 #include <linux/gfp.h>
-#include <linux/vringh.h>
 
 /**
  * virtqueue - a queue to register buffers for sending or receiving.
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 0d1fe9297ac6..e8a924eeea3d 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/udp.h>
 #include <uapi/linux/virtio_net.h>
 
 static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
@@ -28,17 +30,26 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					bool little_endian)
 {
 	unsigned int gso_type = 0;
+	unsigned int thlen = 0;
+	unsigned int p_off = 0;
+	unsigned int ip_proto;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 		case VIRTIO_NET_HDR_GSO_TCPV4:
 			gso_type = SKB_GSO_TCPV4;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			gso_type = SKB_GSO_TCPV6;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
+			ip_proto = IPPROTO_UDP;
+			thlen = sizeof(struct udphdr);
 			break;
 		default:
 			return -EINVAL;
@@ -57,16 +68,23 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
+
+		p_off = skb_transport_offset(skb) + thlen;
+		if (p_off > skb_headlen(skb))
+			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
 		 * probe and drop if does not match one of the above types.
 		 */
 		if (gso_type && skb->network_header) {
+			struct flow_keys_basic keys;
+
 			if (!skb->protocol)
 				virtio_net_hdr_set_proto(skb, hdr);
 retry:
-			skb_probe_transport_header(skb);
-			if (!skb_transport_header_was_set(skb)) {
+			if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
+							      NULL, 0, 0, 0,
+							      0)) {
 				/* UFO does not specify ipv4 or 6: try both */
 				if (gso_type & SKB_GSO_UDP &&
 				    skb->protocol == htons(ETH_P_IP)) {
@@ -75,18 +93,33 @@ retry:
 				}
 				return -EINVAL;
 			}
+
+			p_off = keys.control.thoff + thlen;
+			if (p_off > skb_headlen(skb) ||
+			    keys.basic.ip_proto != ip_proto)
+				return -EINVAL;
+
+			skb_set_transport_header(skb, keys.control.thoff);
+		} else if (gso_type) {
+			p_off = thlen;
+			if (p_off > skb_headlen(skb))
+				return -EINVAL;
 		}
 	}
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		skb_shinfo(skb)->gso_size = gso_size;
-		skb_shinfo(skb)->gso_type = gso_type;
+		/* Too small packets are not really GSO ones. */
+		if (skb->len - p_off > gso_size) {
+			shinfo->gso_size = gso_size;
+			shinfo->gso_type = gso_type;
 
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
+			/* Header must be checked, and gso_segs computed. */
+			shinfo->gso_type |= SKB_GSO_DODGY;
+			shinfo->gso_segs = 0;
+		}
 	}
 
 	return 0;
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 71c81e0dc8f2..dc636b727179 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -48,6 +48,7 @@ struct virtio_vsock_pkt {
 	u32 len;
 	u32 off;
 	bool reply;
+	bool tap_delivered;
 };
 
 struct virtio_vsock_pkt_info {
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 0507a162ccd0..a95d3cc74d79 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -137,7 +137,7 @@ extern void vunmap(const void *addr);
 
 extern int remap_vmalloc_range_partial(struct vm_area_struct *vma,
 				       unsigned long uaddr, void *kaddr,
-				       unsigned long size);
+				       unsigned long pgoff, unsigned long size);
 
 extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 							unsigned long pgoff);
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
index bd0503ca6f8f..9e2763d7c159 100644
--- a/include/linux/vringh.h
+++ b/include/linux/vringh.h
@@ -14,8 +14,10 @@
 #include <linux/virtio_byteorder.h>
 #include <linux/uio.h>
 #include <linux/slab.h>
+#if IS_REACHABLE(CONFIG_VHOST_IOTLB)
 #include <linux/dma-direction.h>
 #include <linux/vhost_iotlb.h>
+#endif
 #include <asm/barrier.h>
 
 /* virtio_ring with information needed for host access. */
@@ -254,6 +256,8 @@ static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val)
 	return __cpu_to_virtio64(vringh_is_little_endian(vrh), val);
 }
 
+#if IS_REACHABLE(CONFIG_VHOST_IOTLB)
+
 void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb);
 
 int vringh_init_iotlb(struct vringh *vrh, u64 features,
@@ -284,4 +288,6 @@ void vringh_notify_disable_iotlb(struct vringh *vrh);
 
 int vringh_need_notify_iotlb(struct vringh *vrh);
 
+#endif /* CONFIG_VHOST_IOTLB */
+
 #endif /* _LINUX_VRINGH_H */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index feeb6be5cad6..898c890fc153 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -1149,4 +1149,6 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i
 		(wait)->flags = 0;						\
 	} while (0)
 
+bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg);
+
 #endif /* _LINUX_WAIT_H */
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index 4cf6e11f4a3c..47eaa34f8761 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -73,7 +73,7 @@ struct simple_xattr {
 	struct list_head list;
 	char *name;
 	size_t size;
-	char value[0];
+	char value[];
 };
 
 /*
diff --git a/include/media/cec-notifier.h b/include/media/cec-notifier.h
index 38956969fd12..b1c839734124 100644
--- a/include/media/cec-notifier.h
+++ b/include/media/cec-notifier.h
@@ -2,7 +2,7 @@
 /*
  * cec-notifier.h - notify CEC drivers of physical address changes
  *
- * Copyright 2016 Russell King <rmk+kernel@arm.linux.org.uk>
+ * Copyright 2016 Russell King.
  * Copyright 2016-2017 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
  */
 
diff --git a/include/net/act_api.h b/include/net/act_api.h
index c24d7643548e..124bd139886c 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -75,7 +75,8 @@ static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm)
 {
 	dtm->install = jiffies_to_clock_t(jiffies - stm->install);
 	dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse);
-	dtm->firstuse = jiffies_to_clock_t(jiffies - stm->firstuse);
+	dtm->firstuse = stm->firstuse ?
+		jiffies_to_clock_t(jiffies - stm->firstuse) : 0;
 	dtm->expires = jiffies_to_clock_t(stm->expires);
 }
 
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 04e97bab6f28..ab988940bf04 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -59,7 +59,7 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
 void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
 void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
 			   struct sockaddr_rxrpc *);
-u64 rxrpc_kernel_get_rtt(struct socket *, struct rxrpc_call *);
+u32 rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *);
 int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 			       rxrpc_user_attach_call_t, unsigned long, gfp_t,
 			       unsigned int);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c78bd4ff9e33..70e48f66dac8 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -905,6 +905,8 @@ struct survey_info {
  *	protocol frames.
  * @control_port_over_nl80211: TRUE if userspace expects to exchange control
  *	port frames over NL80211 instead of the network interface.
+ * @control_port_no_preauth: disables pre-auth rx over the nl80211 control
+ *	port for mac80211
  * @wep_keys: static WEP keys, if not NULL points to an array of
  *	CFG80211_MAX_WEP_KEYS WEP keys
  * @wep_tx_key: key index (0..3) of the default TX static WEP key
@@ -1222,6 +1224,7 @@ struct sta_txpwr {
  * @he_capa: HE capabilities of station
  * @he_capa_len: the length of the HE capabilities
  * @airtime_weight: airtime scheduler weight for this station
+ * @txpwr: transmit power for an associated station
  */
 struct station_parameters {
 	const u8 *supported_rates;
@@ -4666,6 +4669,9 @@ struct wiphy_iftype_akm_suites {
  * @txq_memory_limit: configuration internal TX queue memory limit
  * @txq_quantum: configuration of internal TX queue scheduler quantum
  *
+ * @tx_queue_len: allow setting transmit queue len for drivers not using
+ *	wake_tx_queue
+ *
  * @support_mbssid: can HW support association with nontransmitted AP
  * @support_only_he_mbssid: don't parse MBSSID elements if it is not
  *	HE AP, in order to avoid compatibility issues.
@@ -4681,6 +4687,10 @@ struct wiphy_iftype_akm_suites {
  *	supported by the driver for each peer
  * @tid_config_support.max_retry: maximum supported retry count for
  *	long/short retry configuration
+ *
+ * @max_data_retry_count: maximum supported per TID retry count for
+ *	configuration through the %NL80211_TID_CONFIG_ATTR_RETRY_SHORT and
+ *	%NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes
  */
 struct wiphy {
 	/* assign these fields before you register the wiphy */
diff --git a/include/net/espintcp.h b/include/net/espintcp.h
index dd7026a00066..0335bbd76552 100644
--- a/include/net/espintcp.h
+++ b/include/net/espintcp.h
@@ -25,6 +25,7 @@ struct espintcp_ctx {
 	struct espintcp_msg partial;
 	void (*saved_data_ready)(struct sock *sk);
 	void (*saved_write_space)(struct sock *sk);
+	void (*saved_destruct)(struct sock *sk);
 	struct work_struct work;
 	bool tx_running;
 };
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 3619c6acf60f..efc8350b42fb 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -166,15 +166,18 @@ enum flow_action_mangle_base {
 enum flow_action_hw_stats_bit {
 	FLOW_ACTION_HW_STATS_IMMEDIATE_BIT,
 	FLOW_ACTION_HW_STATS_DELAYED_BIT,
+	FLOW_ACTION_HW_STATS_DISABLED_BIT,
 };
 
 enum flow_action_hw_stats {
-	FLOW_ACTION_HW_STATS_DISABLED = 0,
+	FLOW_ACTION_HW_STATS_DONT_CARE = 0,
 	FLOW_ACTION_HW_STATS_IMMEDIATE =
 		BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT),
 	FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT),
 	FLOW_ACTION_HW_STATS_ANY = FLOW_ACTION_HW_STATS_IMMEDIATE |
 				   FLOW_ACTION_HW_STATS_DELAYED,
+	FLOW_ACTION_HW_STATS_DISABLED =
+		BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT),
 };
 
 typedef void (*action_destr)(void *priv);
@@ -325,7 +328,11 @@ __flow_action_hw_stats_check(const struct flow_action *action,
 		return true;
 	if (!flow_action_mixed_hw_stats_check(action, extack))
 		return false;
+
 	action_entry = flow_action_first_entry_get(action);
+	if (action_entry->hw_stats == FLOW_ACTION_HW_STATS_DONT_CARE)
+		return true;
+
 	if (!check_allow_bit &&
 	    action_entry->hw_stats != FLOW_ACTION_HW_STATS_ANY) {
 		NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\"");
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index c8e2bebd8d93..0f0d1efe06dd 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -99,6 +99,20 @@ static inline int IP_ECN_set_ce(struct iphdr *iph)
 	return 1;
 }
 
+static inline int IP_ECN_set_ect1(struct iphdr *iph)
+{
+	u32 check = (__force u32)iph->check;
+
+	if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	check += (__force u16)htons(0x100);
+
+	iph->check = (__force __sum16)(check + (check>=0xFFFF));
+	iph->tos ^= INET_ECN_MASK;
+	return 1;
+}
+
 static inline void IP_ECN_clear(struct iphdr *iph)
 {
 	iph->tos &= ~INET_ECN_MASK;
@@ -134,6 +148,22 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 	return 1;
 }
 
+static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph)
+{
+	__be32 from, to;
+
+	if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	from = *(__be32 *)iph;
+	to = from ^ htonl(INET_ECN_MASK << 20);
+	*(__be32 *)iph = to;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from),
+				     (__force __wsum)to);
+	return 1;
+}
+
 static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 {
 	dscp &= ~INET_ECN_MASK;
@@ -159,6 +189,25 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 	return 0;
 }
 
+static inline int INET_ECN_set_ect1(struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case cpu_to_be16(ETH_P_IP):
+		if (skb_network_header(skb) + sizeof(struct iphdr) <=
+		    skb_tail_pointer(skb))
+			return IP_ECN_set_ect1(ip_hdr(skb));
+		break;
+
+	case cpu_to_be16(ETH_P_IPV6):
+		if (skb_network_header(skb) + sizeof(struct ipv6hdr) <=
+		    skb_tail_pointer(skb))
+			return IP6_ECN_set_ect1(skb, ipv6_hdr(skb));
+		break;
+	}
+
+	return 0;
+}
+
 /*
  * RFC 6040 4.2
  *  To decapsulate the inner header at the tunnel egress, a compliant
@@ -208,8 +257,12 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb,
 	int rc;
 
 	rc = __INET_ECN_decapsulate(outer, inner, &set_ce);
-	if (!rc && set_ce)
-		INET_ECN_set_ce(skb);
+	if (!rc) {
+		if (set_ce)
+			INET_ECN_set_ce(skb);
+		else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1)
+			INET_ECN_set_ect1(skb);
+	}
 
 	return rc;
 }
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 80262d2980f5..1d98828c6649 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -203,6 +203,7 @@ struct fib6_info {
 struct rt6_info {
 	struct dst_entry		dst;
 	struct fib6_info __rcu		*from;
+	int				sernum;
 
 	struct rt6key			rt6i_dst;
 	struct rt6key			rt6i_src;
@@ -291,6 +292,9 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 	struct fib6_info *from;
 	u32 cookie = 0;
 
+	if (rt->sernum)
+		return rt->sernum;
+
 	rcu_read_lock();
 
 	from = rcu_dereference(rt->from);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index f7543c095b33..9947eb1e9eb6 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -254,6 +254,7 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
 
 	return rt->rt6i_flags & RTF_ANYCAST ||
 		(rt->rt6i_dst.plen < 127 &&
+		 !(rt->rt6i_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) &&
 		 ipv6_addr_equal(&rt->rt6i_dst.addr, daddr));
 }
 
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 59e0d4e99f94..2ec062aaa978 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -257,7 +257,6 @@ struct fib_dump_filter {
 	u32			table_id;
 	/* filter_set is an optimization that an entry is set */
 	bool			filter_set;
-	bool			dump_all_families;
 	bool			dump_routes;
 	bool			dump_exceptions;
 	unsigned char		protocol;
@@ -448,6 +447,16 @@ static inline int fib_num_tclassid_users(struct net *net)
 #endif
 int fib_unmerge(struct net *net);
 
+static inline bool nhc_l3mdev_matches_dev(const struct fib_nh_common *nhc,
+const struct net_device *dev)
+{
+	if (nhc->nhc_dev == dev ||
+	    l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex)
+		return true;
+
+	return false;
+}
+
 /* Exported by fib_semantics.c */
 int ip_fib_check_default(__be32 gw, struct net_device *dev);
 int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
@@ -480,6 +489,8 @@ void fib_nh_common_release(struct fib_nh_common *nhc);
 void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri);
 void fib_trie_init(void);
 struct fib_table *fib_trie_table(u32 id, struct fib_table *alias);
+bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags,
+			 const struct flowi4 *flp);
 
 static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
 {
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index b6b4de0e4b5e..97fec4d310ac 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -6007,7 +6007,9 @@ enum rate_control_capabilities {
 struct rate_control_ops {
 	unsigned long capa;
 	const char *name;
-	void *(*alloc)(struct ieee80211_hw *hw, struct dentry *debugfsdir);
+	void *(*alloc)(struct ieee80211_hw *hw);
+	void (*add_debugfs)(struct ieee80211_hw *hw, void *priv,
+			    struct dentry *debugfsdir);
 	void (*free)(void *priv);
 
 	void *(*alloc_sta)(void *priv, struct ieee80211_sta *sta, gfp_t gfp);
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 0e7c5471010b..3bce2019e4da 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -68,11 +68,8 @@ static inline bool rsk_is_mptcp(const struct request_sock *req)
 	return tcp_rsk(req)->is_mptcp;
 }
 
-void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
-			int opsize, struct tcp_options_received *opt_rx);
 bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 		       unsigned int *size, struct mptcp_out_options *opts);
-void mptcp_rcv_synsent(struct sock *sk);
 bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 			  struct mptcp_out_options *opts);
 bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 7d107113f988..9205a76d967a 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -41,7 +41,7 @@ enum {
 	ND_OPT_DNSSL = 31,		/* RFC6106 */
 	ND_OPT_6CO = 34,		/* RFC6775 */
 	ND_OPT_CAPTIVE_PORTAL = 37,	/* RFC7710 */
-	ND_OPT_PREF64 = 38,		/* RFC-ietf-6man-ra-pref64-09 */
+	ND_OPT_PREF64 = 38,		/* RFC8781 */
 	__ND_OPT_MAX
 };
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index ab96fb59131c..8e001e049497 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -437,6 +437,13 @@ static inline int rt_genid_ipv4(const struct net *net)
 	return atomic_read(&net->ipv4.rt_genid);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int rt_genid_ipv6(const struct net *net)
+{
+	return atomic_read(&net->ipv6.fib6_sernum);
+}
+#endif
+
 static inline void rt_genid_bump_ipv4(struct net *net)
 {
 	atomic_inc(&net->ipv4.rt_genid);
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 9f551f3b69c6..90690e37a56f 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -87,7 +87,7 @@ struct nf_conn {
 	struct hlist_node	nat_bysource;
 #endif
 	/* all members below initialized via memset */
-	u8 __nfct_init_offset[0];
+	struct { } __nfct_init_offset;
 
 	/* If we were expected by an expectation, this will be it */
 	struct nf_conn *master;
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 6bf69652f57d..c54a7f707e50 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -127,6 +127,7 @@ enum nf_flow_flags {
 	NF_FLOW_HW_DYING,
 	NF_FLOW_HW_DEAD,
 	NF_FLOW_HW_REFRESH,
+	NF_FLOW_HW_PENDING,
 };
 
 enum flow_offload_type {
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 6eb627b3c99b..4ff7c81e6717 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -901,7 +901,7 @@ static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext,
 {
 	struct nft_expr *expr;
 
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) {
+	if (__nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) {
 		expr = nft_set_ext_expr(ext);
 		expr->ops->eval(expr, regs, pkt);
 	}
diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index c440ccc861fc..8c9f1a718859 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -70,6 +70,7 @@ struct nh_grp_entry {
 };
 
 struct nh_group {
+	struct nh_group		*spare; /* spare group for removals */
 	u16			num_nh;
 	bool			mpath;
 	bool			has_v4;
@@ -136,21 +137,20 @@ static inline unsigned int nexthop_num_path(const struct nexthop *nh)
 {
 	unsigned int rc = 1;
 
-	if (nexthop_is_multipath(nh)) {
+	if (nh->is_group) {
 		struct nh_group *nh_grp;
 
 		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
-		rc = nh_grp->num_nh;
+		if (nh_grp->mpath)
+			rc = nh_grp->num_nh;
 	}
 
 	return rc;
 }
 
 static inline
-struct nexthop *nexthop_mpath_select(const struct nexthop *nh, int nhsel)
+struct nexthop *nexthop_mpath_select(const struct nh_group *nhg, int nhsel)
 {
-	const struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp);
-
 	/* for_nexthops macros in fib_semantics.c grabs a pointer to
 	 * the nexthop before checking nhsel
 	 */
@@ -185,12 +185,14 @@ static inline bool nexthop_is_blackhole(const struct nexthop *nh)
 {
 	const struct nh_info *nhi;
 
-	if (nexthop_is_multipath(nh)) {
-		if (nexthop_num_path(nh) > 1)
-			return false;
-		nh = nexthop_mpath_select(nh, 0);
-		if (!nh)
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		if (nh_grp->num_nh > 1)
 			return false;
+
+		nh = nh_grp->nh_entries[0].nh;
 	}
 
 	nhi = rcu_dereference_rtnl(nh->nh_info);
@@ -216,16 +218,79 @@ struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel)
 	BUILD_BUG_ON(offsetof(struct fib_nh, nh_common) != 0);
 	BUILD_BUG_ON(offsetof(struct fib6_nh, nh_common) != 0);
 
-	if (nexthop_is_multipath(nh)) {
-		nh = nexthop_mpath_select(nh, nhsel);
-		if (!nh)
-			return NULL;
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		if (nh_grp->mpath) {
+			nh = nexthop_mpath_select(nh_grp, nhsel);
+			if (!nh)
+				return NULL;
+		}
 	}
 
 	nhi = rcu_dereference_rtnl(nh->nh_info);
 	return &nhi->fib_nhc;
 }
 
+/* called from fib_table_lookup with rcu_lock */
+static inline
+struct fib_nh_common *nexthop_get_nhc_lookup(const struct nexthop *nh,
+					     int fib_flags,
+					     const struct flowi4 *flp,
+					     int *nhsel)
+{
+	struct nh_info *nhi;
+
+	if (nh->is_group) {
+		struct nh_group *nhg = rcu_dereference(nh->nh_grp);
+		int i;
+
+		for (i = 0; i < nhg->num_nh; i++) {
+			struct nexthop *nhe = nhg->nh_entries[i].nh;
+
+			nhi = rcu_dereference(nhe->nh_info);
+			if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) {
+				*nhsel = i;
+				return &nhi->fib_nhc;
+			}
+		}
+	} else {
+		nhi = rcu_dereference(nh->nh_info);
+		if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) {
+			*nhsel = 0;
+			return &nhi->fib_nhc;
+		}
+	}
+
+	return NULL;
+}
+
+static inline bool nexthop_uses_dev(const struct nexthop *nh,
+				    const struct net_device *dev)
+{
+	struct nh_info *nhi;
+
+	if (nh->is_group) {
+		struct nh_group *nhg = rcu_dereference(nh->nh_grp);
+		int i;
+
+		for (i = 0; i < nhg->num_nh; i++) {
+			struct nexthop *nhe = nhg->nh_entries[i].nh;
+
+			nhi = rcu_dereference(nhe->nh_info);
+			if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev))
+				return true;
+		}
+	} else {
+		nhi = rcu_dereference(nh->nh_info);
+		if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev))
+			return true;
+	}
+
+	return false;
+}
+
 static inline unsigned int fib_info_num_path(const struct fib_info *fi)
 {
 	if (unlikely(fi->nh))
@@ -263,8 +328,11 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh)
 {
 	struct nh_info *nhi;
 
-	if (nexthop_is_multipath(nh)) {
-		nh = nexthop_mpath_select(nh, 0);
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		nh = nexthop_mpath_select(nh_grp, 0);
 		if (!nh)
 			return NULL;
 	}
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 25d2ec4c8f00..8428aa614265 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -407,6 +407,7 @@ struct tcf_block {
 	struct mutex lock;
 	struct list_head chain_list;
 	u32 index; /* block index for shared blocks */
+	u32 classid; /* which class this block belongs to */
 	refcount_t refcnt;
 	struct net *net;
 	struct Qdisc *q;
diff --git a/include/net/sock.h b/include/net/sock.h
index 6d84784d33fa..3e8c6d4b4b59 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2553,9 +2553,9 @@ sk_is_refcounted(struct sock *sk)
 }
 
 /**
- * skb_steal_sock
- * @skb to steal the socket from
- * @refcounted is set to true if the socket is reference-counted
+ * skb_steal_sock - steal a socket from an sk_buff
+ * @skb: sk_buff to steal the socket from
+ * @refcounted: is set to true if the socket is reference-counted
  */
 static inline struct sock *
 skb_steal_sock(struct sk_buff *skb, bool *refcounted)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5fa9eacd965a..cf5649a2e795 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -23,7 +23,6 @@
 #include <linux/cache.h>
 #include <linux/percpu.h>
 #include <linux/skbuff.h>
-#include <linux/cryptohash.h>
 #include <linux/kref.h>
 #include <linux/ktime.h>
 
@@ -51,7 +50,7 @@ extern struct inet_hashinfo tcp_hashinfo;
 extern struct percpu_counter tcp_orphan_count;
 void tcp_time_wait(struct sock *sk, int state, int timeo);
 
-#define MAX_TCP_HEADER	(128 + MAX_HEADER)
+#define MAX_TCP_HEADER	L1_CACHE_ALIGN(128 + MAX_HEADER)
 #define MAX_TCP_OPTION_SPACE 40
 #define TCP_MIN_SND_MSS		48
 #define TCP_MIN_GSO_SIZE	(TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)
@@ -1376,7 +1375,6 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
 	rx_opt->num_sacks = 0;
 }
 
-u32 tcp_default_init_rwnd(u32 mss);
 void tcp_cwnd_restart(struct sock *sk, s32 delta);
 
 static inline void tcp_slow_start_after_idle_check(struct sock *sk)
@@ -1421,6 +1419,19 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
+/* We provision sk_rcvbuf around 200% of sk_rcvlowat.
+ * If 87.5 % (7/8) of the space has been consumed, we want to override
+ * SO_RCVLOWAT constraint, since we are receiving skbs with too small
+ * len/truesize ratio.
+ */
+static inline bool tcp_rmem_pressure(const struct sock *sk)
+{
+	int rcvbuf = READ_ONCE(sk->sk_rcvbuf);
+	int threshold = rcvbuf - (rcvbuf >> 3);
+
+	return atomic_read(&sk->sk_rmem_alloc) > threshold;
+}
+
 extern void tcp_openreq_init_rwin(struct request_sock *req,
 				  const struct sock *sk_listener,
 				  const struct dst_entry *dst);
diff --git a/include/net/tls.h b/include/net/tls.h
index bf9eb4823933..18cd4f418464 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -135,6 +135,8 @@ struct tls_sw_context_tx {
 	struct tls_rec *open_rec;
 	struct list_head tx_list;
 	atomic_t encrypt_pending;
+	/* protect crypto_wait with encrypt_pending */
+	spinlock_t encrypt_compl_lock;
 	int async_notify;
 	u8 async_capable:1;
 
@@ -155,6 +157,8 @@ struct tls_sw_context_rx {
 	u8 async_capable:1;
 	u8 decrypted:1;
 	atomic_t decrypt_pending;
+	/* protect crypto_wait with decrypt_pending*/
+	spinlock_t decrypt_compl_lock;
 	bool async_notify;
 };
 
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 4b1f95e08307..e7312ceb2794 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -143,14 +143,12 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb
 			 __be16 df, __be16 src_port, __be16 dst_port,
 			 bool xnet, bool nocheck);
 
-#if IS_ENABLED(CONFIG_IPV6)
 int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
 			 struct sk_buff *skb,
 			 struct net_device *dev, struct in6_addr *saddr,
 			 struct in6_addr *daddr,
 			 __u8 prio, __u8 ttl, __be32 label,
 			 __be16 src_port, __be16 dst_port, bool nocheck);
-#endif
 
 void udp_tunnel_sock_release(struct socket *sock);
 
diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h
index 1b28ce1aba07..325fdaa3bb66 100644
--- a/include/rdma/uverbs_std_types.h
+++ b/include/rdma/uverbs_std_types.h
@@ -88,7 +88,7 @@ struct ib_uobject *__uobj_get_destroy(const struct uverbs_api_object *obj,
 
 static inline void uobj_put_destroy(struct ib_uobject *uobj)
 {
-	rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_WRITE);
+	rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_DESTROY);
 }
 
 static inline void uobj_put_read(struct ib_uobject *uobj)
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index ebffcb36a7e3..efc8b613d486 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -476,6 +476,8 @@ struct ocelot_port {
 
 	void __iomem			*regs;
 
+	bool				vlan_aware;
+
 	/* Ingress default VLAN (pvid) */
 	u16				pvid;
 
@@ -500,6 +502,7 @@ struct ocelot {
 	unsigned int			num_stats;
 
 	int				shared_queue_sz;
+	int				num_mact_rows;
 
 	struct net_device		*hw_bridge_dev;
 	u16				bridge_mask;
@@ -610,7 +613,7 @@ int ocelot_port_bridge_leave(struct ocelot *ocelot, int port,
 int ocelot_fdb_dump(struct ocelot *ocelot, int port,
 		    dsa_fdb_dump_cb_t *cb, void *data);
 int ocelot_fdb_add(struct ocelot *ocelot, int port,
-		   const unsigned char *addr, u16 vid, bool vlan_aware);
+		   const unsigned char *addr, u16 vid);
 int ocelot_fdb_del(struct ocelot *ocelot, int port,
 		   const unsigned char *addr, u16 vid);
 int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
diff --git a/include/soc/tegra/pmc.h b/include/soc/tegra/pmc.h
index 0dd52b0a5c1b..361cb64246f7 100644
--- a/include/soc/tegra/pmc.h
+++ b/include/soc/tegra/pmc.h
@@ -168,7 +168,6 @@ int tegra_io_pad_power_disable(enum tegra_io_pad id);
 int tegra_io_rail_power_on(unsigned int id);
 int tegra_io_rail_power_off(unsigned int id);
 
-enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void);
 void tegra_pmc_set_suspend_mode(enum tegra_suspend_mode mode);
 void tegra_pmc_enter_suspend_mode(enum tegra_suspend_mode mode);
 
@@ -220,11 +219,6 @@ static inline int tegra_io_rail_power_off(unsigned int id)
 	return -ENOSYS;
 }
 
-static inline enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void)
-{
-	return TEGRA_SUSPEND_NONE;
-}
-
 static inline void tegra_pmc_set_suspend_mode(enum tegra_suspend_mode mode)
 {
 }
@@ -235,4 +229,13 @@ static inline void tegra_pmc_enter_suspend_mode(enum tegra_suspend_mode mode)
 
 #endif /* CONFIG_SOC_TEGRA_PMC */
 
+#if defined(CONFIG_SOC_TEGRA_PMC) && defined(CONFIG_PM_SLEEP)
+enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void);
+#else
+static inline enum tegra_suspend_mode tegra_pmc_get_suspend_mode(void)
+{
+	return TEGRA_SUSPEND_NONE;
+}
+#endif
+
 #endif /* __SOC_TEGRA_PMC_H__ */
diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h
index 3ee8036f5436..225154a4f2ed 100644
--- a/include/sound/hda_codec.h
+++ b/include/sound/hda_codec.h
@@ -494,6 +494,11 @@ void snd_hda_update_power_acct(struct hda_codec *codec);
 static inline void snd_hda_set_power_save(struct hda_bus *bus, int delay) {}
 #endif
 
+static inline bool hda_codec_need_resume(struct hda_codec *codec)
+{
+	return !codec->relaxed_resume && codec->jacktbl.used;
+}
+
 #ifdef CONFIG_SND_HDA_PATCH_LOADER
 /*
  * patch firmware
diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h
index a36b7227a15a..334842daa904 100644
--- a/include/sound/rawmidi.h
+++ b/include/sound/rawmidi.h
@@ -61,6 +61,7 @@ struct snd_rawmidi_runtime {
 	size_t avail_min;	/* min avail for wakeup */
 	size_t avail;		/* max used buffer for wakeup */
 	size_t xruns;		/* over/underruns counter */
+	int buffer_ref;		/* buffer reference count */
 	/* misc */
 	spinlock_t lock;
 	wait_queue_head_t sleep;
diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index d4825b82c7a3..b33abe93b905 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -351,7 +351,6 @@ struct snd_soc_dai {
 
 	/* bit field */
 	unsigned int probed:1;
-	unsigned int started[SNDRV_PCM_STREAM_LAST + 1];
 };
 
 static inline struct snd_soc_pcm_stream *
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 13458e4fbb13..946f88a6c63d 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -790,6 +790,9 @@ struct snd_soc_dai_link {
 	const struct snd_soc_pcm_stream *params;
 	unsigned int num_params;
 
+	struct snd_soc_dapm_widget *playback_widget;
+	struct snd_soc_dapm_widget *capture_widget;
+
 	unsigned int dai_fmt;           /* format to set on init */
 
 	enum snd_soc_dpcm_trigger trigger[2]; /* trigger type for DPCM */
diff --git a/include/trace/events/gpu_mem.h b/include/trace/events/gpu_mem.h
index 1897822a9150..26d871f96e94 100644
--- a/include/trace/events/gpu_mem.h
+++ b/include/trace/events/gpu_mem.h
@@ -24,7 +24,7 @@
  *
  * @pid: Put 0 for global total, while positive pid for process total.
  *
- * @size: Virtual size of the allocation in bytes.
+ * @size: Size of the allocation in bytes.
  *
  */
 TRACE_EVENT(gpu_mem_total,
diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
index 7ecaa65b7106..c2f580fd371b 100644
--- a/include/trace/events/iocost.h
+++ b/include/trace/events/iocost.h
@@ -130,7 +130,7 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset,
 
 TRACE_EVENT(iocost_ioc_vrate_adj,
 
-	TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 (*missed_ppm)[2],
+	TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 *missed_ppm,
 		u32 rq_wait_pct, int nr_lagging, int nr_shortages,
 		int nr_surpluses),
 
@@ -155,8 +155,8 @@ TRACE_EVENT(iocost_ioc_vrate_adj,
 		__entry->old_vrate = atomic64_read(&ioc->vtime_rate);;
 		__entry->new_vrate = new_vrate;
 		__entry->busy_level = ioc->busy_level;
-		__entry->read_missed_ppm = (*missed_ppm)[READ];
-		__entry->write_missed_ppm = (*missed_ppm)[WRITE];
+		__entry->read_missed_ppm = missed_ppm[READ];
+		__entry->write_missed_ppm = missed_ppm[WRITE];
 		__entry->rq_wait_pct = rq_wait_pct;
 		__entry->nr_lagging = nr_lagging;
 		__entry->nr_shortages = nr_shortages;
diff --git a/include/trace/events/regulator.h b/include/trace/events/regulator.h
index b70583c32c08..72b3ba93b0a5 100644
--- a/include/trace/events/regulator.h
+++ b/include/trace/events/regulator.h
@@ -70,6 +70,38 @@ DEFINE_EVENT(regulator_basic, regulator_disable_complete,
 
 );
 
+DEFINE_EVENT(regulator_basic, regulator_bypass_enable,
+
+	TP_PROTO(const char *name),
+
+	TP_ARGS(name)
+
+);
+
+DEFINE_EVENT(regulator_basic, regulator_bypass_enable_complete,
+
+	TP_PROTO(const char *name),
+
+	TP_ARGS(name)
+
+);
+
+DEFINE_EVENT(regulator_basic, regulator_bypass_disable,
+
+	TP_PROTO(const char *name),
+
+	TP_ARGS(name)
+
+);
+
+DEFINE_EVENT(regulator_basic, regulator_bypass_disable_complete,
+
+	TP_PROTO(const char *name),
+
+	TP_ARGS(name)
+
+);
+
 /*
  * Events that take a range of numerical values, mostly for voltages
  * and so on.
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 051f26fedc4d..132c3c778a43 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -692,11 +692,10 @@ TRACE_EVENT(xprtrdma_prepsend_failed,
 
 TRACE_EVENT(xprtrdma_post_send,
 	TP_PROTO(
-		const struct rpcrdma_req *req,
-		int status
+		const struct rpcrdma_req *req
 	),
 
-	TP_ARGS(req, status),
+	TP_ARGS(req),
 
 	TP_STRUCT__entry(
 		__field(const void *, req)
@@ -705,7 +704,6 @@ TRACE_EVENT(xprtrdma_post_send,
 		__field(unsigned int, client_id)
 		__field(int, num_sge)
 		__field(int, signaled)
-		__field(int, status)
 	),
 
 	TP_fast_assign(
@@ -718,15 +716,13 @@ TRACE_EVENT(xprtrdma_post_send,
 		__entry->sc = req->rl_sendctx;
 		__entry->num_sge = req->rl_wr.num_sge;
 		__entry->signaled = req->rl_wr.send_flags & IB_SEND_SIGNALED;
-		__entry->status = status;
 	),
 
-	TP_printk("task:%u@%u req=%p sc=%p (%d SGE%s) %sstatus=%d",
+	TP_printk("task:%u@%u req=%p sc=%p (%d SGE%s) %s",
 		__entry->task_id, __entry->client_id,
 		__entry->req, __entry->sc, __entry->num_sge,
 		(__entry->num_sge == 1 ? "" : "s"),
-		(__entry->signaled ? "signaled " : ""),
-		__entry->status
+		(__entry->signaled ? "signaled" : "")
 	)
 );
 
@@ -1695,17 +1691,15 @@ DECLARE_EVENT_CLASS(svcrdma_sendcomp_event,
 
 TRACE_EVENT(svcrdma_post_send,
 	TP_PROTO(
-		const struct ib_send_wr *wr,
-		int status
+		const struct ib_send_wr *wr
 	),
 
-	TP_ARGS(wr, status),
+	TP_ARGS(wr),
 
 	TP_STRUCT__entry(
 		__field(const void *, cqe)
 		__field(unsigned int, num_sge)
 		__field(u32, inv_rkey)
-		__field(int, status)
 	),
 
 	TP_fast_assign(
@@ -1713,12 +1707,11 @@ TRACE_EVENT(svcrdma_post_send,
 		__entry->num_sge = wr->num_sge;
 		__entry->inv_rkey = (wr->opcode == IB_WR_SEND_WITH_INV) ?
 					wr->ex.invalidate_rkey : 0;
-		__entry->status = status;
 	),
 
-	TP_printk("cqe=%p num_sge=%u inv_rkey=0x%08x status=%d",
+	TP_printk("cqe=%p num_sge=%u inv_rkey=0x%08x",
 		__entry->cqe, __entry->num_sge,
-		__entry->inv_rkey, __entry->status
+		__entry->inv_rkey
 	)
 );
 
@@ -1783,26 +1776,23 @@ TRACE_EVENT(svcrdma_wc_receive,
 TRACE_EVENT(svcrdma_post_rw,
 	TP_PROTO(
 		const void *cqe,
-		int sqecount,
-		int status
+		int sqecount
 	),
 
-	TP_ARGS(cqe, sqecount, status),
+	TP_ARGS(cqe, sqecount),
 
 	TP_STRUCT__entry(
 		__field(const void *, cqe)
 		__field(int, sqecount)
-		__field(int, status)
 	),
 
 	TP_fast_assign(
 		__entry->cqe = cqe;
 		__entry->sqecount = sqecount;
-		__entry->status = status;
 	),
 
-	TP_printk("cqe=%p sqecount=%d status=%d",
-		__entry->cqe, __entry->sqecount, __entry->status
+	TP_printk("cqe=%p sqecount=%d",
+		__entry->cqe, __entry->sqecount
 	)
 );
 
@@ -1870,6 +1860,34 @@ DECLARE_EVENT_CLASS(svcrdma_sendqueue_event,
 DEFINE_SQ_EVENT(full);
 DEFINE_SQ_EVENT(retry);
 
+TRACE_EVENT(svcrdma_sq_post_err,
+	TP_PROTO(
+		const struct svcxprt_rdma *rdma,
+		int status
+	),
+
+	TP_ARGS(rdma, status),
+
+	TP_STRUCT__entry(
+		__field(int, avail)
+		__field(int, depth)
+		__field(int, status)
+		__string(addr, rdma->sc_xprt.xpt_remotebuf)
+	),
+
+	TP_fast_assign(
+		__entry->avail = atomic_read(&rdma->sc_sq_avail);
+		__entry->depth = rdma->sc_sq_depth;
+		__entry->status = status;
+		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
+	),
+
+	TP_printk("addr=%s sc_sq_avail=%d/%d status=%d",
+		__get_str(addr), __entry->avail, __entry->depth,
+		__entry->status
+	)
+);
+
 #endif /* _TRACE_RPCRDMA_H */
 
 #include <trace/define_trace.h>
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 191fe447f990..ba9efdc848f9 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -1112,18 +1112,17 @@ TRACE_EVENT(rxrpc_rtt_tx,
 TRACE_EVENT(rxrpc_rtt_rx,
 	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
 		     rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
-		     s64 rtt, u8 nr, s64 avg),
+		     u32 rtt, u32 rto),
 
-	    TP_ARGS(call, why, send_serial, resp_serial, rtt, nr, avg),
+	    TP_ARGS(call, why, send_serial, resp_serial, rtt, rto),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call		)
 		    __field(enum rxrpc_rtt_rx_trace,	why		)
-		    __field(u8,				nr		)
 		    __field(rxrpc_serial_t,		send_serial	)
 		    __field(rxrpc_serial_t,		resp_serial	)
-		    __field(s64,			rtt		)
-		    __field(u64,			avg		)
+		    __field(u32,			rtt		)
+		    __field(u32,			rto		)
 			     ),
 
 	    TP_fast_assign(
@@ -1132,18 +1131,16 @@ TRACE_EVENT(rxrpc_rtt_rx,
 		    __entry->send_serial = send_serial;
 		    __entry->resp_serial = resp_serial;
 		    __entry->rtt = rtt;
-		    __entry->nr = nr;
-		    __entry->avg = avg;
+		    __entry->rto = rto;
 			   ),
 
-	    TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%lld nr=%u avg=%lld",
+	    TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%u rto=%u",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_rtt_rx_traces),
 		      __entry->send_serial,
 		      __entry->resp_serial,
 		      __entry->rtt,
-		      __entry->nr,
-		      __entry->avg)
+		      __entry->rto)
 	    );
 
 TRACE_EVENT(rxrpc_timer,
@@ -1544,6 +1541,41 @@ TRACE_EVENT(rxrpc_notify_socket,
 		      __entry->serial)
 	    );
 
+TRACE_EVENT(rxrpc_rx_discard_ack,
+	    TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial,
+		     rxrpc_seq_t first_soft_ack, rxrpc_seq_t call_ackr_first,
+		     rxrpc_seq_t prev_pkt, rxrpc_seq_t call_ackr_prev),
+
+	    TP_ARGS(debug_id, serial, first_soft_ack, call_ackr_first,
+		    prev_pkt, call_ackr_prev),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	debug_id	)
+		    __field(rxrpc_serial_t,	serial		)
+		    __field(rxrpc_seq_t,	first_soft_ack)
+		    __field(rxrpc_seq_t,	call_ackr_first)
+		    __field(rxrpc_seq_t,	prev_pkt)
+		    __field(rxrpc_seq_t,	call_ackr_prev)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->debug_id		= debug_id;
+		    __entry->serial		= serial;
+		    __entry->first_soft_ack	= first_soft_ack;
+		    __entry->call_ackr_first	= call_ackr_first;
+		    __entry->prev_pkt		= prev_pkt;
+		    __entry->call_ackr_prev	= call_ackr_prev;
+			   ),
+
+	    TP_printk("c=%08x r=%08x %08x<%08x %08x<%08x",
+		      __entry->debug_id,
+		      __entry->serial,
+		      __entry->first_soft_ack,
+		      __entry->call_ackr_first,
+		      __entry->prev_pkt,
+		      __entry->call_ackr_prev)
+	    );
+
 #endif /* _TRACE_RXRPC_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h
index 37342a13c9cb..9c66e59d859c 100644
--- a/include/trace/events/wbt.h
+++ b/include/trace/events/wbt.h
@@ -33,7 +33,7 @@ TRACE_EVENT(wbt_stat,
 	),
 
 	TP_fast_assign(
-		strlcpy(__entry->name, dev_name(bdi->dev),
+		strlcpy(__entry->name, bdi_dev_name(bdi),
 			ARRAY_SIZE(__entry->name));
 		__entry->rmean		= stat[0].mean;
 		__entry->rmin		= stat[0].min;
@@ -46,7 +46,7 @@ TRACE_EVENT(wbt_stat,
 	),
 
 	TP_printk("%s: rmean=%llu, rmin=%llu, rmax=%llu, rsamples=%llu, "
-		  "wmean=%llu, wmin=%llu, wmax=%llu, wsamples=%llu\n",
+		  "wmean=%llu, wmin=%llu, wmax=%llu, wsamples=%llu",
 		  __entry->name, __entry->rmean, __entry->rmin, __entry->rmax,
 		  __entry->rnr_samples, __entry->wmean, __entry->wmin,
 		  __entry->wmax, __entry->wnr_samples)
@@ -68,12 +68,12 @@ TRACE_EVENT(wbt_lat,
 	),
 
 	TP_fast_assign(
-		strlcpy(__entry->name, dev_name(bdi->dev),
+		strlcpy(__entry->name, bdi_dev_name(bdi),
 			ARRAY_SIZE(__entry->name));
 		__entry->lat = div_u64(lat, 1000);
 	),
 
-	TP_printk("%s: latency %lluus\n", __entry->name,
+	TP_printk("%s: latency %lluus", __entry->name,
 			(unsigned long long) __entry->lat)
 );
 
@@ -105,7 +105,7 @@ TRACE_EVENT(wbt_step,
 	),
 
 	TP_fast_assign(
-		strlcpy(__entry->name, dev_name(bdi->dev),
+		strlcpy(__entry->name, bdi_dev_name(bdi),
 			ARRAY_SIZE(__entry->name));
 		__entry->msg	= msg;
 		__entry->step	= step;
@@ -115,7 +115,7 @@ TRACE_EVENT(wbt_step,
 		__entry->max	= max;
 	),
 
-	TP_printk("%s: %s: step=%d, window=%luus, background=%u, normal=%u, max=%u\n",
+	TP_printk("%s: %s: step=%d, window=%luus, background=%u, normal=%u, max=%u",
 		  __entry->name, __entry->msg, __entry->step, __entry->window,
 		  __entry->bg, __entry->normal, __entry->max)
 );
@@ -141,14 +141,14 @@ TRACE_EVENT(wbt_timer,
 	),
 
 	TP_fast_assign(
-		strlcpy(__entry->name, dev_name(bdi->dev),
+		strlcpy(__entry->name, bdi_dev_name(bdi),
 			ARRAY_SIZE(__entry->name));
 		__entry->status		= status;
 		__entry->step		= step;
 		__entry->inflight	= inflight;
 	),
 
-	TP_printk("%s: status=%u, step=%d, inflight=%u\n", __entry->name,
+	TP_printk("%s: status=%u, step=%d, inflight=%u", __entry->name,
 		  __entry->status, __entry->step, __entry->inflight)
 );
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index d94def25e4dc..85a33bea76f1 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -36,7 +36,6 @@
 	EM( WB_REASON_SYNC,			"sync")			\
 	EM( WB_REASON_PERIODIC,			"periodic")		\
 	EM( WB_REASON_LAPTOP_TIMER,		"laptop_timer")		\
-	EM( WB_REASON_FREE_MORE_MEM,		"free_more_memory")	\
 	EM( WB_REASON_FS_FREE_SPACE,		"fs_free_space")	\
 	EMe(WB_REASON_FORKER_THREAD,		"forker_thread")
 
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 65f69723cbdc..d28b4ce744d5 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -346,6 +346,10 @@ struct drm_amdgpu_gem_userptr {
 #define AMDGPU_TILING_DCC_PITCH_MAX_MASK		0x3FFF
 #define AMDGPU_TILING_DCC_INDEPENDENT_64B_SHIFT		43
 #define AMDGPU_TILING_DCC_INDEPENDENT_64B_MASK		0x1
+#define AMDGPU_TILING_DCC_INDEPENDENT_128B_SHIFT	44
+#define AMDGPU_TILING_DCC_INDEPENDENT_128B_MASK		0x1
+#define AMDGPU_TILING_SCANOUT_SHIFT			63
+#define AMDGPU_TILING_SCANOUT_MASK			0x1
 
 /* Set/Get helpers for tiling flags. */
 #define AMDGPU_TILING_SET(field, value) \
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2e29a671d67e..f9b7fdd951e4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -73,7 +73,7 @@ struct bpf_insn {
 /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
 struct bpf_lpm_trie_key {
 	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */
-	__u8	data[];	/* Arbitrary size */
+	__u8	data[0];	/* Arbitrary size */
 };
 
 struct bpf_cgroup_storage_key {
@@ -1642,7 +1642,7 @@ union bpf_attr {
  * 		ifindex, but doesn't require a map to do so.
  * 	Return
  * 		**XDP_REDIRECT** on success, or the value of the two lower bits
- * 		of the **flags* argument on error.
+ * 		of the *flags* argument on error.
  *
  * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 8134924cfc17..e6b6cb0f8bc6 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -36,12 +36,10 @@ struct btrfs_ioctl_vol_args {
 #define BTRFS_DEVICE_PATH_NAME_MAX	1024
 #define BTRFS_SUBVOL_NAME_MAX 		4039
 
-/*
- * Deprecated since 5.7:
- *
- * BTRFS_SUBVOL_CREATE_ASYNC	(1ULL << 0)
- */
-
+#ifndef __KERNEL__
+/* Deprecated since 5.7 */
+# define BTRFS_SUBVOL_CREATE_ASYNC	(1ULL << 0)
+#endif
 #define BTRFS_SUBVOL_RDONLY		(1ULL << 1)
 #define BTRFS_SUBVOL_QGROUP_INHERIT	(1ULL << 2)
 
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 272dc69fa080..e58c9636741b 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -367,8 +367,14 @@ struct vfs_ns_cap_data {
 
 #define CAP_AUDIT_READ		37
 
+/*
+ * Allow system performance and observability privileged operations
+ * using perf_events, i915_perf and other kernel subsystems
+ */
+
+#define CAP_PERFMON		38
 
-#define CAP_LAST_CAP         CAP_AUDIT_READ
+#define CAP_LAST_CAP         CAP_PERFMON
 
 #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
 
diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h
index dbc7092e04b5..7f30393b92c3 100644
--- a/include/uapi/linux/dma-buf.h
+++ b/include/uapi/linux/dma-buf.h
@@ -39,6 +39,12 @@ struct dma_buf_sync {
 
 #define DMA_BUF_BASE		'b'
 #define DMA_BUF_IOCTL_SYNC	_IOW(DMA_BUF_BASE, 0, struct dma_buf_sync)
+
+/* 32/64bitness of this uapi was botched in android, there's no difference
+ * between them in actual uapi, they're just different numbers.
+ */
 #define DMA_BUF_SET_NAME	_IOW(DMA_BUF_BASE, 1, const char *)
+#define DMA_BUF_SET_NAME_A	_IOW(DMA_BUF_BASE, 1, u32)
+#define DMA_BUF_SET_NAME_B	_IOW(DMA_BUF_BASE, 1, u64)
 
 #endif
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 34c02e4290fe..c6dd0215482e 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -36,6 +36,7 @@ typedef __s64	Elf64_Sxword;
 #define PT_LOPROC  0x70000000
 #define PT_HIPROC  0x7fffffff
 #define PT_GNU_EH_FRAME		0x6474e550
+#define PT_GNU_PROPERTY		0x6474e553
 
 #define PT_GNU_STACK	(PT_LOOS + 0x474e551)
 
@@ -367,6 +368,7 @@ typedef struct elf64_shdr {
  * Notes used in ET_CORE. Architectures export some of the arch register sets
  * using the corresponding note types via the PTRACE_GETREGSET and
  * PTRACE_SETREGSET requests.
+ * The note name for all these is "LINUX".
  */
 #define NT_PRSTATUS	1
 #define NT_PRFPREG	2
@@ -429,6 +431,9 @@ typedef struct elf64_shdr {
 #define NT_MIPS_FP_MODE	0x801		/* MIPS floating-point mode */
 #define NT_MIPS_MSA	0x802		/* MIPS SIMD registers */
 
+/* Note types with note name "GNU" */
+#define NT_GNU_PROPERTY_TYPE_0	5
+
 /* Note header in a PT_NOTE section */
 typedef struct elf32_note {
   Elf32_Word	n_namesz;	/* Name size */
@@ -443,4 +448,10 @@ typedef struct elf64_note {
   Elf64_Word n_type;	/* Content type */
 } Elf64_Nhdr;
 
+/* .note.gnu.property types for EM_AARCH64: */
+#define GNU_PROPERTY_AARCH64_FEATURE_1_AND	0xc0000000
+
+/* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */
+#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI	(1U << 0)
+
 #endif /* _UAPI_LINUX_ELF_H */
diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h
index a10e3cdc2839..7875709ccfeb 100644
--- a/include/uapi/linux/fscrypt.h
+++ b/include/uapi/linux/fscrypt.h
@@ -19,7 +19,8 @@
 #define FSCRYPT_POLICY_FLAGS_PAD_MASK		0x03
 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY		0x04
 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64	0x08
-#define FSCRYPT_POLICY_FLAGS_VALID		0x0F
+#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32	0x10
+#define FSCRYPT_POLICY_FLAGS_VALID		0x1F
 
 /* Encryption algorithms */
 #define FSCRYPT_MODE_AES_256_XTS		1
diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h
index 991b2b7ada7a..8f24404ad04f 100644
--- a/include/uapi/linux/hyperv.h
+++ b/include/uapi/linux/hyperv.h
@@ -119,8 +119,8 @@ enum hv_fcopy_op {
 
 struct hv_fcopy_hdr {
 	__u32 operation;
-	uuid_le service_id0; /* currently unused */
-	uuid_le service_id1; /* currently unused */
+	__u8 service_id0[16]; /* currently unused */
+	__u8 service_id1[16]; /* currently unused */
 } __attribute__((packed));
 
 #define OVER_WRITE	0x1
diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h
index b122cfac7128..683878036d76 100644
--- a/include/uapi/linux/if_arcnet.h
+++ b/include/uapi/linux/if_arcnet.h
@@ -60,7 +60,7 @@ struct arc_rfc1201 {
 	__u8  proto;		/* protocol ID field - varies		*/
 	__u8  split_flag;	/* for use with split packets		*/
 	__be16   sequence;	/* sequence number			*/
-	__u8  payload[];	/* space remaining in packet (504 bytes)*/
+	__u8  payload[0];	/* space remaining in packet (504 bytes)*/
 };
 #define RFC1201_HDR_SIZE 4
 
@@ -69,7 +69,7 @@ struct arc_rfc1201 {
  */
 struct arc_rfc1051 {
 	__u8 proto;		/* ARC_P_RFC1051_ARP/RFC1051_IP	*/
-	__u8 payload[];	/* 507 bytes			*/
+	__u8 payload[0];	/* 507 bytes			*/
 };
 #define RFC1051_HDR_SIZE 1
 
@@ -80,7 +80,7 @@ struct arc_rfc1051 {
 struct arc_eth_encap {
 	__u8 proto;		/* Always ARC_P_ETHER			*/
 	struct ethhdr eth;	/* standard ethernet header (yuck!)	*/
-	__u8 payload[];	/* 493 bytes				*/
+	__u8 payload[0];	/* 493 bytes				*/
 };
 #define ETH_ENCAP_HDR_SIZE 14
 
diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h
index 98e29e7f54ac..00c08120f3ba 100644
--- a/include/uapi/linux/mmc/ioctl.h
+++ b/include/uapi/linux/mmc/ioctl.h
@@ -57,7 +57,7 @@ struct mmc_ioc_cmd {
  */
 struct mmc_ioc_multi_cmd {
 	__u64 num_of_cmds;
-	struct mmc_ioc_cmd cmds[];
+	struct mmc_ioc_cmd cmds[0];
 };
 
 #define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd)
diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h
index 67e31f329190..66048cc5d7b3 100644
--- a/include/uapi/linux/net_dropmon.h
+++ b/include/uapi/linux/net_dropmon.h
@@ -29,12 +29,12 @@ struct net_dm_config_entry {
 
 struct net_dm_config_msg {
 	__u32 entries;
-	struct net_dm_config_entry options[];
+	struct net_dm_config_entry options[0];
 };
 
 struct net_dm_alert_msg {
 	__u32 entries;
-	struct net_dm_drop_point points[];
+	struct net_dm_drop_point points[0];
 };
 
 struct net_dm_user_msg {
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 30f2a87270dc..4565456c0ef4 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -276,6 +276,7 @@ enum nft_rule_compat_attributes {
  * @NFT_SET_TIMEOUT: set uses timeouts
  * @NFT_SET_EVAL: set can be updated from the evaluation path
  * @NFT_SET_OBJECT: set contains stateful objects
+ * @NFT_SET_CONCAT: set contains a concatenation
  */
 enum nft_set_flags {
 	NFT_SET_ANONYMOUS		= 0x1,
@@ -285,6 +286,7 @@ enum nft_set_flags {
 	NFT_SET_TIMEOUT			= 0x10,
 	NFT_SET_EVAL			= 0x20,
 	NFT_SET_OBJECT			= 0x40,
+	NFT_SET_CONCAT			= 0x80,
 };
 
 /**
diff --git a/include/uapi/linux/netfilter/xt_IDLETIMER.h b/include/uapi/linux/netfilter/xt_IDLETIMER.h
index 434e6506abaa..49ddcdc61c09 100644
--- a/include/uapi/linux/netfilter/xt_IDLETIMER.h
+++ b/include/uapi/linux/netfilter/xt_IDLETIMER.h
@@ -48,6 +48,7 @@ struct idletimer_tg_info_v1 {
 
 	char label[MAX_IDLETIMER_LABEL_SIZE];
 
+	__u8 send_nl_msg;   /* unused: for compatibility with Android */
 	__u8 timer_type;
 
 	/* for kernel module internal use only */
diff --git a/include/uapi/linux/netfilter_bridge/ebt_among.h b/include/uapi/linux/netfilter_bridge/ebt_among.h
index 73b26a280c4f..9acf757bc1f7 100644
--- a/include/uapi/linux/netfilter_bridge/ebt_among.h
+++ b/include/uapi/linux/netfilter_bridge/ebt_among.h
@@ -40,7 +40,7 @@ struct ebt_mac_wormhash_tuple {
 struct ebt_mac_wormhash {
 	int table[257];
 	int poolsize;
-	struct ebt_mac_wormhash_tuple pool[];
+	struct ebt_mac_wormhash_tuple pool[0];
 };
 
 #define ebt_mac_wormhash_size(x) ((x) ? sizeof(struct ebt_mac_wormhash) \
diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h
index 0549a5c622bf..91b4c63d5cbf 100644
--- a/include/uapi/linux/psp-sev.h
+++ b/include/uapi/linux/psp-sev.h
@@ -83,6 +83,8 @@ struct sev_user_data_status {
 	__u32 guest_count;			/* Out */
 } __packed;
 
+#define SEV_STATUS_FLAGS_CONFIG_ES	0x0100
+
 /**
  * struct sev_user_data_pek_csr - PEK_CSR command parameters
  *
diff --git a/include/uapi/linux/usb/raw_gadget.h b/include/uapi/linux/usb/raw_gadget.h
index ea375082b3ac..0be685272eb1 100644
--- a/include/uapi/linux/usb/raw_gadget.h
+++ b/include/uapi/linux/usb/raw_gadget.h
@@ -93,6 +93,64 @@ struct usb_raw_ep_io {
 	__u8		data[0];
 };
 
+/* Maximum number of non-control endpoints in struct usb_raw_eps_info. */
+#define USB_RAW_EPS_NUM_MAX	30
+
+/* Maximum length of UDC endpoint name in struct usb_raw_ep_info. */
+#define USB_RAW_EP_NAME_MAX	16
+
+/* Used as addr in struct usb_raw_ep_info if endpoint accepts any address. */
+#define USB_RAW_EP_ADDR_ANY	0xff
+
+/*
+ * struct usb_raw_ep_caps - exposes endpoint capabilities from struct usb_ep
+ *     (technically from its member struct usb_ep_caps).
+ */
+struct usb_raw_ep_caps {
+	__u32	type_control	: 1;
+	__u32	type_iso	: 1;
+	__u32	type_bulk	: 1;
+	__u32	type_int	: 1;
+	__u32	dir_in		: 1;
+	__u32	dir_out		: 1;
+};
+
+/*
+ * struct usb_raw_ep_limits - exposes endpoint limits from struct usb_ep.
+ * @maxpacket_limit: Maximum packet size value supported by this endpoint.
+ * @max_streams: maximum number of streams supported by this endpoint
+ *     (actual number is 2^n).
+ * @reserved: Empty, reserved for potential future extensions.
+ */
+struct usb_raw_ep_limits {
+	__u16	maxpacket_limit;
+	__u16	max_streams;
+	__u32	reserved;
+};
+
+/*
+ * struct usb_raw_ep_info - stores information about a gadget endpoint.
+ * @name: Name of the endpoint as it is defined in the UDC driver.
+ * @addr: Address of the endpoint that must be specified in the endpoint
+ *     descriptor passed to USB_RAW_IOCTL_EP_ENABLE ioctl.
+ * @caps: Endpoint capabilities.
+ * @limits: Endpoint limits.
+ */
+struct usb_raw_ep_info {
+	__u8				name[USB_RAW_EP_NAME_MAX];
+	__u32				addr;
+	struct usb_raw_ep_caps		caps;
+	struct usb_raw_ep_limits	limits;
+};
+
+/*
+ * struct usb_raw_eps_info - argument for USB_RAW_IOCTL_EPS_INFO ioctl.
+ * eps: Structures that store information about non-control endpoints.
+ */
+struct usb_raw_eps_info {
+	struct usb_raw_ep_info	eps[USB_RAW_EPS_NUM_MAX];
+};
+
 /*
  * Initializes a Raw Gadget instance.
  * Accepts a pointer to the usb_raw_init struct as an argument.
@@ -115,37 +173,38 @@ struct usb_raw_ep_io {
 #define USB_RAW_IOCTL_EVENT_FETCH	_IOR('U', 2, struct usb_raw_event)
 
 /*
- * Queues an IN (OUT for READ) urb as a response to the last control request
- * received on endpoint 0, provided that was an IN (OUT for READ) request and
- * waits until the urb is completed. Copies received data to user for READ.
+ * Queues an IN (OUT for READ) request as a response to the last setup request
+ * received on endpoint 0 (provided that was an IN (OUT for READ) request), and
+ * waits until the request is completed. Copies received data to user for READ.
  * Accepts a pointer to the usb_raw_ep_io struct as an argument.
- * Returns length of trasferred data on success or negative error code on
+ * Returns length of transferred data on success or negative error code on
  * failure.
  */
 #define USB_RAW_IOCTL_EP0_WRITE		_IOW('U', 3, struct usb_raw_ep_io)
 #define USB_RAW_IOCTL_EP0_READ		_IOWR('U', 4, struct usb_raw_ep_io)
 
 /*
- * Finds an endpoint that supports the transfer type specified in the
- * descriptor and enables it.
- * Accepts a pointer to the usb_endpoint_descriptor struct as an argument.
+ * Finds an endpoint that satisfies the parameters specified in the provided
+ * descriptors (address, transfer type, etc.) and enables it.
+ * Accepts a pointer to the usb_raw_ep_descs struct as an argument.
  * Returns enabled endpoint handle on success or negative error code on failure.
  */
 #define USB_RAW_IOCTL_EP_ENABLE		_IOW('U', 5, struct usb_endpoint_descriptor)
 
-/* Disables specified endpoint.
+/*
+ * Disables specified endpoint.
  * Accepts endpoint handle as an argument.
  * Returns 0 on success or negative error code on failure.
  */
 #define USB_RAW_IOCTL_EP_DISABLE	_IOW('U', 6, __u32)
 
 /*
- * Queues an IN (OUT for READ) urb as a response to the last control request
- * received on endpoint usb_raw_ep_io.ep, provided that was an IN (OUT for READ)
- * request and waits until the urb is completed. Copies received data to user
- * for READ.
+ * Queues an IN (OUT for READ) request as a response to the last setup request
+ * received on endpoint usb_raw_ep_io.ep (provided that was an IN (OUT for READ)
+ * request), and waits until the request is completed. Copies received data to
+ * user for READ.
  * Accepts a pointer to the usb_raw_ep_io struct as an argument.
- * Returns length of trasferred data on success or negative error code on
+ * Returns length of transferred data on success or negative error code on
  * failure.
  */
 #define USB_RAW_IOCTL_EP_WRITE		_IOW('U', 7, struct usb_raw_ep_io)
@@ -164,4 +223,27 @@ struct usb_raw_ep_io {
  */
 #define USB_RAW_IOCTL_VBUS_DRAW		_IOW('U', 10, __u32)
 
+/*
+ * Fills in the usb_raw_eps_info structure with information about non-control
+ * endpoints available for the currently connected UDC.
+ * Returns the number of available endpoints on success or negative error code
+ * on failure.
+ */
+#define USB_RAW_IOCTL_EPS_INFO		_IOR('U', 11, struct usb_raw_eps_info)
+
+/*
+ * Stalls a pending control request on endpoint 0.
+ * Returns 0 on success or negative error code on failure.
+ */
+#define USB_RAW_IOCTL_EP0_STALL		_IO('U', 12)
+
+/*
+ * Sets or clears halt or wedge status of the endpoint.
+ * Accepts endpoint handle as an argument.
+ * Returns 0 on success or negative error code on failure.
+ */
+#define USB_RAW_IOCTL_EP_SET_HALT	_IOW('U', 13, __u32)
+#define USB_RAW_IOCTL_EP_CLEAR_HALT	_IOW('U', 14, __u32)
+#define USB_RAW_IOCTL_EP_SET_WEDGE	_IOW('U', 15, __u32)
+
 #endif /* _UAPI__LINUX_USB_RAW_GADGET_H */
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 19974392d324..dc3e656470dd 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -48,8 +48,15 @@ struct virtio_balloon_config {
 	__u32 num_pages;
 	/* Number of pages we've actually got in balloon. */
 	__u32 actual;
-	/* Free page report command id, readonly by guest */
-	__u32 free_page_report_cmd_id;
+	/*
+	 * Free page hint command id, readonly by guest.
+	 * Was previously named free_page_report_cmd_id so we
+	 * need to carry that name for legacy support.
+	 */
+	union {
+		__u32 free_page_hint_cmd_id;
+		__u32 free_page_report_cmd_id;	/* deprecated */
+	};
 	/* Stores PAGE_POISON if page poisoning is in use */
 	__u32 poison_val;
 };
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 5f3b9fec7b5f..ff7cfdc6cb44 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -304,7 +304,7 @@ enum xfrm_attr_type_t {
 	XFRMA_PROTO,		/* __u8 */
 	XFRMA_ADDRESS_FILTER,	/* struct xfrm_address_filter */
 	XFRMA_PAD,
-	XFRMA_OFFLOAD_DEV,	/* struct xfrm_state_offload */
+	XFRMA_OFFLOAD_DEV,	/* struct xfrm_user_offload */
 	XFRMA_SET_MARK,		/* __u32 */
 	XFRMA_SET_MARK_MASK,	/* __u32 */
 	XFRMA_IF_ID,		/* __u32 */
diff --git a/include/uapi/scsi/scsi_bsg_fc.h b/include/uapi/scsi/scsi_bsg_fc.h
index 7f5930801f72..3ae65e93235c 100644
--- a/include/uapi/scsi/scsi_bsg_fc.h
+++ b/include/uapi/scsi/scsi_bsg_fc.h
@@ -209,7 +209,7 @@ struct fc_bsg_host_vendor {
 	__u64 vendor_id;
 
 	/* start of vendor command area */
-	__u32 vendor_cmd[];
+	__u32 vendor_cmd[0];
 };
 
 /* Response:
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 5cbc9fcbfd45..7955c56d6b3c 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -73,8 +73,8 @@ struct vdso_timestamp {
  *
  * @offset is used by the special time namespace VVAR pages which are
  * installed instead of the real VVAR page. These namespace pages must set
- * @seq to 1 and @clock_mode to VLOCK_TIMENS to force the code into the
- * time namespace slow path. The namespace aware functions retrieve the
+ * @seq to 1 and @clock_mode to VDSO_CLOCKMODE_TIMENS to force the code into
+ * the time namespace slow path. The namespace aware functions retrieve the
  * real system wide VVAR page, read host time and add the per clock offset.
  * For clocks which are not affected by time namespace adjustment the
  * offset must be zero.
diff --git a/init/Kconfig b/init/Kconfig
index 9e22ee8fbd75..74a5ac65644f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -39,22 +39,6 @@ config TOOLS_SUPPORT_RELR
 config CC_HAS_ASM_INLINE
 	def_bool $(success,echo 'void foo(void) { asm inline (""); }' | $(CC) -x c - -c -o /dev/null)
 
-config CC_HAS_WARN_MAYBE_UNINITIALIZED
-	def_bool $(cc-option,-Wmaybe-uninitialized)
-	help
-	  GCC >= 4.7 supports this option.
-
-config CC_DISABLE_WARN_MAYBE_UNINITIALIZED
-	bool
-	depends on CC_HAS_WARN_MAYBE_UNINITIALIZED
-	default CC_IS_GCC && GCC_VERSION < 40900  # unreliable for GCC < 4.9
-	help
-	  GCC's -Wmaybe-uninitialized is not reliable by definition.
-	  Lots of false positive warnings are produced in some cases.
-
-	  If this option is enabled, -Wno-maybe-uninitialzed is passed
-	  to the compiler to suppress maybe-uninitialized warnings.
-
 config CONSTRUCTORS
 	bool
 	depends on !UML
@@ -1257,14 +1241,12 @@ config CC_OPTIMIZE_FOR_PERFORMANCE
 config CC_OPTIMIZE_FOR_PERFORMANCE_O3
 	bool "Optimize more for performance (-O3)"
 	depends on ARC
-	imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED  # avoid false positives
 	help
 	  Choosing this option will pass "-O3" to your compiler to optimize
 	  the kernel yet more for performance.
 
 config CC_OPTIMIZE_FOR_SIZE
 	bool "Optimize for size (-Os)"
-	imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED  # avoid false positives
 	help
 	  Choosing this option will pass "-Os" to your compiler resulting
 	  in a smaller kernel.
@@ -2279,6 +2261,9 @@ config ASN1
 
 source "kernel/Kconfig.locks"
 
+config ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	bool
+
 config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
 	bool
 
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index dab8b1151b56..d72beda824aa 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -28,7 +28,7 @@ static int __init no_initrd(char *str)
 
 __setup("noinitrd", no_initrd);
 
-static int __init early_initrd(char *p)
+static int __init early_initrdmem(char *p)
 {
 	phys_addr_t start;
 	unsigned long size;
@@ -43,6 +43,17 @@ static int __init early_initrd(char *p)
 	}
 	return 0;
 }
+early_param("initrdmem", early_initrdmem);
+
+/*
+ * This is here as the initrd keyword has been in use since 11/2018
+ * on ARM, PowerPC, and MIPS.
+ * It should not be; it is reserved for bootloaders.
+ */
+static int __init early_initrd(char *p)
+{
+	return early_initrdmem(p);
+}
 early_param("initrd", early_initrd);
 
 static int init_linuxrc(struct subprocess_info *info, struct cred *new)
diff --git a/init/init_task.c b/init/init_task.c
index bd403ed3e418..15303d58d9db 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -11,6 +11,7 @@
 #include <linux/mm.h>
 #include <linux/audit.h>
 #include <linux/numa.h>
+#include <linux/scs.h>
 
 #include <asm/pgtable.h>
 #include <linux/uaccess.h>
@@ -50,6 +51,13 @@ static struct sighand_struct init_sighand = {
 	.signalfd_wqh	= __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh),
 };
 
+#ifdef CONFIG_SHADOW_CALL_STACK
+unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)]
+		__init_task_data = {
+	[(SCS_SIZE / sizeof(long)) - 1] = SCS_END_MAGIC
+};
+#endif
+
 /*
  * Set up the first task table, touch at your own risk!. Base=0,
  * limit=0x1fffff (=2MB)
@@ -141,6 +149,11 @@ struct task_struct init_task
 	.rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list),
 	.rcu_tasks_idle_cpu = -1,
 #endif
+#ifdef CONFIG_TASKS_TRACE_RCU
+	.trc_reader_nesting = 0,
+	.trc_reader_special.s = 0,
+	.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
+#endif
 #ifdef CONFIG_CPUSETS
 	.mems_allowed_seq = SEQCNT_ZERO(init_task.mems_allowed_seq),
 #endif
diff --git a/init/initramfs.c b/init/initramfs.c
index 8ec1be4d7d51..7a38012e1af7 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -542,7 +542,7 @@ void __weak free_initrd_mem(unsigned long start, unsigned long end)
 }
 
 #ifdef CONFIG_KEXEC_CORE
-static bool kexec_free_initrd(void)
+static bool __init kexec_free_initrd(void)
 {
 	unsigned long crashk_start = (unsigned long)__va(crashk_res.start);
 	unsigned long crashk_end   = (unsigned long)__va(crashk_res.end);
diff --git a/init/main.c b/init/main.c
index a48617f2e5e5..03371976d387 100644
--- a/init/main.c
+++ b/init/main.c
@@ -257,6 +257,47 @@ static int __init loglevel(char *str)
 
 early_param("loglevel", loglevel);
 
+#ifdef CONFIG_BLK_DEV_INITRD
+static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum)
+{
+	u32 size, csum;
+	char *data;
+	u32 *hdr;
+
+	if (!initrd_end)
+		return NULL;
+
+	data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
+	if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
+		return NULL;
+
+	hdr = (u32 *)(data - 8);
+	size = hdr[0];
+	csum = hdr[1];
+
+	data = ((void *)hdr) - size;
+	if ((unsigned long)data < initrd_start) {
+		pr_err("bootconfig size %d is greater than initrd size %ld\n",
+			size, initrd_end - initrd_start);
+		return NULL;
+	}
+
+	/* Remove bootconfig from initramfs/initrd */
+	initrd_end = (unsigned long)data;
+	if (_size)
+		*_size = size;
+	if (_csum)
+		*_csum = csum;
+
+	return data;
+}
+#else
+static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum)
+{
+	return NULL;
+}
+#endif
+
 #ifdef CONFIG_BOOT_CONFIG
 
 char xbc_namebuf[XBC_KEYLEN_MAX] __initdata;
@@ -357,9 +398,11 @@ static void __init setup_boot_config(const char *cmdline)
 	int pos;
 	u32 size, csum;
 	char *data, *copy;
-	u32 *hdr;
 	int ret;
 
+	/* Cut out the bootconfig data even if we have no bootconfig option */
+	data = get_boot_config_from_initrd(&size, &csum);
+
 	strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
 	parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL,
 		   bootconfig_params);
@@ -367,16 +410,10 @@ static void __init setup_boot_config(const char *cmdline)
 	if (!bootconfig_found)
 		return;
 
-	if (!initrd_end)
-		goto not_found;
-
-	data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
-	if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
-		goto not_found;
-
-	hdr = (u32 *)(data - 8);
-	size = hdr[0];
-	csum = hdr[1];
+	if (!data) {
+		pr_err("'bootconfig' found on command line, but no bootconfig found\n");
+		return;
+	}
 
 	if (size >= XBC_DATA_MAX) {
 		pr_err("bootconfig size %d greater than max size %d\n",
@@ -384,10 +421,6 @@ static void __init setup_boot_config(const char *cmdline)
 		return;
 	}
 
-	data = ((void *)hdr) - size;
-	if ((unsigned long)data < initrd_start)
-		goto not_found;
-
 	if (boot_config_checksum((unsigned char *)data, size) != csum) {
 		pr_err("bootconfig checksum failed\n");
 		return;
@@ -417,11 +450,15 @@ static void __init setup_boot_config(const char *cmdline)
 		extra_init_args = xbc_make_cmdline("init");
 	}
 	return;
-not_found:
-	pr_err("'bootconfig' found on command line, but no bootconfig found\n");
 }
+
 #else
-#define setup_boot_config(cmdline)	do { } while (0)
+
+static void __init setup_boot_config(const char *cmdline)
+{
+	/* Remove bootconfig data from initrd */
+	get_boot_config_from_initrd(NULL, NULL);
+}
 
 static int __init warn_bootconfig(char *str)
 {
@@ -1001,6 +1038,8 @@ asmlinkage __visible void __init start_kernel(void)
 
 	/* Do the rest non-__init'ed, we're now alive */
 	arch_call_rest_init();
+
+	prevent_tail_call_optimization();
 }
 
 /* Call all constructor functions linked into the kernel. */
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index dc8307bf2d74..beff0cfcd1e8 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -142,6 +142,7 @@ struct mqueue_inode_info {
 
 	struct sigevent notify;
 	struct pid *notify_owner;
+	u32 notify_self_exec_id;
 	struct user_namespace *notify_user_ns;
 	struct user_struct *user;	/* user who created, for accounting */
 	struct sock *notify_sock;
@@ -773,28 +774,44 @@ static void __do_notify(struct mqueue_inode_info *info)
 	 * synchronously. */
 	if (info->notify_owner &&
 	    info->attr.mq_curmsgs == 1) {
-		struct kernel_siginfo sig_i;
 		switch (info->notify.sigev_notify) {
 		case SIGEV_NONE:
 			break;
-		case SIGEV_SIGNAL:
-			/* sends signal */
+		case SIGEV_SIGNAL: {
+			struct kernel_siginfo sig_i;
+			struct task_struct *task;
+
+			/* do_mq_notify() accepts sigev_signo == 0, why?? */
+			if (!info->notify.sigev_signo)
+				break;
 
 			clear_siginfo(&sig_i);
 			sig_i.si_signo = info->notify.sigev_signo;
 			sig_i.si_errno = 0;
 			sig_i.si_code = SI_MESGQ;
 			sig_i.si_value = info->notify.sigev_value;
-			/* map current pid/uid into info->owner's namespaces */
 			rcu_read_lock();
+			/* map current pid/uid into info->owner's namespaces */
 			sig_i.si_pid = task_tgid_nr_ns(current,
 						ns_of_pid(info->notify_owner));
-			sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid());
+			sig_i.si_uid = from_kuid_munged(info->notify_user_ns,
+						current_uid());
+			/*
+			 * We can't use kill_pid_info(), this signal should
+			 * bypass check_kill_permission(). It is from kernel
+			 * but si_fromuser() can't know this.
+			 * We do check the self_exec_id, to avoid sending
+			 * signals to programs that don't expect them.
+			 */
+			task = pid_task(info->notify_owner, PIDTYPE_TGID);
+			if (task && task->self_exec_id ==
+						info->notify_self_exec_id) {
+				do_send_sig_info(info->notify.sigev_signo,
+						&sig_i, task, PIDTYPE_TGID);
+			}
 			rcu_read_unlock();
-
-			kill_pid_info(info->notify.sigev_signo,
-				      &sig_i, info->notify_owner);
 			break;
+		}
 		case SIGEV_THREAD:
 			set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
 			netlink_sendskb(info->notify_sock, info->notify_cookie);
@@ -1383,6 +1400,7 @@ retry:
 			info->notify.sigev_signo = notification->sigev_signo;
 			info->notify.sigev_value = notification->sigev_value;
 			info->notify.sigev_notify = SIGEV_SIGNAL;
+			info->notify_self_exec_id = current->self_exec_id;
 			break;
 		}
 
diff --git a/ipc/util.c b/ipc/util.c
index 7acccfded7cb..cfa0045e748d 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -764,21 +764,21 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
 			total++;
 	}
 
-	*new_pos = pos + 1;
+	ipc = NULL;
 	if (total >= ids->in_use)
-		return NULL;
+		goto out;
 
 	for (; pos < ipc_mni; pos++) {
 		ipc = idr_find(&ids->ipcs_idr, pos);
 		if (ipc != NULL) {
 			rcu_read_lock();
 			ipc_lock_object(ipc);
-			return ipc;
+			break;
 		}
 	}
-
-	/* Out of range - return NULL to terminate iteration */
-	return NULL;
+out:
+	*new_pos = pos + 1;
+	return ipc;
 }
 
 static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos)
diff --git a/kernel/Makefile b/kernel/Makefile
index 4cb4130ced32..c332eb9d4841 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -103,6 +103,7 @@ obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_CPU_PM) += cpu_pm.o
 obj-$(CONFIG_BPF) += bpf/
+obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
diff --git a/kernel/audit.c b/kernel/audit.c
index b69c8b460341..87f31bf1f0a0 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1326,6 +1326,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
 		if (!audit_enabled && msg_type != AUDIT_USER_AVC)
 			return 0;
+		/* exit early if there isn't at least one character to print */
+		if (data_len < 2)
+			return -EINVAL;
 
 		err = audit_filter(msg_type, AUDIT_FILTER_USER);
 		if (err == 1) { /* match or error */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 95d77770353c..1d6120fd5ba6 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -486,7 +486,12 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 	if (!(map->map_flags & BPF_F_MMAPABLE))
 		return -EINVAL;
 
-	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff);
+	if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) >
+	    PAGE_ALIGN((u64)array->map.max_entries * array->elem_size))
+		return -EINVAL;
+
+	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array),
+				   vma->vm_pgoff + pgoff);
 }
 
 const struct bpf_map_ops array_map_ops = {
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index f02504640e18..6b12f06ee18c 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -30,7 +30,7 @@ struct bpf_lru_node {
 struct bpf_lru_list {
 	struct list_head lists[NR_BPF_LRU_LIST_T];
 	unsigned int counts[NR_BPF_LRU_LIST_COUNT];
-	/* The next inacitve list rotation starts from here */
+	/* The next inactive list rotation starts from here */
 	struct list_head *next_inactive_rotation;
 
 	raw_spinlock_t lock ____cacheline_aligned_in_smp;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 916f5132a984..14aa1f74dd10 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -262,10 +262,10 @@ void __bpf_prog_free(struct bpf_prog *fp)
 
 int bpf_prog_calc_tag(struct bpf_prog *fp)
 {
-	const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
+	const u32 bits_offset = SHA1_BLOCK_SIZE - sizeof(__be64);
 	u32 raw_size = bpf_prog_tag_scratch_size(fp);
-	u32 digest[SHA_DIGEST_WORDS];
-	u32 ws[SHA_WORKSPACE_WORDS];
+	u32 digest[SHA1_DIGEST_WORDS];
+	u32 ws[SHA1_WORKSPACE_WORDS];
 	u32 i, bsize, psize, blocks;
 	struct bpf_insn *dst;
 	bool was_ld_map;
@@ -277,7 +277,7 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	if (!raw)
 		return -ENOMEM;
 
-	sha_init(digest);
+	sha1_init(digest);
 	memset(ws, 0, sizeof(ws));
 
 	/* We need to take out the map fd for the digest calculation
@@ -308,8 +308,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	memset(&raw[psize], 0, raw_size - psize);
 	raw[psize++] = 0x80;
 
-	bsize  = round_up(psize, SHA_MESSAGE_BYTES);
-	blocks = bsize / SHA_MESSAGE_BYTES;
+	bsize  = round_up(psize, SHA1_BLOCK_SIZE);
+	blocks = bsize / SHA1_BLOCK_SIZE;
 	todo   = raw;
 	if (bsize - psize >= sizeof(__be64)) {
 		bits = (__be64 *)(todo + bsize - sizeof(__be64));
@@ -320,12 +320,12 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 	*bits = cpu_to_be64((psize - 1) << 3);
 
 	while (blocks--) {
-		sha_transform(digest, todo, ws);
-		todo += SHA_MESSAGE_BYTES;
+		sha1_transform(digest, todo, ws);
+		todo += SHA1_BLOCK_SIZE;
 	}
 
 	result = (__force __be32 *)digest;
-	for (i = 0; i < SHA_DIGEST_WORDS; i++)
+	for (i = 0; i < SHA1_DIGEST_WORDS; i++)
 		result[i] = cpu_to_be32(digest[i]);
 	memcpy(fp->tag, result, sizeof(fp->tag));
 
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 70f71b154fa5..3fe0b006d2d2 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -469,7 +469,7 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -EOVERFLOW;
 
 	/* Make sure CPU is a valid possible cpu */
-	if (!cpu_possible(key_cpu))
+	if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
 		return -ENODEV;
 
 	if (qsize == 0) {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 64783da34202..4e6dee19a668 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -586,9 +586,7 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	bpf_map_inc_with_uref(map);
-
-	if (vma->vm_flags & VM_WRITE) {
+	if (vma->vm_flags & VM_MAYWRITE) {
 		mutex_lock(&map->freeze_mutex);
 		map->writecnt++;
 		mutex_unlock(&map->freeze_mutex);
@@ -600,13 +598,11 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_WRITE) {
+	if (vma->vm_flags & VM_MAYWRITE) {
 		mutex_lock(&map->freeze_mutex);
 		map->writecnt--;
 		mutex_unlock(&map->freeze_mutex);
 	}
-
-	bpf_map_put_with_uref(map);
 }
 
 static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -627,22 +623,35 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	mutex_lock(&map->freeze_mutex);
 
-	if ((vma->vm_flags & VM_WRITE) && map->frozen) {
-		err = -EPERM;
-		goto out;
+	if (vma->vm_flags & VM_WRITE) {
+		if (map->frozen) {
+			err = -EPERM;
+			goto out;
+		}
+		/* map is meant to be read-only, so do not allow mapping as
+		 * writable, because it's possible to leak a writable page
+		 * reference and allows user-space to still modify it after
+		 * freezing, while verifier will assume contents do not change
+		 */
+		if (map->map_flags & BPF_F_RDONLY_PROG) {
+			err = -EACCES;
+			goto out;
+		}
 	}
 
 	/* set default open/close callbacks */
 	vma->vm_ops = &bpf_map_default_vmops;
 	vma->vm_private_data = map;
+	vma->vm_flags &= ~VM_MAYEXEC;
+	if (!(vma->vm_flags & VM_WRITE))
+		/* disallow re-mapping with PROT_WRITE */
+		vma->vm_flags &= ~VM_MAYWRITE;
 
 	err = map->ops->map_mmap(map, vma);
 	if (err)
 		goto out;
 
-	bpf_map_inc_with_uref(map);
-
-	if (vma->vm_flags & VM_WRITE)
+	if (vma->vm_flags & VM_MAYWRITE)
 		map->writecnt++;
 out:
 	mutex_unlock(&map->freeze_mutex);
@@ -1487,8 +1496,10 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	if (err)
 		goto free_value;
 
-	if (copy_to_user(uvalue, value, value_size) != 0)
+	if (copy_to_user(uvalue, value, value_size) != 0) {
+		err = -EFAULT;
 		goto free_value;
+	}
 
 	err = 0;
 
@@ -2285,7 +2296,7 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp)
 }
 #endif
 
-const struct file_operations bpf_link_fops = {
+static const struct file_operations bpf_link_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_link_show_fdinfo,
 #endif
@@ -3630,8 +3641,10 @@ static int link_update(union bpf_attr *attr)
 		return PTR_ERR(link);
 
 	new_prog = bpf_prog_get(attr->link_update.new_prog_fd);
-	if (IS_ERR(new_prog))
-		return PTR_ERR(new_prog);
+	if (IS_ERR(new_prog)) {
+		ret = PTR_ERR(new_prog);
+		goto out_put_link;
+	}
 
 	if (flags & BPF_F_REPLACE) {
 		old_prog = bpf_prog_get(attr->link_update.old_prog_fd);
@@ -3640,6 +3653,9 @@ static int link_update(union bpf_attr *attr)
 			old_prog = NULL;
 			goto out_put_progs;
 		}
+	} else if (attr->link_update.old_prog_fd) {
+		ret = -EINVAL;
+		goto out_put_progs;
 	}
 
 #ifdef CONFIG_CGROUP_BPF
@@ -3655,6 +3671,8 @@ out_put_progs:
 		bpf_prog_put(old_prog);
 	if (ret)
 		bpf_prog_put(new_prog);
+out_put_link:
+	bpf_link_put(link);
 	return ret;
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 04c6630cc18f..efe14cf24bc6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1168,14 +1168,14 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
 	 * but must be positive otherwise set to worse case bounds
 	 * and refine later from tnum.
 	 */
-	if (reg->s32_min_value > 0)
-		reg->smin_value = reg->s32_min_value;
-	else
-		reg->smin_value = 0;
-	if (reg->s32_max_value > 0)
+	if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
 		reg->smax_value = reg->s32_max_value;
 	else
 		reg->smax_value = U32_MAX;
+	if (reg->s32_min_value >= 0)
+		reg->smin_value = reg->s32_min_value;
+	else
+		reg->smin_value = 0;
 }
 
 static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
@@ -1255,8 +1255,7 @@ static void __mark_reg_unknown(const struct bpf_verifier_env *env,
 	reg->type = SCALAR_VALUE;
 	reg->var_off = tnum_unknown;
 	reg->frameno = 0;
-	reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
-		       true : false;
+	reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks;
 	__mark_reg_unbounded(reg);
 }
 
@@ -2119,6 +2118,15 @@ static bool register_is_const(struct bpf_reg_state *reg)
 	return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
 }
 
+static bool __is_pointer_value(bool allow_ptr_leaks,
+			       const struct bpf_reg_state *reg)
+{
+	if (allow_ptr_leaks)
+		return false;
+
+	return reg->type != SCALAR_VALUE;
+}
+
 static void save_register_state(struct bpf_func_state *state,
 				int spi, struct bpf_reg_state *reg)
 {
@@ -2309,6 +2317,16 @@ static int check_stack_read(struct bpf_verifier_env *env,
 			 * which resets stack/reg liveness for state transitions
 			 */
 			state->regs[value_regno].live |= REG_LIVE_WRITTEN;
+		} else if (__is_pointer_value(env->allow_ptr_leaks, reg)) {
+			/* If value_regno==-1, the caller is asking us whether
+			 * it is acceptable to use this value as a SCALAR_VALUE
+			 * (e.g. for XADD).
+			 * We must not allow unprivileged callers to do that
+			 * with spilled pointers.
+			 */
+			verbose(env, "leaking pointer from stack off %d\n",
+				off);
+			return -EACCES;
 		}
 		mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
 	} else {
@@ -2674,15 +2692,6 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
 	return -EACCES;
 }
 
-static bool __is_pointer_value(bool allow_ptr_leaks,
-			       const struct bpf_reg_state *reg)
-{
-	if (allow_ptr_leaks)
-		return false;
-
-	return reg->type != SCALAR_VALUE;
-}
-
 static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
 {
 	return cur_regs(env) + regno;
@@ -3090,7 +3099,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	if (ret < 0)
 		return ret;
 
-	if (atype == BPF_READ) {
+	if (atype == BPF_READ && value_regno >= 0) {
 		if (ret == SCALAR_VALUE) {
 			mark_reg_unknown(env, regs, value_regno);
 			return 0;
@@ -4331,7 +4340,9 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
 
 	if (ret_type != RET_INTEGER ||
 	    (func_id != BPF_FUNC_get_stack &&
-	     func_id != BPF_FUNC_probe_read_str))
+	     func_id != BPF_FUNC_probe_read_str &&
+	     func_id != BPF_FUNC_probe_read_kernel_str &&
+	     func_id != BPF_FUNC_probe_read_user_str))
 		return;
 
 	ret_reg->smax_value = meta->msize_max_value;
@@ -7050,6 +7061,23 @@ static int check_return_code(struct bpf_verifier_env *env)
 			return 0;
 		range = tnum_const(0);
 		break;
+	case BPF_PROG_TYPE_TRACING:
+		switch (env->prog->expected_attach_type) {
+		case BPF_TRACE_FENTRY:
+		case BPF_TRACE_FEXIT:
+			range = tnum_const(0);
+			break;
+		case BPF_TRACE_RAW_TP:
+		case BPF_MODIFY_RETURN:
+			return 0;
+		default:
+			return -ENOTSUPP;
+		}
+		break;
+	case BPF_PROG_TYPE_EXT:
+		/* freplace program can return anything as its return value
+		 * depends on the to-be-replaced kernel func or bpf program.
+		 */
 	default:
 		return 0;
 	}
@@ -10400,22 +10428,13 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 }
 #define SECURITY_PREFIX "security_"
 
-static int check_attach_modify_return(struct bpf_verifier_env *env)
+static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr)
 {
-	struct bpf_prog *prog = env->prog;
-	unsigned long addr = (unsigned long) prog->aux->trampoline->func.addr;
-
-	/* This is expected to be cleaned up in the future with the KRSI effort
-	 * introducing the LSM_HOOK macro for cleaning up lsm_hooks.h.
-	 */
 	if (within_error_injection_list(addr) ||
 	    !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name,
 		     sizeof(SECURITY_PREFIX) - 1))
 		return 0;
 
-	verbose(env, "fmod_ret attach_btf_id %u (%s) is not modifiable\n",
-		prog->aux->attach_btf_id, prog->aux->attach_func_name);
-
 	return -EINVAL;
 }
 
@@ -10488,6 +10507,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				return -EINVAL;
 			}
 			env->ops = bpf_verifier_ops[tgt_prog->type];
+			prog->expected_attach_type = tgt_prog->expected_attach_type;
 		}
 		if (!tgt_prog->jited) {
 			verbose(env, "Can attach to only JITed progs\n");
@@ -10625,11 +10645,18 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				goto out;
 			}
 		}
+
+		if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
+			ret = check_attach_modify_return(prog, addr);
+			if (ret)
+				verbose(env, "%s() is not modifiable\n",
+					prog->aux->attach_func_name);
+		}
+
+		if (ret)
+			goto out;
 		tr->func.addr = (void *)addr;
 		prog->aux->trampoline = tr;
-
-		if (prog->expected_attach_type == BPF_MODIFY_RETURN)
-			ret = check_attach_modify_return(env);
 out:
 		mutex_unlock(&tr->mutex);
 		if (ret)
@@ -10832,6 +10859,13 @@ err_release_maps:
 		 * them now. Otherwise free_used_maps() will release them.
 		 */
 		release_maps(env);
+
+	/* extension progs temporarily inherit the attach_type of their targets
+	   for verification purposes, so set it back to zero before returning
+	 */
+	if (env->prog->type == BPF_PROG_TYPE_EXT)
+		env->prog->expected_attach_type = 0;
+
 	*prog = env->prog;
 err_unlock:
 	if (!is_priv)
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 6f87352f8219..41ca996568df 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -33,12 +33,9 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 		return;
 
 	/*
-	 * Paired with the one in cgroup_rstat_cpu_pop_updated().  Either we
-	 * see NULL updated_next or they see our updated stat.
-	 */
-	smp_mb();
-
-	/*
+	 * Speculative already-on-list test. This may race leading to
+	 * temporary inaccuracies, which is fine.
+	 *
 	 * Because @parent's updated_children is terminated with @parent
 	 * instead of NULL, we can tell whether @cgrp is on the list by
 	 * testing the next pointer for NULL.
@@ -134,13 +131,6 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 		*nextp = rstatc->updated_next;
 		rstatc->updated_next = NULL;
 
-		/*
-		 * Paired with the one in cgroup_rstat_cpu_updated().
-		 * Either they see NULL updated_next or we see their
-		 * updated stat.
-		 */
-		smp_mb();
-
 		return pos;
 	}
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 2371292f30b0..9f892144db6b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -432,7 +432,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu)
 	/*
 	 * On x86 it's required to boot all logical CPUs at least once so
 	 * that the init code can get a chance to set CR4.MCE on each
-	 * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
+	 * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any
 	 * core will shutdown the machine.
 	 */
 	return !cpumask_test_cpu(cpu, &cpus_booted_once_mask);
@@ -1327,7 +1327,7 @@ void bringup_nonboot_cpus(unsigned int setup_max_cpus)
 #ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_var_t frozen_cpus;
 
-int __freeze_secondary_cpus(int primary, bool suspend)
+int freeze_secondary_cpus(int primary)
 {
 	int cpu, error = 0;
 
@@ -1352,7 +1352,7 @@ int __freeze_secondary_cpus(int primary, bool suspend)
 		if (cpu == primary)
 			continue;
 
-		if (suspend && pm_wakeup_pending()) {
+		if (pm_wakeup_pending()) {
 			pr_info("Wakeup pending. Abort CPU freeze\n");
 			error = -EBUSY;
 			break;
@@ -1376,8 +1376,8 @@ int __freeze_secondary_cpus(int primary, bool suspend)
 
 	/*
 	 * Make sure the CPUs won't be enabled by someone else. We need to do
-	 * this even in case of failure as all disable_nonboot_cpus() users are
-	 * supposed to do enable_nonboot_cpus() on the failure path.
+	 * this even in case of failure as all freeze_secondary_cpus() users are
+	 * supposed to do thaw_secondary_cpus() on the failure path.
 	 */
 	cpu_hotplug_disabled++;
 
@@ -1385,15 +1385,15 @@ int __freeze_secondary_cpus(int primary, bool suspend)
 	return error;
 }
 
-void __weak arch_enable_nonboot_cpus_begin(void)
+void __weak arch_thaw_secondary_cpus_begin(void)
 {
 }
 
-void __weak arch_enable_nonboot_cpus_end(void)
+void __weak arch_thaw_secondary_cpus_end(void)
 {
 }
 
-void enable_nonboot_cpus(void)
+void thaw_secondary_cpus(void)
 {
 	int cpu, error;
 
@@ -1405,7 +1405,7 @@ void enable_nonboot_cpus(void)
 
 	pr_info("Enabling non-boot CPUs ...\n");
 
-	arch_enable_nonboot_cpus_begin();
+	arch_thaw_secondary_cpus_begin();
 
 	for_each_cpu(cpu, frozen_cpus) {
 		trace_suspend_resume(TPS("CPU_ON"), cpu, true);
@@ -1418,7 +1418,7 @@ void enable_nonboot_cpus(void)
 		pr_warn("Error taking CPU%d up: %d\n", cpu, error);
 	}
 
-	arch_enable_nonboot_cpus_end();
+	arch_thaw_secondary_cpus_end();
 
 	cpumask_clear(frozen_cpus);
 out:
diff --git a/kernel/crash_dump.c b/kernel/crash_dump.c
index 9c23ae074b40..92da32275af5 100644
--- a/kernel/crash_dump.c
+++ b/kernel/crash_dump.c
@@ -6,12 +6,6 @@
 #include <linux/export.h>
 
 /*
- * If we have booted due to a crash, max_pfn will be a very low value. We need
- * to know the amount of memory that the previous kernel used.
- */
-unsigned long saved_max_pfn;
-
-/*
  * stores the physical address of elf header of crash image
  *
  * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index c2b41a263166..b1991043b7d8 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -16,7 +16,7 @@
 
 struct callchain_cpus_entries {
 	struct rcu_head			rcu_head;
-	struct perf_callchain_entry	*cpu_entries[0];
+	struct perf_callchain_entry	*cpu_entries[];
 };
 
 int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bc9b98a9af9a..e296c5c59c6f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -95,11 +95,11 @@ static void remote_function(void *data)
  * @info:	the function call argument
  *
  * Calls the function @func when the task is currently running. This might
- * be on the current CPU, which just calls the function directly
+ * be on the current CPU, which just calls the function directly.  This will
+ * retry due to any failures in smp_call_function_single(), such as if the
+ * task_cpu() goes offline concurrently.
  *
- * returns: @func return value, or
- *	    -ESRCH  - when the process isn't running
- *	    -EAGAIN - when the process moved away
+ * returns @func return value or -ESRCH when the process isn't running
  */
 static int
 task_function_call(struct task_struct *p, remote_function_f func, void *info)
@@ -112,11 +112,16 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
 	};
 	int ret;
 
-	do {
-		ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1);
-		if (!ret)
-			ret = data.ret;
-	} while (ret == -EAGAIN);
+	for (;;) {
+		ret = smp_call_function_single(task_cpu(p), remote_function,
+					       &data, 1);
+		ret = !ret ? data.ret : -EAGAIN;
+
+		if (ret != -EAGAIN)
+			break;
+
+		cond_resched();
+	}
 
 	return ret;
 }
@@ -7491,10 +7496,17 @@ static void perf_event_task_output(struct perf_event *event,
 		goto out;
 
 	task_event->event_id.pid = perf_event_pid(event, task);
-	task_event->event_id.ppid = perf_event_pid(event, current);
-
 	task_event->event_id.tid = perf_event_tid(event, task);
-	task_event->event_id.ptid = perf_event_tid(event, current);
+
+	if (task_event->event_id.header.type == PERF_RECORD_EXIT) {
+		task_event->event_id.ppid = perf_event_pid(event,
+							task->real_parent);
+		task_event->event_id.ptid = perf_event_pid(event,
+							task->real_parent);
+	} else {  /* PERF_RECORD_FORK */
+		task_event->event_id.ppid = perf_event_pid(event, current);
+		task_event->event_id.ptid = perf_event_tid(event, current);
+	}
 
 	task_event->event_id.time = perf_event_clock(event);
 
@@ -9397,7 +9409,7 @@ static int perf_kprobe_event_init(struct perf_event *event)
 	if (event->attr.type != perf_kprobe.type)
 		return -ENOENT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	/*
@@ -9457,7 +9469,7 @@ static int perf_uprobe_event_init(struct perf_event *event)
 	if (event->attr.type != perf_uprobe.type)
 		return -ENOENT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	/*
@@ -11504,7 +11516,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	if (attr.namespaces) {
-		if (!capable(CAP_SYS_ADMIN))
+		if (!perfmon_capable())
 			return -EACCES;
 	}
 
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index f16f66b6b655..fcbf5616a441 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -55,7 +55,7 @@ struct perf_buffer {
 	void				*aux_priv;
 
 	struct perf_event_mmap_page	*user_page;
-	void				*data_pages[0];
+	void				*data_pages[];
 };
 
 extern void rb_free(struct perf_buffer *rb);
diff --git a/kernel/exit.c b/kernel/exit.c
index 389a88cb3081..ce2a75bc0ade 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -219,6 +219,7 @@ repeat:
 
 	write_unlock_irq(&tasklist_lock);
 	proc_flush_pid(thread_pid);
+	put_pid(thread_pid);
 	release_thread(p);
 	put_task_struct_rcu_user(p);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 4385f3d639f2..be98e94cb3cc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -94,6 +94,7 @@
 #include <linux/thread_info.h>
 #include <linux/stackleak.h>
 #include <linux/kasan.h>
+#include <linux/scs.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -456,6 +457,8 @@ void put_task_stack(struct task_struct *tsk)
 
 void free_task(struct task_struct *tsk)
 {
+	scs_release(tsk);
+
 #ifndef CONFIG_THREAD_INFO_IN_TASK
 	/*
 	 * The task is finally done with both the stack and thread_info,
@@ -840,6 +843,8 @@ void __init fork_init(void)
 			  NULL, free_vm_stack_cache);
 #endif
 
+	scs_init();
+
 	lockdep_init_task(&init_task);
 	uprobes_init();
 }
@@ -899,6 +904,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	if (err)
 		goto free_stack;
 
+	err = scs_prepare(tsk, node);
+	if (err)
+		goto free_stack;
+
 #ifdef CONFIG_SECCOMP
 	/*
 	 * We must handle setting up seccomp filters once we're under
@@ -1683,6 +1692,11 @@ static inline void rcu_copy_process(struct task_struct *p)
 	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
 	p->rcu_tasks_idle_cpu = -1;
 #endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_TRACE_RCU
+	p->trc_reader_nesting = 0;
+	p->trc_reader_special.s = 0;
+	INIT_LIST_HEAD(&p->trc_holdout_list);
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 }
 
 struct pid *pidfd_pid(const struct file *file)
@@ -2486,11 +2500,11 @@ long do_fork(unsigned long clone_flags,
 	      int __user *child_tidptr)
 {
 	struct kernel_clone_args args = {
-		.flags		= (clone_flags & ~CSIGNAL),
+		.flags		= (lower_32_bits(clone_flags) & ~CSIGNAL),
 		.pidfd		= parent_tidptr,
 		.child_tid	= child_tidptr,
 		.parent_tid	= parent_tidptr,
-		.exit_signal	= (clone_flags & CSIGNAL),
+		.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL),
 		.stack		= stack_start,
 		.stack_size	= stack_size,
 	};
@@ -2508,8 +2522,9 @@ long do_fork(unsigned long clone_flags,
 pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 {
 	struct kernel_clone_args args = {
-		.flags		= ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL),
-		.exit_signal	= (flags & CSIGNAL),
+		.flags		= ((lower_32_bits(flags) | CLONE_VM |
+				    CLONE_UNTRACED) & ~CSIGNAL),
+		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
 		.stack		= (unsigned long)fn,
 		.stack_size	= (unsigned long)arg,
 	};
@@ -2570,11 +2585,11 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 #endif
 {
 	struct kernel_clone_args args = {
-		.flags		= (clone_flags & ~CSIGNAL),
+		.flags		= (lower_32_bits(clone_flags) & ~CSIGNAL),
 		.pidfd		= parent_tidptr,
 		.child_tid	= child_tidptr,
 		.parent_tid	= parent_tidptr,
-		.exit_signal	= (clone_flags & CSIGNAL),
+		.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL),
 		.stack		= newsp,
 		.tls		= tls,
 	};
@@ -2605,6 +2620,14 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 	struct clone_args args;
 	pid_t *kset_tid = kargs->set_tid;
 
+	BUILD_BUG_ON(offsetofend(struct clone_args, tls) !=
+		     CLONE_ARGS_SIZE_VER0);
+	BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) !=
+		     CLONE_ARGS_SIZE_VER1);
+	BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) !=
+		     CLONE_ARGS_SIZE_VER2);
+	BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2);
+
 	if (unlikely(usize > PAGE_SIZE))
 		return -E2BIG;
 	if (unlikely(usize < CLONE_ARGS_SIZE_VER0))
@@ -2631,7 +2654,8 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 		     !valid_signal(args.exit_signal)))
 		return -EINVAL;
 
-	if ((args.flags & CLONE_INTO_CGROUP) && args.cgroup < 0)
+	if ((args.flags & CLONE_INTO_CGROUP) &&
+	    (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2))
 		return -EINVAL;
 
 	*kargs = (struct kernel_clone_args){
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index fe40c658f86f..453a8a0f4804 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1690,34 +1690,6 @@ out_mput:
 	return ret;
 }
 
-/**
- *	setup_irq - setup an interrupt
- *	@irq: Interrupt line to setup
- *	@act: irqaction for the interrupt
- *
- * Used to statically setup interrupts in the early boot process.
- */
-int setup_irq(unsigned int irq, struct irqaction *act)
-{
-	int retval;
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
-		return -EINVAL;
-
-	retval = irq_chip_pm_get(&desc->irq_data);
-	if (retval < 0)
-		return retval;
-
-	retval = __setup_irq(irq, desc, act);
-
-	if (retval)
-		irq_chip_pm_put(&desc->irq_data);
-
-	return retval;
-}
-EXPORT_SYMBOL_GPL(setup_irq);
-
 /*
  * Internal function to unregister an irqaction - used to free
  * regular and special interrupts that are part of the architecture.
@@ -1859,22 +1831,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 }
 
 /**
- *	remove_irq - free an interrupt
- *	@irq: Interrupt line to free
- *	@act: irqaction for the interrupt
- *
- * Used to remove interrupts statically setup by the early boot process.
- */
-void remove_irq(unsigned int irq, struct irqaction *act)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
-		__free_irq(desc, act->dev_id);
-}
-EXPORT_SYMBOL_GPL(remove_irq);
-
-/**
  *	free_irq - free an interrupt allocated with request_irq
  *	@irq: Interrupt line to free
  *	@dev_id: Device identity to free
diff --git a/kernel/kcov.c b/kernel/kcov.c
index f50354202dbe..8accc9722a81 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -740,8 +740,8 @@ static const struct file_operations kcov_fops = {
  * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an
  * arbitrary 4-byte non-zero number as the instance id). This common handle
  * then gets saved into the task_struct of the process that issued the
- * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn
- * kernel threads, the common handle must be retrived via kcov_common_handle()
+ * KCOV_REMOTE_ENABLE ioctl. When this process issues system calls that spawn
+ * kernel threads, the common handle must be retrieved via kcov_common_handle()
  * and passed to the spawned threads via custom annotations. Those kernel
  * threads must in turn be annotated with kcov_remote_start(common_handle) and
  * kcov_remote_stop(). All of the threads that are spawned by the same process
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 2625c241ac00..3f310df4a693 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2179,6 +2179,24 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
 	return 0;
 }
 
+/* Remove all symbols in given area from kprobe blacklist */
+static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
+{
+	struct kprobe_blacklist_entry *ent, *n;
+
+	list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) {
+		if (ent->start_addr < start || ent->start_addr >= end)
+			continue;
+		list_del(&ent->list);
+		kfree(ent);
+	}
+}
+
+static void kprobe_remove_ksym_blacklist(unsigned long entry)
+{
+	kprobe_remove_area_blacklist(entry, entry + 1);
+}
+
 int __init __weak arch_populate_kprobe_blacklist(void)
 {
 	return 0;
@@ -2211,10 +2229,62 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
 	/* Symbols in __kprobes_text are blacklisted */
 	ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start,
 					(unsigned long)__kprobes_text_end);
+	if (ret)
+		return ret;
+
+	/* Symbols in noinstr section are blacklisted */
+	ret = kprobe_add_area_blacklist((unsigned long)__noinstr_text_start,
+					(unsigned long)__noinstr_text_end);
 
 	return ret ? : arch_populate_kprobe_blacklist();
 }
 
+static void add_module_kprobe_blacklist(struct module *mod)
+{
+	unsigned long start, end;
+	int i;
+
+	if (mod->kprobe_blacklist) {
+		for (i = 0; i < mod->num_kprobe_blacklist; i++)
+			kprobe_add_ksym_blacklist(mod->kprobe_blacklist[i]);
+	}
+
+	start = (unsigned long)mod->kprobes_text_start;
+	if (start) {
+		end = start + mod->kprobes_text_size;
+		kprobe_add_area_blacklist(start, end);
+	}
+
+	start = (unsigned long)mod->noinstr_text_start;
+	if (start) {
+		end = start + mod->noinstr_text_size;
+		kprobe_add_area_blacklist(start, end);
+	}
+}
+
+static void remove_module_kprobe_blacklist(struct module *mod)
+{
+	unsigned long start, end;
+	int i;
+
+	if (mod->kprobe_blacklist) {
+		for (i = 0; i < mod->num_kprobe_blacklist; i++)
+			kprobe_remove_ksym_blacklist(mod->kprobe_blacklist[i]);
+	}
+
+	start = (unsigned long)mod->kprobes_text_start;
+	if (start) {
+		end = start + mod->kprobes_text_size;
+		kprobe_remove_area_blacklist(start, end);
+	}
+
+	start = (unsigned long)mod->noinstr_text_start;
+	if (start) {
+		end = start + mod->noinstr_text_size;
+		kprobe_remove_area_blacklist(start, end);
+	}
+}
+
 /* Module notifier call back, checking kprobes on the module */
 static int kprobes_module_callback(struct notifier_block *nb,
 				   unsigned long val, void *data)
@@ -2225,6 +2295,11 @@ static int kprobes_module_callback(struct notifier_block *nb,
 	unsigned int i;
 	int checkcore = (val == MODULE_STATE_GOING);
 
+	if (val == MODULE_STATE_COMING) {
+		mutex_lock(&kprobe_mutex);
+		add_module_kprobe_blacklist(mod);
+		mutex_unlock(&kprobe_mutex);
+	}
 	if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE)
 		return NOTIFY_DONE;
 
@@ -2255,6 +2330,8 @@ static int kprobes_module_callback(struct notifier_block *nb,
 				kill_kprobe(p);
 			}
 	}
+	if (val == MODULE_STATE_GOING)
+		remove_module_kprobe_blacklist(mod);
 	mutex_unlock(&kprobe_mutex);
 	return NOTIFY_DONE;
 }
@@ -2420,6 +2497,7 @@ static const struct file_operations debugfs_kprobes_operations = {
 /* kprobes/blacklist -- shows which functions can not be probed */
 static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos)
 {
+	mutex_lock(&kprobe_mutex);
 	return seq_list_start(&kprobe_blacklist, *pos);
 }
 
@@ -2446,10 +2524,15 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	return 0;
 }
 
+static void kprobe_blacklist_seq_stop(struct seq_file *f, void *v)
+{
+	mutex_unlock(&kprobe_mutex);
+}
+
 static const struct seq_operations kprobe_blacklist_seq_ops = {
 	.start = kprobe_blacklist_seq_start,
 	.next  = kprobe_blacklist_seq_next,
-	.stop  = kprobe_seq_stop,	/* Reuse void function */
+	.stop  = kprobe_blacklist_seq_stop,
 	.show  = kprobe_blacklist_seq_show,
 };
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index ac10db66cc63..dd3cc0854c32 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -393,25 +393,6 @@ void lockdep_init_task(struct task_struct *task)
 	task->lockdep_recursion = 0;
 }
 
-/*
- * Split the recrursion counter in two to readily detect 'off' vs recursion.
- */
-#define LOCKDEP_RECURSION_BITS	16
-#define LOCKDEP_OFF		(1U << LOCKDEP_RECURSION_BITS)
-#define LOCKDEP_RECURSION_MASK	(LOCKDEP_OFF - 1)
-
-void lockdep_off(void)
-{
-	current->lockdep_recursion += LOCKDEP_OFF;
-}
-EXPORT_SYMBOL(lockdep_off);
-
-void lockdep_on(void)
-{
-	current->lockdep_recursion -= LOCKDEP_OFF;
-}
-EXPORT_SYMBOL(lockdep_on);
-
 static inline void lockdep_recursion_finish(void)
 {
 	if (WARN_ON_ONCE(--current->lockdep_recursion))
@@ -489,7 +470,7 @@ struct lock_trace {
 	struct hlist_node	hash_entry;
 	u32			hash;
 	u32			nr_entries;
-	unsigned long		entries[0] __aligned(sizeof(unsigned long));
+	unsigned long		entries[] __aligned(sizeof(unsigned long));
 };
 #define LOCK_TRACE_SIZE_IN_LONGS				\
 	(sizeof(struct lock_trace) / sizeof(unsigned long))
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index c9f090d64f00..cfdd5b93264d 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -141,7 +141,6 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
  * set up.
  */
 #ifndef CONFIG_DEBUG_RT_MUTEXES
-# define rt_mutex_cmpxchg_relaxed(l,c,n) (cmpxchg_relaxed(&l->owner, c, n) == c)
 # define rt_mutex_cmpxchg_acquire(l,c,n) (cmpxchg_acquire(&l->owner, c, n) == c)
 # define rt_mutex_cmpxchg_release(l,c,n) (cmpxchg_release(&l->owner, c, n) == c)
 
@@ -202,7 +201,6 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
 }
 
 #else
-# define rt_mutex_cmpxchg_relaxed(l,c,n)	(0)
 # define rt_mutex_cmpxchg_acquire(l,c,n)	(0)
 # define rt_mutex_cmpxchg_release(l,c,n)	(0)
 
diff --git a/kernel/module.c b/kernel/module.c
index 646f1e2330d2..64a2b4daaaa5 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2400,7 +2400,7 @@ static void layout_sections(struct module *mod, struct load_info *info)
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || strstarts(sname, ".init"))
+			    || module_init_section(sname))
 				continue;
 			s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i);
 			pr_debug("\t%s\n", sname);
@@ -2433,7 +2433,7 @@ static void layout_sections(struct module *mod, struct load_info *info)
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || !strstarts(sname, ".init"))
+			    || !module_init_section(sname))
 				continue;
 			s->sh_entsize = (get_offset(mod, &mod->init_layout.size, s, i)
 					 | INIT_OFFSET_MASK);
@@ -2768,6 +2768,11 @@ void * __weak module_alloc(unsigned long size)
 	return vmalloc_exec(size);
 }
 
+bool __weak module_init_section(const char *name)
+{
+	return strstarts(name, ".init");
+}
+
 bool __weak module_exit_section(const char *name)
 {
 	return strstarts(name, ".exit");
@@ -3150,6 +3155,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	}
 #endif
 
+	mod->noinstr_text_start = section_objs(info, ".noinstr.text", 1,
+						&mod->noinstr_text_size);
+
 #ifdef CONFIG_TRACEPOINTS
 	mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs",
 					     sizeof(*mod->tracepoints_ptrs),
@@ -3194,6 +3202,13 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 					    sizeof(*mod->ei_funcs),
 					    &mod->num_ei_funcs);
 #endif
+#ifdef CONFIG_KPROBES
+	mod->kprobes_text_start = section_objs(info, ".kprobes.text", 1,
+						&mod->kprobes_text_size);
+	mod->kprobe_blacklist = section_objs(info, "_kprobe_blacklist",
+						sizeof(unsigned long),
+						&mod->num_kprobe_blacklist);
+#endif
 	mod->extable = section_objs(info, "__ex_table",
 				    sizeof(*mod->extable), &mod->num_exentries);
 
diff --git a/kernel/padata.c b/kernel/padata.c
index a6afa12fb75e..aae789896616 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -703,7 +703,7 @@ static int padata_cpu_online(unsigned int cpu, struct hlist_node *node)
 	struct padata_instance *pinst;
 	int ret;
 
-	pinst = hlist_entry_safe(node, struct padata_instance, node);
+	pinst = hlist_entry_safe(node, struct padata_instance, cpu_online_node);
 	if (!pinst_has_cpu(pinst, cpu))
 		return 0;
 
@@ -718,7 +718,7 @@ static int padata_cpu_dead(unsigned int cpu, struct hlist_node *node)
 	struct padata_instance *pinst;
 	int ret;
 
-	pinst = hlist_entry_safe(node, struct padata_instance, node);
+	pinst = hlist_entry_safe(node, struct padata_instance, cpu_dead_node);
 	if (!pinst_has_cpu(pinst, cpu))
 		return 0;
 
@@ -734,8 +734,9 @@ static enum cpuhp_state hp_online;
 static void __padata_free(struct padata_instance *pinst)
 {
 #ifdef CONFIG_HOTPLUG_CPU
-	cpuhp_state_remove_instance_nocalls(CPUHP_PADATA_DEAD, &pinst->node);
-	cpuhp_state_remove_instance_nocalls(hp_online, &pinst->node);
+	cpuhp_state_remove_instance_nocalls(CPUHP_PADATA_DEAD,
+					    &pinst->cpu_dead_node);
+	cpuhp_state_remove_instance_nocalls(hp_online, &pinst->cpu_online_node);
 #endif
 
 	WARN_ON(!list_empty(&pinst->pslist));
@@ -939,9 +940,10 @@ static struct padata_instance *padata_alloc(const char *name,
 	mutex_init(&pinst->lock);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	cpuhp_state_add_instance_nocalls_cpuslocked(hp_online, &pinst->node);
+	cpuhp_state_add_instance_nocalls_cpuslocked(hp_online,
+						    &pinst->cpu_online_node);
 	cpuhp_state_add_instance_nocalls_cpuslocked(CPUHP_PADATA_DEAD,
-						    &pinst->node);
+						    &pinst->cpu_dead_node);
 #endif
 
 	put_online_cpus();
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 86aba8706b16..30bd28d1d418 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -898,6 +898,13 @@ static int software_resume(void)
 	error = freeze_processes();
 	if (error)
 		goto Close_Finish;
+
+	error = freeze_kernel_threads();
+	if (error) {
+		thaw_processes();
+		goto Close_Finish;
+	}
+
 	error = load_image_and_restore();
 	thaw_processes();
  Finish:
diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h
index 11f19c466af5..3ca74ad391d6 100644
--- a/kernel/printk/console_cmdline.h
+++ b/kernel/printk/console_cmdline.h
@@ -6,6 +6,7 @@ struct console_cmdline
 {
 	char	name[16];			/* Name of the driver	    */
 	int	index;				/* Minor dev. to use	    */
+	bool	user_specified;			/* Specified by command line vs. platform */
 	char	*options;			/* Options for the driver   */
 #ifdef CONFIG_A11Y_BRAILLE_CONSOLE
 	char	*brl_options;			/* Options for braille driver */
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index b2b0f526f249..660f9a6bf73a 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -6,9 +6,11 @@
 
 #ifdef CONFIG_PRINTK
 
-#define PRINTK_SAFE_CONTEXT_MASK	 0x3fffffff
-#define PRINTK_NMI_DIRECT_CONTEXT_MASK	 0x40000000
-#define PRINTK_NMI_CONTEXT_MASK		 0x80000000
+#define PRINTK_SAFE_CONTEXT_MASK	0x007ffffff
+#define PRINTK_NMI_DIRECT_CONTEXT_MASK	0x008000000
+#define PRINTK_NMI_CONTEXT_MASK		0xff0000000
+
+#define PRINTK_NMI_CONTEXT_OFFSET	0x010000000
 
 extern raw_spinlock_t logbuf_lock;
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 9a9b6156270b..9fdd6a42ad6a 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -280,6 +280,7 @@ static struct console *exclusive_console;
 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES];
 
 static int preferred_console = -1;
+static bool has_preferred_console;
 int console_set_on_cmdline;
 EXPORT_SYMBOL(console_set_on_cmdline);
 
@@ -974,6 +975,16 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
 		user->idx = log_next_idx;
 		user->seq = log_next_seq;
 		break;
+	case SEEK_CUR:
+		/*
+		 * It isn't supported due to the record nature of this
+		 * interface: _SET _DATA and _END point to very specific
+		 * record positions, while _CUR would be more useful in case
+		 * of a byte-based log. Because of that, return the default
+		 * errno value for invalid seek operation.
+		 */
+		ret = -ESPIPE;
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -2140,7 +2151,7 @@ asmlinkage __visible void early_printk(const char *fmt, ...)
 #endif
 
 static int __add_preferred_console(char *name, int idx, char *options,
-				   char *brl_options)
+				   char *brl_options, bool user_specified)
 {
 	struct console_cmdline *c;
 	int i;
@@ -2155,6 +2166,8 @@ static int __add_preferred_console(char *name, int idx, char *options,
 		if (strcmp(c->name, name) == 0 && c->index == idx) {
 			if (!brl_options)
 				preferred_console = i;
+			if (user_specified)
+				c->user_specified = true;
 			return 0;
 		}
 	}
@@ -2164,6 +2177,7 @@ static int __add_preferred_console(char *name, int idx, char *options,
 		preferred_console = i;
 	strlcpy(c->name, name, sizeof(c->name));
 	c->options = options;
+	c->user_specified = user_specified;
 	braille_set_options(c, brl_options);
 
 	c->index = idx;
@@ -2190,6 +2204,9 @@ static int __init console_setup(char *str)
 	char *s, *options, *brl_options = NULL;
 	int idx;
 
+	if (str[0] == 0)
+		return 1;
+
 	if (_braille_console_setup(&str, &brl_options))
 		return 1;
 
@@ -2218,7 +2235,7 @@ static int __init console_setup(char *str)
 	idx = simple_strtoul(s, NULL, 10);
 	*s = 0;
 
-	__add_preferred_console(buf, idx, options, brl_options);
+	__add_preferred_console(buf, idx, options, brl_options, true);
 	console_set_on_cmdline = 1;
 	return 1;
 }
@@ -2239,7 +2256,7 @@ __setup("console=", console_setup);
  */
 int add_preferred_console(char *name, int idx, char *options)
 {
-	return __add_preferred_console(name, idx, options, NULL);
+	return __add_preferred_console(name, idx, options, NULL, false);
 }
 
 bool console_suspend_enabled = true;
@@ -2438,9 +2455,9 @@ again:
 		printk_safe_enter_irqsave(flags);
 		raw_spin_lock(&logbuf_lock);
 		if (console_seq < log_first_seq) {
-			len = sprintf(text,
-				      "** %llu printk messages dropped **\n",
-				      log_first_seq - console_seq);
+			len = snprintf(text, sizeof(text),
+				       "** %llu printk messages dropped **\n",
+				       log_first_seq - console_seq);
 
 			/* messages are gone, move to first one */
 			console_seq = log_first_seq;
@@ -2652,6 +2669,63 @@ static int __init keep_bootcon_setup(char *str)
 early_param("keep_bootcon", keep_bootcon_setup);
 
 /*
+ * This is called by register_console() to try to match
+ * the newly registered console with any of the ones selected
+ * by either the command line or add_preferred_console() and
+ * setup/enable it.
+ *
+ * Care need to be taken with consoles that are statically
+ * enabled such as netconsole
+ */
+static int try_enable_new_console(struct console *newcon, bool user_specified)
+{
+	struct console_cmdline *c;
+	int i;
+
+	for (i = 0, c = console_cmdline;
+	     i < MAX_CMDLINECONSOLES && c->name[0];
+	     i++, c++) {
+		if (c->user_specified != user_specified)
+			continue;
+		if (!newcon->match ||
+		    newcon->match(newcon, c->name, c->index, c->options) != 0) {
+			/* default matching */
+			BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
+			if (strcmp(c->name, newcon->name) != 0)
+				continue;
+			if (newcon->index >= 0 &&
+			    newcon->index != c->index)
+				continue;
+			if (newcon->index < 0)
+				newcon->index = c->index;
+
+			if (_braille_register_console(newcon, c))
+				return 0;
+
+			if (newcon->setup &&
+			    newcon->setup(newcon, c->options) != 0)
+				return -EIO;
+		}
+		newcon->flags |= CON_ENABLED;
+		if (i == preferred_console) {
+			newcon->flags |= CON_CONSDEV;
+			has_preferred_console = true;
+		}
+		return 0;
+	}
+
+	/*
+	 * Some consoles, such as pstore and netconsole, can be enabled even
+	 * without matching. Accept the pre-enabled consoles only when match()
+	 * and setup() had a change to be called.
+	 */
+	if (newcon->flags & CON_ENABLED && c->user_specified ==	user_specified)
+		return 0;
+
+	return -ENOENT;
+}
+
+/*
  * The console driver calls this routine during kernel initialization
  * to register the console printing procedure with printk() and to
  * print any messages that were printed by the kernel before the
@@ -2672,11 +2746,9 @@ early_param("keep_bootcon", keep_bootcon_setup);
  */
 void register_console(struct console *newcon)
 {
-	int i;
 	unsigned long flags;
 	struct console *bcon = NULL;
-	struct console_cmdline *c;
-	static bool has_preferred;
+	int err;
 
 	for_each_console(bcon) {
 		if (WARN(bcon == newcon, "console '%s%d' already registered\n",
@@ -2701,15 +2773,15 @@ void register_console(struct console *newcon)
 	if (console_drivers && console_drivers->flags & CON_BOOT)
 		bcon = console_drivers;
 
-	if (!has_preferred || bcon || !console_drivers)
-		has_preferred = preferred_console >= 0;
+	if (!has_preferred_console || bcon || !console_drivers)
+		has_preferred_console = preferred_console >= 0;
 
 	/*
 	 *	See if we want to use this console driver. If we
 	 *	didn't select a console we take the first one
 	 *	that registers here.
 	 */
-	if (!has_preferred) {
+	if (!has_preferred_console) {
 		if (newcon->index < 0)
 			newcon->index = 0;
 		if (newcon->setup == NULL ||
@@ -2717,47 +2789,20 @@ void register_console(struct console *newcon)
 			newcon->flags |= CON_ENABLED;
 			if (newcon->device) {
 				newcon->flags |= CON_CONSDEV;
-				has_preferred = true;
+				has_preferred_console = true;
 			}
 		}
 	}
 
-	/*
-	 *	See if this console matches one we selected on
-	 *	the command line.
-	 */
-	for (i = 0, c = console_cmdline;
-	     i < MAX_CMDLINECONSOLES && c->name[0];
-	     i++, c++) {
-		if (!newcon->match ||
-		    newcon->match(newcon, c->name, c->index, c->options) != 0) {
-			/* default matching */
-			BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
-			if (strcmp(c->name, newcon->name) != 0)
-				continue;
-			if (newcon->index >= 0 &&
-			    newcon->index != c->index)
-				continue;
-			if (newcon->index < 0)
-				newcon->index = c->index;
-
-			if (_braille_register_console(newcon, c))
-				return;
-
-			if (newcon->setup &&
-			    newcon->setup(newcon, c->options) != 0)
-				break;
-		}
+	/* See if this console matches one we selected on the command line */
+	err = try_enable_new_console(newcon, true);
 
-		newcon->flags |= CON_ENABLED;
-		if (i == preferred_console) {
-			newcon->flags |= CON_CONSDEV;
-			has_preferred = true;
-		}
-		break;
-	}
+	/* If not, try to match against the platform default(s) */
+	if (err == -ENOENT)
+		err = try_enable_new_console(newcon, false);
 
-	if (!(newcon->flags & CON_ENABLED))
+	/* printk() messages are not printed to the Braille console. */
+	if (err || newcon->flags & CON_BRL)
 		return;
 
 	/*
@@ -2779,6 +2824,8 @@ void register_console(struct console *newcon)
 		console_drivers = newcon;
 		if (newcon->next)
 			newcon->next->flags &= ~CON_CONSDEV;
+		/* Ensure this flag is always set for the head of the list */
+		newcon->flags |= CON_CONSDEV;
 	} else {
 		newcon->next = console_drivers->next;
 		console_drivers->next = newcon;
@@ -3144,6 +3191,23 @@ EXPORT_SYMBOL_GPL(kmsg_dump_unregister);
 static bool always_kmsg_dump;
 module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR);
 
+const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason)
+{
+	switch (reason) {
+	case KMSG_DUMP_PANIC:
+		return "Panic";
+	case KMSG_DUMP_OOPS:
+		return "Oops";
+	case KMSG_DUMP_EMERG:
+		return "Emergency";
+	case KMSG_DUMP_SHUTDOWN:
+		return "Shutdown";
+	default:
+		return "Unknown";
+	}
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_reason_str);
+
 /**
  * kmsg_dump - dump kernel log to kernel message dumpers.
  * @reason: the reason (oops, panic etc) for dumping
@@ -3157,12 +3221,19 @@ void kmsg_dump(enum kmsg_dump_reason reason)
 	struct kmsg_dumper *dumper;
 	unsigned long flags;
 
-	if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump)
-		return;
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(dumper, &dump_list, list) {
-		if (dumper->max_reason && reason > dumper->max_reason)
+		enum kmsg_dump_reason max_reason = dumper->max_reason;
+
+		/*
+		 * If client has not provided a specific max_reason, default
+		 * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set.
+		 */
+		if (max_reason == KMSG_DUMP_UNDEF) {
+			max_reason = always_kmsg_dump ? KMSG_DUMP_MAX :
+							KMSG_DUMP_OOPS;
+		}
+		if (reason > max_reason)
 			continue;
 
 		/* initialize iterator with data about the stored records */
@@ -3360,7 +3431,7 @@ out:
 EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);
 
 /**
- * kmsg_dump_rewind_nolock - reset the interator (unlocked version)
+ * kmsg_dump_rewind_nolock - reset the iterator (unlocked version)
  * @dumper: registered kmsg dumper
  *
  * Reset the dumper's iterator so that kmsg_dump_get_line() and
@@ -3378,7 +3449,7 @@ void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper)
 }
 
 /**
- * kmsg_dump_rewind - reset the interator
+ * kmsg_dump_rewind - reset the iterator
  * @dumper: registered kmsg dumper
  *
  * Reset the dumper's iterator so that kmsg_dump_get_line() and
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index d9a659a686f3..4242403316bb 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -10,6 +10,7 @@
 #include <linux/cpumask.h>
 #include <linux/irq_work.h>
 #include <linux/printk.h>
+#include <linux/kprobes.h>
 
 #include "internal.h"
 
@@ -293,14 +294,14 @@ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
 	return printk_safe_log_store(s, fmt, args);
 }
 
-void notrace printk_nmi_enter(void)
+void noinstr printk_nmi_enter(void)
 {
-	this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK);
+	this_cpu_add(printk_context, PRINTK_NMI_CONTEXT_OFFSET);
 }
 
-void notrace printk_nmi_exit(void)
+void noinstr printk_nmi_exit(void)
 {
-	this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK);
+	this_cpu_sub(printk_context, PRINTK_NMI_CONTEXT_OFFSET);
 }
 
 /*
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 1cc940fef17c..0ebe15a84985 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -70,13 +70,37 @@ config TREE_SRCU
 	help
 	  This option selects the full-fledged version of SRCU.
 
+config TASKS_RCU_GENERIC
+	def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU
+	select SRCU
+	help
+	  This option enables generic infrastructure code supporting
+	  task-based RCU implementations.  Not for manual selection.
+
 config TASKS_RCU
 	def_bool PREEMPTION
-	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses
 	  only voluntary context switch (not preemption!), idle, and
-	  user-mode execution as quiescent states.
+	  user-mode execution as quiescent states.  Not for manual selection.
+
+config TASKS_RUDE_RCU
+	def_bool 0
+	help
+	  This option enables a task-based RCU implementation that uses
+	  only context switch (including preemption) and user-mode
+	  execution as quiescent states.  It forces IPIs and context
+	  switches on all online CPUs, including idle ones, so use
+	  with caution.
+
+config TASKS_TRACE_RCU
+	def_bool 0
+	help
+	  This option enables a task-based RCU implementation that uses
+	  explicit rcu_read_lock_trace() read-side markers, and allows
+	  these readers to appear in the idle loop as well as on the CPU
+	  hotplug code paths.  It can force IPIs on online CPUs, including
+	  idle ones, so use with caution.
 
 config RCU_STALL_COMMON
 	def_bool TREE_RCU
@@ -210,4 +234,22 @@ config RCU_NOCB_CPU
 	  Say Y here if you want to help to debug reduced OS jitter.
 	  Say N here if you are unsure.
 
+config TASKS_TRACE_RCU_READ_MB
+	bool "Tasks Trace RCU readers use memory barriers in user and idle"
+	depends on RCU_EXPERT
+	default PREEMPT_RT || NR_CPUS < 8
+	help
+	  Use this option to further reduce the number of IPIs sent
+	  to CPUs executing in userspace or idle during tasks trace
+	  RCU grace periods.  Given that a reasonable setting of
+	  the rcupdate.rcu_task_ipi_delay kernel boot parameter
+	  eliminates such IPIs for many workloads, proper setting
+	  of this Kconfig option is important mostly for aggressive
+	  real-time installations and for battery-powered devices,
+	  hence the default chosen above.
+
+	  Say Y here if you hate IPIs.
+	  Say N here if you hate read-side memory barriers.
+	  Take the default if you are unsure.
+
 endmenu # "RCU Subsystem"
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 4aa02eee8f6c..452feae8de20 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -29,6 +29,8 @@ config RCU_PERF_TEST
 	select TORTURE_TEST
 	select SRCU
 	select TASKS_RCU
+	select TASKS_RUDE_RCU
+	select TASKS_TRACE_RCU
 	default n
 	help
 	  This option provides a kernel module that runs performance
@@ -46,6 +48,8 @@ config RCU_TORTURE_TEST
 	select TORTURE_TEST
 	select SRCU
 	select TASKS_RCU
+	select TASKS_RUDE_RCU
+	select TASKS_TRACE_RCU
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 00ddc92c5774..cf66a3ccd757 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -431,6 +431,7 @@ bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
 void rcu_expedite_gp(void);
 void rcu_unexpedite_gp(void);
 void rcupdate_announce_bootup_oddness(void);
+void show_rcu_tasks_gp_kthreads(void);
 void rcu_request_urgent_qs_task(struct task_struct *t);
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
@@ -441,6 +442,8 @@ void rcu_request_urgent_qs_task(struct task_struct *t);
 enum rcutorture_type {
 	RCU_FLAVOR,
 	RCU_TASKS_FLAVOR,
+	RCU_TASKS_RUDE_FLAVOR,
+	RCU_TASKS_TRACING_FLAVOR,
 	RCU_TRIVIAL_FLAVOR,
 	SRCU_FLAVOR,
 	INVALID_RCU_FLAVOR
@@ -454,6 +457,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long secs,
 			       unsigned long c_old,
 			       unsigned long c);
+void rcu_gp_set_torture_wait(int duration);
 #else
 static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 					  int *flags, unsigned long *gp_seq)
@@ -471,6 +475,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 #define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
 	do { } while (0)
 #endif
+static inline void rcu_gp_set_torture_wait(int duration) { }
 #endif
 
 #if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST)
@@ -498,6 +503,7 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
 #endif
 
 #ifdef CONFIG_TINY_RCU
+static inline bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) { return false; }
 static inline unsigned long rcu_get_gp_seq(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
 static inline unsigned long
@@ -507,6 +513,7 @@ static inline void show_rcu_gp_kthreads(void) { }
 static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
 static inline void rcu_fwd_progress_check(unsigned long j) { }
 #else /* #ifdef CONFIG_TINY_RCU */
+bool rcu_dynticks_zero_in_eqs(int cpu, int *vp);
 unsigned long rcu_get_gp_seq(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index a4a8d097d84d..16dd1e6b7c09 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -88,6 +88,7 @@ torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
 torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
 torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() perf test?");
+torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate.");
 
 static char *perf_type = "rcu";
 module_param(perf_type, charp, 0444);
@@ -635,7 +636,7 @@ kfree_perf_thread(void *arg)
 		}
 
 		for (i = 0; i < kfree_alloc_num; i++) {
-			alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL);
+			alloc_ptr = kmalloc(kfree_mult * sizeof(struct kfree_obj), GFP_KERNEL);
 			if (!alloc_ptr)
 				return -ENOMEM;
 
@@ -722,6 +723,8 @@ kfree_perf_init(void)
 		schedule_timeout_uninterruptible(1);
 	}
 
+	pr_alert("kfree object size=%lu\n", kfree_mult * sizeof(struct kfree_obj));
+
 	kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]),
 			       GFP_KERNEL);
 	if (kfree_reader_tasks == NULL) {
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 5453bd557f43..efb792e13fca 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -20,7 +20,7 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/interrupt.h>
 #include <linux/sched/signal.h>
 #include <uapi/linux/sched/types.h>
@@ -45,12 +45,25 @@
 #include <linux/sched/sysctl.h>
 #include <linux/oom.h>
 #include <linux/tick.h>
+#include <linux/rcupdate_trace.h>
 
 #include "rcu.h"
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
 
 /* Bits for ->extendables field, extendables param, and related definitions. */
 #define RCUTORTURE_RDR_SHIFT	 8	/* Put SRCU index in upper bits. */
@@ -102,6 +115,9 @@ torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
 torture_param(int, stall_cpu_holdoff, 10,
 	     "Time to wait before starting stall (s).");
 torture_param(int, stall_cpu_irqsoff, 0, "Disable interrupts while stalling.");
+torture_param(int, stall_cpu_block, 0, "Sleep while stalling.");
+torture_param(int, stall_gp_kthread, 0,
+	      "Grace-period kthread stall duration (s).");
 torture_param(int, stat_interval, 60,
 	     "Number of seconds between stats printk()s");
 torture_param(int, stutter, 5, "Number of seconds to run/halt test");
@@ -665,6 +681,11 @@ static void rcu_tasks_torture_deferred_free(struct rcu_torture *p)
 	call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb);
 }
 
+static void synchronize_rcu_mult_test(void)
+{
+	synchronize_rcu_mult(call_rcu_tasks, call_rcu);
+}
+
 static struct rcu_torture_ops tasks_ops = {
 	.ttype		= RCU_TASKS_FLAVOR,
 	.init		= rcu_sync_torture_init,
@@ -674,7 +695,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.get_gp_seq	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
-	.exp_sync	= synchronize_rcu_tasks,
+	.exp_sync	= synchronize_rcu_mult_test,
 	.call		= call_rcu_tasks,
 	.cb_barrier	= rcu_barrier_tasks,
 	.fqs		= NULL,
@@ -725,6 +746,72 @@ static struct rcu_torture_ops trivial_ops = {
 	.name		= "trivial"
 };
 
+/*
+ * Definitions for rude RCU-tasks torture testing.
+ */
+
+static void rcu_tasks_rude_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_tasks_rude(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_rude_ops = {
+	.ttype		= RCU_TASKS_RUDE_FLAVOR,
+	.init		= rcu_sync_torture_init,
+	.readlock	= rcu_torture_read_lock_trivial,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= rcu_torture_read_unlock_trivial,
+	.get_gp_seq	= rcu_no_completed,
+	.deferred_free	= rcu_tasks_rude_torture_deferred_free,
+	.sync		= synchronize_rcu_tasks_rude,
+	.exp_sync	= synchronize_rcu_tasks_rude,
+	.call		= call_rcu_tasks_rude,
+	.cb_barrier	= rcu_barrier_tasks_rude,
+	.fqs		= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "tasks-rude"
+};
+
+/*
+ * Definitions for tracing RCU-tasks torture testing.
+ */
+
+static int tasks_tracing_torture_read_lock(void)
+{
+	rcu_read_lock_trace();
+	return 0;
+}
+
+static void tasks_tracing_torture_read_unlock(int idx)
+{
+	rcu_read_unlock_trace();
+}
+
+static void rcu_tasks_tracing_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_tasks_trace(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_tracing_ops = {
+	.ttype		= RCU_TASKS_TRACING_FLAVOR,
+	.init		= rcu_sync_torture_init,
+	.readlock	= tasks_tracing_torture_read_lock,
+	.read_delay	= srcu_read_delay,  /* just reuse srcu's version. */
+	.readunlock	= tasks_tracing_torture_read_unlock,
+	.get_gp_seq	= rcu_no_completed,
+	.deferred_free	= rcu_tasks_tracing_torture_deferred_free,
+	.sync		= synchronize_rcu_tasks_trace,
+	.exp_sync	= synchronize_rcu_tasks_trace,
+	.call		= call_rcu_tasks_trace,
+	.cb_barrier	= rcu_barrier_tasks_trace,
+	.fqs		= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.slow_gps	= 1,
+	.name		= "tasks-tracing"
+};
+
 static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
 {
 	if (!cur_ops->gp_diff)
@@ -734,7 +821,7 @@ static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
 
 static bool __maybe_unused torturing_tasks(void)
 {
-	return cur_ops == &tasks_ops;
+	return cur_ops == &tasks_ops || cur_ops == &tasks_rude_ops;
 }
 
 /*
@@ -833,7 +920,7 @@ static int rcu_torture_boost(void *arg)
 
 		/* Wait for the next test interval. */
 		oldstarttime = boost_starttime;
-		while (ULONG_CMP_LT(jiffies, oldstarttime)) {
+		while (time_before(jiffies, oldstarttime)) {
 			schedule_timeout_interruptible(oldstarttime - jiffies);
 			stutter_wait("rcu_torture_boost");
 			if (torture_must_stop())
@@ -843,7 +930,7 @@ static int rcu_torture_boost(void *arg)
 		/* Do one boost-test interval. */
 		endtime = oldstarttime + test_boost_duration * HZ;
 		call_rcu_time = jiffies;
-		while (ULONG_CMP_LT(jiffies, endtime)) {
+		while (time_before(jiffies, endtime)) {
 			/* If we don't have a callback in flight, post one. */
 			if (!smp_load_acquire(&rbi.inflight)) {
 				/* RCU core before ->inflight = 1. */
@@ -914,7 +1001,7 @@ rcu_torture_fqs(void *arg)
 	VERBOSE_TOROUT_STRING("rcu_torture_fqs task started");
 	do {
 		fqs_resume_time = jiffies + fqs_stutter * HZ;
-		while (ULONG_CMP_LT(jiffies, fqs_resume_time) &&
+		while (time_before(jiffies, fqs_resume_time) &&
 		       !kthread_should_stop()) {
 			schedule_timeout_interruptible(1);
 		}
@@ -1147,6 +1234,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 				  struct torture_random_state *trsp,
 				  struct rt_read_seg *rtrsp)
 {
+	unsigned long flags;
 	int idxnew = -1;
 	int idxold = *readstate;
 	int statesnew = ~*readstate & newstate;
@@ -1181,8 +1269,15 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		rcu_read_unlock_bh();
 	if (statesold & RCUTORTURE_RDR_SCHED)
 		rcu_read_unlock_sched();
-	if (statesold & RCUTORTURE_RDR_RCU)
+	if (statesold & RCUTORTURE_RDR_RCU) {
+		bool lockit = !statesnew && !(torture_random(trsp) & 0xffff);
+
+		if (lockit)
+			raw_spin_lock_irqsave(&current->pi_lock, flags);
 		cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+		if (lockit)
+			raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+	}
 
 	/* Delay if neither beginning nor end and there was a change. */
 	if ((statesnew || statesold) && *readstate && newstate)
@@ -1283,6 +1378,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 				  rcu_read_lock_bh_held() ||
 				  rcu_read_lock_sched_held() ||
 				  srcu_read_lock_held(srcu_ctlp) ||
+				  rcu_read_lock_trace_held() ||
 				  torturing_tasks());
 	if (p == NULL) {
 		/* Wait for rcu_torture_writer to get underway */
@@ -1444,9 +1540,9 @@ rcu_torture_stats_print(void)
 		atomic_long_read(&n_rcu_torture_timers));
 	torture_onoff_stats();
 	pr_cont("barrier: %ld/%ld:%ld\n",
-		n_barrier_successes,
-		n_barrier_attempts,
-		n_rcu_torture_barrier_error);
+		data_race(n_barrier_successes),
+		data_race(n_barrier_attempts),
+		data_race(n_rcu_torture_barrier_error));
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) ||
@@ -1536,6 +1632,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 "test_boost=%d/%d test_boost_interval=%d "
 		 "test_boost_duration=%d shutdown_secs=%d "
 		 "stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d "
+		 "stall_cpu_block=%d "
 		 "n_barrier_cbs=%d "
 		 "onoff_interval=%d onoff_holdoff=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
@@ -1544,6 +1641,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 test_boost, cur_ops->can_boost,
 		 test_boost_interval, test_boost_duration, shutdown_secs,
 		 stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff,
+		 stall_cpu_block,
 		 n_barrier_cbs,
 		 onoff_interval, onoff_holdoff);
 }
@@ -1599,6 +1697,7 @@ static int rcutorture_booster_init(unsigned int cpu)
  */
 static int rcu_torture_stall(void *args)
 {
+	int idx;
 	unsigned long stop_at;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
@@ -1607,26 +1706,37 @@ static int rcu_torture_stall(void *args)
 		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
 		VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
 	}
-	if (!kthread_should_stop()) {
+	if (!kthread_should_stop() && stall_gp_kthread > 0) {
+		VERBOSE_TOROUT_STRING("rcu_torture_stall begin GP stall");
+		rcu_gp_set_torture_wait(stall_gp_kthread * HZ);
+		for (idx = 0; idx < stall_gp_kthread + 2; idx++) {
+			if (kthread_should_stop())
+				break;
+			schedule_timeout_uninterruptible(HZ);
+		}
+	}
+	if (!kthread_should_stop() && stall_cpu > 0) {
+		VERBOSE_TOROUT_STRING("rcu_torture_stall begin CPU stall");
 		stop_at = ktime_get_seconds() + stall_cpu;
 		/* RCU CPU stall is expected behavior in following code. */
-		rcu_read_lock();
+		idx = cur_ops->readlock();
 		if (stall_cpu_irqsoff)
 			local_irq_disable();
-		else
+		else if (!stall_cpu_block)
 			preempt_disable();
 		pr_alert("rcu_torture_stall start on CPU %d.\n",
-			 smp_processor_id());
+			 raw_smp_processor_id());
 		while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
 				    stop_at))
-			continue;  /* Induce RCU CPU stall warning. */
+			if (stall_cpu_block)
+				schedule_timeout_uninterruptible(HZ);
 		if (stall_cpu_irqsoff)
 			local_irq_enable();
-		else
+		else if (!stall_cpu_block)
 			preempt_enable();
-		rcu_read_unlock();
-		pr_alert("rcu_torture_stall end.\n");
+		cur_ops->readunlock(idx);
 	}
+	pr_alert("rcu_torture_stall end.\n");
 	torture_shutdown_absorb("rcu_torture_stall");
 	while (!kthread_should_stop())
 		schedule_timeout_interruptible(10 * HZ);
@@ -1636,7 +1746,7 @@ static int rcu_torture_stall(void *args)
 /* Spawn CPU-stall kthread, if stall_cpu specified. */
 static int __init rcu_torture_stall_init(void)
 {
-	if (stall_cpu <= 0)
+	if (stall_cpu <= 0 && stall_gp_kthread <= 0)
 		return 0;
 	return torture_create_kthread(rcu_torture_stall, NULL, stall_task);
 }
@@ -1692,8 +1802,8 @@ struct rcu_fwd {
 	unsigned long rcu_launder_gp_seq_start;
 };
 
-struct rcu_fwd *rcu_fwds;
-bool rcu_fwd_emergency_stop;
+static struct rcu_fwd *rcu_fwds;
+static bool rcu_fwd_emergency_stop;
 
 static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 {
@@ -2400,7 +2510,8 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
-		&busted_srcud_ops, &tasks_ops, &trivial_ops,
+		&busted_srcud_ops, &tasks_ops, &tasks_rude_ops,
+		&tasks_tracing_ops, &trivial_ops,
 	};
 
 	if (!torture_init_begin(torture_type, verbose))
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 0c71505f0e19..6d3ef700fb0e 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -29,6 +29,19 @@
 #include "rcu.h"
 #include "rcu_segcblist.h"
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
+
 /* Holdoff in nanoseconds for auto-expediting. */
 #define DEFAULT_SRCU_EXP_HOLDOFF (25 * 1000)
 static ulong exp_holdoff = DEFAULT_SRCU_EXP_HOLDOFF;
@@ -1268,8 +1281,8 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
 		struct srcu_data *sdp;
 
 		sdp = per_cpu_ptr(ssp->sda, cpu);
-		u0 = sdp->srcu_unlock_count[!idx];
-		u1 = sdp->srcu_unlock_count[idx];
+		u0 = data_race(sdp->srcu_unlock_count[!idx]);
+		u1 = data_race(sdp->srcu_unlock_count[idx]);
 
 		/*
 		 * Make sure that a lock is always counted if the corresponding
@@ -1277,8 +1290,8 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
 		 */
 		smp_rmb();
 
-		l0 = sdp->srcu_lock_count[!idx];
-		l1 = sdp->srcu_lock_count[idx];
+		l0 = data_race(sdp->srcu_lock_count[!idx]);
+		l1 = data_race(sdp->srcu_lock_count[idx]);
 
 		c0 = l0 - u0;
 		c1 = l1 - u1;
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
new file mode 100644
index 000000000000..ce23f6cc5043
--- /dev/null
+++ b/kernel/rcu/tasks.h
@@ -0,0 +1,1193 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Task-based RCU implementations.
+ *
+ * Copyright (C) 2020 Paul E. McKenney
+ */
+
+#ifdef CONFIG_TASKS_RCU_GENERIC
+
+////////////////////////////////////////////////////////////////////////
+//
+// Generic data structures.
+
+struct rcu_tasks;
+typedef void (*rcu_tasks_gp_func_t)(struct rcu_tasks *rtp);
+typedef void (*pregp_func_t)(void);
+typedef void (*pertask_func_t)(struct task_struct *t, struct list_head *hop);
+typedef void (*postscan_func_t)(struct list_head *hop);
+typedef void (*holdouts_func_t)(struct list_head *hop, bool ndrpt, bool *frptp);
+typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
+
+/**
+ * Definition for a Tasks-RCU-like mechanism.
+ * @cbs_head: Head of callback list.
+ * @cbs_tail: Tail pointer for callback list.
+ * @cbs_wq: Wait queue allowning new callback to get kthread's attention.
+ * @cbs_lock: Lock protecting callback list.
+ * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
+ * @gp_func: This flavor's grace-period-wait function.
+ * @gp_state: Grace period's most recent state transition (debugging).
+ * @gp_jiffies: Time of last @gp_state transition.
+ * @gp_start: Most recent grace-period start in jiffies.
+ * @n_gps: Number of grace periods completed since boot.
+ * @n_ipis: Number of IPIs sent to encourage grace periods to end.
+ * @n_ipis_fails: Number of IPI-send failures.
+ * @pregp_func: This flavor's pre-grace-period function (optional).
+ * @pertask_func: This flavor's per-task scan function (optional).
+ * @postscan_func: This flavor's post-task scan function (optional).
+ * @holdout_func: This flavor's holdout-list scan function (optional).
+ * @postgp_func: This flavor's post-grace-period function (optional).
+ * @call_func: This flavor's call_rcu()-equivalent function.
+ * @name: This flavor's textual name.
+ * @kname: This flavor's kthread name.
+ */
+struct rcu_tasks {
+	struct rcu_head *cbs_head;
+	struct rcu_head **cbs_tail;
+	struct wait_queue_head cbs_wq;
+	raw_spinlock_t cbs_lock;
+	int gp_state;
+	unsigned long gp_jiffies;
+	unsigned long gp_start;
+	unsigned long n_gps;
+	unsigned long n_ipis;
+	unsigned long n_ipis_fails;
+	struct task_struct *kthread_ptr;
+	rcu_tasks_gp_func_t gp_func;
+	pregp_func_t pregp_func;
+	pertask_func_t pertask_func;
+	postscan_func_t postscan_func;
+	holdouts_func_t holdouts_func;
+	postgp_func_t postgp_func;
+	call_rcu_func_t call_func;
+	char *name;
+	char *kname;
+};
+
+#define DEFINE_RCU_TASKS(rt_name, gp, call, n)				\
+static struct rcu_tasks rt_name =					\
+{									\
+	.cbs_tail = &rt_name.cbs_head,					\
+	.cbs_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rt_name.cbs_wq),	\
+	.cbs_lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name.cbs_lock),		\
+	.gp_func = gp,							\
+	.call_func = call,						\
+	.name = n,							\
+	.kname = #rt_name,						\
+}
+
+/* Track exiting tasks in order to allow them to be waited for. */
+DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
+
+/* Avoid IPIing CPUs early in the grace period. */
+#define RCU_TASK_IPI_DELAY (HZ / 2)
+static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY;
+module_param(rcu_task_ipi_delay, int, 0644);
+
+/* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
+#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
+static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
+module_param(rcu_task_stall_timeout, int, 0644);
+
+/* RCU tasks grace-period state for debugging. */
+#define RTGS_INIT		 0
+#define RTGS_WAIT_WAIT_CBS	 1
+#define RTGS_WAIT_GP		 2
+#define RTGS_PRE_WAIT_GP	 3
+#define RTGS_SCAN_TASKLIST	 4
+#define RTGS_POST_SCAN_TASKLIST	 5
+#define RTGS_WAIT_SCAN_HOLDOUTS	 6
+#define RTGS_SCAN_HOLDOUTS	 7
+#define RTGS_POST_GP		 8
+#define RTGS_WAIT_READERS	 9
+#define RTGS_INVOKE_CBS		10
+#define RTGS_WAIT_CBS		11
+static const char * const rcu_tasks_gp_state_names[] = {
+	"RTGS_INIT",
+	"RTGS_WAIT_WAIT_CBS",
+	"RTGS_WAIT_GP",
+	"RTGS_PRE_WAIT_GP",
+	"RTGS_SCAN_TASKLIST",
+	"RTGS_POST_SCAN_TASKLIST",
+	"RTGS_WAIT_SCAN_HOLDOUTS",
+	"RTGS_SCAN_HOLDOUTS",
+	"RTGS_POST_GP",
+	"RTGS_WAIT_READERS",
+	"RTGS_INVOKE_CBS",
+	"RTGS_WAIT_CBS",
+};
+
+////////////////////////////////////////////////////////////////////////
+//
+// Generic code.
+
+/* Record grace-period phase and time. */
+static void set_tasks_gp_state(struct rcu_tasks *rtp, int newstate)
+{
+	rtp->gp_state = newstate;
+	rtp->gp_jiffies = jiffies;
+}
+
+/* Return state name. */
+static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
+{
+	int i = data_race(rtp->gp_state); // Let KCSAN detect update races
+	int j = READ_ONCE(i); // Prevent the compiler from reading twice
+
+	if (j >= ARRAY_SIZE(rcu_tasks_gp_state_names))
+		return "???";
+	return rcu_tasks_gp_state_names[j];
+}
+
+// Enqueue a callback for the specified flavor of Tasks RCU.
+static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
+				   struct rcu_tasks *rtp)
+{
+	unsigned long flags;
+	bool needwake;
+
+	rhp->next = NULL;
+	rhp->func = func;
+	raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
+	needwake = !rtp->cbs_head;
+	WRITE_ONCE(*rtp->cbs_tail, rhp);
+	rtp->cbs_tail = &rhp->next;
+	raw_spin_unlock_irqrestore(&rtp->cbs_lock, flags);
+	/* We can't create the thread unless interrupts are enabled. */
+	if (needwake && READ_ONCE(rtp->kthread_ptr))
+		wake_up(&rtp->cbs_wq);
+}
+
+// Wait for a grace period for the specified flavor of Tasks RCU.
+static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
+{
+	/* Complain if the scheduler has not started.  */
+	RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
+			 "synchronize_rcu_tasks called too soon");
+
+	/* Wait for the grace period. */
+	wait_rcu_gp(rtp->call_func);
+}
+
+/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
+static int __noreturn rcu_tasks_kthread(void *arg)
+{
+	unsigned long flags;
+	struct rcu_head *list;
+	struct rcu_head *next;
+	struct rcu_tasks *rtp = arg;
+
+	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
+	housekeeping_affine(current, HK_FLAG_RCU);
+	WRITE_ONCE(rtp->kthread_ptr, current); // Let GPs start!
+
+	/*
+	 * Each pass through the following loop makes one check for
+	 * newly arrived callbacks, and, if there are some, waits for
+	 * one RCU-tasks grace period and then invokes the callbacks.
+	 * This loop is terminated by the system going down.  ;-)
+	 */
+	for (;;) {
+
+		/* Pick up any new callbacks. */
+		raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
+		smp_mb__after_spinlock(); // Order updates vs. GP.
+		list = rtp->cbs_head;
+		rtp->cbs_head = NULL;
+		rtp->cbs_tail = &rtp->cbs_head;
+		raw_spin_unlock_irqrestore(&rtp->cbs_lock, flags);
+
+		/* If there were none, wait a bit and start over. */
+		if (!list) {
+			wait_event_interruptible(rtp->cbs_wq,
+						 READ_ONCE(rtp->cbs_head));
+			if (!rtp->cbs_head) {
+				WARN_ON(signal_pending(current));
+				set_tasks_gp_state(rtp, RTGS_WAIT_WAIT_CBS);
+				schedule_timeout_interruptible(HZ/10);
+			}
+			continue;
+		}
+
+		// Wait for one grace period.
+		set_tasks_gp_state(rtp, RTGS_WAIT_GP);
+		rtp->gp_start = jiffies;
+		rtp->gp_func(rtp);
+		rtp->n_gps++;
+
+		/* Invoke the callbacks. */
+		set_tasks_gp_state(rtp, RTGS_INVOKE_CBS);
+		while (list) {
+			next = list->next;
+			local_bh_disable();
+			list->func(list);
+			local_bh_enable();
+			list = next;
+			cond_resched();
+		}
+		/* Paranoid sleep to keep this from entering a tight loop */
+		schedule_timeout_uninterruptible(HZ/10);
+
+		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
+	}
+}
+
+/* Spawn RCU-tasks grace-period kthread, e.g., at core_initcall() time. */
+static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp)
+{
+	struct task_struct *t;
+
+	t = kthread_run(rcu_tasks_kthread, rtp, "%s_kthread", rtp->kname);
+	if (WARN_ONCE(IS_ERR(t), "%s: Could not start %s grace-period kthread, OOM is now expected behavior\n", __func__, rtp->name))
+		return;
+	smp_mb(); /* Ensure others see full kthread. */
+}
+
+#ifndef CONFIG_TINY_RCU
+
+/*
+ * Print any non-default Tasks RCU settings.
+ */
+static void __init rcu_tasks_bootup_oddness(void)
+{
+#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
+	if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT)
+		pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout);
+#endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_RCU
+	pr_info("\tTrampoline variant of Tasks RCU enabled.\n");
+#endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_RUDE_RCU
+	pr_info("\tRude variant of Tasks RCU enabled.\n");
+#endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
+#ifdef CONFIG_TASKS_TRACE_RCU
+	pr_info("\tTracing variant of Tasks RCU enabled.\n");
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+}
+
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+/* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */
+static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
+{
+	pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c %s\n",
+		rtp->kname,
+		tasks_gp_state_getname(rtp), data_race(rtp->gp_state),
+		jiffies - data_race(rtp->gp_jiffies),
+		data_race(rtp->n_gps),
+		data_race(rtp->n_ipis_fails), data_race(rtp->n_ipis),
+		".k"[!!data_race(rtp->kthread_ptr)],
+		".C"[!!data_race(rtp->cbs_head)],
+		s);
+}
+
+static void exit_tasks_rcu_finish_trace(struct task_struct *t);
+
+#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
+
+////////////////////////////////////////////////////////////////////////
+//
+// Shared code between task-list-scanning variants of Tasks RCU.
+
+/* Wait for one RCU-tasks grace period. */
+static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
+{
+	struct task_struct *g, *t;
+	unsigned long lastreport;
+	LIST_HEAD(holdouts);
+	int fract;
+
+	set_tasks_gp_state(rtp, RTGS_PRE_WAIT_GP);
+	rtp->pregp_func();
+
+	/*
+	 * There were callbacks, so we need to wait for an RCU-tasks
+	 * grace period.  Start off by scanning the task list for tasks
+	 * that are not already voluntarily blocked.  Mark these tasks
+	 * and make a list of them in holdouts.
+	 */
+	set_tasks_gp_state(rtp, RTGS_SCAN_TASKLIST);
+	rcu_read_lock();
+	for_each_process_thread(g, t)
+		rtp->pertask_func(t, &holdouts);
+	rcu_read_unlock();
+
+	set_tasks_gp_state(rtp, RTGS_POST_SCAN_TASKLIST);
+	rtp->postscan_func(&holdouts);
+
+	/*
+	 * Each pass through the following loop scans the list of holdout
+	 * tasks, removing any that are no longer holdouts.  When the list
+	 * is empty, we are done.
+	 */
+	lastreport = jiffies;
+
+	/* Start off with HZ/10 wait and slowly back off to 1 HZ wait. */
+	fract = 10;
+
+	for (;;) {
+		bool firstreport;
+		bool needreport;
+		int rtst;
+
+		if (list_empty(&holdouts))
+			break;
+
+		/* Slowly back off waiting for holdouts */
+		set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS);
+		schedule_timeout_interruptible(HZ/fract);
+
+		if (fract > 1)
+			fract--;
+
+		rtst = READ_ONCE(rcu_task_stall_timeout);
+		needreport = rtst > 0 && time_after(jiffies, lastreport + rtst);
+		if (needreport)
+			lastreport = jiffies;
+		firstreport = true;
+		WARN_ON(signal_pending(current));
+		set_tasks_gp_state(rtp, RTGS_SCAN_HOLDOUTS);
+		rtp->holdouts_func(&holdouts, needreport, &firstreport);
+	}
+
+	set_tasks_gp_state(rtp, RTGS_POST_GP);
+	rtp->postgp_func(rtp);
+}
+
+#endif /* #if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) */
+
+#ifdef CONFIG_TASKS_RCU
+
+////////////////////////////////////////////////////////////////////////
+//
+// Simple variant of RCU whose quiescent states are voluntary context
+// switch, cond_resched_rcu_qs(), user-space execution, and idle.
+// As such, grace periods can take one good long time.  There are no
+// read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
+// because this implementation is intended to get the system into a safe
+// state for some of the manipulations involved in tracing and the like.
+// Finally, this implementation does not support high call_rcu_tasks()
+// rates from multiple CPUs.  If this is required, per-CPU callback lists
+// will be needed.
+
+/* Pre-grace-period preparation. */
+static void rcu_tasks_pregp_step(void)
+{
+	/*
+	 * Wait for all pre-existing t->on_rq and t->nvcsw transitions
+	 * to complete.  Invoking synchronize_rcu() suffices because all
+	 * these transitions occur with interrupts disabled.  Without this
+	 * synchronize_rcu(), a read-side critical section that started
+	 * before the grace period might be incorrectly seen as having
+	 * started after the grace period.
+	 *
+	 * This synchronize_rcu() also dispenses with the need for a
+	 * memory barrier on the first store to t->rcu_tasks_holdout,
+	 * as it forces the store to happen after the beginning of the
+	 * grace period.
+	 */
+	synchronize_rcu();
+}
+
+/* Per-task initial processing. */
+static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop)
+{
+	if (t != current && READ_ONCE(t->on_rq) && !is_idle_task(t)) {
+		get_task_struct(t);
+		t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
+		WRITE_ONCE(t->rcu_tasks_holdout, true);
+		list_add(&t->rcu_tasks_holdout_list, hop);
+	}
+}
+
+/* Processing between scanning taskslist and draining the holdout list. */
+void rcu_tasks_postscan(struct list_head *hop)
+{
+	/*
+	 * Wait for tasks that are in the process of exiting.  This
+	 * does only part of the job, ensuring that all tasks that were
+	 * previously exiting reach the point where they have disabled
+	 * preemption, allowing the later synchronize_rcu() to finish
+	 * the job.
+	 */
+	synchronize_srcu(&tasks_rcu_exit_srcu);
+}
+
+/* See if tasks are still holding out, complain if so. */
+static void check_holdout_task(struct task_struct *t,
+			       bool needreport, bool *firstreport)
+{
+	int cpu;
+
+	if (!READ_ONCE(t->rcu_tasks_holdout) ||
+	    t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
+	    !READ_ONCE(t->on_rq) ||
+	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
+	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
+		WRITE_ONCE(t->rcu_tasks_holdout, false);
+		list_del_init(&t->rcu_tasks_holdout_list);
+		put_task_struct(t);
+		return;
+	}
+	rcu_request_urgent_qs_task(t);
+	if (!needreport)
+		return;
+	if (*firstreport) {
+		pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
+		*firstreport = false;
+	}
+	cpu = task_cpu(t);
+	pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
+		 t, ".I"[is_idle_task(t)],
+		 "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
+		 t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
+		 t->rcu_tasks_idle_cpu, cpu);
+	sched_show_task(t);
+}
+
+/* Scan the holdout lists for tasks no longer holding out. */
+static void check_all_holdout_tasks(struct list_head *hop,
+				    bool needreport, bool *firstreport)
+{
+	struct task_struct *t, *t1;
+
+	list_for_each_entry_safe(t, t1, hop, rcu_tasks_holdout_list) {
+		check_holdout_task(t, needreport, firstreport);
+		cond_resched();
+	}
+}
+
+/* Finish off the Tasks-RCU grace period. */
+static void rcu_tasks_postgp(struct rcu_tasks *rtp)
+{
+	/*
+	 * Because ->on_rq and ->nvcsw are not guaranteed to have a full
+	 * memory barriers prior to them in the schedule() path, memory
+	 * reordering on other CPUs could cause their RCU-tasks read-side
+	 * critical sections to extend past the end of the grace period.
+	 * However, because these ->nvcsw updates are carried out with
+	 * interrupts disabled, we can use synchronize_rcu() to force the
+	 * needed ordering on all such CPUs.
+	 *
+	 * This synchronize_rcu() also confines all ->rcu_tasks_holdout
+	 * accesses to be within the grace period, avoiding the need for
+	 * memory barriers for ->rcu_tasks_holdout accesses.
+	 *
+	 * In addition, this synchronize_rcu() waits for exiting tasks
+	 * to complete their final preempt_disable() region of execution,
+	 * cleaning up after the synchronize_srcu() above.
+	 */
+	synchronize_rcu();
+}
+
+void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
+
+/**
+ * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks() assumes
+ * that the read-side critical sections end at a voluntary context
+ * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * or transition to usermode execution.  As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
+{
+	call_rcu_tasks_generic(rhp, func, &rcu_tasks);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks);
+
+/**
+ * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed.  These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
+ * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function
+ * preambles and profiling hooks.  The synchronize_rcu_tasks() function
+ * is not (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+void synchronize_rcu_tasks(void)
+{
+	synchronize_rcu_tasks_generic(&rcu_tasks);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
+
+/**
+ * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks(void)
+{
+	/* There is only one callback queue, so this is easy.  ;-) */
+	synchronize_rcu_tasks();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
+
+static int __init rcu_spawn_tasks_kthread(void)
+{
+	rcu_tasks.pregp_func = rcu_tasks_pregp_step;
+	rcu_tasks.pertask_func = rcu_tasks_pertask;
+	rcu_tasks.postscan_func = rcu_tasks_postscan;
+	rcu_tasks.holdouts_func = check_all_holdout_tasks;
+	rcu_tasks.postgp_func = rcu_tasks_postgp;
+	rcu_spawn_tasks_kthread_generic(&rcu_tasks);
+	return 0;
+}
+core_initcall(rcu_spawn_tasks_kthread);
+
+static void show_rcu_tasks_classic_gp_kthread(void)
+{
+	show_rcu_tasks_generic_gp_kthread(&rcu_tasks, "");
+}
+
+/* Do the srcu_read_lock() for the above synchronize_srcu().  */
+void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
+{
+	preempt_disable();
+	current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
+	preempt_enable();
+}
+
+/* Do the srcu_read_unlock() for the above synchronize_srcu().  */
+void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
+{
+	struct task_struct *t = current;
+
+	preempt_disable();
+	__srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx);
+	preempt_enable();
+	exit_tasks_rcu_finish_trace(t);
+}
+
+#else /* #ifdef CONFIG_TASKS_RCU */
+static void show_rcu_tasks_classic_gp_kthread(void) { }
+void exit_tasks_rcu_start(void) { }
+void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
+#endif /* #else #ifdef CONFIG_TASKS_RCU */
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+
+////////////////////////////////////////////////////////////////////////
+//
+// "Rude" variant of Tasks RCU, inspired by Steve Rostedt's trick of
+// passing an empty function to schedule_on_each_cpu().  This approach
+// provides an asynchronous call_rcu_tasks_rude() API and batching
+// of concurrent calls to the synchronous synchronize_rcu_rude() API.
+// This sends IPIs far and wide and induces otherwise unnecessary context
+// switches on all online CPUs, whether idle or not.
+
+// Empty function to allow workqueues to force a context switch.
+static void rcu_tasks_be_rude(struct work_struct *work)
+{
+}
+
+// Wait for one rude RCU-tasks grace period.
+static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp)
+{
+	rtp->n_ipis += cpumask_weight(cpu_online_mask);
+	schedule_on_each_cpu(rcu_tasks_be_rude);
+}
+
+void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks_rude, rcu_tasks_rude_wait_gp, call_rcu_tasks_rude,
+		 "RCU Tasks Rude");
+
+/**
+ * call_rcu_tasks_rude() - Queue a callback rude task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks_rude()
+ * assumes that the read-side critical sections end at context switch,
+ * cond_resched_rcu_qs(), or transition to usermode execution.  As such,
+ * there are no read-side primitives analogous to rcu_read_lock() and
+ * rcu_read_unlock() because this primitive is intended to determine
+ * that all tasks have passed through a safe state, not so much for
+ * data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func)
+{
+	call_rcu_tasks_generic(rhp, func, &rcu_tasks_rude);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks_rude);
+
+/**
+ * synchronize_rcu_tasks_rude - wait for a rude rcu-tasks grace period
+ *
+ * Control will return to the caller some time after a rude rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed.  These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory,
+ * anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function preambles
+ * and profiling hooks.  The synchronize_rcu_tasks_rude() function is not
+ * (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+void synchronize_rcu_tasks_rude(void)
+{
+	synchronize_rcu_tasks_generic(&rcu_tasks_rude);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_rude);
+
+/**
+ * rcu_barrier_tasks_rude - Wait for in-flight call_rcu_tasks_rude() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks_rude(void)
+{
+	/* There is only one callback queue, so this is easy.  ;-) */
+	synchronize_rcu_tasks_rude();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks_rude);
+
+static int __init rcu_spawn_tasks_rude_kthread(void)
+{
+	rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
+	return 0;
+}
+core_initcall(rcu_spawn_tasks_rude_kthread);
+
+static void show_rcu_tasks_rude_gp_kthread(void)
+{
+	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, "");
+}
+
+#else /* #ifdef CONFIG_TASKS_RUDE_RCU */
+static void show_rcu_tasks_rude_gp_kthread(void) {}
+#endif /* #else #ifdef CONFIG_TASKS_RUDE_RCU */
+
+////////////////////////////////////////////////////////////////////////
+//
+// Tracing variant of Tasks RCU.  This variant is designed to be used
+// to protect tracing hooks, including those of BPF.  This variant
+// therefore:
+//
+// 1.	Has explicit read-side markers to allow finite grace periods
+//	in the face of in-kernel loops for PREEMPT=n builds.
+//
+// 2.	Protects code in the idle loop, exception entry/exit, and
+//	CPU-hotplug code paths, similar to the capabilities of SRCU.
+//
+// 3.	Avoids expensive read-side instruction, having overhead similar
+//	to that of Preemptible RCU.
+//
+// There are of course downsides.  The grace-period code can send IPIs to
+// CPUs, even when those CPUs are in the idle loop or in nohz_full userspace.
+// It is necessary to scan the full tasklist, much as for Tasks RCU.  There
+// is a single callback queue guarded by a single lock, again, much as for
+// Tasks RCU.  If needed, these downsides can be at least partially remedied.
+//
+// Perhaps most important, this variant of RCU does not affect the vanilla
+// flavors, rcu_preempt and rcu_sched.  The fact that RCU Tasks Trace
+// readers can operate from idle, offline, and exception entry/exit in no
+// way allows rcu_preempt and rcu_sched readers to also do so.
+
+// The lockdep state must be outside of #ifdef to be useful.
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key rcu_lock_trace_key;
+struct lockdep_map rcu_trace_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_trace", &rcu_lock_trace_key);
+EXPORT_SYMBOL_GPL(rcu_trace_lock_map);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+
+atomic_t trc_n_readers_need_end;	// Number of waited-for readers.
+DECLARE_WAIT_QUEUE_HEAD(trc_wait);	// List of holdout tasks.
+
+// Record outstanding IPIs to each CPU.  No point in sending two...
+static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
+
+// The number of detections of task quiescent state relying on
+// heavyweight readers executing explicit memory barriers.
+unsigned long n_heavy_reader_attempts;
+unsigned long n_heavy_reader_updates;
+unsigned long n_heavy_reader_ofl_updates;
+
+void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace,
+		 "RCU Tasks Trace");
+
+/*
+ * This irq_work handler allows rcu_read_unlock_trace() to be invoked
+ * while the scheduler locks are held.
+ */
+static void rcu_read_unlock_iw(struct irq_work *iwp)
+{
+	wake_up(&trc_wait);
+}
+static DEFINE_IRQ_WORK(rcu_tasks_trace_iw, rcu_read_unlock_iw);
+
+/* If we are the last reader, wake up the grace-period kthread. */
+void rcu_read_unlock_trace_special(struct task_struct *t, int nesting)
+{
+	int nq = t->trc_reader_special.b.need_qs;
+
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
+	    t->trc_reader_special.b.need_mb)
+		smp_mb(); // Pairs with update-side barriers.
+	// Update .need_qs before ->trc_reader_nesting for irq/NMI handlers.
+	if (nq)
+		WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
+	WRITE_ONCE(t->trc_reader_nesting, nesting);
+	if (nq && atomic_dec_and_test(&trc_n_readers_need_end))
+		irq_work_queue(&rcu_tasks_trace_iw);
+}
+EXPORT_SYMBOL_GPL(rcu_read_unlock_trace_special);
+
+/* Add a task to the holdout list, if it is not already on the list. */
+static void trc_add_holdout(struct task_struct *t, struct list_head *bhp)
+{
+	if (list_empty(&t->trc_holdout_list)) {
+		get_task_struct(t);
+		list_add(&t->trc_holdout_list, bhp);
+	}
+}
+
+/* Remove a task from the holdout list, if it is in fact present. */
+static void trc_del_holdout(struct task_struct *t)
+{
+	if (!list_empty(&t->trc_holdout_list)) {
+		list_del_init(&t->trc_holdout_list);
+		put_task_struct(t);
+	}
+}
+
+/* IPI handler to check task state. */
+static void trc_read_check_handler(void *t_in)
+{
+	struct task_struct *t = current;
+	struct task_struct *texp = t_in;
+
+	// If the task is no longer running on this CPU, leave.
+	if (unlikely(texp != t)) {
+		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+			wake_up(&trc_wait);
+		goto reset_ipi; // Already on holdout list, so will check later.
+	}
+
+	// If the task is not in a read-side critical section, and
+	// if this is the last reader, awaken the grace-period kthread.
+	if (likely(!t->trc_reader_nesting)) {
+		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+			wake_up(&trc_wait);
+		// Mark as checked after decrement to avoid false
+		// positives on the above WARN_ON_ONCE().
+		WRITE_ONCE(t->trc_reader_checked, true);
+		goto reset_ipi;
+	}
+	WRITE_ONCE(t->trc_reader_checked, true);
+
+	// Get here if the task is in a read-side critical section.  Set
+	// its state so that it will awaken the grace-period kthread upon
+	// exit from that critical section.
+	WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+	WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
+
+reset_ipi:
+	// Allow future IPIs to be sent on CPU and for task.
+	// Also order this IPI handler against any later manipulations of
+	// the intended task.
+	smp_store_release(&per_cpu(trc_ipi_to_cpu, smp_processor_id()), false); // ^^^
+	smp_store_release(&texp->trc_ipi_to_cpu, -1); // ^^^
+}
+
+/* Callback function for scheduler to check locked-down task.  */
+static bool trc_inspect_reader(struct task_struct *t, void *arg)
+{
+	int cpu = task_cpu(t);
+	bool in_qs = false;
+	bool ofl = cpu_is_offline(cpu);
+
+	if (task_curr(t)) {
+		WARN_ON_ONCE(ofl & !is_idle_task(t));
+
+		// If no chance of heavyweight readers, do it the hard way.
+		if (!ofl && !IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+			return false;
+
+		// If heavyweight readers are enabled on the remote task,
+		// we can inspect its state despite its currently running.
+		// However, we cannot safely change its state.
+		n_heavy_reader_attempts++;
+		if (!ofl && // Check for "running" idle tasks on offline CPUs.
+		    !rcu_dynticks_zero_in_eqs(cpu, &t->trc_reader_nesting))
+			return false; // No quiescent state, do it the hard way.
+		n_heavy_reader_updates++;
+		if (ofl)
+			n_heavy_reader_ofl_updates++;
+		in_qs = true;
+	} else {
+		in_qs = likely(!t->trc_reader_nesting);
+	}
+
+	// Mark as checked.  Because this is called from the grace-period
+	// kthread, also remove the task from the holdout list.
+	t->trc_reader_checked = true;
+	trc_del_holdout(t);
+
+	if (in_qs)
+		return true;  // Already in quiescent state, done!!!
+
+	// The task is in a read-side critical section, so set up its
+	// state so that it will awaken the grace-period kthread upon exit
+	// from that critical section.
+	atomic_inc(&trc_n_readers_need_end); // One more to wait on.
+	WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+	WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
+	return true;
+}
+
+/* Attempt to extract the state for the specified task. */
+static void trc_wait_for_one_reader(struct task_struct *t,
+				    struct list_head *bhp)
+{
+	int cpu;
+
+	// If a previous IPI is still in flight, let it complete.
+	if (smp_load_acquire(&t->trc_ipi_to_cpu) != -1) // Order IPI
+		return;
+
+	// The current task had better be in a quiescent state.
+	if (t == current) {
+		t->trc_reader_checked = true;
+		trc_del_holdout(t);
+		WARN_ON_ONCE(t->trc_reader_nesting);
+		return;
+	}
+
+	// Attempt to nail down the task for inspection.
+	get_task_struct(t);
+	if (try_invoke_on_locked_down_task(t, trc_inspect_reader, NULL)) {
+		put_task_struct(t);
+		return;
+	}
+	put_task_struct(t);
+
+	// If currently running, send an IPI, either way, add to list.
+	trc_add_holdout(t, bhp);
+	if (task_curr(t) && time_after(jiffies, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) {
+		// The task is currently running, so try IPIing it.
+		cpu = task_cpu(t);
+
+		// If there is already an IPI outstanding, let it happen.
+		if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0)
+			return;
+
+		atomic_inc(&trc_n_readers_need_end);
+		per_cpu(trc_ipi_to_cpu, cpu) = true;
+		t->trc_ipi_to_cpu = cpu;
+		rcu_tasks_trace.n_ipis++;
+		if (smp_call_function_single(cpu,
+					     trc_read_check_handler, t, 0)) {
+			// Just in case there is some other reason for
+			// failure than the target CPU being offline.
+			rcu_tasks_trace.n_ipis_fails++;
+			per_cpu(trc_ipi_to_cpu, cpu) = false;
+			t->trc_ipi_to_cpu = cpu;
+			if (atomic_dec_and_test(&trc_n_readers_need_end)) {
+				WARN_ON_ONCE(1);
+				wake_up(&trc_wait);
+			}
+		}
+	}
+}
+
+/* Initialize for a new RCU-tasks-trace grace period. */
+static void rcu_tasks_trace_pregp_step(void)
+{
+	int cpu;
+
+	// Allow for fast-acting IPIs.
+	atomic_set(&trc_n_readers_need_end, 1);
+
+	// There shouldn't be any old IPIs, but...
+	for_each_possible_cpu(cpu)
+		WARN_ON_ONCE(per_cpu(trc_ipi_to_cpu, cpu));
+
+	// Disable CPU hotplug across the tasklist scan.
+	// This also waits for all readers in CPU-hotplug code paths.
+	cpus_read_lock();
+}
+
+/* Do first-round processing for the specified task. */
+static void rcu_tasks_trace_pertask(struct task_struct *t,
+				    struct list_head *hop)
+{
+	WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
+	WRITE_ONCE(t->trc_reader_checked, false);
+	t->trc_ipi_to_cpu = -1;
+	trc_wait_for_one_reader(t, hop);
+}
+
+/*
+ * Do intermediate processing between task and holdout scans and
+ * pick up the idle tasks.
+ */
+static void rcu_tasks_trace_postscan(struct list_head *hop)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		rcu_tasks_trace_pertask(idle_task(cpu), hop);
+
+	// Re-enable CPU hotplug now that the tasklist scan has completed.
+	cpus_read_unlock();
+
+	// Wait for late-stage exiting tasks to finish exiting.
+	// These might have passed the call to exit_tasks_rcu_finish().
+	synchronize_rcu();
+	// Any tasks that exit after this point will set ->trc_reader_checked.
+}
+
+/* Show the state of a task stalling the current RCU tasks trace GP. */
+static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
+{
+	int cpu;
+
+	if (*firstreport) {
+		pr_err("INFO: rcu_tasks_trace detected stalls on tasks:\n");
+		*firstreport = false;
+	}
+	// FIXME: This should attempt to use try_invoke_on_nonrunning_task().
+	cpu = task_cpu(t);
+	pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
+		 t->pid,
+		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) > 0],
+		 ".i"[is_idle_task(t)],
+		 ".N"[cpu > 0 && tick_nohz_full_cpu(cpu)],
+		 t->trc_reader_nesting,
+		 " N"[!!t->trc_reader_special.b.need_qs],
+		 cpu);
+	sched_show_task(t);
+}
+
+/* List stalled IPIs for RCU tasks trace. */
+static void show_stalled_ipi_trace(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		if (per_cpu(trc_ipi_to_cpu, cpu))
+			pr_alert("\tIPI outstanding to CPU %d\n", cpu);
+}
+
+/* Do one scan of the holdout list. */
+static void check_all_holdout_tasks_trace(struct list_head *hop,
+					  bool needreport, bool *firstreport)
+{
+	struct task_struct *g, *t;
+
+	// Disable CPU hotplug across the holdout list scan.
+	cpus_read_lock();
+
+	list_for_each_entry_safe(t, g, hop, trc_holdout_list) {
+		// If safe and needed, try to check the current task.
+		if (READ_ONCE(t->trc_ipi_to_cpu) == -1 &&
+		    !READ_ONCE(t->trc_reader_checked))
+			trc_wait_for_one_reader(t, hop);
+
+		// If check succeeded, remove this task from the list.
+		if (READ_ONCE(t->trc_reader_checked))
+			trc_del_holdout(t);
+		else if (needreport)
+			show_stalled_task_trace(t, firstreport);
+	}
+
+	// Re-enable CPU hotplug now that the holdout list scan has completed.
+	cpus_read_unlock();
+
+	if (needreport) {
+		if (firstreport)
+			pr_err("INFO: rcu_tasks_trace detected stalls? (Late IPI?)\n");
+		show_stalled_ipi_trace();
+	}
+}
+
+/* Wait for grace period to complete and provide ordering. */
+static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
+{
+	bool firstreport;
+	struct task_struct *g, *t;
+	LIST_HEAD(holdouts);
+	long ret;
+
+	// Remove the safety count.
+	smp_mb__before_atomic();  // Order vs. earlier atomics
+	atomic_dec(&trc_n_readers_need_end);
+	smp_mb__after_atomic();  // Order vs. later atomics
+
+	// Wait for readers.
+	set_tasks_gp_state(rtp, RTGS_WAIT_READERS);
+	for (;;) {
+		ret = wait_event_idle_exclusive_timeout(
+				trc_wait,
+				atomic_read(&trc_n_readers_need_end) == 0,
+				READ_ONCE(rcu_task_stall_timeout));
+		if (ret)
+			break;  // Count reached zero.
+		// Stall warning time, so make a list of the offenders.
+		for_each_process_thread(g, t)
+			if (READ_ONCE(t->trc_reader_special.b.need_qs))
+				trc_add_holdout(t, &holdouts);
+		firstreport = true;
+		list_for_each_entry_safe(t, g, &holdouts, trc_holdout_list)
+			if (READ_ONCE(t->trc_reader_special.b.need_qs)) {
+				show_stalled_task_trace(t, &firstreport);
+				trc_del_holdout(t);
+			}
+		if (firstreport)
+			pr_err("INFO: rcu_tasks_trace detected stalls? (Counter/taskslist mismatch?)\n");
+		show_stalled_ipi_trace();
+		pr_err("\t%d holdouts\n", atomic_read(&trc_n_readers_need_end));
+	}
+	smp_mb(); // Caller's code must be ordered after wakeup.
+		  // Pairs with pretty much every ordering primitive.
+}
+
+/* Report any needed quiescent state for this exiting task. */
+static void exit_tasks_rcu_finish_trace(struct task_struct *t)
+{
+	WRITE_ONCE(t->trc_reader_checked, true);
+	WARN_ON_ONCE(t->trc_reader_nesting);
+	WRITE_ONCE(t->trc_reader_nesting, 0);
+	if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)))
+		rcu_read_unlock_trace_special(t, 0);
+}
+
+/**
+ * call_rcu_tasks_trace() - Queue a callback trace task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks_trace()
+ * assumes that the read-side critical sections end at context switch,
+ * cond_resched_rcu_qs(), or transition to usermode execution.  As such,
+ * there are no read-side primitives analogous to rcu_read_lock() and
+ * rcu_read_unlock() because this primitive is intended to determine
+ * that all tasks have passed through a safe state, not so much for
+ * data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func)
+{
+	call_rcu_tasks_generic(rhp, func, &rcu_tasks_trace);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks_trace);
+
+/**
+ * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period
+ *
+ * Control will return to the caller some time after a trace rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed.  These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory,
+ * anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function preambles
+ * and profiling hooks.  The synchronize_rcu_tasks_trace() function is not
+ * (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+void synchronize_rcu_tasks_trace(void)
+{
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_trace_lock_map), "Illegal synchronize_rcu_tasks_trace() in RCU Tasks Trace read-side critical section");
+	synchronize_rcu_tasks_generic(&rcu_tasks_trace);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_trace);
+
+/**
+ * rcu_barrier_tasks_trace - Wait for in-flight call_rcu_tasks_trace() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks_trace(void)
+{
+	/* There is only one callback queue, so this is easy.  ;-) */
+	synchronize_rcu_tasks_trace();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace);
+
+static int __init rcu_spawn_tasks_trace_kthread(void)
+{
+	rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step;
+	rcu_tasks_trace.pertask_func = rcu_tasks_trace_pertask;
+	rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan;
+	rcu_tasks_trace.holdouts_func = check_all_holdout_tasks_trace;
+	rcu_tasks_trace.postgp_func = rcu_tasks_trace_postgp;
+	rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace);
+	return 0;
+}
+core_initcall(rcu_spawn_tasks_trace_kthread);
+
+static void show_rcu_tasks_trace_gp_kthread(void)
+{
+	char buf[64];
+
+	sprintf(buf, "N%d h:%lu/%lu/%lu", atomic_read(&trc_n_readers_need_end),
+		data_race(n_heavy_reader_ofl_updates),
+		data_race(n_heavy_reader_updates),
+		data_race(n_heavy_reader_attempts));
+	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf);
+}
+
+#else /* #ifdef CONFIG_TASKS_TRACE_RCU */
+static void exit_tasks_rcu_finish_trace(struct task_struct *t) { }
+static inline void show_rcu_tasks_trace_gp_kthread(void) {}
+#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
+
+void show_rcu_tasks_gp_kthreads(void)
+{
+	show_rcu_tasks_classic_gp_kthread();
+	show_rcu_tasks_rude_gp_kthread();
+	show_rcu_tasks_trace_gp_kthread();
+}
+
+#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
+static inline void rcu_tasks_bootup_oddness(void) {}
+void show_rcu_tasks_gp_kthreads(void) {}
+#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 06548e2ebb72..c716eadc7617 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -67,6 +67,19 @@
 #endif
 #define MODULE_PARAM_PREFIX "rcutree."
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
+
 /* Data structures. */
 
 /*
@@ -75,9 +88,6 @@
  */
 #define RCU_DYNTICK_CTRL_MASK 0x1
 #define RCU_DYNTICK_CTRL_CTR  (RCU_DYNTICK_CTRL_MASK + 1)
-#ifndef rcu_eqs_special_exit
-#define rcu_eqs_special_exit() do { } while (0)
-#endif
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
 	.dynticks_nesting = 1,
@@ -100,7 +110,7 @@ static struct rcu_state rcu_state = {
 static bool dump_tree;
 module_param(dump_tree, bool, 0444);
 /* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */
-static bool use_softirq = 1;
+static bool use_softirq = true;
 module_param(use_softirq, bool, 0444);
 /* Control rcu_node-tree auto-balancing at boot time. */
 static bool rcu_fanout_exact;
@@ -225,9 +235,11 @@ void rcu_softirq_qs(void)
 
 /*
  * Record entry into an extended quiescent state.  This is only to be
- * called when not already in an extended quiescent state.
+ * called when not already in an extended quiescent state, that is,
+ * RCU is watching prior to the call to this function and is no longer
+ * watching upon return.
  */
-static void rcu_dynticks_eqs_enter(void)
+static noinstr void rcu_dynticks_eqs_enter(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	int seq;
@@ -237,8 +249,9 @@ static void rcu_dynticks_eqs_enter(void)
 	 * critical sections, and we also must force ordering with the
 	 * next idle sojourn.
 	 */
+	rcu_dynticks_task_trace_enter();  // Before ->dynticks update!
 	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
-	/* Better be in an extended quiescent state! */
+	// RCU is no longer watching.  Better be in extended quiescent state!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     (seq & RCU_DYNTICK_CTRL_CTR));
 	/* Better not have special action (TLB flush) pending! */
@@ -248,9 +261,10 @@ static void rcu_dynticks_eqs_enter(void)
 
 /*
  * Record exit from an extended quiescent state.  This is only to be
- * called from an extended quiescent state.
+ * called from an extended quiescent state, that is, RCU is not watching
+ * prior to the call to this function and is watching upon return.
  */
-static void rcu_dynticks_eqs_exit(void)
+static noinstr void rcu_dynticks_eqs_exit(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	int seq;
@@ -261,13 +275,13 @@ static void rcu_dynticks_eqs_exit(void)
 	 * critical section.
 	 */
 	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	// RCU is now watching.  Better not be in an extended quiescent state!
+	rcu_dynticks_task_trace_exit();  // After ->dynticks update!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     !(seq & RCU_DYNTICK_CTRL_CTR));
 	if (seq & RCU_DYNTICK_CTRL_MASK) {
 		atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
 		smp_mb__after_atomic(); /* _exit after clearing mask. */
-		/* Prefer duplicate flushes to losing a flush. */
-		rcu_eqs_special_exit();
 	}
 }
 
@@ -295,7 +309,7 @@ static void rcu_dynticks_eqs_online(void)
  *
  * No ordering, as we are sampling CPU-local information.
  */
-static bool rcu_dynticks_curr_cpu_in_eqs(void)
+static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
@@ -333,6 +347,28 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap)
 }
 
 /*
+ * Return true if the referenced integer is zero while the specified
+ * CPU remains within a single extended quiescent state.
+ */
+bool rcu_dynticks_zero_in_eqs(int cpu, int *vp)
+{
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	int snap;
+
+	// If not quiescent, force back to earlier extended quiescent state.
+	snap = atomic_read(&rdp->dynticks) & ~(RCU_DYNTICK_CTRL_MASK |
+					       RCU_DYNTICK_CTRL_CTR);
+
+	smp_rmb(); // Order ->dynticks and *vp reads.
+	if (READ_ONCE(*vp))
+		return false;  // Non-zero, so report failure;
+	smp_rmb(); // Order *vp read and ->dynticks re-read.
+
+	// If still in the same extended quiescent state, we are good!
+	return snap == (atomic_read(&rdp->dynticks) & ~RCU_DYNTICK_CTRL_MASK);
+}
+
+/*
  * Set the special (bottom) bit of the specified CPU so that it
  * will take special action (such as flushing its TLB) on the
  * next exit from an extended quiescent state.  Returns true if
@@ -382,16 +418,23 @@ void rcu_momentary_dyntick_idle(void)
 EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle);
 
 /**
- * rcu_is_cpu_rrupt_from_idle - see if interrupted from idle
+ * rcu_is_cpu_rrupt_from_idle - see if 'interrupted' from idle
  *
  * If the current CPU is idle and running at a first-level (not nested)
- * interrupt from idle, return true.  The caller must have at least
- * disabled preemption.
+ * interrupt, or directly, from idle, return true.
+ *
+ * The caller must have at least disabled IRQs.
  */
 static int rcu_is_cpu_rrupt_from_idle(void)
 {
-	/* Called only from within the scheduling-clock interrupt */
-	lockdep_assert_in_irq();
+	long nesting;
+
+	/*
+	 * Usually called from the tick; but also used from smp_function_call()
+	 * for expedited grace periods. This latter can result in running from
+	 * the idle task, instead of an actual IPI.
+	 */
+	lockdep_assert_irqs_disabled();
 
 	/* Check for counter underflows */
 	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) < 0,
@@ -400,9 +443,15 @@ static int rcu_is_cpu_rrupt_from_idle(void)
 			 "RCU dynticks_nmi_nesting counter underflow/zero!");
 
 	/* Are we at first interrupt nesting level? */
-	if (__this_cpu_read(rcu_data.dynticks_nmi_nesting) != 1)
+	nesting = __this_cpu_read(rcu_data.dynticks_nmi_nesting);
+	if (nesting > 1)
 		return false;
 
+	/*
+	 * If we're not in an interrupt, we must be in the idle task!
+	 */
+	WARN_ON_ONCE(!nesting && !is_idle_task(current));
+
 	/* Does CPU appear to be idle from an RCU standpoint? */
 	return __this_cpu_read(rcu_data.dynticks_nesting) == 0;
 }
@@ -562,7 +611,7 @@ EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
  * the possibility of usermode upcalls having messed up our count
  * of interrupt nesting level during the prior busy period.
  */
-static void rcu_eqs_enter(bool user)
+static noinstr void rcu_eqs_enter(bool user)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
@@ -571,19 +620,24 @@ static void rcu_eqs_enter(bool user)
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     rdp->dynticks_nesting == 0);
 	if (rdp->dynticks_nesting != 1) {
+		// RCU will still be watching, so just do accounting and leave.
 		rdp->dynticks_nesting--;
 		return;
 	}
 
 	lockdep_assert_irqs_disabled();
+	instrumentation_begin();
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	rdp = this_cpu_ptr(&rcu_data);
 	do_nocb_deferred_wakeup(rdp);
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
+	instrumentation_end();
 	WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
+	// RCU is watching here ...
 	rcu_dynticks_eqs_enter();
+	// ... but is no longer watching here.
 	rcu_dynticks_task_enter();
 }
 
@@ -616,23 +670,25 @@ void rcu_idle_enter(void)
  * If you add or remove a call to rcu_user_enter(), be sure to test with
  * CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_user_enter(void)
+noinstr void rcu_user_enter(void)
 {
 	lockdep_assert_irqs_disabled();
 	rcu_eqs_enter(true);
 }
 #endif /* CONFIG_NO_HZ_FULL */
 
-/*
+/**
+ * rcu_nmi_exit - inform RCU of exit from NMI context
+ *
  * If we are returning from the outermost NMI handler that interrupted an
  * RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting
  * to let the RCU grace-period handling know that the CPU is back to
  * being RCU-idle.
  *
- * If you add or remove a call to rcu_nmi_exit_common(), be sure to test
+ * If you add or remove a call to rcu_nmi_exit(), be sure to test
  * with CONFIG_RCU_EQS_DEBUG=y.
  */
-static __always_inline void rcu_nmi_exit_common(bool irq)
+noinstr void rcu_nmi_exit(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
@@ -649,38 +705,33 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
 	 * leave it in non-RCU-idle state.
 	 */
 	if (rdp->dynticks_nmi_nesting != 1) {
+		instrumentation_begin();
 		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
 				  atomic_read(&rdp->dynticks));
 		WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
 			   rdp->dynticks_nmi_nesting - 2);
+		instrumentation_end();
 		return;
 	}
 
+	instrumentation_begin();
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
 	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
-	if (irq)
+	if (!in_nmi())
 		rcu_prepare_for_idle();
+	instrumentation_end();
 
+	// RCU is watching here ...
 	rcu_dynticks_eqs_enter();
+	// ... but is no longer watching here.
 
-	if (irq)
+	if (!in_nmi())
 		rcu_dynticks_task_enter();
 }
 
 /**
- * rcu_nmi_exit - inform RCU of exit from NMI context
- *
- * If you add or remove a call to rcu_nmi_exit(), be sure to test
- * with CONFIG_RCU_EQS_DEBUG=y.
- */
-void rcu_nmi_exit(void)
-{
-	rcu_nmi_exit_common(false);
-}
-
-/**
  * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
  *
  * Exit from an interrupt handler, which might possibly result in entering
@@ -699,12 +750,52 @@ void rcu_nmi_exit(void)
  * If you add or remove a call to rcu_irq_exit(), be sure to test with
  * CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_irq_exit(void)
+void noinstr rcu_irq_exit(void)
+{
+	lockdep_assert_irqs_disabled();
+	rcu_nmi_exit();
+}
+
+/**
+ * rcu_irq_exit_preempt - Inform RCU that current CPU is exiting irq
+ *			  towards in kernel preemption
+ *
+ * Same as rcu_irq_exit() but has a sanity check that scheduling is safe
+ * from RCU point of view. Invoked from return from interrupt before kernel
+ * preemption.
+ */
+void rcu_irq_exit_preempt(void)
 {
 	lockdep_assert_irqs_disabled();
-	rcu_nmi_exit_common(true);
+	rcu_nmi_exit();
+
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
+			 "RCU dynticks_nesting counter underflow/zero!");
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
+			 DYNTICK_IRQ_NONIDLE,
+			 "Bad RCU  dynticks_nmi_nesting counter\n");
+	RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+			 "RCU in extended quiescent state!");
 }
 
+#ifdef CONFIG_PROVE_RCU
+/**
+ * rcu_irq_exit_check_preempt - Validate that scheduling is possible
+ */
+void rcu_irq_exit_check_preempt(void)
+{
+	lockdep_assert_irqs_disabled();
+
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
+			 "RCU dynticks_nesting counter underflow/zero!");
+	RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
+			 DYNTICK_IRQ_NONIDLE,
+			 "Bad RCU  dynticks_nmi_nesting counter\n");
+	RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+			 "RCU in extended quiescent state!");
+}
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
 /*
  * Wrapper for rcu_irq_exit() where interrupts are enabled.
  *
@@ -728,7 +819,7 @@ void rcu_irq_exit_irqson(void)
  * allow for the possibility of usermode upcalls messing up our count of
  * interrupt nesting level during the busy period that is just now starting.
  */
-static void rcu_eqs_exit(bool user)
+static void noinstr rcu_eqs_exit(bool user)
 {
 	struct rcu_data *rdp;
 	long oldval;
@@ -738,17 +829,22 @@ static void rcu_eqs_exit(bool user)
 	oldval = rdp->dynticks_nesting;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
 	if (oldval) {
+		// RCU was already watching, so just do accounting and leave.
 		rdp->dynticks_nesting++;
 		return;
 	}
 	rcu_dynticks_task_exit();
+	// RCU is not watching here ...
 	rcu_dynticks_eqs_exit();
+	// ... but is watching here.
+	instrumentation_begin();
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	WRITE_ONCE(rdp->dynticks_nesting, 1);
 	WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE);
+	instrumentation_end();
 }
 
 /**
@@ -779,14 +875,75 @@ void rcu_idle_exit(void)
  * If you add or remove a call to rcu_user_exit(), be sure to test with
  * CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_user_exit(void)
+void noinstr rcu_user_exit(void)
 {
 	rcu_eqs_exit(1);
 }
+
+/**
+ * __rcu_irq_enter_check_tick - Enable scheduler tick on CPU if RCU needs it.
+ *
+ * The scheduler tick is not normally enabled when CPUs enter the kernel
+ * from nohz_full userspace execution.  After all, nohz_full userspace
+ * execution is an RCU quiescent state and the time executing in the kernel
+ * is quite short.  Except of course when it isn't.  And it is not hard to
+ * cause a large system to spend tens of seconds or even minutes looping
+ * in the kernel, which can cause a number of problems, include RCU CPU
+ * stall warnings.
+ *
+ * Therefore, if a nohz_full CPU fails to report a quiescent state
+ * in a timely manner, the RCU grace-period kthread sets that CPU's
+ * ->rcu_urgent_qs flag with the expectation that the next interrupt or
+ * exception will invoke this function, which will turn on the scheduler
+ * tick, which will enable RCU to detect that CPU's quiescent states,
+ * for example, due to cond_resched() calls in CONFIG_PREEMPT=n kernels.
+ * The tick will be disabled once a quiescent state is reported for
+ * this CPU.
+ *
+ * Of course, in carefully tuned systems, there might never be an
+ * interrupt or exception.  In that case, the RCU grace-period kthread
+ * will eventually cause one to happen.  However, in less carefully
+ * controlled environments, this function allows RCU to get what it
+ * needs without creating otherwise useless interruptions.
+ */
+void __rcu_irq_enter_check_tick(void)
+{
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
+	 // Enabling the tick is unsafe in NMI handlers.
+	if (WARN_ON_ONCE(in_nmi()))
+		return;
+
+	RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+			 "Illegal rcu_irq_enter_check_tick() from extended quiescent state");
+
+	if (!tick_nohz_full_cpu(rdp->cpu) ||
+	    !READ_ONCE(rdp->rcu_urgent_qs) ||
+	    READ_ONCE(rdp->rcu_forced_tick)) {
+		// RCU doesn't need nohz_full help from this CPU, or it is
+		// already getting that help.
+		return;
+	}
+
+	// We get here only when not in an extended quiescent state and
+	// from interrupts (as opposed to NMIs).  Therefore, (1) RCU is
+	// already watching and (2) The fact that we are in an interrupt
+	// handler and that the rcu_node lock is an irq-disabled lock
+	// prevents self-deadlock.  So we can safely recheck under the lock.
+	// Note that the nohz_full state currently cannot change.
+	raw_spin_lock_rcu_node(rdp->mynode);
+	if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
+		// A nohz_full CPU is in the kernel and RCU needs a
+		// quiescent state.  Turn on the tick!
+		WRITE_ONCE(rdp->rcu_forced_tick, true);
+		tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+	}
+	raw_spin_unlock_rcu_node(rdp->mynode);
+}
 #endif /* CONFIG_NO_HZ_FULL */
 
 /**
- * rcu_nmi_enter_common - inform RCU of entry to NMI context
+ * rcu_nmi_enter - inform RCU of entry to NMI context
  * @irq: Is this call from rcu_irq_enter?
  *
  * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and
@@ -795,10 +952,10 @@ void rcu_user_exit(void)
  * long as the nesting level does not overflow an int.  (You will probably
  * run out of stack space first.)
  *
- * If you add or remove a call to rcu_nmi_enter_common(), be sure to test
+ * If you add or remove a call to rcu_nmi_enter(), be sure to test
  * with CONFIG_RCU_EQS_DEBUG=y.
  */
-static __always_inline void rcu_nmi_enter_common(bool irq)
+noinstr void rcu_nmi_enter(void)
 {
 	long incby = 2;
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -816,45 +973,33 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 	 */
 	if (rcu_dynticks_curr_cpu_in_eqs()) {
 
-		if (irq)
+		if (!in_nmi())
 			rcu_dynticks_task_exit();
 
+		// RCU is not watching here ...
 		rcu_dynticks_eqs_exit();
+		// ... but is watching here.
 
-		if (irq)
+		if (!in_nmi())
 			rcu_cleanup_after_idle();
 
 		incby = 1;
-	} else if (tick_nohz_full_cpu(rdp->cpu) &&
-		   rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE &&
-		   READ_ONCE(rdp->rcu_urgent_qs) &&
-		   !READ_ONCE(rdp->rcu_forced_tick)) {
-		raw_spin_lock_rcu_node(rdp->mynode);
-		// Recheck under lock.
-		if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
-			WRITE_ONCE(rdp->rcu_forced_tick, true);
-			tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
-		}
-		raw_spin_unlock_rcu_node(rdp->mynode);
+	} else if (!in_nmi()) {
+		instrumentation_begin();
+		rcu_irq_enter_check_tick();
+		instrumentation_end();
 	}
+	instrumentation_begin();
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
 			  rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
+	instrumentation_end();
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
 		   rdp->dynticks_nmi_nesting + incby);
 	barrier();
 }
 
 /**
- * rcu_nmi_enter - inform RCU of entry to NMI context
- */
-void rcu_nmi_enter(void)
-{
-	rcu_nmi_enter_common(false);
-}
-NOKPROBE_SYMBOL(rcu_nmi_enter);
-
-/**
  * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
  *
  * Enter an interrupt handler, which might possibly result in exiting
@@ -876,10 +1021,10 @@ NOKPROBE_SYMBOL(rcu_nmi_enter);
  * If you add or remove a call to rcu_irq_enter(), be sure to test with
  * CONFIG_RCU_EQS_DEBUG=y.
  */
-void rcu_irq_enter(void)
+noinstr void rcu_irq_enter(void)
 {
 	lockdep_assert_irqs_disabled();
-	rcu_nmi_enter_common(true);
+	rcu_nmi_enter();
 }
 
 /*
@@ -913,6 +1058,11 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
 	}
 }
 
+noinstr bool __rcu_is_watching(void)
+{
+	return !rcu_dynticks_curr_cpu_in_eqs();
+}
+
 /**
  * rcu_is_watching - see if RCU thinks that the current CPU is not idle
  *
@@ -921,7 +1071,7 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
  * if the current CPU is not in its idle loop or is in an interrupt or
  * NMI handler, return true.
  */
-bool notrace rcu_is_watching(void)
+bool rcu_is_watching(void)
 {
 	bool ret;
 
@@ -973,12 +1123,12 @@ bool rcu_lockdep_current_cpu_online(void)
 
 	if (in_nmi() || !rcu_scheduler_fully_active)
 		return true;
-	preempt_disable();
+	preempt_disable_notrace();
 	rdp = this_cpu_ptr(&rcu_data);
 	rnp = rdp->mynode;
 	if (rdp->grpmask & rcu_rnp_online_cpus(rnp))
 		ret = true;
-	preempt_enable();
+	preempt_enable_notrace();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
@@ -1217,7 +1367,7 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
 		trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
 		goto unlock_out;
 	}
-	trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("newreq"));
+	trace_rcu_grace_period(rcu_state.name, data_race(rcu_state.gp_seq), TPS("newreq"));
 	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
 	/* Push furthest requested GP to leaf node and rcu_data structure. */
@@ -1473,6 +1623,31 @@ static void rcu_gp_slow(int delay)
 		schedule_timeout_uninterruptible(delay);
 }
 
+static unsigned long sleep_duration;
+
+/* Allow rcutorture to stall the grace-period kthread. */
+void rcu_gp_set_torture_wait(int duration)
+{
+	if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST) && duration > 0)
+		WRITE_ONCE(sleep_duration, duration);
+}
+EXPORT_SYMBOL_GPL(rcu_gp_set_torture_wait);
+
+/* Actually implement the aforementioned wait. */
+static void rcu_gp_torture_wait(void)
+{
+	unsigned long duration;
+
+	if (!IS_ENABLED(CONFIG_RCU_TORTURE_TEST))
+		return;
+	duration = xchg(&sleep_duration, 0UL);
+	if (duration > 0) {
+		pr_alert("%s: Waiting %lu jiffies\n", __func__, duration);
+		schedule_timeout_uninterruptible(duration);
+		pr_alert("%s: Wait complete\n", __func__);
+	}
+}
+
 /*
  * Initialize a new grace period.  Return false if no grace period required.
  */
@@ -1506,6 +1681,7 @@ static bool rcu_gp_init(void)
 	record_gp_stall_check_time();
 	/* Record GP times before starting GP, hence rcu_seq_start(). */
 	rcu_seq_start(&rcu_state.gp_seq);
+	ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
 	trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start"));
 	raw_spin_unlock_irq_rcu_node(rnp);
 
@@ -1611,12 +1787,16 @@ static bool rcu_gp_fqs_check_wake(int *gfp)
 {
 	struct rcu_node *rnp = rcu_get_root();
 
-	/* Someone like call_rcu() requested a force-quiescent-state scan. */
+	// If under overload conditions, force an immediate FQS scan.
+	if (*gfp & RCU_GP_FLAG_OVLD)
+		return true;
+
+	// Someone like call_rcu() requested a force-quiescent-state scan.
 	*gfp = READ_ONCE(rcu_state.gp_flags);
 	if (*gfp & RCU_GP_FLAG_FQS)
 		return true;
 
-	/* The current grace period has completed. */
+	// The current grace period has completed.
 	if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp))
 		return true;
 
@@ -1654,13 +1834,15 @@ static void rcu_gp_fqs(bool first_time)
 static void rcu_gp_fqs_loop(void)
 {
 	bool first_gp_fqs;
-	int gf;
+	int gf = 0;
 	unsigned long j;
 	int ret;
 	struct rcu_node *rnp = rcu_get_root();
 
 	first_gp_fqs = true;
 	j = READ_ONCE(jiffies_till_first_fqs);
+	if (rcu_state.cbovld)
+		gf = RCU_GP_FLAG_OVLD;
 	ret = 0;
 	for (;;) {
 		if (!ret) {
@@ -1673,6 +1855,7 @@ static void rcu_gp_fqs_loop(void)
 		rcu_state.gp_state = RCU_GP_WAIT_FQS;
 		ret = swait_event_idle_timeout_exclusive(
 				rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j);
+		rcu_gp_torture_wait();
 		rcu_state.gp_state = RCU_GP_DOING_FQS;
 		/* Locking provides needed memory barriers. */
 		/* If grace period done, leave loop. */
@@ -1680,12 +1863,16 @@ static void rcu_gp_fqs_loop(void)
 		    !rcu_preempt_blocked_readers_cgp(rnp))
 			break;
 		/* If time for quiescent-state forcing, do it. */
-		if (ULONG_CMP_GE(jiffies, rcu_state.jiffies_force_qs) ||
+		if (!time_after(rcu_state.jiffies_force_qs, jiffies) ||
 		    (gf & RCU_GP_FLAG_FQS)) {
 			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("fqsstart"));
 			rcu_gp_fqs(first_gp_fqs);
-			first_gp_fqs = false;
+			gf = 0;
+			if (first_gp_fqs) {
+				first_gp_fqs = false;
+				gf = rcu_state.cbovld ? RCU_GP_FLAG_OVLD : 0;
+			}
 			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("fqsend"));
 			cond_resched_tasks_rcu_qs();
@@ -1705,6 +1892,7 @@ static void rcu_gp_fqs_loop(void)
 				j = 1;
 			else
 				j = rcu_state.jiffies_force_qs - j;
+			gf = 0;
 		}
 	}
 }
@@ -1781,6 +1969,7 @@ static void rcu_gp_cleanup(void)
 	/* Declare grace period done, trace first to use old GP number. */
 	trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
 	rcu_seq_end(&rcu_state.gp_seq);
+	ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
 	rcu_state.gp_state = RCU_GP_IDLE;
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(&rcu_data);
@@ -1821,6 +2010,7 @@ static int __noreturn rcu_gp_kthread(void *unused)
 			swait_event_idle_exclusive(rcu_state.gp_wq,
 					 READ_ONCE(rcu_state.gp_flags) &
 					 RCU_GP_FLAG_INIT);
+			rcu_gp_torture_wait();
 			rcu_state.gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init())
@@ -2811,6 +3001,8 @@ struct kfree_rcu_cpu {
 	struct delayed_work monitor_work;
 	bool monitor_todo;
 	bool initialized;
+	// Number of objects for which GP not started
+	int count;
 };
 
 static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc);
@@ -2924,6 +3116,8 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 				krcp->head = NULL;
 			}
 
+			WRITE_ONCE(krcp->count, 0);
+
 			/*
 			 * One work is per one batch, so there are two "free channels",
 			 * "bhead_free" and "head_free" the batch can handle. It can be
@@ -3060,6 +3254,8 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		krcp->head = head;
 	}
 
+	WRITE_ONCE(krcp->count, krcp->count + 1);
+
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
 	    !krcp->monitor_todo) {
@@ -3074,6 +3270,56 @@ unlock_return:
 }
 EXPORT_SYMBOL_GPL(kfree_call_rcu);
 
+static unsigned long
+kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu;
+	unsigned long count = 0;
+
+	/* Snapshot count of all CPUs */
+	for_each_online_cpu(cpu) {
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		count += READ_ONCE(krcp->count);
+	}
+
+	return count;
+}
+
+static unsigned long
+kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu, freed = 0;
+	unsigned long flags;
+
+	for_each_online_cpu(cpu) {
+		int count;
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		count = krcp->count;
+		spin_lock_irqsave(&krcp->lock, flags);
+		if (krcp->monitor_todo)
+			kfree_rcu_drain_unlock(krcp, flags);
+		else
+			spin_unlock_irqrestore(&krcp->lock, flags);
+
+		sc->nr_to_scan -= count;
+		freed += count;
+
+		if (sc->nr_to_scan <= 0)
+			break;
+	}
+
+	return freed;
+}
+
+static struct shrinker kfree_rcu_shrinker = {
+	.count_objects = kfree_rcu_shrink_count,
+	.scan_objects = kfree_rcu_shrink_scan,
+	.batch = 0,
+	.seeks = DEFAULT_SEEKS,
+};
+
 void __init kfree_rcu_scheduler_running(void)
 {
 	int cpu;
@@ -3599,6 +3845,7 @@ void rcu_cpu_starting(unsigned int cpu)
 	nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
 	/* Allow lockless access for expedited grace periods. */
 	smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + nbits); /* ^^^ */
+	ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus);
 	rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
 	rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
 	rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
@@ -3994,6 +4241,8 @@ static void __init kfree_rcu_batch_init(void)
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
 		krcp->initialized = true;
 	}
+	if (register_shrinker(&kfree_rcu_shrinker))
+		pr_err("Failed to register kfree_rcu() shrinker!\n");
 }
 
 void __init rcu_init(void)
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 9dc2ec021da5..43991a40b084 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -359,6 +359,7 @@ struct rcu_state {
 /* Values for rcu_state structure's gp_flags field. */
 #define RCU_GP_FLAG_INIT 0x1	/* Need grace-period initialization. */
 #define RCU_GP_FLAG_FQS  0x2	/* Need grace-period quiescent-state forcing. */
+#define RCU_GP_FLAG_OVLD 0x4	/* Experiencing callback overload. */
 
 /* Values for rcu_state structure's gp_state field. */
 #define RCU_GP_IDLE	 0	/* Initial state and no GP in progress. */
@@ -454,6 +455,8 @@ static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(void);
 static void rcu_dynticks_task_enter(void);
 static void rcu_dynticks_task_exit(void);
+static void rcu_dynticks_task_trace_enter(void);
+static void rcu_dynticks_task_trace_exit(void);
 
 /* Forward declarations for tree_stall.h */
 static void record_gp_stall_check_time(void);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 1a617b9dffb0..72952edad1e4 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -150,7 +150,7 @@ static void __maybe_unused sync_exp_reset_tree(void)
 static bool sync_rcu_exp_done(struct rcu_node *rnp)
 {
 	raw_lockdep_assert_held_rcu_node(rnp);
-	return rnp->exp_tasks == NULL &&
+	return READ_ONCE(rnp->exp_tasks) == NULL &&
 	       READ_ONCE(rnp->expmask) == 0;
 }
 
@@ -373,7 +373,7 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	 * until such time as the ->expmask bits are cleared.
 	 */
 	if (rcu_preempt_has_tasks(rnp))
-		rnp->exp_tasks = rnp->blkd_tasks.next;
+		WRITE_ONCE(rnp->exp_tasks, rnp->blkd_tasks.next);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	/* IPI the remaining CPUs for expedited quiescent state. */
@@ -542,8 +542,8 @@ static void synchronize_rcu_expedited_wait(void)
 		}
 		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
 			jiffies - jiffies_start, rcu_state.expedited_sequence,
-			READ_ONCE(rnp_root->expmask),
-			".T"[!!rnp_root->exp_tasks]);
+			data_race(rnp_root->expmask),
+			".T"[!!data_race(rnp_root->exp_tasks)]);
 		if (ndetected) {
 			pr_err("blocking rcu_node structures:");
 			rcu_for_each_node_breadth_first(rnp) {
@@ -553,8 +553,8 @@ static void synchronize_rcu_expedited_wait(void)
 					continue;
 				pr_cont(" l=%u:%d-%d:%#lx/%c",
 					rnp->level, rnp->grplo, rnp->grphi,
-					READ_ONCE(rnp->expmask),
-					".T"[!!rnp->exp_tasks]);
+					data_race(rnp->expmask),
+					".T"[!!data_race(rnp->exp_tasks)]);
 			}
 			pr_cont("\n");
 		}
@@ -639,6 +639,7 @@ static void wait_rcu_exp_gp(struct work_struct *wp)
  */
 static void rcu_exp_handler(void *unused)
 {
+	int depth = rcu_preempt_depth();
 	unsigned long flags;
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
@@ -649,7 +650,7 @@ static void rcu_exp_handler(void *unused)
 	 * critical section.  If also enabled or idle, immediately
 	 * report the quiescent state, otherwise defer.
 	 */
-	if (!rcu_preempt_depth()) {
+	if (!depth) {
 		if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
 		    rcu_dynticks_curr_cpu_in_eqs()) {
 			rcu_report_exp_rdp(rdp);
@@ -673,7 +674,7 @@ static void rcu_exp_handler(void *unused)
 	 * can have caused this quiescent state to already have been
 	 * reported, so we really do need to check ->expmask.
 	 */
-	if (rcu_preempt_depth() > 0) {
+	if (depth > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
 			rdp->exp_deferred_qs = true;
@@ -683,30 +684,8 @@ static void rcu_exp_handler(void *unused)
 		return;
 	}
 
-	/*
-	 * The final and least likely case is where the interrupted
-	 * code was just about to or just finished exiting the RCU-preempt
-	 * read-side critical section, and no, we can't tell which.
-	 * So either way, set ->deferred_qs to flag later code that
-	 * a quiescent state is required.
-	 *
-	 * If the CPU is fully enabled (or if some buggy RCU-preempt
-	 * read-side critical section is being used from idle), just
-	 * invoke rcu_preempt_deferred_qs() to immediately report the
-	 * quiescent state.  We cannot use rcu_read_unlock_special()
-	 * because we are in an interrupt handler, which will cause that
-	 * function to take an early exit without doing anything.
-	 *
-	 * Otherwise, force a context switch after the CPU enables everything.
-	 */
-	rdp->exp_deferred_qs = true;
-	if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
-	    WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs())) {
-		rcu_preempt_deferred_qs(t);
-	} else {
-		set_tsk_need_resched(t);
-		set_preempt_need_resched();
-	}
+	// Finally, negative nesting depth should not happen.
+	WARN_ON_ONCE(1);
 }
 
 /* PREEMPTION=y, so no PREEMPTION=n expedited grace period to clean up after. */
@@ -721,17 +700,20 @@ static void sync_sched_exp_online_cleanup(int cpu)
  */
 static int rcu_print_task_exp_stall(struct rcu_node *rnp)
 {
-	struct task_struct *t;
+	unsigned long flags;
 	int ndetected = 0;
+	struct task_struct *t;
 
-	if (!rnp->exp_tasks)
+	if (!READ_ONCE(rnp->exp_tasks))
 		return 0;
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	t = list_entry(rnp->exp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
 		pr_cont(" P%d", t->pid);
 		ndetected++;
 	}
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	return ndetected;
 }
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 097635c41135..352223664ebd 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -226,7 +226,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
 	}
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
-		rnp->exp_tasks = &t->rcu_node_entry;
+		WRITE_ONCE(rnp->exp_tasks, &t->rcu_node_entry);
 	WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
 		     !(rnp->qsmask & rdp->grpmask));
 	WARN_ON_ONCE(!(blkd_state & RCU_EXP_BLKD) !=
@@ -331,6 +331,7 @@ void rcu_note_context_switch(bool preempt)
 	rcu_qs();
 	if (rdp->exp_deferred_qs)
 		rcu_report_exp_rdp(rdp);
+	rcu_tasks_qs(current, preempt);
 	trace_rcu_utilization(TPS("End context switch"));
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -345,9 +346,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 	return READ_ONCE(rnp->gp_tasks) != NULL;
 }
 
-/* Bias and limit values for ->rcu_read_lock_nesting. */
-#define RCU_NEST_BIAS INT_MAX
-#define RCU_NEST_NMAX (-INT_MAX / 2)
+/* limit value for ->rcu_read_lock_nesting. */
 #define RCU_NEST_PMAX (INT_MAX / 2)
 
 static void rcu_preempt_read_enter(void)
@@ -355,9 +354,9 @@ static void rcu_preempt_read_enter(void)
 	current->rcu_read_lock_nesting++;
 }
 
-static void rcu_preempt_read_exit(void)
+static int rcu_preempt_read_exit(void)
 {
-	current->rcu_read_lock_nesting--;
+	return --current->rcu_read_lock_nesting;
 }
 
 static void rcu_preempt_depth_set(int val)
@@ -390,21 +389,15 @@ void __rcu_read_unlock(void)
 {
 	struct task_struct *t = current;
 
-	if (rcu_preempt_depth() != 1) {
-		rcu_preempt_read_exit();
-	} else {
+	if (rcu_preempt_read_exit() == 0) {
 		barrier();  /* critical section before exit code. */
-		rcu_preempt_depth_set(-RCU_NEST_BIAS);
-		barrier();  /* assign before ->rcu_read_unlock_special load */
 		if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
-		barrier();  /* ->rcu_read_unlock_special load before assign */
-		rcu_preempt_depth_set(0);
 	}
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
 		int rrln = rcu_preempt_depth();
 
-		WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX);
+		WARN_ON_ONCE(rrln < 0 || rrln > RCU_NEST_PMAX);
 	}
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
@@ -500,12 +493,12 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		if (&t->rcu_node_entry == rnp->gp_tasks)
 			WRITE_ONCE(rnp->gp_tasks, np);
 		if (&t->rcu_node_entry == rnp->exp_tasks)
-			rnp->exp_tasks = np;
+			WRITE_ONCE(rnp->exp_tasks, np);
 		if (IS_ENABLED(CONFIG_RCU_BOOST)) {
 			/* Snapshot ->boost_mtx ownership w/rnp->lock held. */
 			drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
 			if (&t->rcu_node_entry == rnp->boost_tasks)
-				rnp->boost_tasks = np;
+				WRITE_ONCE(rnp->boost_tasks, np);
 		}
 
 		/*
@@ -556,7 +549,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
 	return (__this_cpu_read(rcu_data.exp_deferred_qs) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
-	       rcu_preempt_depth() <= 0;
+	       rcu_preempt_depth() == 0;
 }
 
 /*
@@ -569,16 +562,11 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 static void rcu_preempt_deferred_qs(struct task_struct *t)
 {
 	unsigned long flags;
-	bool couldrecurse = rcu_preempt_depth() >= 0;
 
 	if (!rcu_preempt_need_deferred_qs(t))
 		return;
-	if (couldrecurse)
-		rcu_preempt_depth_set(rcu_preempt_depth() - RCU_NEST_BIAS);
 	local_irq_save(flags);
 	rcu_preempt_deferred_qs_irqrestore(t, flags);
-	if (couldrecurse)
-		rcu_preempt_depth_set(rcu_preempt_depth() + RCU_NEST_BIAS);
 }
 
 /*
@@ -615,19 +603,18 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 		struct rcu_node *rnp = rdp->mynode;
 
-		exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) ||
-		      (rdp->grpmask & READ_ONCE(rnp->expmask)) ||
-		      tick_nohz_full_cpu(rdp->cpu);
+		exp = (t->rcu_blocked_node &&
+		       READ_ONCE(t->rcu_blocked_node->exp_tasks)) ||
+		      (rdp->grpmask & READ_ONCE(rnp->expmask));
 		// Need to defer quiescent state until everything is enabled.
-		if (irqs_were_disabled && use_softirq &&
-		    (in_interrupt() ||
-		     (exp && !t->rcu_read_unlock_special.b.deferred_qs))) {
-			// Using softirq, safe to awaken, and we get
-			// no help from enabling irqs, unlike bh/preempt.
+		if (use_softirq && (in_irq() || (exp && !irqs_were_disabled))) {
+			// Using softirq, safe to awaken, and either the
+			// wakeup is free or there is an expedited GP.
 			raise_softirq_irqoff(RCU_SOFTIRQ);
 		} else {
 			// Enabling BH or preempt does reschedule, so...
-			// Also if no expediting or NO_HZ_FULL, slow is OK.
+			// Also if no expediting, slow is OK.
+			// Plus nohz_full CPUs eventually get tick enabled.
 			set_tsk_need_resched(current);
 			set_preempt_need_resched();
 			if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
@@ -640,7 +627,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 				irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu);
 			}
 		}
-		t->rcu_read_unlock_special.b.deferred_qs = true;
 		local_irq_restore(flags);
 		return;
 	}
@@ -699,7 +685,7 @@ static void rcu_flavor_sched_clock_irq(int user)
 	} else if (rcu_preempt_need_deferred_qs(t)) {
 		rcu_preempt_deferred_qs(t); /* Report deferred QS. */
 		return;
-	} else if (!rcu_preempt_depth()) {
+	} else if (!WARN_ON_ONCE(rcu_preempt_depth())) {
 		rcu_qs(); /* Report immediate QS. */
 		return;
 	}
@@ -760,8 +746,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 		pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
 			__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
 	pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
-		__func__, READ_ONCE(rnp->gp_tasks), rnp->boost_tasks,
-		rnp->exp_tasks);
+		__func__, READ_ONCE(rnp->gp_tasks), data_race(rnp->boost_tasks),
+		READ_ONCE(rnp->exp_tasks));
 	pr_info("%s: ->blkd_tasks", __func__);
 	i = 0;
 	list_for_each(lhp, &rnp->blkd_tasks) {
@@ -854,8 +840,7 @@ void rcu_note_context_switch(bool preempt)
 	this_cpu_write(rcu_data.rcu_urgent_qs, false);
 	if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs)))
 		rcu_momentary_dyntick_idle();
-	if (!preempt)
-		rcu_tasks_qs(current);
+	rcu_tasks_qs(current, preempt);
 out:
 	trace_rcu_utilization(TPS("End context switch"));
 }
@@ -1036,7 +1021,8 @@ static int rcu_boost_kthread(void *arg)
 	for (;;) {
 		WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_WAITING);
 		trace_rcu_utilization(TPS("End boost kthread@rcu_wait"));
-		rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
+		rcu_wait(READ_ONCE(rnp->boost_tasks) ||
+			 READ_ONCE(rnp->exp_tasks));
 		trace_rcu_utilization(TPS("Start boost kthread@rcu_wait"));
 		WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_RUNNING);
 		more2boost = rcu_boost(rnp);
@@ -1079,9 +1065,9 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	    (rnp->gp_tasks != NULL &&
 	     rnp->boost_tasks == NULL &&
 	     rnp->qsmask == 0 &&
-	     (ULONG_CMP_GE(jiffies, rnp->boost_time) || rcu_state.cbovld))) {
+	     (!time_after(rnp->boost_time, jiffies) || rcu_state.cbovld))) {
 		if (rnp->exp_tasks == NULL)
-			rnp->boost_tasks = rnp->gp_tasks;
+			WRITE_ONCE(rnp->boost_tasks, rnp->gp_tasks);
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		rcu_wake_cond(rnp->boost_kthread_task,
 			      READ_ONCE(rnp->boost_kthread_status));
@@ -2536,7 +2522,7 @@ static bool rcu_nohz_full_cpu(void)
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_cpu(smp_processor_id()) &&
 	    (!rcu_gp_in_progress() ||
-	     ULONG_CMP_LT(jiffies, READ_ONCE(rcu_state.gp_start) + HZ)))
+	     time_before(jiffies, READ_ONCE(rcu_state.gp_start) + HZ)))
 		return true;
 #endif /* #ifdef CONFIG_NO_HZ_FULL */
 	return false;
@@ -2553,7 +2539,7 @@ static void rcu_bind_gp_kthread(void)
 }
 
 /* Record the current task on dyntick-idle entry. */
-static void rcu_dynticks_task_enter(void)
+static void noinstr rcu_dynticks_task_enter(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
 	WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
@@ -2561,9 +2547,27 @@ static void rcu_dynticks_task_enter(void)
 }
 
 /* Record no current task on dyntick-idle exit. */
-static void rcu_dynticks_task_exit(void)
+static void noinstr rcu_dynticks_task_exit(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
 	WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
 #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
 }
+
+/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */
+static void rcu_dynticks_task_trace_enter(void)
+{
+#ifdef CONFIG_TASKS_RCU_TRACE
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+		current->trc_reader_special.b.need_mb = true;
+#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */
+}
+
+/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
+static void rcu_dynticks_task_trace_exit(void)
+{
+#ifdef CONFIG_TASKS_RCU_TRACE
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+		current->trc_reader_special.b.need_mb = false;
+#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */
+}
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 119ed6afd20f..ae76bd329582 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -15,10 +15,12 @@
 int sysctl_panic_on_rcu_stall __read_mostly;
 
 #ifdef CONFIG_PROVE_RCU
-#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
+#define RCU_STALL_DELAY_DELTA		(5 * HZ)
 #else
-#define RCU_STALL_DELAY_DELTA	       0
+#define RCU_STALL_DELAY_DELTA		0
 #endif
+#define RCU_STALL_MIGHT_DIV		8
+#define RCU_STALL_MIGHT_MIN		(2 * HZ)
 
 /* Limit-check stall timeouts specified at boottime and runtime. */
 int rcu_jiffies_till_stall_check(void)
@@ -40,6 +42,36 @@ int rcu_jiffies_till_stall_check(void)
 }
 EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
 
+/**
+ * rcu_gp_might_be_stalled - Is it likely that the grace period is stalled?
+ *
+ * Returns @true if the current grace period is sufficiently old that
+ * it is reasonable to assume that it might be stalled.  This can be
+ * useful when deciding whether to allocate memory to enable RCU-mediated
+ * freeing on the one hand or just invoking synchronize_rcu() on the other.
+ * The latter is preferable when the grace period is stalled.
+ *
+ * Note that sampling of the .gp_start and .gp_seq fields must be done
+ * carefully to avoid false positives at the beginnings and ends of
+ * grace periods.
+ */
+bool rcu_gp_might_be_stalled(void)
+{
+	unsigned long d = rcu_jiffies_till_stall_check() / RCU_STALL_MIGHT_DIV;
+	unsigned long j = jiffies;
+
+	if (d < RCU_STALL_MIGHT_MIN)
+		d = RCU_STALL_MIGHT_MIN;
+	smp_mb(); // jiffies before .gp_seq to avoid false positives.
+	if (!rcu_gp_in_progress())
+		return false;
+	// Long delays at this point avoids false positive, but a delay
+	// of ULONG_MAX/4 jiffies voids your no-false-positive warranty.
+	smp_mb(); // .gp_seq before second .gp_start
+	// And ditto here.
+	return !time_before(j, READ_ONCE(rcu_state.gp_start) + d);
+}
+
 /* Don't do RCU CPU stall warnings during long sysrq printouts. */
 void rcu_sysrq_start(void)
 {
@@ -104,8 +136,8 @@ static void record_gp_stall_check_time(void)
 
 	WRITE_ONCE(rcu_state.gp_start, j);
 	j1 = rcu_jiffies_till_stall_check();
-	/* Record ->gp_start before ->jiffies_stall. */
-	smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
+	smp_mb(); // ->gp_start before ->jiffies_stall and caller's ->gp_seq.
+	WRITE_ONCE(rcu_state.jiffies_stall, j + j1);
 	rcu_state.jiffies_resched = j + j1 / 2;
 	rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
 }
@@ -192,14 +224,40 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
+// Communicate task state back to the RCU CPU stall warning request.
+struct rcu_stall_chk_rdr {
+	int nesting;
+	union rcu_special rs;
+	bool on_blkd_list;
+};
+
+/*
+ * Report out the state of a not-running task that is stalling the
+ * current RCU grace period.
+ */
+static bool check_slow_task(struct task_struct *t, void *arg)
+{
+	struct rcu_node *rnp;
+	struct rcu_stall_chk_rdr *rscrp = arg;
+
+	if (task_curr(t))
+		return false; // It is running, so decline to inspect it.
+	rscrp->nesting = t->rcu_read_lock_nesting;
+	rscrp->rs = t->rcu_read_unlock_special;
+	rnp = t->rcu_blocked_node;
+	rscrp->on_blkd_list = !list_empty(&t->rcu_node_entry);
+	return true;
+}
+
 /*
  * Scan the current list of tasks blocked within RCU read-side critical
  * sections, printing out the tid of each.
  */
 static int rcu_print_task_stall(struct rcu_node *rnp)
 {
-	struct task_struct *t;
 	int ndetected = 0;
+	struct rcu_stall_chk_rdr rscr;
+	struct task_struct *t;
 
 	if (!rcu_preempt_blocked_readers_cgp(rnp))
 		return 0;
@@ -208,7 +266,15 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		pr_cont(" P%d", t->pid);
+		if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
+			pr_cont(" P%d", t->pid);
+		else
+			pr_cont(" P%d/%d:%c%c%c%c",
+				t->pid, rscr.nesting,
+				".b"[rscr.rs.b.blocked],
+				".q"[rscr.rs.b.need_qs],
+				".e"[rscr.rs.b.exp_hint],
+				".l"[rscr.on_blkd_list]);
 		ndetected++;
 	}
 	pr_cont("\n");
@@ -299,6 +365,16 @@ static const char *gp_state_getname(short gs)
 	return gp_state_names[gs];
 }
 
+/* Is the RCU grace-period kthread being starved of CPU time? */
+static bool rcu_is_gp_kthread_starving(unsigned long *jp)
+{
+	unsigned long j = jiffies - READ_ONCE(rcu_state.gp_activity);
+
+	if (jp)
+		*jp = j;
+	return j > 2 * HZ;
+}
+
 /*
  * Print out diagnostic information for the specified stalled CPU.
  *
@@ -313,6 +389,7 @@ static const char *gp_state_getname(short gs)
 static void print_cpu_stall_info(int cpu)
 {
 	unsigned long delta;
+	bool falsepositive;
 	char fast_no_hz[72];
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	char *ticks_title;
@@ -333,7 +410,9 @@ static void print_cpu_stall_info(int cpu)
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
 	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
+	falsepositive = rcu_is_gp_kthread_starving(NULL) &&
+			rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s%s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -345,8 +424,9 @@ static void print_cpu_stall_info(int cpu)
 	       rcu_dynticks_snap(rdp) & 0xfff,
 	       rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
-	       READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
-	       fast_no_hz);
+	       data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
+	       fast_no_hz,
+	       falsepositive ? " (false positive?)" : "");
 }
 
 /* Complain about starvation of grace-period kthread.  */
@@ -355,15 +435,15 @@ static void rcu_check_gp_kthread_starvation(void)
 	struct task_struct *gpk = rcu_state.gp_kthread;
 	unsigned long j;
 
-	j = jiffies - READ_ONCE(rcu_state.gp_activity);
-	if (j > 2 * HZ) {
+	if (rcu_is_gp_kthread_starving(&j)) {
 		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
 		       rcu_state.name, j,
 		       (long)rcu_seq_current(&rcu_state.gp_seq),
-		       READ_ONCE(rcu_state.gp_flags),
+		       data_race(rcu_state.gp_flags),
 		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
 		       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
 		if (gpk) {
+			pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
 			pr_err("RCU grace-period kthread stack dump:\n");
 			sched_show_task(gpk);
 			wake_up_process(gpk);
@@ -371,7 +451,7 @@ static void rcu_check_gp_kthread_starvation(void)
 	}
 }
 
-static void print_other_cpu_stall(unsigned long gp_seq)
+static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 {
 	int cpu;
 	unsigned long flags;
@@ -408,7 +488,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_get_n_cbs_cpu(cpu);
 	pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
-	       smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
+	       smp_processor_id(), (long)(jiffies - gps),
 	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
 	if (ndetected) {
 		rcu_dump_cpu_stacks();
@@ -421,13 +501,11 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 			pr_err("INFO: Stall ended before state dump start\n");
 		} else {
 			j = jiffies;
-			gpa = READ_ONCE(rcu_state.gp_activity);
+			gpa = data_race(rcu_state.gp_activity);
 			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
 			       rcu_state.name, j - gpa, j, gpa,
-			       READ_ONCE(jiffies_till_next_fqs),
+			       data_race(jiffies_till_next_fqs),
 			       rcu_get_root()->qsmask);
-			/* In this case, the current CPU might be at fault. */
-			sched_show_task(current);
 		}
 	}
 	/* Rewrite if needed in case of slow consoles. */
@@ -442,7 +520,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
 	rcu_force_quiescent_state();  /* Kick them all. */
 }
 
-static void print_cpu_stall(void)
+static void print_cpu_stall(unsigned long gps)
 {
 	int cpu;
 	unsigned long flags;
@@ -467,7 +545,7 @@ static void print_cpu_stall(void)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_get_n_cbs_cpu(cpu);
 	pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n",
-		jiffies - rcu_state.gp_start,
+		jiffies - gps,
 		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
 
 	rcu_check_gp_kthread_starvation();
@@ -546,7 +624,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	    cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
 
 		/* We haven't checked in, so go dump stack. */
-		print_cpu_stall();
+		print_cpu_stall(gps);
 		if (rcu_cpu_stall_ftrace_dump)
 			rcu_ftrace_dump(DUMP_ALL);
 
@@ -555,7 +633,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
 		   cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
 
 		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(gs2);
+		print_other_cpu_stall(gs2, gps);
 		if (rcu_cpu_stall_ftrace_dump)
 			rcu_ftrace_dump(DUMP_ALL);
 	}
@@ -581,23 +659,23 @@ void show_rcu_gp_kthreads(void)
 	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
 
 	j = jiffies;
-	ja = j - READ_ONCE(rcu_state.gp_activity);
-	jr = j - READ_ONCE(rcu_state.gp_req_activity);
-	jw = j - READ_ONCE(rcu_state.gp_wake_time);
+	ja = j - data_race(rcu_state.gp_activity);
+	jr = j - data_race(rcu_state.gp_req_activity);
+	jw = j - data_race(rcu_state.gp_wake_time);
 	pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
 		rcu_state.name, gp_state_getname(rcu_state.gp_state),
 		rcu_state.gp_state, t ? t->state : 0x1ffffL,
-		ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
-		(long)READ_ONCE(rcu_state.gp_seq),
-		(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
-		READ_ONCE(rcu_state.gp_flags));
+		ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq),
+		(long)data_race(rcu_state.gp_seq),
+		(long)data_race(rcu_get_root()->gp_seq_needed),
+		data_race(rcu_state.gp_flags));
 	rcu_for_each_node_breadth_first(rnp) {
 		if (ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq),
 				 READ_ONCE(rnp->gp_seq_needed)))
 			continue;
 		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
-			rnp->grplo, rnp->grphi, (long)READ_ONCE(rnp->gp_seq),
-			(long)READ_ONCE(rnp->gp_seq_needed));
+			rnp->grplo, rnp->grphi, (long)data_race(rnp->gp_seq),
+			(long)data_race(rnp->gp_seq_needed));
 		if (!rcu_is_leaf_node(rnp))
 			continue;
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
@@ -607,7 +685,7 @@ void show_rcu_gp_kthreads(void)
 					 READ_ONCE(rdp->gp_seq_needed)))
 				continue;
 			pr_info("\tcpu %d ->gp_seq_needed %ld\n",
-				cpu, (long)READ_ONCE(rdp->gp_seq_needed));
+				cpu, (long)data_race(rdp->gp_seq_needed));
 		}
 	}
 	for_each_possible_cpu(cpu) {
@@ -615,7 +693,7 @@ void show_rcu_gp_kthreads(void)
 		if (rcu_segcblist_is_offloaded(&rdp->cblist))
 			show_rcu_nocb_state(rdp);
 	}
-	/* sched_show_task(rcu_state.gp_kthread); */
+	show_rcu_tasks_gp_kthreads();
 }
 EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 28a8bdc5072f..84843adfd939 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -41,6 +41,7 @@
 #include <linux/sched/isolation.h>
 #include <linux/kprobes.h>
 #include <linux/slab.h>
+#include <linux/irq_work.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -51,6 +52,19 @@
 #endif
 #define MODULE_PARAM_PREFIX "rcupdate."
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
+
 #ifndef CONFIG_TINY_RCU
 module_param(rcu_expedited, int, 0);
 module_param(rcu_normal, int, 0);
@@ -63,12 +77,12 @@ module_param(rcu_normal_after_boot, int, 0);
  * rcu_read_lock_held_common() - might we be in RCU-sched read-side critical section?
  * @ret:	Best guess answer if lockdep cannot be relied on
  *
- * Returns true if lockdep must be ignored, in which case *ret contains
+ * Returns true if lockdep must be ignored, in which case ``*ret`` contains
  * the best guess described below.  Otherwise returns false, in which
- * case *ret tells the caller nothing and the caller should instead
+ * case ``*ret`` tells the caller nothing and the caller should instead
  * consult lockdep.
  *
- * If CONFIG_DEBUG_LOCK_ALLOC is selected, set *ret to nonzero iff in an
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, set ``*ret`` to nonzero iff in an
  * RCU-sched read-side critical section.  In absence of
  * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
  * critical section unless it can prove otherwise.  Note that disabling
@@ -82,7 +96,7 @@ module_param(rcu_normal_after_boot, int, 0);
  *
  * Note that if the CPU is in the idle loop from an RCU point of view (ie:
  * that we are in the section between rcu_idle_enter() and rcu_idle_exit())
- * then rcu_read_lock_held() sets *ret to false even if the CPU did an
+ * then rcu_read_lock_held() sets ``*ret`` to false even if the CPU did an
  * rcu_read_lock().  The reason for this is that RCU ignores CPUs that are
  * in such a section, considering these as in extended quiescent state,
  * so such a CPU is effectively never in an RCU read-side critical section
@@ -98,15 +112,15 @@ module_param(rcu_normal_after_boot, int, 0);
 static bool rcu_read_lock_held_common(bool *ret)
 {
 	if (!debug_lockdep_rcu_enabled()) {
-		*ret = 1;
+		*ret = true;
 		return true;
 	}
 	if (!rcu_is_watching()) {
-		*ret = 0;
+		*ret = false;
 		return true;
 	}
 	if (!rcu_lockdep_current_cpu_online()) {
-		*ret = 0;
+		*ret = false;
 		return true;
 	}
 	return false;
@@ -270,13 +284,12 @@ struct lockdep_map rcu_callback_map =
 	STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
 EXPORT_SYMBOL_GPL(rcu_callback_map);
 
-int notrace debug_lockdep_rcu_enabled(void)
+noinstr int notrace debug_lockdep_rcu_enabled(void)
 {
 	return rcu_scheduler_active != RCU_SCHEDULER_INACTIVE && debug_locks &&
 	       current->lockdep_recursion == 0;
 }
 EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
-NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled);
 
 /**
  * rcu_read_lock_held() - might we be in RCU read-side critical section?
@@ -501,370 +514,6 @@ int rcu_cpu_stall_suppress_at_boot __read_mostly; // !0 = suppress boot stalls.
 EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress_at_boot);
 module_param(rcu_cpu_stall_suppress_at_boot, int, 0444);
 
-#ifdef CONFIG_TASKS_RCU
-
-/*
- * Simple variant of RCU whose quiescent states are voluntary context
- * switch, cond_resched_rcu_qs(), user-space execution, and idle.
- * As such, grace periods can take one good long time.  There are no
- * read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
- * because this implementation is intended to get the system into a safe
- * state for some of the manipulations involved in tracing and the like.
- * Finally, this implementation does not support high call_rcu_tasks()
- * rates from multiple CPUs.  If this is required, per-CPU callback lists
- * will be needed.
- */
-
-/* Global list of callbacks and associated lock. */
-static struct rcu_head *rcu_tasks_cbs_head;
-static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
-static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);
-static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
-
-/* Track exiting tasks in order to allow them to be waited for. */
-DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
-
-/* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
-#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
-static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
-module_param(rcu_task_stall_timeout, int, 0644);
-
-static struct task_struct *rcu_tasks_kthread_ptr;
-
-/**
- * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
- * @rhp: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_tasks() assumes
- * that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
- * or transition to usermode execution.  As such, there are no read-side
- * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
- * this primitive is intended to determine that all tasks have passed
- * through a safe state, not so much for data-strcuture synchronization.
- *
- * See the description of call_rcu() for more detailed information on
- * memory ordering guarantees.
- */
-void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
-{
-	unsigned long flags;
-	bool needwake;
-
-	rhp->next = NULL;
-	rhp->func = func;
-	raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
-	needwake = !rcu_tasks_cbs_head;
-	WRITE_ONCE(*rcu_tasks_cbs_tail, rhp);
-	rcu_tasks_cbs_tail = &rhp->next;
-	raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
-	/* We can't create the thread unless interrupts are enabled. */
-	if (needwake && READ_ONCE(rcu_tasks_kthread_ptr))
-		wake_up(&rcu_tasks_cbs_wq);
-}
-EXPORT_SYMBOL_GPL(call_rcu_tasks);
-
-/**
- * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu-tasks
- * grace period has elapsed, in other words after all currently
- * executing rcu-tasks read-side critical sections have elapsed.  These
- * read-side critical sections are delimited by calls to schedule(),
- * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
- * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
- *
- * This is a very specialized primitive, intended only for a few uses in
- * tracing and other situations requiring manipulation of function
- * preambles and profiling hooks.  The synchronize_rcu_tasks() function
- * is not (yet) intended for heavy use from multiple CPUs.
- *
- * Note that this guarantee implies further memory-ordering guarantees.
- * On systems with more than one CPU, when synchronize_rcu_tasks() returns,
- * each CPU is guaranteed to have executed a full memory barrier since the
- * end of its last RCU-tasks read-side critical section whose beginning
- * preceded the call to synchronize_rcu_tasks().  In addition, each CPU
- * having an RCU-tasks read-side critical section that extends beyond
- * the return from synchronize_rcu_tasks() is guaranteed to have executed
- * a full memory barrier after the beginning of synchronize_rcu_tasks()
- * and before the beginning of that RCU-tasks read-side critical section.
- * Note that these guarantees include CPUs that are offline, idle, or
- * executing in user mode, as well as CPUs that are executing in the kernel.
- *
- * Furthermore, if CPU A invoked synchronize_rcu_tasks(), which returned
- * to its caller on CPU B, then both CPU A and CPU B are guaranteed
- * to have executed a full memory barrier during the execution of
- * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU
- * (but again only if the system has more than one CPU).
- */
-void synchronize_rcu_tasks(void)
-{
-	/* Complain if the scheduler has not started.  */
-	RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
-			 "synchronize_rcu_tasks called too soon");
-
-	/* Wait for the grace period. */
-	wait_rcu_gp(call_rcu_tasks);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
-
-/**
- * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
- *
- * Although the current implementation is guaranteed to wait, it is not
- * obligated to, for example, if there are no pending callbacks.
- */
-void rcu_barrier_tasks(void)
-{
-	/* There is only one callback queue, so this is easy.  ;-) */
-	synchronize_rcu_tasks();
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
-
-/* See if tasks are still holding out, complain if so. */
-static void check_holdout_task(struct task_struct *t,
-			       bool needreport, bool *firstreport)
-{
-	int cpu;
-
-	if (!READ_ONCE(t->rcu_tasks_holdout) ||
-	    t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
-	    !READ_ONCE(t->on_rq) ||
-	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
-	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
-		WRITE_ONCE(t->rcu_tasks_holdout, false);
-		list_del_init(&t->rcu_tasks_holdout_list);
-		put_task_struct(t);
-		return;
-	}
-	rcu_request_urgent_qs_task(t);
-	if (!needreport)
-		return;
-	if (*firstreport) {
-		pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
-		*firstreport = false;
-	}
-	cpu = task_cpu(t);
-	pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
-		 t, ".I"[is_idle_task(t)],
-		 "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
-		 t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
-		 t->rcu_tasks_idle_cpu, cpu);
-	sched_show_task(t);
-}
-
-/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
-static int __noreturn rcu_tasks_kthread(void *arg)
-{
-	unsigned long flags;
-	struct task_struct *g, *t;
-	unsigned long lastreport;
-	struct rcu_head *list;
-	struct rcu_head *next;
-	LIST_HEAD(rcu_tasks_holdouts);
-	int fract;
-
-	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
-	housekeeping_affine(current, HK_FLAG_RCU);
-
-	/*
-	 * Each pass through the following loop makes one check for
-	 * newly arrived callbacks, and, if there are some, waits for
-	 * one RCU-tasks grace period and then invokes the callbacks.
-	 * This loop is terminated by the system going down.  ;-)
-	 */
-	for (;;) {
-
-		/* Pick up any new callbacks. */
-		raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
-		list = rcu_tasks_cbs_head;
-		rcu_tasks_cbs_head = NULL;
-		rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
-		raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
-
-		/* If there were none, wait a bit and start over. */
-		if (!list) {
-			wait_event_interruptible(rcu_tasks_cbs_wq,
-						 READ_ONCE(rcu_tasks_cbs_head));
-			if (!rcu_tasks_cbs_head) {
-				WARN_ON(signal_pending(current));
-				schedule_timeout_interruptible(HZ/10);
-			}
-			continue;
-		}
-
-		/*
-		 * Wait for all pre-existing t->on_rq and t->nvcsw
-		 * transitions to complete.  Invoking synchronize_rcu()
-		 * suffices because all these transitions occur with
-		 * interrupts disabled.  Without this synchronize_rcu(),
-		 * a read-side critical section that started before the
-		 * grace period might be incorrectly seen as having started
-		 * after the grace period.
-		 *
-		 * This synchronize_rcu() also dispenses with the
-		 * need for a memory barrier on the first store to
-		 * ->rcu_tasks_holdout, as it forces the store to happen
-		 * after the beginning of the grace period.
-		 */
-		synchronize_rcu();
-
-		/*
-		 * There were callbacks, so we need to wait for an
-		 * RCU-tasks grace period.  Start off by scanning
-		 * the task list for tasks that are not already
-		 * voluntarily blocked.  Mark these tasks and make
-		 * a list of them in rcu_tasks_holdouts.
-		 */
-		rcu_read_lock();
-		for_each_process_thread(g, t) {
-			if (t != current && READ_ONCE(t->on_rq) &&
-			    !is_idle_task(t)) {
-				get_task_struct(t);
-				t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
-				WRITE_ONCE(t->rcu_tasks_holdout, true);
-				list_add(&t->rcu_tasks_holdout_list,
-					 &rcu_tasks_holdouts);
-			}
-		}
-		rcu_read_unlock();
-
-		/*
-		 * Wait for tasks that are in the process of exiting.
-		 * This does only part of the job, ensuring that all
-		 * tasks that were previously exiting reach the point
-		 * where they have disabled preemption, allowing the
-		 * later synchronize_rcu() to finish the job.
-		 */
-		synchronize_srcu(&tasks_rcu_exit_srcu);
-
-		/*
-		 * Each pass through the following loop scans the list
-		 * of holdout tasks, removing any that are no longer
-		 * holdouts.  When the list is empty, we are done.
-		 */
-		lastreport = jiffies;
-
-		/* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
-		fract = 10;
-
-		for (;;) {
-			bool firstreport;
-			bool needreport;
-			int rtst;
-			struct task_struct *t1;
-
-			if (list_empty(&rcu_tasks_holdouts))
-				break;
-
-			/* Slowly back off waiting for holdouts */
-			schedule_timeout_interruptible(HZ/fract);
-
-			if (fract > 1)
-				fract--;
-
-			rtst = READ_ONCE(rcu_task_stall_timeout);
-			needreport = rtst > 0 &&
-				     time_after(jiffies, lastreport + rtst);
-			if (needreport)
-				lastreport = jiffies;
-			firstreport = true;
-			WARN_ON(signal_pending(current));
-			list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts,
-						rcu_tasks_holdout_list) {
-				check_holdout_task(t, needreport, &firstreport);
-				cond_resched();
-			}
-		}
-
-		/*
-		 * Because ->on_rq and ->nvcsw are not guaranteed
-		 * to have a full memory barriers prior to them in the
-		 * schedule() path, memory reordering on other CPUs could
-		 * cause their RCU-tasks read-side critical sections to
-		 * extend past the end of the grace period.  However,
-		 * because these ->nvcsw updates are carried out with
-		 * interrupts disabled, we can use synchronize_rcu()
-		 * to force the needed ordering on all such CPUs.
-		 *
-		 * This synchronize_rcu() also confines all
-		 * ->rcu_tasks_holdout accesses to be within the grace
-		 * period, avoiding the need for memory barriers for
-		 * ->rcu_tasks_holdout accesses.
-		 *
-		 * In addition, this synchronize_rcu() waits for exiting
-		 * tasks to complete their final preempt_disable() region
-		 * of execution, cleaning up after the synchronize_srcu()
-		 * above.
-		 */
-		synchronize_rcu();
-
-		/* Invoke the callbacks. */
-		while (list) {
-			next = list->next;
-			local_bh_disable();
-			list->func(list);
-			local_bh_enable();
-			list = next;
-			cond_resched();
-		}
-		/* Paranoid sleep to keep this from entering a tight loop */
-		schedule_timeout_uninterruptible(HZ/10);
-	}
-}
-
-/* Spawn rcu_tasks_kthread() at core_initcall() time. */
-static int __init rcu_spawn_tasks_kthread(void)
-{
-	struct task_struct *t;
-
-	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
-	if (WARN_ONCE(IS_ERR(t), "%s: Could not start Tasks-RCU grace-period kthread, OOM is now expected behavior\n", __func__))
-		return 0;
-	smp_mb(); /* Ensure others see full kthread. */
-	WRITE_ONCE(rcu_tasks_kthread_ptr, t);
-	return 0;
-}
-core_initcall(rcu_spawn_tasks_kthread);
-
-/* Do the srcu_read_lock() for the above synchronize_srcu().  */
-void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
-{
-	preempt_disable();
-	current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
-	preempt_enable();
-}
-
-/* Do the srcu_read_unlock() for the above synchronize_srcu().  */
-void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
-{
-	preempt_disable();
-	__srcu_read_unlock(&tasks_rcu_exit_srcu, current->rcu_tasks_idx);
-	preempt_enable();
-}
-
-#endif /* #ifdef CONFIG_TASKS_RCU */
-
-#ifndef CONFIG_TINY_RCU
-
-/*
- * Print any non-default Tasks RCU settings.
- */
-static void __init rcu_tasks_bootup_oddness(void)
-{
-#ifdef CONFIG_TASKS_RCU
-	if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT)
-		pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout);
-	else
-		pr_info("\tTasks RCU enabled.\n");
-#endif /* #ifdef CONFIG_TASKS_RCU */
-}
-
-#endif /* #ifndef CONFIG_TINY_RCU */
-
 #ifdef CONFIG_PROVE_RCU
 
 /*
@@ -935,6 +584,8 @@ late_initcall(rcu_verify_early_boot_tests);
 void rcu_early_boot_tests(void) {}
 #endif /* CONFIG_PROVE_RCU */
 
+#include "tasks.h"
+
 #ifndef CONFIG_TINY_RCU
 
 /*
diff --git a/kernel/reboot.c b/kernel/reboot.c
index c4d472b7f1b4..491f1347bf43 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -250,7 +250,7 @@ void kernel_restart(char *cmd)
 		pr_emerg("Restarting system\n");
 	else
 		pr_emerg("Restarting system with command '%s'\n", cmd);
-	kmsg_dump(KMSG_DUMP_RESTART);
+	kmsg_dump(KMSG_DUMP_SHUTDOWN);
 	machine_restart(cmd);
 }
 EXPORT_SYMBOL_GPL(kernel_restart);
@@ -274,7 +274,7 @@ void kernel_halt(void)
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	pr_emerg("System halted\n");
-	kmsg_dump(KMSG_DUMP_HALT);
+	kmsg_dump(KMSG_DUMP_SHUTDOWN);
 	machine_halt();
 }
 EXPORT_SYMBOL_GPL(kernel_halt);
@@ -292,7 +292,7 @@ void kernel_power_off(void)
 	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	pr_emerg("Power down\n");
-	kmsg_dump(KMSG_DUMP_POWEROFF);
+	kmsg_dump(KMSG_DUMP_SHUTDOWN);
 	machine_power_off();
 }
 EXPORT_SYMBOL_GPL(kernel_power_off);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3a61a3b8eaa9..0ae29fd57817 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -11,6 +11,7 @@
 #include <linux/nospec.h>
 
 #include <linux/kcov.h>
+#include <linux/scs.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -1232,13 +1233,8 @@ static void uclamp_fork(struct task_struct *p)
 		return;
 
 	for_each_clamp_id(clamp_id) {
-		unsigned int clamp_value = uclamp_none(clamp_id);
-
-		/* By default, RT tasks always get 100% boost */
-		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			clamp_value = uclamp_none(UCLAMP_MAX);
-
-		uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false);
+		uclamp_se_set(&p->uclamp_req[clamp_id],
+			      uclamp_none(clamp_id), false);
 	}
 }
 
@@ -2566,6 +2562,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
@@ -2640,6 +2638,52 @@ out:
 }
 
 /**
+ * try_invoke_on_locked_down_task - Invoke a function on task in fixed state
+ * @p: Process for which the function is to be invoked.
+ * @func: Function to invoke.
+ * @arg: Argument to function.
+ *
+ * If the specified task can be quickly locked into a definite state
+ * (either sleeping or on a given runqueue), arrange to keep it in that
+ * state while invoking @func(@arg).  This function can use ->on_rq and
+ * task_curr() to work out what the state is, if required.  Given that
+ * @func can be invoked with a runqueue lock held, it had better be quite
+ * lightweight.
+ *
+ * Returns:
+ *	@false if the task slipped out from under the locks.
+ *	@true if the task was locked onto a runqueue or is sleeping.
+ *		However, @func can override this by returning @false.
+ */
+bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg)
+{
+	bool ret = false;
+	struct rq_flags rf;
+	struct rq *rq;
+
+	lockdep_assert_irqs_enabled();
+	raw_spin_lock_irq(&p->pi_lock);
+	if (p->on_rq) {
+		rq = __task_rq_lock(p, &rf);
+		if (task_rq(p) == rq)
+			ret = func(p, arg);
+		rq_unlock(rq, &rf);
+	} else {
+		switch (p->state) {
+		case TASK_RUNNING:
+		case TASK_WAKING:
+			break;
+		default:
+			smp_rmb(); // See smp_rmb() comment in try_to_wake_up().
+			if (!p->on_rq)
+				ret = func(p, arg);
+		}
+	}
+	raw_spin_unlock_irq(&p->pi_lock);
+	return ret;
+}
+
+/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -3882,6 +3926,9 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 #ifdef CONFIG_SCHED_STACK_END_CHECK
 	if (task_stack_end_corrupted(prev))
 		panic("corrupted stack end detected inside scheduler\n");
+
+	if (task_scs_end_corrupted(prev))
+		panic("corrupted shadow stack detected inside scheduler\n");
 #endif
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
@@ -6045,6 +6092,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	idle->se.exec_start = sched_clock();
 	idle->flags |= PF_IDLE;
 
+	scs_task_reset(idle);
 	kasan_unpoison_task_stack(idle);
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index dac9104d126f..ff9435dee1df 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -1003,12 +1003,12 @@ u64 kcpustat_field(struct kernel_cpustat *kcpustat,
 		   enum cpu_usage_stat usage, int cpu)
 {
 	u64 *cpustat = kcpustat->cpustat;
+	u64 val = cpustat[usage];
 	struct rq *rq;
-	u64 val;
 	int err;
 
 	if (!vtime_accounting_enabled_cpu(cpu))
-		return cpustat[usage];
+		return val;
 
 	rq = cpu_rq(cpu);
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index a562df57a86e..239970b991c0 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -948,8 +948,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	P(se.avg.util_est.enqueued);
 #endif
 #ifdef CONFIG_UCLAMP_TASK
-	__PS("uclamp.min", p->uclamp[UCLAMP_MIN].value);
-	__PS("uclamp.max", p->uclamp[UCLAMP_MAX].value);
+	__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
+	__PS("uclamp.max", p->uclamp_req[UCLAMP_MAX].value);
 	__PS("effective uclamp.min", uclamp_eff_value(p, UCLAMP_MIN));
 	__PS("effective uclamp.max", uclamp_eff_value(p, UCLAMP_MAX));
 #endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 02f323b85b6d..da3e5b54715b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2908,7 +2908,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 	/*
 	 * We don't care about NUMA placement if we don't have memory.
 	 */
-	if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
+	if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work)
 		return;
 
 	/*
@@ -4774,7 +4774,6 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
-	int enqueue = 1;
 	long task_delta, idle_task_delta;
 
 	se = cfs_rq->tg->se[cpu_of(rq)];
@@ -4798,26 +4797,44 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
 		if (se->on_rq)
-			enqueue = 0;
+			break;
+		cfs_rq = cfs_rq_of(se);
+		enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+
+		cfs_rq->h_nr_running += task_delta;
+		cfs_rq->idle_h_nr_running += idle_task_delta;
+
+		/* end evaluation on encountering a throttled cfs_rq */
+		if (cfs_rq_throttled(cfs_rq))
+			goto unthrottle_throttle;
+	}
 
+	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		if (enqueue) {
-			enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
-		} else {
-			update_load_avg(cfs_rq, se, 0);
-			se_update_runnable(se);
-		}
+
+		update_load_avg(cfs_rq, se, UPDATE_TG);
+		se_update_runnable(se);
 
 		cfs_rq->h_nr_running += task_delta;
 		cfs_rq->idle_h_nr_running += idle_task_delta;
 
+
+		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			break;
+			goto unthrottle_throttle;
+
+		/*
+		 * One parent has been throttled and cfs_rq removed from the
+		 * list. Add it back to not break the leaf list.
+		 */
+		if (throttled_hierarchy(cfs_rq))
+			list_add_leaf_cfs_rq(cfs_rq);
 	}
 
-	if (!se)
-		add_nr_running(rq, task_delta);
+	/* At this point se is NULL and we are at root level*/
+	add_nr_running(rq, task_delta);
 
+unthrottle_throttle:
 	/*
 	 * The cfs_rq_throttled() breaks in the above iteration can result in
 	 * incomplete leaf list maintenance, resulting in triggering the
@@ -4826,7 +4843,8 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 
-		list_add_leaf_cfs_rq(cfs_rq);
+		if (list_add_leaf_cfs_rq(cfs_rq))
+			break;
 	}
 
 	assert_list_leaf_cfs_rq(rq);
@@ -5479,6 +5497,13 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
 			goto enqueue_throttle;
+
+               /*
+                * One parent has been throttled and cfs_rq removed from the
+                * list. Add it back to not break the leaf list.
+                */
+               if (throttled_hierarchy(cfs_rq))
+                       list_add_leaf_cfs_rq(cfs_rq);
 	}
 
 enqueue_throttle:
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 008d6ac2342b..808244f3ddd9 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -149,6 +149,9 @@ __setup("nohz_full=", housekeeping_nohz_full_setup);
 static int __init housekeeping_isolcpus_setup(char *str)
 {
 	unsigned int flags = 0;
+	bool illegal = false;
+	char *par;
+	int len;
 
 	while (isalpha(*str)) {
 		if (!strncmp(str, "nohz,", 5)) {
@@ -169,8 +172,22 @@ static int __init housekeeping_isolcpus_setup(char *str)
 			continue;
 		}
 
-		pr_warn("isolcpus: Error, unknown flag\n");
-		return 0;
+		/*
+		 * Skip unknown sub-parameter and validate that it is not
+		 * containing an invalid character.
+		 */
+		for (par = str, len = 0; *str && *str != ','; str++, len++) {
+			if (!isalpha(*str) && *str != '_')
+				illegal = true;
+		}
+
+		if (illegal) {
+			pr_warn("isolcpus: Invalid flag %.*s\n", len, par);
+			return 0;
+		}
+
+		pr_info("isolcpus: Skipped unknown flag %.*s\n", len, par);
+		str++;
 	}
 
 	/* Default behaviour for isolcpus without flags */
diff --git a/kernel/scs.c b/kernel/scs.c
new file mode 100644
index 000000000000..222a7a9ad543
--- /dev/null
+++ b/kernel/scs.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shadow Call Stack support.
+ *
+ * Copyright (C) 2019 Google LLC
+ */
+
+#include <linux/kasan.h>
+#include <linux/mm.h>
+#include <linux/scs.h>
+#include <linux/slab.h>
+#include <linux/vmstat.h>
+
+static struct kmem_cache *scs_cache;
+
+static void __scs_account(void *s, int account)
+{
+	struct page *scs_page = virt_to_page(s);
+
+	mod_zone_page_state(page_zone(scs_page), NR_KERNEL_SCS_KB,
+			    account * (SCS_SIZE / SZ_1K));
+}
+
+static void *scs_alloc(int node)
+{
+	void *s = kmem_cache_alloc_node(scs_cache, GFP_SCS, node);
+
+	if (!s)
+		return NULL;
+
+	*__scs_magic(s) = SCS_END_MAGIC;
+
+	/*
+	 * Poison the allocation to catch unintentional accesses to
+	 * the shadow stack when KASAN is enabled.
+	 */
+	kasan_poison_object_data(scs_cache, s);
+	__scs_account(s, 1);
+	return s;
+}
+
+static void scs_free(void *s)
+{
+	__scs_account(s, -1);
+	kasan_unpoison_object_data(scs_cache, s);
+	kmem_cache_free(scs_cache, s);
+}
+
+void __init scs_init(void)
+{
+	scs_cache = kmem_cache_create("scs_cache", SCS_SIZE, 0, 0, NULL);
+}
+
+int scs_prepare(struct task_struct *tsk, int node)
+{
+	void *s = scs_alloc(node);
+
+	if (!s)
+		return -ENOMEM;
+
+	task_scs(tsk) = task_scs_sp(tsk) = s;
+	return 0;
+}
+
+static void scs_check_usage(struct task_struct *tsk)
+{
+	static unsigned long highest;
+
+	unsigned long *p, prev, curr = highest, used = 0;
+
+	if (!IS_ENABLED(CONFIG_DEBUG_STACK_USAGE))
+		return;
+
+	for (p = task_scs(tsk); p < __scs_magic(tsk); ++p) {
+		if (!READ_ONCE_NOCHECK(*p))
+			break;
+		used++;
+	}
+
+	while (used > curr) {
+		prev = cmpxchg_relaxed(&highest, curr, used);
+
+		if (prev == curr) {
+			pr_info("%s (%d): highest shadow stack usage: %lu bytes\n",
+				tsk->comm, task_pid_nr(tsk), used);
+			break;
+		}
+
+		curr = prev;
+	}
+}
+
+void scs_release(struct task_struct *tsk)
+{
+	void *s = task_scs(tsk);
+
+	if (!s)
+		return;
+
+	WARN(task_scs_end_corrupted(tsk),
+	     "corrupted shadow stack detected when freeing task\n");
+	scs_check_usage(tsk);
+	scs_free(s);
+}
diff --git a/kernel/signal.c b/kernel/signal.c
index e58a6c619824..284fc1600063 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1510,15 +1510,15 @@ int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr,
 	unsigned long flags;
 	int ret = -EINVAL;
 
+	if (!valid_signal(sig))
+		return ret;
+
 	clear_siginfo(&info);
 	info.si_signo = sig;
 	info.si_errno = errno;
 	info.si_code = SI_ASYNCIO;
 	*((sigval_t *)&info.si_pid) = addr;
 
-	if (!valid_signal(sig))
-		return ret;
-
 	rcu_read_lock();
 	p = pid_task(pid, PIDTYPE_PID);
 	if (!p) {
@@ -1557,12 +1557,8 @@ static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid)
 {
 	int ret;
 
-	if (pid > 0) {
-		rcu_read_lock();
-		ret = kill_pid_info(sig, info, find_vpid(pid));
-		rcu_read_unlock();
-		return ret;
-	}
+	if (pid > 0)
+		return kill_proc_info(sig, info, pid);
 
 	/* -INT_MIN is undefined.  Exclude this case to avoid a UBSAN warning */
 	if (pid == INT_MIN)
@@ -1993,8 +1989,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
 			sig = 0;
 	}
+	/*
+	 * Send with __send_signal as si_pid and si_uid are in the
+	 * parent's namespaces.
+	 */
 	if (valid_signal(sig) && sig)
-		__group_send_sig_info(sig, &info, tsk->parent);
+		__send_signal(sig, &info, tsk->parent, PIDTYPE_TGID, false);
 	__wake_up_parent(tsk, tsk->parent);
 	spin_unlock_irqrestore(&psig->siglock, flags);
 
diff --git a/kernel/smp.c b/kernel/smp.c
index 786092aabdcd..84303197caf9 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -620,7 +620,7 @@ void __init smp_init(void)
  * early_boot_irqs_disabled is set.  Use local_irq_save/restore() instead
  * of local_irq_disable/enable().
  */
-void on_each_cpu(void (*func) (void *info), void *info, int wait)
+void on_each_cpu(smp_call_func_t func, void *info, int wait)
 {
 	unsigned long flags;
 
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 3b30288793fe..53bce347cd50 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -338,7 +338,20 @@ static struct user_namespace *timens_owner(struct ns_common *ns)
 
 static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts)
 {
-	seq_printf(m, "%d %lld %ld\n", clockid, ts->tv_sec, ts->tv_nsec);
+	char *clock;
+
+	switch (clockid) {
+	case CLOCK_BOOTTIME:
+		clock = "boottime";
+		break;
+	case CLOCK_MONOTONIC:
+		clock = "monotonic";
+		break;
+	default:
+		clock = "unknown";
+		break;
+	}
+	seq_printf(m, "%-10s %10lld %9ld\n", clock, ts->tv_sec, ts->tv_nsec);
 }
 
 void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m)
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 402eef84c859..24876faac753 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -10,11 +10,6 @@ config USER_STACKTRACE_SUPPORT
 config NOP_TRACER
 	bool
 
-config HAVE_FTRACE_NMI_ENTER
-	bool
-	help
-	  See Documentation/trace/ftrace-design.rst
-
 config HAVE_FUNCTION_TRACER
 	bool
 	help
@@ -72,11 +67,6 @@ config RING_BUFFER
 	select TRACE_CLOCK
 	select IRQ_WORK
 
-config FTRACE_NMI_ENTER
-       bool
-       depends on HAVE_FTRACE_NMI_ENTER
-       default y
-
 config EVENT_TRACING
 	select CONTEXT_SWITCH_TRACER
 	select GLOB
@@ -158,6 +148,7 @@ config FUNCTION_TRACER
 	select CONTEXT_SWITCH_TRACER
 	select GLOB
 	select TASKS_RCU if PREEMPTION
+	select TASKS_RUDE_RCU
 	help
 	  Enable the kernel to trace every kernel function. This is done
 	  by using a compiler feature to insert a small, 5-byte No-Operation
@@ -466,7 +457,6 @@ config PROFILE_ANNOTATED_BRANCHES
 config PROFILE_ALL_BRANCHES
 	bool "Profile all if conditionals" if !FORTIFY_SOURCE
 	select TRACE_BRANCH_PROFILING
-	imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED  # avoid false positives
 	help
 	  This tracer profiles all branch conditions. Every if ()
 	  taken in the kernel is recorded whether it hit or miss.
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ca1796747a77..92ba69b716dc 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -323,17 +323,15 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
 
 /*
  * Only limited trace_printk() conversion specifiers allowed:
- * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s
+ * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s
  */
 BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 	   u64, arg2, u64, arg3)
 {
+	int i, mod[3] = {}, fmt_cnt = 0;
+	char buf[64], fmt_ptype;
+	void *unsafe_ptr = NULL;
 	bool str_seen = false;
-	int mod[3] = {};
-	int fmt_cnt = 0;
-	u64 unsafe_addr;
-	char buf[64];
-	int i;
 
 	/*
 	 * bpf_check()->check_func_arg()->check_stack_boundary()
@@ -359,40 +357,71 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		if (fmt[i] == 'l') {
 			mod[fmt_cnt]++;
 			i++;
-		} else if (fmt[i] == 'p' || fmt[i] == 's') {
+		} else if (fmt[i] == 'p') {
 			mod[fmt_cnt]++;
+			if ((fmt[i + 1] == 'k' ||
+			     fmt[i + 1] == 'u') &&
+			    fmt[i + 2] == 's') {
+				fmt_ptype = fmt[i + 1];
+				i += 2;
+				goto fmt_str;
+			}
+
 			/* disallow any further format extensions */
 			if (fmt[i + 1] != 0 &&
 			    !isspace(fmt[i + 1]) &&
 			    !ispunct(fmt[i + 1]))
 				return -EINVAL;
-			fmt_cnt++;
-			if (fmt[i] == 's') {
-				if (str_seen)
-					/* allow only one '%s' per fmt string */
-					return -EINVAL;
-				str_seen = true;
-
-				switch (fmt_cnt) {
-				case 1:
-					unsafe_addr = arg1;
-					arg1 = (long) buf;
-					break;
-				case 2:
-					unsafe_addr = arg2;
-					arg2 = (long) buf;
-					break;
-				case 3:
-					unsafe_addr = arg3;
-					arg3 = (long) buf;
-					break;
-				}
-				buf[0] = 0;
-				strncpy_from_unsafe(buf,
-						    (void *) (long) unsafe_addr,
+
+			goto fmt_next;
+		} else if (fmt[i] == 's') {
+			mod[fmt_cnt]++;
+			fmt_ptype = fmt[i];
+fmt_str:
+			if (str_seen)
+				/* allow only one '%s' per fmt string */
+				return -EINVAL;
+			str_seen = true;
+
+			if (fmt[i + 1] != 0 &&
+			    !isspace(fmt[i + 1]) &&
+			    !ispunct(fmt[i + 1]))
+				return -EINVAL;
+
+			switch (fmt_cnt) {
+			case 0:
+				unsafe_ptr = (void *)(long)arg1;
+				arg1 = (long)buf;
+				break;
+			case 1:
+				unsafe_ptr = (void *)(long)arg2;
+				arg2 = (long)buf;
+				break;
+			case 2:
+				unsafe_ptr = (void *)(long)arg3;
+				arg3 = (long)buf;
+				break;
+			}
+
+			buf[0] = 0;
+			switch (fmt_ptype) {
+			case 's':
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+				strncpy_from_unsafe(buf, unsafe_ptr,
 						    sizeof(buf));
+				break;
+#endif
+			case 'k':
+				strncpy_from_unsafe_strict(buf, unsafe_ptr,
+							   sizeof(buf));
+				break;
+			case 'u':
+				strncpy_from_unsafe_user(buf,
+					(__force void __user *)unsafe_ptr,
+							 sizeof(buf));
+				break;
 			}
-			continue;
+			goto fmt_next;
 		}
 
 		if (fmt[i] == 'l') {
@@ -403,6 +432,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		if (fmt[i] != 'i' && fmt[i] != 'd' &&
 		    fmt[i] != 'u' && fmt[i] != 'x')
 			return -EINVAL;
+fmt_next:
 		fmt_cnt++;
 	}
 
@@ -825,14 +855,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_probe_read_user_proto;
 	case BPF_FUNC_probe_read_kernel:
 		return &bpf_probe_read_kernel_proto;
-	case BPF_FUNC_probe_read:
-		return &bpf_probe_read_compat_proto;
 	case BPF_FUNC_probe_read_user_str:
 		return &bpf_probe_read_user_str_proto;
 	case BPF_FUNC_probe_read_kernel_str:
 		return &bpf_probe_read_kernel_str_proto;
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+	case BPF_FUNC_probe_read:
+		return &bpf_probe_read_compat_proto;
 	case BPF_FUNC_probe_read_str:
 		return &bpf_probe_read_compat_str_proto;
+#endif
 #ifdef CONFIG_CGROUPS
 	case BPF_FUNC_get_current_cgroup_id:
 		return &bpf_get_current_cgroup_id_proto;
@@ -1468,7 +1500,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 	u32 *ids, prog_cnt, ids_len;
 	int ret;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EPERM;
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -EINVAL;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 041694a1eb74..b5765aeea698 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -160,17 +160,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 	op->saved_func(ip, parent_ip, op, regs);
 }
 
-static void ftrace_sync(struct work_struct *work)
-{
-	/*
-	 * This function is just a stub to implement a hard force
-	 * of synchronize_rcu(). This requires synchronizing
-	 * tasks even in userspace and idle.
-	 *
-	 * Yes, function tracing is rude.
-	 */
-}
-
 static void ftrace_sync_ipi(void *data)
 {
 	/* Probably not needed, but do it anyway */
@@ -256,7 +245,7 @@ static void update_ftrace_function(void)
 	 * Make sure all CPUs see this. Yes this is slow, but static
 	 * tracing is slow and nasty to have enabled.
 	 */
-	schedule_on_each_cpu(ftrace_sync);
+	synchronize_rcu_tasks_rude();
 	/* Now all cpus are using the list ops. */
 	function_trace_op = set_function_trace_op;
 	/* Make sure the function_trace_op is visible on all CPUs */
@@ -2932,7 +2921,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		 * infrastructure to do the synchronization, thus we must do it
 		 * ourselves.
 		 */
-		schedule_on_each_cpu(ftrace_sync);
+		synchronize_rcu_tasks_rude();
 
 		/*
 		 * When the kernel is preeptive, tasks can be preempted
@@ -5165,6 +5154,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 			list_del_rcu(&direct->next);
 			synchronize_rcu_tasks();
 			kfree(direct);
+			kfree(entry);
 			ftrace_direct_func_count--;
 		}
 	}
@@ -5887,7 +5877,7 @@ ftrace_graph_release(struct inode *inode, struct file *file)
 		 * infrastructure to do the synchronization, thus we must do it
 		 * ourselves.
 		 */
-		schedule_on_each_cpu(ftrace_sync);
+		synchronize_rcu_tasks_rude();
 
 		free_ftrace_hash(old_hash);
 	}
diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h
index 0456e0a3dab1..382775edf690 100644
--- a/kernel/trace/ftrace_internal.h
+++ b/kernel/trace/ftrace_internal.h
@@ -4,28 +4,6 @@
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-/*
- * Traverse the ftrace_global_list, invoking all entries.  The reason that we
- * can use rcu_dereference_raw_check() is that elements removed from this list
- * are simply leaked, so there is no need to interact with a grace-period
- * mechanism.  The rcu_dereference_raw_check() calls are needed to handle
- * concurrent insertions into the ftrace_global_list.
- *
- * Silly Alpha and silly pointer-speculation compiler optimizations!
- */
-#define do_for_each_ftrace_op(op, list)			\
-	op = rcu_dereference_raw_check(list);			\
-	do
-
-/*
- * Optimized for just a single item in the list (as that is the normal case).
- */
-#define while_for_each_ftrace_op(op)				\
-	while (likely(op = rcu_dereference_raw_check((op)->next)) &&	\
-	       unlikely((op) != &ftrace_list_end))
-
-extern struct ftrace_ops __rcu *ftrace_ops_list;
-extern struct ftrace_ops ftrace_list_end;
 extern struct mutex ftrace_lock;
 extern struct ftrace_ops global_ops;
 
diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c
index 31c0fad4cb9e..312d1a0ca3b6 100644
--- a/kernel/trace/preemptirq_delay_test.c
+++ b/kernel/trace/preemptirq_delay_test.c
@@ -16,6 +16,7 @@
 #include <linux/printk.h>
 #include <linux/string.h>
 #include <linux/sysfs.h>
+#include <linux/completion.h>
 
 static ulong delay = 100;
 static char test_mode[12] = "irq";
@@ -28,6 +29,8 @@ MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)");
 MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)");
 MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)");
 
+static struct completion done;
+
 #define MIN(x, y) ((x) < (y) ? (x) : (y))
 
 static void busy_wait(ulong time)
@@ -113,22 +116,47 @@ static int preemptirq_delay_run(void *data)
 
 	for (i = 0; i < s; i++)
 		(testfuncs[i])(i);
+
+	complete(&done);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+
+	__set_current_state(TASK_RUNNING);
+
 	return 0;
 }
 
-static struct task_struct *preemptirq_start_test(void)
+static int preemptirq_run_test(void)
 {
+	struct task_struct *task;
 	char task_name[50];
 
+	init_completion(&done);
+
 	snprintf(task_name, sizeof(task_name), "%s_test", test_mode);
-	return kthread_run(preemptirq_delay_run, NULL, task_name);
+	task =  kthread_run(preemptirq_delay_run, NULL, task_name);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	if (task) {
+		wait_for_completion(&done);
+		kthread_stop(task);
+	}
+	return 0;
 }
 
 
 static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr,
 			 const char *buf, size_t count)
 {
-	preemptirq_start_test();
+	ssize_t ret;
+
+	ret = preemptirq_run_test();
+	if (ret)
+		return ret;
 	return count;
 }
 
@@ -148,11 +176,9 @@ static struct kobject *preemptirq_delay_kobj;
 
 static int __init preemptirq_delay_init(void)
 {
-	struct task_struct *test_task;
 	int retval;
 
-	test_task = preemptirq_start_test();
-	retval = PTR_ERR_OR_ZERO(test_task);
+	retval = preemptirq_run_test();
 	if (retval != 0)
 		return retval;
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6f0b42ceeb00..b8e1ca48be50 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -193,7 +193,7 @@ rb_event_length(struct ring_buffer_event *event)
 	case RINGBUF_TYPE_DATA:
 		return rb_event_data_length(event);
 	default:
-		BUG();
+		WARN_ON_ONCE(1);
 	}
 	/* not hit */
 	return 0;
@@ -249,7 +249,7 @@ rb_event_data(struct ring_buffer_event *event)
 {
 	if (extended_time(event))
 		event = skip_time_extend(event);
-	BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+	WARN_ON_ONCE(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
 	/* If length is in len field, then array[0] has the data */
 	if (event->type_len)
 		return (void *)&event->array[0];
@@ -3727,7 +3727,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
 		return;
 
 	default:
-		BUG();
+		RB_WARN_ON(cpu_buffer, 1);
 	}
 	return;
 }
@@ -3757,7 +3757,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 		return;
 
 	default:
-		BUG();
+		RB_WARN_ON(iter->cpu_buffer, 1);
 	}
 	return;
 }
@@ -4020,7 +4020,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
 		return event;
 
 	default:
-		BUG();
+		RB_WARN_ON(cpu_buffer, 1);
 	}
 
 	return NULL;
@@ -4034,7 +4034,6 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
 	int nr_loops = 0;
-	bool failed = false;
 
 	if (ts)
 		*ts = 0;
@@ -4056,19 +4055,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 		return NULL;
 
 	/*
-	 * We repeat when a time extend is encountered or we hit
-	 * the end of the page. Since the time extend is always attached
-	 * to a data event, we should never loop more than three times.
-	 * Once for going to next page, once on time extend, and
-	 * finally once to get the event.
-	 * We should never hit the following condition more than thrice,
-	 * unless the buffer is very small, and there's a writer
-	 * that is causing the reader to fail getting an event.
+	 * As the writer can mess with what the iterator is trying
+	 * to read, just give up if we fail to get an event after
+	 * three tries. The iterator is not as reliable when reading
+	 * the ring buffer with an active write as the consumer is.
+	 * Do not warn if the three failures is reached.
 	 */
-	if (++nr_loops > 3) {
-		RB_WARN_ON(cpu_buffer, !failed);
+	if (++nr_loops > 3)
 		return NULL;
-	}
 
 	if (rb_per_cpu_empty(cpu_buffer))
 		return NULL;
@@ -4079,10 +4073,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	}
 
 	event = rb_iter_head_event(iter);
-	if (!event) {
-		failed = true;
+	if (!event)
 		goto again;
-	}
 
 	switch (event->type_len) {
 	case RINGBUF_TYPE_PADDING:
@@ -4117,7 +4109,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 		return event;
 
 	default:
-		BUG();
+		RB_WARN_ON(cpu_buffer, 1);
 	}
 
 	return NULL;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8d2b98812625..29615f15a820 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -947,7 +947,8 @@ int __trace_bputs(unsigned long ip, const char *str)
 EXPORT_SYMBOL_GPL(__trace_bputs);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data)
+static void tracing_snapshot_instance_cond(struct trace_array *tr,
+					   void *cond_data)
 {
 	struct tracer *tracer = tr->current_trace;
 	unsigned long flags;
@@ -8525,6 +8526,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	 */
 	allocate_snapshot = false;
 #endif
+
+	/*
+	 * Because of some magic with the way alloc_percpu() works on
+	 * x86_64, we need to synchronize the pgd of all the tables,
+	 * otherwise the trace events that happen in x86_64 page fault
+	 * handlers can't cope with accessing the chance that a
+	 * alloc_percpu()'d memory might be touched in the page fault trace
+	 * event. Oh, and we need to audit all other alloc_percpu() and vmalloc()
+	 * calls in tracing, because something might get triggered within a
+	 * page fault trace event!
+	 */
+	vmalloc_sync_mappings();
+
 	return 0;
 }
 
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 06d7feb5255f..9de29bb45a27 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -95,24 +95,20 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
 	struct xbc_node *anode;
 	char buf[MAX_BUF_LEN];
 	const char *val;
-	int ret;
+	int ret = 0;
 
-	kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
+	xbc_node_for_each_array_value(node, "probes", anode, val) {
+		kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
 
-	ret = kprobe_event_gen_cmd_start(&cmd, event, NULL);
-	if (ret)
-		return ret;
+		ret = kprobe_event_gen_cmd_start(&cmd, event, val);
+		if (ret)
+			break;
 
-	xbc_node_for_each_array_value(node, "probes", anode, val) {
-		ret = kprobe_event_add_field(&cmd, val);
+		ret = kprobe_event_gen_cmd_end(&cmd);
 		if (ret)
-			return ret;
+			pr_err("Failed to add probe: %s\n", buf);
 	}
 
-	ret = kprobe_event_gen_cmd_end(&cmd);
-	if (ret)
-		pr_err("Failed to add probe: %s\n", buf);
-
 	return ret;
 }
 #else
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 5f6834a2bf41..fcab11cc6833 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3320,6 +3320,9 @@ static void __destroy_hist_field(struct hist_field *hist_field)
 	kfree(hist_field->name);
 	kfree(hist_field->type);
 
+	kfree(hist_field->system);
+	kfree(hist_field->event_name);
+
 	kfree(hist_field);
 }
 
@@ -4382,6 +4385,7 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data,
 		goto out;
 	}
 
+	var->ref = 1;
 	var->flags = HIST_FIELD_FL_VAR;
 	var->var.idx = idx;
 	var->var.hist_data = var->hist_data = hist_data;
@@ -5011,6 +5015,9 @@ static void destroy_field_vars(struct hist_trigger_data *hist_data)
 
 	for (i = 0; i < hist_data->n_field_vars; i++)
 		destroy_field_var(hist_data->field_vars[i]);
+
+	for (i = 0; i < hist_data->n_save_vars; i++)
+		destroy_field_var(hist_data->save_vars[i]);
 }
 
 static void save_field_var(struct hist_trigger_data *hist_data,
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index dd34a1b46a86..3a74736da363 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1088,14 +1088,10 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
 			  struct event_trigger_data *data,
 			  struct trace_event_file *file)
 {
-	int ret = register_trigger(glob, ops, data, file);
-
-	if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) {
-		unregister_trigger(glob, ops, data, file);
-		ret = 0;
-	}
+	if (tracing_alloc_snapshot_instance(file->tr) != 0)
+		return 0;
 
-	return ret;
+	return register_trigger(glob, ops, data, file);
 }
 
 static int
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d0568af4a0ef..35989383ae11 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -453,7 +453,7 @@ static bool __within_notrace_func(unsigned long addr)
 
 static bool within_notrace_func(struct trace_kprobe *tk)
 {
-	unsigned long addr = addr = trace_kprobe_address(tk);
+	unsigned long addr = trace_kprobe_address(tk);
 	char symname[KSYM_NAME_LEN], *p;
 
 	if (!__within_notrace_func(addr))
@@ -940,6 +940,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init);
  * complete command or only the first part of it; in the latter case,
  * kprobe_event_add_fields() can be used to add more fields following this.
  *
+ * Unlikely the synth_event_gen_cmd_start(), @loc must be specified. This
+ * returns -EINVAL if @loc == NULL.
+ *
  * Return: 0 if successful, error otherwise.
  */
 int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
@@ -953,6 +956,9 @@ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
 	if (cmd->type != DYNEVENT_TYPE_KPROBE)
 		return -EINVAL;
 
+	if (!loc)
+		return -EINVAL;
+
 	if (kretprobe)
 		snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name);
 	else
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9e31bfc818ff..74738c9856f1 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -283,7 +283,7 @@ int tracing_map_add_key_field(struct tracing_map *map,
 	return idx;
 }
 
-void tracing_map_array_clear(struct tracing_map_array *a)
+static void tracing_map_array_clear(struct tracing_map_array *a)
 {
 	unsigned int i;
 
@@ -294,7 +294,7 @@ void tracing_map_array_clear(struct tracing_map_array *a)
 		memset(a->pages[i], 0, PAGE_SIZE);
 }
 
-void tracing_map_array_free(struct tracing_map_array *a)
+static void tracing_map_array_free(struct tracing_map_array *a)
 {
 	unsigned int i;
 
@@ -316,7 +316,7 @@ void tracing_map_array_free(struct tracing_map_array *a)
 	kfree(a);
 }
 
-struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
+static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
 						  unsigned int entry_size)
 {
 	struct tracing_map_array *a;
diff --git a/kernel/umh.c b/kernel/umh.c
index 7f255b5a8845..3474d6aa55d8 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -475,6 +475,12 @@ static void umh_clean_and_save_pid(struct subprocess_info *info)
 {
 	struct umh_info *umh_info = info->data;
 
+	/* cleanup if umh_pipe_setup() was successful but exec failed */
+	if (info->pid && info->retval) {
+		fput(umh_info->pipe_to_umh);
+		fput(umh_info->pipe_from_umh);
+	}
+
 	argv_free(info->argv);
 	umh_info->pid = info->pid;
 }
@@ -544,6 +550,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob);
  * Runs a user-space application.  The application is started
  * asynchronously if wait is not set, and runs as a child of system workqueues.
  * (ie. it runs with full root capabilities and optimized affinity).
+ *
+ * Note: successful return value does not guarantee the helper was called at
+ * all. You can't rely on sub_info->{init,cleanup} being called even for
+ * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers
+ * into a successful no-op.
  */
 int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 {
diff --git a/lib/Kconfig b/lib/Kconfig
index 8005e36c3459..df3f3da95990 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -19,6 +19,9 @@ config RAID6_PQ_BENCHMARK
 	  Benchmark all available RAID6 PQ functions on init and choose the
 	  fastest one.
 
+config LINEAR_RANGES
+	tristate
+
 config PACKING
 	bool "Generic bitfield packing and unpacking"
 	default n
@@ -80,6 +83,9 @@ config ARCH_USE_CMPXCHG_LOCKREF
 config ARCH_HAS_FAST_MULTIPLIER
 	bool
 
+config ARCH_USE_SYM_ANNOTATIONS
+	bool
+
 config INDIRECT_PIO
 	bool "Access I/O in non-MMIO mode"
 	depends on ARM64
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 298e81357c8a..b3b05adab575 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -242,6 +242,8 @@ config DEBUG_INFO_DWARF4
 config DEBUG_INFO_BTF
 	bool "Generate BTF typeinfo"
 	depends on DEBUG_INFO
+	depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED
+	depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST
 	help
 	  Generate deduplicated BTF type information from DWARF debug info.
 	  Turning this on expects presence of pahole tool, which will convert
@@ -367,6 +369,11 @@ config STACK_VALIDATION
 	  For more information, see
 	  tools/objtool/Documentation/stack-validation.txt.
 
+config VMLINUX_VALIDATION
+	bool
+	depends on STACK_VALIDATION && DEBUG_ENTRY && !PARAVIRT
+	default y
+
 config DEBUG_FORCE_WEAK_PER_CPU
 	bool "Force weak per-cpu definitions"
 	depends on DEBUG_KERNEL
@@ -2090,6 +2097,18 @@ config LIST_KUNIT_TEST
 
 	  If unsure, say N.
 
+config LINEAR_RANGES_TEST
+	tristate "KUnit test for linear_ranges"
+	depends on KUNIT
+	select LINEAR_RANGES
+	help
+	  This builds the linear_ranges unit test, which runs on boot.
+	  Tests the linear_ranges logic correctness.
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
 config TEST_UDELAY
 	tristate "udelay test driver"
 	help
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index 48469c95d78e..929211039bac 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -60,18 +60,15 @@ config UBSAN_SANITIZE_ALL
 	  Enabling this option will get kernel image size increased
 	  significantly.
 
-config UBSAN_NO_ALIGNMENT
-	bool "Disable checking of pointers alignment"
-	default y if HAVE_EFFICIENT_UNALIGNED_ACCESS
+config UBSAN_ALIGNMENT
+	bool "Enable checks for pointers alignment"
+	default !HAVE_EFFICIENT_UNALIGNED_ACCESS
+	depends on !X86 || !COMPILE_TEST
 	help
-	  This option disables the check of unaligned memory accesses.
-	  This option should be used when building allmodconfig.
-	  Disabling this option on architectures that support unaligned
+	  This option enables the check of unaligned memory accesses.
+	  Enabling this option on architectures that support unaligned
 	  accesses may produce a lot of false positives.
 
-config UBSAN_ALIGNMENT
-	def_bool !UBSAN_NO_ALIGNMENT
-
 config TEST_UBSAN
 	tristate "Module for testing for undefined behavior detection"
 	depends on m
diff --git a/lib/Makefile b/lib/Makefile
index 685aee60de1d..cd548bfa8df9 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -125,6 +125,7 @@ obj-$(CONFIG_DEBUG_LIST) += list_debug.o
 obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
 
 obj-$(CONFIG_BITREVERSE) += bitrev.o
+obj-$(CONFIG_LINEAR_RANGES) += linear_ranges.o
 obj-$(CONFIG_PACKING)	+= packing.o
 obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
 obj-$(CONFIG_CRC16)	+= crc16.o
@@ -309,3 +310,4 @@ obj-$(CONFIG_OBJAGG) += objagg.o
 
 # KUnit tests
 obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o
+obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o
diff --git a/lib/crypto/chacha.c b/lib/crypto/chacha.c
index 65ead6b0c7e0..4ccbec442469 100644
--- a/lib/crypto/chacha.c
+++ b/lib/crypto/chacha.c
@@ -10,7 +10,6 @@
 #include <linux/export.h>
 #include <linux/bitops.h>
 #include <linux/string.h>
-#include <linux/cryptohash.h>
 #include <asm/unaligned.h>
 #include <crypto/chacha.h>
 
diff --git a/lib/crypto/sha256.c b/lib/crypto/sha256.c
index 66cb04b0cf4e..2e621697c5c3 100644
--- a/lib/crypto/sha256.c
+++ b/lib/crypto/sha256.c
@@ -206,7 +206,7 @@ static void sha256_transform(u32 *state, const u8 *input)
 	memzero_explicit(W, 64 * sizeof(u32));
 }
 
-int sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
+void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 {
 	unsigned int partial, done;
 	const u8 *src;
@@ -232,18 +232,16 @@ int sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 		partial = 0;
 	}
 	memcpy(sctx->buf + partial, src, len - done);
-
-	return 0;
 }
 EXPORT_SYMBOL(sha256_update);
 
-int sha224_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
+void sha224_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 {
-	return sha256_update(sctx, data, len);
+	sha256_update(sctx, data, len);
 }
 EXPORT_SYMBOL(sha224_update);
 
-static int __sha256_final(struct sha256_state *sctx, u8 *out, int digest_words)
+static void __sha256_final(struct sha256_state *sctx, u8 *out, int digest_words)
 {
 	__be32 *dst = (__be32 *)out;
 	__be64 bits;
@@ -268,19 +266,17 @@ static int __sha256_final(struct sha256_state *sctx, u8 *out, int digest_words)
 
 	/* Zeroize sensitive information. */
 	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
 }
 
-int sha256_final(struct sha256_state *sctx, u8 *out)
+void sha256_final(struct sha256_state *sctx, u8 *out)
 {
-	return __sha256_final(sctx, out, 8);
+	__sha256_final(sctx, out, 8);
 }
 EXPORT_SYMBOL(sha256_final);
 
-int sha224_final(struct sha256_state *sctx, u8 *out)
+void sha224_final(struct sha256_state *sctx, u8 *out)
 {
-	return __sha256_final(sctx, out, 7);
+	__sha256_final(sctx, out, 7);
 }
 EXPORT_SYMBOL(sha224_final);
 
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 7a6430a7fca0..ccb2ffad8dcf 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -93,7 +93,7 @@ static void kunit_print_ok_not_ok(void *test_or_suite,
 	 * representation.
 	 */
 	if (suite)
-		pr_info("%s %zd - %s",
+		pr_info("%s %zd - %s\n",
 			kunit_status_to_string(is_ok),
 			test_number, description);
 	else
diff --git a/lib/linear_ranges.c b/lib/linear_ranges.c
new file mode 100644
index 000000000000..9495ef3572b7
--- /dev/null
+++ b/lib/linear_ranges.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * helpers to map values in a linear range to range index
+ *
+ * Original idea borrowed from regulator framework
+ *
+ * It might be useful if we could support also inversely proportional ranges?
+ * Copyright 2020 ROHM Semiconductors
+ */
+
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/linear_range.h>
+#include <linux/module.h>
+
+/**
+ * linear_range_values_in_range - return the amount of values in a range
+ * @r:		pointer to linear range where values are counted
+ *
+ * Compute the amount of values in range pointed by @r. Note, values can
+ * be all equal - range with selectors 0,...,2 with step 0 still contains
+ * 3 values even though they are all equal.
+ *
+ * Return: the amount of values in range pointed by @r
+ */
+unsigned int linear_range_values_in_range(const struct linear_range *r)
+{
+	if (!r)
+		return 0;
+	return r->max_sel - r->min_sel + 1;
+}
+EXPORT_SYMBOL_GPL(linear_range_values_in_range);
+
+/**
+ * linear_range_values_in_range_array - return the amount of values in ranges
+ * @r:		pointer to array of linear ranges where values are counted
+ * @ranges:	amount of ranges we include in computation.
+ *
+ * Compute the amount of values in ranges pointed by @r. Note, values can
+ * be all equal - range with selectors 0,...,2 with step 0 still contains
+ * 3 values even though they are all equal.
+ *
+ * Return: the amount of values in first @ranges ranges pointed by @r
+ */
+unsigned int linear_range_values_in_range_array(const struct linear_range *r,
+						int ranges)
+{
+	int i, values_in_range = 0;
+
+	for (i = 0; i < ranges; i++) {
+		int values;
+
+		values = linear_range_values_in_range(&r[i]);
+		if (!values)
+			return values;
+
+		values_in_range += values;
+	}
+	return values_in_range;
+}
+EXPORT_SYMBOL_GPL(linear_range_values_in_range_array);
+
+/**
+ * linear_range_get_max_value - return the largest value in a range
+ * @r:		pointer to linear range where value is looked from
+ *
+ * Return: the largest value in the given range
+ */
+unsigned int linear_range_get_max_value(const struct linear_range *r)
+{
+	return r->min + (r->max_sel - r->min_sel) * r->step;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_max_value);
+
+/**
+ * linear_range_get_value - fetch a value from given range
+ * @r:		pointer to linear range where value is looked from
+ * @selector:	selector for which the value is searched
+ * @val:	address where found value is updated
+ *
+ * Search given ranges for value which matches given selector.
+ *
+ * Return: 0 on success, -EINVAL given selector is not found from any of the
+ * ranges.
+ */
+int linear_range_get_value(const struct linear_range *r, unsigned int selector,
+			   unsigned int *val)
+{
+	if (r->min_sel > selector || r->max_sel < selector)
+		return -EINVAL;
+
+	*val = r->min + (selector - r->min_sel) * r->step;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_value);
+
+/**
+ * linear_range_get_value_array - fetch a value from array of ranges
+ * @r:		pointer to array of linear ranges where value is looked from
+ * @ranges:	amount of ranges in an array
+ * @selector:	selector for which the value is searched
+ * @val:	address where found value is updated
+ *
+ * Search through an array of ranges for value which matches given selector.
+ *
+ * Return: 0 on success, -EINVAL given selector is not found from any of the
+ * ranges.
+ */
+int linear_range_get_value_array(const struct linear_range *r, int ranges,
+				 unsigned int selector, unsigned int *val)
+{
+	int i;
+
+	for (i = 0; i < ranges; i++)
+		if (r[i].min_sel <= selector && r[i].max_sel >= selector)
+			return linear_range_get_value(&r[i], selector, val);
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_value_array);
+
+/**
+ * linear_range_get_selector_low - return linear range selector for value
+ * @r:		pointer to linear range where selector is looked from
+ * @val:	value for which the selector is searched
+ * @selector:	address where found selector value is updated
+ * @found:	flag to indicate that given value was in the range
+ *
+ * Return selector which which range value is closest match for given
+ * input value. Value is matching if it is equal or smaller than given
+ * value. If given value is in the range, then @found is set true.
+ *
+ * Return: 0 on success, -EINVAL if range is invalid or does not contain
+ * value smaller or equal to given value
+ */
+int linear_range_get_selector_low(const struct linear_range *r,
+				  unsigned int val, unsigned int *selector,
+				  bool *found)
+{
+	*found = false;
+
+	if (r->min > val)
+		return -EINVAL;
+
+	if (linear_range_get_max_value(r) < val) {
+		*selector = r->max_sel;
+		return 0;
+	}
+
+	*found = true;
+
+	if (r->step == 0)
+		*selector = r->min_sel;
+	else
+		*selector = (val - r->min) / r->step + r->min_sel;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_selector_low);
+
+/**
+ * linear_range_get_selector_low_array - return linear range selector for value
+ * @r:		pointer to array of linear ranges where selector is looked from
+ * @ranges:	amount of ranges to scan from array
+ * @val:	value for which the selector is searched
+ * @selector:	address where found selector value is updated
+ * @found:	flag to indicate that given value was in the range
+ *
+ * Scan array of ranges for selector which which range value matches given
+ * input value. Value is matching if it is equal or smaller than given
+ * value. If given value is found to be in a range scanning is stopped and
+ * @found is set true. If a range with values smaller than given value is found
+ * but the range max is being smaller than given value, then the ranges
+ * biggest selector is updated to @selector but scanning ranges is continued
+ * and @found is set to false.
+ *
+ * Return: 0 on success, -EINVAL if range array is invalid or does not contain
+ * range with a value smaller or equal to given value
+ */
+int linear_range_get_selector_low_array(const struct linear_range *r,
+					int ranges, unsigned int val,
+					unsigned int *selector, bool *found)
+{
+	int i;
+	int ret = -EINVAL;
+
+	for (i = 0; i < ranges; i++) {
+		int tmpret;
+
+		tmpret = linear_range_get_selector_low(&r[i], val, selector,
+						       found);
+		if (!tmpret)
+			ret = 0;
+
+		if (*found)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_selector_low_array);
+
+/**
+ * linear_range_get_selector_high - return linear range selector for value
+ * @r:		pointer to linear range where selector is looked from
+ * @val:	value for which the selector is searched
+ * @selector:	address where found selector value is updated
+ * @found:	flag to indicate that given value was in the range
+ *
+ * Return selector which which range value is closest match for given
+ * input value. Value is matching if it is equal or higher than given
+ * value. If given value is in the range, then @found is set true.
+ *
+ * Return: 0 on success, -EINVAL if range is invalid or does not contain
+ * value greater or equal to given value
+ */
+int linear_range_get_selector_high(const struct linear_range *r,
+				   unsigned int val, unsigned int *selector,
+				   bool *found)
+{
+	*found = false;
+
+	if (linear_range_get_max_value(r) < val)
+		return -EINVAL;
+
+	if (r->min > val) {
+		*selector = r->min_sel;
+		return 0;
+	}
+
+	*found = true;
+
+	if (r->step == 0)
+		*selector = r->max_sel;
+	else
+		*selector = DIV_ROUND_UP(val - r->min, r->step) + r->min_sel;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(linear_range_get_selector_high);
+
+MODULE_DESCRIPTION("linear-ranges helper");
+MODULE_LICENSE("GPL");
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h
index 2dceaca27489..afbd99987cf8 100644
--- a/lib/mpi/longlong.h
+++ b/lib/mpi/longlong.h
@@ -653,7 +653,7 @@ do {						\
 	**************  MIPS/64  **************
 	***************************************/
 #if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64
-#if defined(__mips_isa_rev) && __mips_isa_rev >= 6
+#if defined(__mips_isa_rev) && __mips_isa_rev >= 6 && defined(CONFIG_CC_IS_GCC)
 /*
  * GCC ends up emitting a __multi3 intrinsic call for MIPS64r6 with the plain C
  * code below, so we special case MIPS64r6 until the compiler can do better.
@@ -722,22 +722,22 @@ do {									\
 do { \
 	if (__builtin_constant_p(bh) && (bh) == 0) \
 		__asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "%r" ((USItype)(ah)), \
 		"%r" ((USItype)(al)), \
 		"rI" ((USItype)(bl))); \
 	else if (__builtin_constant_p(bh) && (bh) == ~(USItype) 0) \
 		__asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "%r" ((USItype)(ah)), \
 		"%r" ((USItype)(al)), \
 		"rI" ((USItype)(bl))); \
 	else \
 		__asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "%r" ((USItype)(ah)), \
 		"r" ((USItype)(bh)), \
 		"%r" ((USItype)(al)), \
@@ -747,36 +747,36 @@ do { \
 do { \
 	if (__builtin_constant_p(ah) && (ah) == 0) \
 		__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(bh)), \
 		"rI" ((USItype)(al)), \
 		"r" ((USItype)(bl))); \
 	else if (__builtin_constant_p(ah) && (ah) == ~(USItype) 0) \
 		__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(bh)), \
 		"rI" ((USItype)(al)), \
 		"r" ((USItype)(bl))); \
 	else if (__builtin_constant_p(bh) && (bh) == 0) \
 		__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(ah)), \
 		"rI" ((USItype)(al)), \
 		"r" ((USItype)(bl))); \
 	else if (__builtin_constant_p(bh) && (bh) == ~(USItype) 0) \
 		__asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(ah)), \
 		"rI" ((USItype)(al)), \
 		"r" ((USItype)(bl))); \
 	else \
 		__asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2" \
-		: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+		: "=r" (sh), \
+		"=&r" (sl) \
 		: "r" ((USItype)(ah)), \
 		"r" ((USItype)(bh)), \
 		"rI" ((USItype)(al)), \
@@ -787,7 +787,7 @@ do { \
 do { \
 	USItype __m0 = (m0), __m1 = (m1); \
 	__asm__ ("mulhwu %0,%1,%2" \
-	: "=r" ((USItype) ph) \
+	: "=r" (ph) \
 	: "%r" (__m0), \
 	"r" (__m1)); \
 	(pl) = __m0 * __m1; \
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 2ee6ae3b0ade..34e406fe561f 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -20,6 +20,7 @@
 #include <linux/kernel.h>
 #include <linux/kmemleak.h>
 #include <linux/percpu.h>
+#include <linux/local_lock.h>
 #include <linux/preempt.h>		/* in_interrupt() */
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
@@ -27,7 +28,6 @@
 #include <linux/string.h>
 #include <linux/xarray.h>
 
-
 /*
  * Radix tree node cache.
  */
@@ -58,12 +58,10 @@ struct kmem_cache *radix_tree_node_cachep;
 /*
  * Per-cpu pool of preloaded nodes
  */
-struct radix_tree_preload {
-	unsigned nr;
-	/* nodes->parent points to next preallocated node */
-	struct radix_tree_node *nodes;
+DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = {
+	.lock = INIT_LOCAL_LOCK(lock),
 };
-static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
+EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads);
 
 static inline struct radix_tree_node *entry_to_node(void *ptr)
 {
@@ -332,14 +330,14 @@ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr)
 	 */
 	gfp_mask &= ~__GFP_ACCOUNT;
 
-	preempt_disable();
+	local_lock(&radix_tree_preloads.lock);
 	rtp = this_cpu_ptr(&radix_tree_preloads);
 	while (rtp->nr < nr) {
-		preempt_enable();
+		local_unlock(&radix_tree_preloads.lock);
 		node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
 		if (node == NULL)
 			goto out;
-		preempt_disable();
+		local_lock(&radix_tree_preloads.lock);
 		rtp = this_cpu_ptr(&radix_tree_preloads);
 		if (rtp->nr < nr) {
 			node->parent = rtp->nodes;
@@ -381,7 +379,7 @@ int radix_tree_maybe_preload(gfp_t gfp_mask)
 	if (gfpflags_allow_blocking(gfp_mask))
 		return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE);
 	/* Preloading doesn't help anything with this gfp mask, skip it */
-	preempt_disable();
+	local_lock(&radix_tree_preloads.lock);
 	return 0;
 }
 EXPORT_SYMBOL(radix_tree_maybe_preload);
@@ -1470,7 +1468,7 @@ EXPORT_SYMBOL(radix_tree_tagged);
 void idr_preload(gfp_t gfp_mask)
 {
 	if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE))
-		preempt_disable();
+		local_lock(&radix_tree_preloads.lock);
 }
 EXPORT_SYMBOL(idr_preload);
 
diff --git a/lib/sha1.c b/lib/sha1.c
index 1d96d2c02b82..49257a915bb6 100644
--- a/lib/sha1.c
+++ b/lib/sha1.c
@@ -9,7 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/bitops.h>
-#include <linux/cryptohash.h>
+#include <crypto/sha.h>
 #include <asm/unaligned.h>
 
 /*
@@ -64,22 +64,24 @@
 #define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) ,  0xca62c1d6, A, B, C, D, E )
 
 /**
- * sha_transform - single block SHA1 transform
+ * sha1_transform - single block SHA1 transform (deprecated)
  *
  * @digest: 160 bit digest to update
  * @data:   512 bits of data to hash
  * @array:  16 words of workspace (see note)
  *
- * This function generates a SHA1 digest for a single 512-bit block.
- * Be warned, it does not handle padding and message digest, do not
- * confuse it with the full FIPS 180-1 digest algorithm for variable
- * length messages.
+ * This function executes SHA-1's internal compression function.  It updates the
+ * 160-bit internal state (@digest) with a single 512-bit data block (@data).
+ *
+ * Don't use this function.  SHA-1 is no longer considered secure.  And even if
+ * you do have to use SHA-1, this isn't the correct way to hash something with
+ * SHA-1 as this doesn't handle padding and finalization.
  *
  * Note: If the hash is security sensitive, the caller should be sure
  * to clear the workspace. This is left to the caller to avoid
  * unnecessary clears between chained hashing operations.
  */
-void sha_transform(__u32 *digest, const char *data, __u32 *array)
+void sha1_transform(__u32 *digest, const char *data, __u32 *array)
 {
 	__u32 A, B, C, D, E;
 
@@ -185,13 +187,13 @@ void sha_transform(__u32 *digest, const char *data, __u32 *array)
 	digest[3] += D;
 	digest[4] += E;
 }
-EXPORT_SYMBOL(sha_transform);
+EXPORT_SYMBOL(sha1_transform);
 
 /**
- * sha_init - initialize the vectors for a SHA1 digest
+ * sha1_init - initialize the vectors for a SHA1 digest
  * @buf: vector to initialize
  */
-void sha_init(__u32 *buf)
+void sha1_init(__u32 *buf)
 {
 	buf[0] = 0x67452301;
 	buf[1] = 0xefcdab89;
@@ -199,4 +201,4 @@ void sha_init(__u32 *buf)
 	buf[3] = 0x10325476;
 	buf[4] = 0xc3d2e1f0;
 }
-EXPORT_SYMBOL(sha_init);
+EXPORT_SYMBOL(sha1_init);
diff --git a/lib/test_linear_ranges.c b/lib/test_linear_ranges.c
new file mode 100644
index 000000000000..676e0b8abcdd
--- /dev/null
+++ b/lib/test_linear_ranges.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit test for the linear_ranges helper.
+ *
+ * Copyright (C) 2020, ROHM Semiconductors.
+ * Author: Matti Vaittinen <matti.vaittien@fi.rohmeurope.com>
+ */
+#include <kunit/test.h>
+
+#include <linux/linear_range.h>
+
+/* First things first. I deeply dislike unit-tests. I have seen all the hell
+ * breaking loose when people who think the unit tests are "the silver bullet"
+ * to kill bugs get to decide how a company should implement testing strategy...
+ *
+ * Believe me, it may get _really_ ridiculous. It is tempting to think that
+ * walking through all the possible execution branches will nail down 100% of
+ * bugs. This may lead to ideas about demands to get certain % of "test
+ * coverage" - measured as line coverage. And that is one of the worst things
+ * you can do.
+ *
+ * Ask people to provide line coverage and they do. I've seen clever tools
+ * which generate test cases to test the existing functions - and by default
+ * these tools expect code to be correct and just generate checks which are
+ * passing when ran against current code-base. Run this generator and you'll get
+ * tests that do not test code is correct but just verify nothing changes.
+ * Problem is that testing working code is pointless. And if it is not
+ * working, your test must not assume it is working. You won't catch any bugs
+ * by such tests. What you can do is to generate a huge amount of tests.
+ * Especially if you were are asked to proivde 100% line-coverage x_x. So what
+ * does these tests - which are not finding any bugs now - do?
+ *
+ * They add inertia to every future development. I think it was Terry Pratchet
+ * who wrote someone having same impact as thick syrup has to chronometre.
+ * Excessive amount of unit-tests have this effect to development. If you do
+ * actually find _any_ bug from code in such environment and try fixing it...
+ * ...chances are you also need to fix the test cases. In sunny day you fix one
+ * test. But I've done refactoring which resulted 500+ broken tests (which had
+ * really zero value other than proving to managers that we do do "quality")...
+ *
+ * After this being said - there are situations where UTs can be handy. If you
+ * have algorithms which take some input and should produce output - then you
+ * can implement few, carefully selected simple UT-cases which test this. I've
+ * previously used this for example for netlink and device-tree data parsing
+ * functions. Feed some data examples to functions and verify the output is as
+ * expected. I am not covering all the cases but I will see the logic should be
+ * working.
+ *
+ * Here we also do some minor testing. I don't want to go through all branches
+ * or test more or less obvious things - but I want to see the main logic is
+ * working. And I definitely don't want to add 500+ test cases that break when
+ * some simple fix is done x_x. So - let's only add few, well selected tests
+ * which ensure as much logic is good as possible.
+ */
+
+/*
+ * Test Range 1:
+ * selectors:	2	3	4	5	6
+ * values (5):	10	20	30	40	50
+ *
+ * Test Range 2:
+ * selectors:	7	8	9	10
+ * values (4):	100	150	200	250
+ */
+
+#define RANGE1_MIN 10
+#define RANGE1_MIN_SEL 2
+#define RANGE1_STEP 10
+
+/* 2, 3, 4, 5, 6 */
+static const unsigned int range1_sels[] = { RANGE1_MIN_SEL, RANGE1_MIN_SEL + 1,
+					    RANGE1_MIN_SEL + 2,
+					    RANGE1_MIN_SEL + 3,
+					    RANGE1_MIN_SEL + 4 };
+/* 10, 20, 30, 40, 50 */
+static const unsigned int range1_vals[] = { RANGE1_MIN, RANGE1_MIN +
+					    RANGE1_STEP,
+					    RANGE1_MIN + RANGE1_STEP * 2,
+					    RANGE1_MIN + RANGE1_STEP * 3,
+					    RANGE1_MIN + RANGE1_STEP * 4 };
+
+#define RANGE2_MIN 100
+#define RANGE2_MIN_SEL 7
+#define RANGE2_STEP 50
+
+/*  7, 8, 9, 10 */
+static const unsigned int range2_sels[] = { RANGE2_MIN_SEL, RANGE2_MIN_SEL + 1,
+					    RANGE2_MIN_SEL + 2,
+					    RANGE2_MIN_SEL + 3 };
+/* 100, 150, 200, 250 */
+static const unsigned int range2_vals[] = { RANGE2_MIN, RANGE2_MIN +
+					    RANGE2_STEP,
+					    RANGE2_MIN + RANGE2_STEP * 2,
+					    RANGE2_MIN + RANGE2_STEP * 3 };
+
+#define RANGE1_NUM_VALS (ARRAY_SIZE(range1_vals))
+#define RANGE2_NUM_VALS (ARRAY_SIZE(range2_vals))
+#define RANGE_NUM_VALS (RANGE1_NUM_VALS + RANGE2_NUM_VALS)
+
+#define RANGE1_MAX_SEL (RANGE1_MIN_SEL + RANGE1_NUM_VALS - 1)
+#define RANGE1_MAX_VAL (range1_vals[RANGE1_NUM_VALS - 1])
+
+#define RANGE2_MAX_SEL (RANGE2_MIN_SEL + RANGE2_NUM_VALS - 1)
+#define RANGE2_MAX_VAL (range2_vals[RANGE2_NUM_VALS - 1])
+
+#define SMALLEST_SEL RANGE1_MIN_SEL
+#define SMALLEST_VAL RANGE1_MIN
+
+static struct linear_range testr[] = {
+	{
+		.min = RANGE1_MIN,
+		.min_sel = RANGE1_MIN_SEL,
+		.max_sel = RANGE1_MAX_SEL,
+		.step = RANGE1_STEP,
+	}, {
+		.min = RANGE2_MIN,
+		.min_sel = RANGE2_MIN_SEL,
+		.max_sel = RANGE2_MAX_SEL,
+		.step = RANGE2_STEP
+	},
+};
+
+static void range_test_get_value(struct kunit *test)
+{
+	int ret, i;
+	unsigned int sel, val;
+
+	for (i = 0; i < RANGE1_NUM_VALS; i++) {
+		sel = range1_sels[i];
+		ret = linear_range_get_value_array(&testr[0], 2, sel, &val);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, val, range1_vals[i]);
+	}
+	for (i = 0; i < RANGE2_NUM_VALS; i++) {
+		sel = range2_sels[i];
+		ret = linear_range_get_value_array(&testr[0], 2, sel, &val);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, val, range2_vals[i]);
+	}
+	ret = linear_range_get_value_array(&testr[0], 2, sel + 1, &val);
+	KUNIT_EXPECT_NE(test, 0, ret);
+}
+
+static void range_test_get_selector_high(struct kunit *test)
+{
+	int ret, i;
+	unsigned int sel;
+	bool found;
+
+	for (i = 0; i < RANGE1_NUM_VALS; i++) {
+		ret = linear_range_get_selector_high(&testr[0], range1_vals[i],
+						     &sel, &found);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, sel, range1_sels[i]);
+		KUNIT_EXPECT_TRUE(test, found);
+	}
+
+	ret = linear_range_get_selector_high(&testr[0], RANGE1_MAX_VAL + 1,
+					     &sel, &found);
+	KUNIT_EXPECT_LE(test, ret, 0);
+
+	ret = linear_range_get_selector_high(&testr[0], RANGE1_MIN - 1,
+					     &sel, &found);
+	KUNIT_EXPECT_EQ(test, 0, ret);
+	KUNIT_EXPECT_FALSE(test, found);
+	KUNIT_EXPECT_EQ(test, sel, range1_sels[0]);
+}
+
+static void range_test_get_value_amount(struct kunit *test)
+{
+	int ret;
+
+	ret = linear_range_values_in_range_array(&testr[0], 2);
+	KUNIT_EXPECT_EQ(test, (int)RANGE_NUM_VALS, ret);
+}
+
+static void range_test_get_selector_low(struct kunit *test)
+{
+	int i, ret;
+	unsigned int sel;
+	bool found;
+
+	for (i = 0; i < RANGE1_NUM_VALS; i++) {
+		ret = linear_range_get_selector_low_array(&testr[0], 2,
+							  range1_vals[i], &sel,
+							  &found);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, sel, range1_sels[i]);
+		KUNIT_EXPECT_TRUE(test, found);
+	}
+	for (i = 0; i < RANGE2_NUM_VALS; i++) {
+		ret = linear_range_get_selector_low_array(&testr[0], 2,
+							  range2_vals[i], &sel,
+							  &found);
+		KUNIT_EXPECT_EQ(test, 0, ret);
+		KUNIT_EXPECT_EQ(test, sel, range2_sels[i]);
+		KUNIT_EXPECT_TRUE(test, found);
+	}
+
+	/*
+	 * Seek value greater than range max => get_selector_*_low should
+	 * return Ok - but set found to false as value is not in range
+	 */
+	ret = linear_range_get_selector_low_array(&testr[0], 2,
+					range2_vals[RANGE2_NUM_VALS - 1] + 1,
+					&sel, &found);
+
+	KUNIT_EXPECT_EQ(test, 0, ret);
+	KUNIT_EXPECT_EQ(test, sel, range2_sels[RANGE2_NUM_VALS - 1]);
+	KUNIT_EXPECT_FALSE(test, found);
+}
+
+static struct kunit_case range_test_cases[] = {
+	KUNIT_CASE(range_test_get_value_amount),
+	KUNIT_CASE(range_test_get_selector_high),
+	KUNIT_CASE(range_test_get_selector_low),
+	KUNIT_CASE(range_test_get_value),
+	{},
+};
+
+static struct kunit_suite range_test_module = {
+	.name = "linear-ranges-test",
+	.test_cases = range_test_cases,
+};
+
+kunit_test_suites(&range_test_module);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 2d9f520d2f27..7d60f24240a4 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -214,6 +214,7 @@ test_string(void)
 #define PTR_STR "ffff0123456789ab"
 #define PTR_VAL_NO_CRNG "(____ptrval____)"
 #define ZEROS "00000000"	/* hex 32 zero bits */
+#define ONES "ffffffff"		/* hex 32 one bits */
 
 static int __init
 plain_format(void)
@@ -245,6 +246,7 @@ plain_format(void)
 #define PTR_STR "456789ab"
 #define PTR_VAL_NO_CRNG "(ptrval)"
 #define ZEROS ""
+#define ONES ""
 
 static int __init
 plain_format(void)
@@ -330,14 +332,28 @@ test_hashed(const char *fmt, const void *p)
 	test(buf, fmt, p);
 }
 
+/*
+ * NULL pointers aren't hashed.
+ */
 static void __init
 null_pointer(void)
 {
-	test_hashed("%p", NULL);
+	test(ZEROS "00000000", "%p", NULL);
 	test(ZEROS "00000000", "%px", NULL);
 	test("(null)", "%pE", NULL);
 }
 
+/*
+ * Error pointers aren't hashed.
+ */
+static void __init
+error_pointer(void)
+{
+	test(ONES "fffffff5", "%p", ERR_PTR(-11));
+	test(ONES "fffffff5", "%px", ERR_PTR(-11));
+	test("(efault)", "%pE", ERR_PTR(-11));
+}
+
 #define PTR_INVALID ((void *)0x000000ab)
 
 static void __init
@@ -478,7 +494,7 @@ struct_va_format(void)
 }
 
 static void __init
-struct_rtc_time(void)
+time_and_date(void)
 {
 	/* 1543210543 */
 	const struct rtc_time tm = {
@@ -489,14 +505,21 @@ struct_rtc_time(void)
 		.tm_mon = 10,
 		.tm_year = 118,
 	};
+	/* 2019-01-04T15:32:23 */
+	time64_t t = 1546615943;
 
-	test("(%ptR?)", "%pt", &tm);
+	test("(%pt?)", "%pt", &tm);
 	test("2018-11-26T05:35:43", "%ptR", &tm);
 	test("0118-10-26T05:35:43", "%ptRr", &tm);
 	test("05:35:43|2018-11-26", "%ptRt|%ptRd", &tm, &tm);
 	test("05:35:43|0118-10-26", "%ptRtr|%ptRdr", &tm, &tm);
 	test("05:35:43|2018-11-26", "%ptRttr|%ptRdtr", &tm, &tm);
 	test("05:35:43 tr|2018-11-26 tr", "%ptRt tr|%ptRd tr", &tm, &tm);
+
+	test("2019-01-04T15:32:23", "%ptT", &t);
+	test("0119-00-04T15:32:23", "%ptTr", &t);
+	test("15:32:23|2019-01-04", "%ptTt|%ptTd", &t, &t);
+	test("15:32:23|0119-00-04", "%ptTtr|%ptTdr", &t, &t);
 }
 
 static void __init
@@ -649,6 +672,7 @@ test_pointer(void)
 {
 	plain();
 	null_pointer();
+	error_pointer();
 	invalid_pointer();
 	symbol_ptr();
 	kernel_ptr();
@@ -661,7 +685,7 @@ test_pointer(void)
 	uuid();
 	dentry();
 	struct_va_format();
-	struct_rtc_time();
+	time_and_date();
 	struct_clk();
 	bitmap();
 	netdev_features();
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 7c488a1ce318..259e55895933 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -34,6 +34,7 @@
 #include <linux/dcache.h>
 #include <linux/cred.h>
 #include <linux/rtc.h>
+#include <linux/time.h>
 #include <linux/uuid.h>
 #include <linux/of.h>
 #include <net/addrconf.h>
@@ -58,7 +59,7 @@
  * @endp: A pointer to the end of the parsed string will be placed here
  * @base: The number base to use
  *
- * This function is obsolete. Please use kstrtoull instead.
+ * This function has caveats. Please use kstrtoull instead.
  */
 unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base)
 {
@@ -83,7 +84,7 @@ EXPORT_SYMBOL(simple_strtoull);
  * @endp: A pointer to the end of the parsed string will be placed here
  * @base: The number base to use
  *
- * This function is obsolete. Please use kstrtoul instead.
+ * This function has caveats. Please use kstrtoul instead.
  */
 unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base)
 {
@@ -97,7 +98,7 @@ EXPORT_SYMBOL(simple_strtoul);
  * @endp: A pointer to the end of the parsed string will be placed here
  * @base: The number base to use
  *
- * This function is obsolete. Please use kstrtol instead.
+ * This function has caveats. Please use kstrtol instead.
  */
 long simple_strtol(const char *cp, char **endp, unsigned int base)
 {
@@ -114,7 +115,7 @@ EXPORT_SYMBOL(simple_strtol);
  * @endp: A pointer to the end of the parsed string will be placed here
  * @base: The number base to use
  *
- * This function is obsolete. Please use kstrtoll instead.
+ * This function has caveats. Please use kstrtoll instead.
  */
 long long simple_strtoll(const char *cp, char **endp, unsigned int base)
 {
@@ -794,6 +795,13 @@ static char *ptr_to_id(char *buf, char *end, const void *ptr,
 	unsigned long hashval;
 	int ret;
 
+	/*
+	 * Print the real pointer value for NULL and error pointers,
+	 * as they are not actual addresses.
+	 */
+	if (IS_ERR_OR_NULL(ptr))
+		return pointer_string(buf, end, ptr, spec);
+
 	/* When debugging early boot use non-cryptographically secure hash. */
 	if (unlikely(debug_boot_weak_hash)) {
 		hashval = hash_long((unsigned long)ptr, 32);
@@ -1820,14 +1828,39 @@ char *rtc_str(char *buf, char *end, const struct rtc_time *tm,
 }
 
 static noinline_for_stack
+char *time64_str(char *buf, char *end, const time64_t time,
+		 struct printf_spec spec, const char *fmt)
+{
+	struct rtc_time rtc_time;
+	struct tm tm;
+
+	time64_to_tm(time, 0, &tm);
+
+	rtc_time.tm_sec = tm.tm_sec;
+	rtc_time.tm_min = tm.tm_min;
+	rtc_time.tm_hour = tm.tm_hour;
+	rtc_time.tm_mday = tm.tm_mday;
+	rtc_time.tm_mon = tm.tm_mon;
+	rtc_time.tm_year = tm.tm_year;
+	rtc_time.tm_wday = tm.tm_wday;
+	rtc_time.tm_yday = tm.tm_yday;
+
+	rtc_time.tm_isdst = 0;
+
+	return rtc_str(buf, end, &rtc_time, spec, fmt);
+}
+
+static noinline_for_stack
 char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec,
 		    const char *fmt)
 {
 	switch (fmt[1]) {
 	case 'R':
 		return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt);
+	case 'T':
+		return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt);
 	default:
-		return error_string(buf, end, "(%ptR?)", spec);
+		return error_string(buf, end, "(%pt?)", spec);
 	}
 }
 
@@ -2143,8 +2176,9 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode,
  * - 'd[234]' For a dentry name (optionally 2-4 last components)
  * - 'D[234]' Same as 'd' but for a struct file
  * - 'g' For block_device name (gendisk + partition number)
- * - 't[R][dt][r]' For time and date as represented:
+ * - 't[RT][dt][r]' For time and date as represented by:
  *      R    struct rtc_time
+ *      T    time64_t
  * - 'C' For a clock, it prints the name (Common Clock Framework) or address
  *       (legacy clock framework) of the clock
  * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address
@@ -2168,6 +2202,10 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode,
  *		f full name
  *		P node name, including a possible unit address
  * - 'x' For printing the address. Equivalent to "%lx".
+ * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of
+ *           bpf_trace_printk() where [ku] prefix specifies either kernel (k)
+ *           or user (u) memory to probe, and:
+ *              s a string, equivalent to "%s" on direct vsnprintf() use
  *
  * ** When making changes please also update:
  *	Documentation/core-api/printk-formats.rst
@@ -2251,6 +2289,14 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		if (!IS_ERR(ptr))
 			break;
 		return err_ptr(buf, end, ptr, spec);
+	case 'u':
+	case 'k':
+		switch (fmt[1]) {
+		case 's':
+			return string(buf, end, ptr, spec);
+		default:
+			return error_string(buf, end, "(einval)", spec);
+		}
 	}
 
 	/* default is to _not_ leak addresses, hash before printing */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c81b4f3a7268..efc5b83acd2d 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -21,7 +21,7 @@ struct backing_dev_info noop_backing_dev_info = {
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
-const char *bdi_unknown_name = "(unknown)";
+static const char *bdi_unknown_name = "(unknown)";
 
 /*
  * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU
@@ -938,7 +938,8 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
 	if (bdi->dev)	/* The driver needs to use separate queues per device */
 		return 0;
 
-	dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args);
+	vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args);
+	dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name);
 	if (IS_ERR(dev))
 		return PTR_ERR(dev);
 
@@ -1043,6 +1044,14 @@ void bdi_put(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_put);
 
+const char *bdi_dev_name(struct backing_dev_info *bdi)
+{
+	if (!bdi || !bdi->dev)
+		return bdi_unknown_name;
+	return bdi->dev_name;
+}
+EXPORT_SYMBOL_GPL(bdi_dev_name);
+
 static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
diff --git a/mm/compaction.c b/mm/compaction.c
index 46f0fcc93081..c9d659e6a02c 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2243,15 +2243,11 @@ check_drain:
 		 * would succeed.
 		 */
 		if (cc->order > 0 && last_migrated_pfn) {
-			int cpu;
 			unsigned long current_block_start =
 				block_start_pfn(cc->migrate_pfn, cc->order);
 
 			if (last_migrated_pfn < current_block_start) {
-				cpu = get_cpu();
-				lru_add_drain_cpu(cpu);
-				drain_local_pages(cc->zone);
-				put_cpu();
+				lru_add_drain_cpu_zone(cc->zone);
 				/* No more flushing until we migrate again */
 				last_migrated_pfn = 0;
 			}
diff --git a/mm/gup.c b/mm/gup.c
index 81e4d0b377fd..a99acdc1b568 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1088,7 +1088,7 @@ retry:
 		 * potentially allocating memory.
 		 */
 		if (fatal_signal_pending(current)) {
-			ret = -ERESTARTSYS;
+			ret = -EINTR;
 			goto out;
 		}
 		cond_resched();
@@ -1218,6 +1218,10 @@ retry:
 	if (!vma_permits_fault(vma, fault_flags))
 		return -EFAULT;
 
+	if ((fault_flags & FAULT_FLAG_KILLABLE) &&
+	    fatal_signal_pending(current))
+		return -EINTR;
+
 	ret = handle_mm_fault(vma, address, fault_flags);
 	major |= ret & VM_FAULT_MAJOR;
 	if (ret & VM_FAULT_ERROR) {
@@ -1230,11 +1234,9 @@ retry:
 
 	if (ret & VM_FAULT_RETRY) {
 		down_read(&mm->mmap_sem);
-		if (!(fault_flags & FAULT_FLAG_TRIED)) {
-			*unlocked = true;
-			fault_flags |= FAULT_FLAG_TRIED;
-			goto retry;
-		}
+		*unlocked = true;
+		fault_flags |= FAULT_FLAG_TRIED;
+		goto retry;
 	}
 
 	if (tsk) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index cd459155d28a..bcabbe02192b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5365,8 +5365,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
+	pud_t *pud, pud_entry;
+	pmd_t *pmd, pmd_entry;
 
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_present(*pgd))
@@ -5376,17 +5376,19 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
-	if (sz != PUD_SIZE && pud_none(*pud))
+	pud_entry = READ_ONCE(*pud);
+	if (sz != PUD_SIZE && pud_none(pud_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pud_huge(*pud) || !pud_present(*pud))
+	if (pud_huge(pud_entry) || !pud_present(pud_entry))
 		return (pte_t *)pud;
 
 	pmd = pmd_offset(pud, addr);
-	if (sz != PMD_SIZE && pmd_none(*pmd))
+	pmd_entry = READ_ONCE(*pmd);
+	if (sz != PMD_SIZE && pmd_none(pmd_entry))
 		return NULL;
 	/* hugepage or swap? */
-	if (pmd_huge(*pmd) || !pmd_present(*pmd))
+	if (pmd_huge(pmd_entry) || !pmd_present(pmd_entry))
 		return (pte_t *)pmd;
 
 	return NULL;
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index 08b43de2383b..de3121848ddf 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -1,23 +1,28 @@
 # SPDX-License-Identifier: GPL-2.0
 KASAN_SANITIZE := n
-UBSAN_SANITIZE_common.o := n
-UBSAN_SANITIZE_generic.o := n
-UBSAN_SANITIZE_generic_report.o := n
-UBSAN_SANITIZE_tags.o := n
+UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
+# Disable ftrace to avoid recursion.
 CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_quarantine.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_tags_report.o = $(CC_FLAGS_FTRACE)
 
 # Function splitter causes unnecessary splits in __asan_load1/__asan_store1
 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
-
-CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
-CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
-CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
-CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_init.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_quarantine.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
+CFLAGS_tags_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) -DDISABLE_BRANCH_PROFILING
 
 obj-$(CONFIG_KASAN) := common.o init.o report.o
 obj-$(CONFIG_KASAN_GENERIC) += generic.o generic_report.o quarantine.o
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 56ff8885fe2e..098a7dbaced6 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -15,7 +15,6 @@
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#define DISABLE_BRANCH_PROFILING
 
 #include <linux/export.h>
 #include <linux/interrupt.h>
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index e8f37199d885..cfade6413528 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -212,8 +212,6 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
 asmlinkage void kasan_unpoison_task_stack_below(const void *watermark);
 void __asan_register_globals(struct kasan_global *globals, size_t size);
 void __asan_unregister_globals(struct kasan_global *globals, size_t size);
-void __asan_loadN(unsigned long addr, size_t size);
-void __asan_storeN(unsigned long addr, size_t size);
 void __asan_handle_no_return(void);
 void __asan_alloca_poison(unsigned long addr, size_t size);
 void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom);
@@ -228,6 +226,8 @@ void __asan_load8(unsigned long addr);
 void __asan_store8(unsigned long addr);
 void __asan_load16(unsigned long addr);
 void __asan_store16(unsigned long addr);
+void __asan_loadN(unsigned long addr, size_t size);
+void __asan_storeN(unsigned long addr, size_t size);
 
 void __asan_load1_noabort(unsigned long addr);
 void __asan_store1_noabort(unsigned long addr);
@@ -239,6 +239,21 @@ void __asan_load8_noabort(unsigned long addr);
 void __asan_store8_noabort(unsigned long addr);
 void __asan_load16_noabort(unsigned long addr);
 void __asan_store16_noabort(unsigned long addr);
+void __asan_loadN_noabort(unsigned long addr, size_t size);
+void __asan_storeN_noabort(unsigned long addr, size_t size);
+
+void __asan_report_load1_noabort(unsigned long addr);
+void __asan_report_store1_noabort(unsigned long addr);
+void __asan_report_load2_noabort(unsigned long addr);
+void __asan_report_store2_noabort(unsigned long addr);
+void __asan_report_load4_noabort(unsigned long addr);
+void __asan_report_store4_noabort(unsigned long addr);
+void __asan_report_load8_noabort(unsigned long addr);
+void __asan_report_store8_noabort(unsigned long addr);
+void __asan_report_load16_noabort(unsigned long addr);
+void __asan_report_store16_noabort(unsigned long addr);
+void __asan_report_load_n_noabort(unsigned long addr, size_t size);
+void __asan_report_store_n_noabort(unsigned long addr, size_t size);
 
 void __asan_set_shadow_00(const void *addr, size_t size);
 void __asan_set_shadow_f1(const void *addr, size_t size);
@@ -247,4 +262,19 @@ void __asan_set_shadow_f3(const void *addr, size_t size);
 void __asan_set_shadow_f5(const void *addr, size_t size);
 void __asan_set_shadow_f8(const void *addr, size_t size);
 
+void __hwasan_load1_noabort(unsigned long addr);
+void __hwasan_store1_noabort(unsigned long addr);
+void __hwasan_load2_noabort(unsigned long addr);
+void __hwasan_store2_noabort(unsigned long addr);
+void __hwasan_load4_noabort(unsigned long addr);
+void __hwasan_store4_noabort(unsigned long addr);
+void __hwasan_load8_noabort(unsigned long addr);
+void __hwasan_store8_noabort(unsigned long addr);
+void __hwasan_load16_noabort(unsigned long addr);
+void __hwasan_store16_noabort(unsigned long addr);
+void __hwasan_loadN_noabort(unsigned long addr, size_t size);
+void __hwasan_storeN_noabort(unsigned long addr, size_t size);
+
+void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size);
+
 #endif
diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c
index 25b7734e7013..8a959fdd30e3 100644
--- a/mm/kasan/tags.c
+++ b/mm/kasan/tags.c
@@ -12,7 +12,6 @@
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#define DISABLE_BRANCH_PROFILING
 
 #include <linux/export.h>
 #include <linux/interrupt.h>
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 99d77ffb79c2..cd280afb246e 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1692,6 +1692,7 @@ static void collapse_file(struct mm_struct *mm,
 		if (page_has_private(page) &&
 		    !try_to_release_page(page, GFP_KERNEL)) {
 			result = SCAN_PAGE_HAS_PRIVATE;
+			putback_lru_page(page);
 			goto out_unlock;
 		}
 
diff --git a/mm/ksm.c b/mm/ksm.c
index a558da9e7177..281c00129a2e 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2112,8 +2112,16 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 
 		down_read(&mm->mmap_sem);
 		vma = find_mergeable_vma(mm, rmap_item->address);
-		err = try_to_merge_one_page(vma, page,
-					    ZERO_PAGE(rmap_item->address));
+		if (vma) {
+			err = try_to_merge_one_page(vma, page,
+					ZERO_PAGE(rmap_item->address));
+		} else {
+			/*
+			 * If the vma is out of date, we do not need to
+			 * continue.
+			 */
+			err = 0;
+		}
 		up_read(&mm->mmap_sem);
 		/*
 		 * In case of failure, the page was not really empty, so we
diff --git a/mm/madvise.c b/mm/madvise.c
index 4bb30ed6c8d2..8cbd8c1bfe15 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -27,6 +27,7 @@
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 #include <linux/mmu_notifier.h>
+#include <linux/sched/mm.h>
 
 #include <asm/tlb.h>
 
@@ -1090,6 +1091,23 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 	if (write) {
 		if (down_write_killable(&current->mm->mmap_sem))
 			return -EINTR;
+
+		/*
+		 * We may have stolen the mm from another process
+		 * that is undergoing core dumping.
+		 *
+		 * Right now that's io_ring, in the future it may
+		 * be remote process management and not "current"
+		 * at all.
+		 *
+		 * We need to fix core dumping to not do this,
+		 * but for now we have the mmget_still_valid()
+		 * model.
+		 */
+		if (!mmget_still_valid(current->mm)) {
+			up_write(&current->mm->mmap_sem);
+			return -EINTR;
+		}
 	} else {
 		down_read(&current->mm->mmap_sem);
 	}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5beea03dd58a..a3b97f103966 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4990,19 +4990,22 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	unsigned int size;
 	int node;
 	int __maybe_unused i;
+	long error = -ENOMEM;
 
 	size = sizeof(struct mem_cgroup);
 	size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);
 
 	memcg = kzalloc(size, GFP_KERNEL);
 	if (!memcg)
-		return NULL;
+		return ERR_PTR(error);
 
 	memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
 				 1, MEM_CGROUP_ID_MAX,
 				 GFP_KERNEL);
-	if (memcg->id.id < 0)
+	if (memcg->id.id < 0) {
+		error = memcg->id.id;
 		goto fail;
+	}
 
 	memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu);
 	if (!memcg->vmstats_local)
@@ -5046,7 +5049,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 fail:
 	mem_cgroup_id_remove(memcg);
 	__mem_cgroup_free(memcg);
-	return NULL;
+	return ERR_PTR(error);
 }
 
 static struct cgroup_subsys_state * __ref
@@ -5057,8 +5060,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	long error = -ENOMEM;
 
 	memcg = mem_cgroup_alloc();
-	if (!memcg)
-		return ERR_PTR(error);
+	if (IS_ERR(memcg))
+		return ERR_CAST(memcg);
 
 	WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX);
 	memcg->soft_limit = PAGE_COUNTER_MAX;
@@ -5108,7 +5111,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 fail:
 	mem_cgroup_id_remove(memcg);
 	mem_cgroup_free(memcg);
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(error);
 }
 
 static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
diff --git a/mm/mremap.c b/mm/mremap.c
index a7e282ead438..6aa6ea605068 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -413,9 +413,20 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 			/* Always put back VM_ACCOUNT since we won't unmap */
 			vma->vm_flags |= VM_ACCOUNT;
 
-			vm_acct_memory(vma_pages(new_vma));
+			vm_acct_memory(new_len >> PAGE_SHIFT);
 		}
 
+		/*
+		 * VMAs can actually be merged back together in copy_vma
+		 * calling merge_vma. This can happen with anonymous vmas
+		 * which have not yet been faulted, so if we were to consider
+		 * this VMA split we'll end up adding VM_ACCOUNT on the
+		 * next VMA, which is completely unrelated if this VMA
+		 * was re-merged.
+		 */
+		if (split && new_vma == vma)
+			split = 0;
+
 		/* We always clear VM_LOCKED[ONFAULT] on the old vma */
 		vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
 
@@ -783,7 +794,7 @@ out:
 	if (locked && new_len > old_len)
 		mm_populate(new_addr + old_len, new_len - old_len);
 	userfaultfd_unmap_complete(mm, &uf_unmap_early);
-	mremap_userfaultfd_complete(&uf, addr, new_addr, old_len);
+	mremap_userfaultfd_complete(&uf, addr, ret, old_len);
 	userfaultfd_unmap_complete(mm, &uf_unmap);
 	return ret;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 69827d4fa052..cbf030160205 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1607,6 +1607,7 @@ void set_zone_contiguous(struct zone *zone)
 		if (!__pageblock_pfn_to_page(block_start_pfn,
 					     block_end_pfn, zone))
 			return;
+		cond_resched();
 	}
 
 	/* We confirm that there is no hole */
@@ -2400,6 +2401,14 @@ static inline void boost_watermark(struct zone *zone)
 
 	if (!watermark_boost_factor)
 		return;
+	/*
+	 * Don't bother in zones that are unlikely to produce results.
+	 * On small machines, including kdump capture kernels running
+	 * in a small area, boosting the watermark can cause an out of
+	 * memory situation immediately.
+	 */
+	if ((pageblock_nr_pages * 4) > zone_managed_pages(zone))
+		return;
 
 	max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
 			watermark_boost_factor, 10000);
@@ -5411,6 +5420,9 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			" managed:%lukB"
 			" mlocked:%lukB"
 			" kernel_stack:%lukB"
+#ifdef CONFIG_SHADOW_CALL_STACK
+			" shadow_call_stack:%lukB"
+#endif
 			" pagetables:%lukB"
 			" bounce:%lukB"
 			" free_pcp:%lukB"
@@ -5433,6 +5445,9 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			K(zone_managed_pages(zone)),
 			K(zone_page_state(zone, NR_MLOCK)),
 			zone_page_state(zone, NR_KERNEL_STACK_KB),
+#ifdef CONFIG_SHADOW_CALL_STACK
+			zone_page_state(zone, NR_KERNEL_SCS_KB),
+#endif
 			K(zone_page_state(zone, NR_PAGETABLE)),
 			K(zone_page_state(zone, NR_BOUNCE)),
 			K(free_pcp),
diff --git a/mm/percpu.c b/mm/percpu.c
index d7e3bc649f4e..7da7d7737dab 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -80,6 +80,7 @@
 #include <linux/workqueue.h>
 #include <linux/kmemleak.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -1557,10 +1558,9 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 				 gfp_t gfp)
 {
-	/* whitelisted flags that can be passed to the backing allocators */
-	gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
-	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
-	bool do_warn = !(gfp & __GFP_NOWARN);
+	gfp_t pcpu_gfp;
+	bool is_atomic;
+	bool do_warn;
 	static int warn_limit = 10;
 	struct pcpu_chunk *chunk, *next;
 	const char *err;
@@ -1569,6 +1569,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
 	void __percpu *ptr;
 	size_t bits, bit_align;
 
+	gfp = current_gfp_context(gfp);
+	/* whitelisted flags that can be passed to the backing allocators */
+	pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
+	is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
+	do_warn = !(gfp & __GFP_NOWARN);
+
 	/*
 	 * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE,
 	 * therefore alignment must be a minimum of that many bytes.
diff --git a/mm/shmem.c b/mm/shmem.c
index d722eb830317..bd8840082c94 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -952,7 +952,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 				VM_BUG_ON_PAGE(PageWriteback(page), page);
 				if (shmem_punch_compound(page, start, end))
 					truncate_inode_page(mapping, page);
-				else {
+				else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
 					/* Wipe the page and don't get stuck */
 					clear_highpage(page);
 					flush_dcache_page(page);
@@ -2179,7 +2179,11 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	int retval = -ENOMEM;
 
-	spin_lock_irq(&info->lock);
+	/*
+	 * What serializes the accesses to info->flags?
+	 * ipc_lock_object() when called from shmctl_do_lock(),
+	 * no serialization needed when called from shm_destroy().
+	 */
 	if (lock && !(info->flags & VM_LOCKED)) {
 		if (!user_shm_lock(inode->i_size, user))
 			goto out_nomem;
@@ -2194,7 +2198,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	retval = 0;
 
 out_nomem:
-	spin_unlock_irq(&info->lock);
 	return retval;
 }
 
@@ -2399,11 +2402,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 
 	lru_cache_add_anon(page);
 
-	spin_lock(&info->lock);
+	spin_lock_irq(&info->lock);
 	info->alloced++;
 	inode->i_blocks += BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
-	spin_unlock(&info->lock);
+	spin_unlock_irq(&info->lock);
 
 	inc_mm_counter(dst_mm, mm_counter_file(page));
 	page_add_file_rmap(page, false);
diff --git a/mm/slub.c b/mm/slub.c
index 332d4b459a90..b762450fc9f0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -551,15 +551,32 @@ static void print_section(char *level, char *text, u8 *addr,
 	metadata_access_disable();
 }
 
+/*
+ * See comment in calculate_sizes().
+ */
+static inline bool freeptr_outside_object(struct kmem_cache *s)
+{
+	return s->offset >= s->inuse;
+}
+
+/*
+ * Return offset of the end of info block which is inuse + free pointer if
+ * not overlapping with object.
+ */
+static inline unsigned int get_info_end(struct kmem_cache *s)
+{
+	if (freeptr_outside_object(s))
+		return s->inuse + sizeof(void *);
+	else
+		return s->inuse;
+}
+
 static struct track *get_track(struct kmem_cache *s, void *object,
 	enum track_item alloc)
 {
 	struct track *p;
 
-	if (s->offset)
-		p = object + s->offset + sizeof(void *);
-	else
-		p = object + s->inuse;
+	p = object + get_info_end(s);
 
 	return p + alloc;
 }
@@ -686,10 +703,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 		print_section(KERN_ERR, "Redzone ", p + s->object_size,
 			s->inuse - s->object_size);
 
-	if (s->offset)
-		off = s->offset + sizeof(void *);
-	else
-		off = s->inuse;
+	off = get_info_end(s);
 
 	if (s->flags & SLAB_STORE_USER)
 		off += 2 * sizeof(struct track);
@@ -782,7 +796,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
  * object address
  * 	Bytes of the object to be managed.
  * 	If the freepointer may overlay the object then the free
- * 	pointer is the first word of the object.
+ *	pointer is at the middle of the object.
  *
  * 	Poisoning uses 0x6b (POISON_FREE) and the last byte is
  * 	0xa5 (POISON_END)
@@ -816,11 +830,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
 
 static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p)
 {
-	unsigned long off = s->inuse;	/* The end of info */
-
-	if (s->offset)
-		/* Freepointer is placed after the object. */
-		off += sizeof(void *);
+	unsigned long off = get_info_end(s);	/* The end of info */
 
 	if (s->flags & SLAB_STORE_USER)
 		/* We also have user information there */
@@ -907,7 +917,7 @@ static int check_object(struct kmem_cache *s, struct page *page,
 		check_pad_bytes(s, page, p);
 	}
 
-	if (!s->offset && val == SLUB_RED_ACTIVE)
+	if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE)
 		/*
 		 * Object and freepointer overlap. Cannot check
 		 * freepointer while object is allocated.
@@ -3533,6 +3543,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 {
 	slab_flags_t flags = s->flags;
 	unsigned int size = s->object_size;
+	unsigned int freepointer_area;
 	unsigned int order;
 
 	/*
@@ -3541,6 +3552,13 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 	 * the possible location of the free pointer.
 	 */
 	size = ALIGN(size, sizeof(void *));
+	/*
+	 * This is the area of the object where a freepointer can be
+	 * safely written. If redzoning adds more to the inuse size, we
+	 * can't use that portion for writing the freepointer, so
+	 * s->offset must be limited within this for the general case.
+	 */
+	freepointer_area = size;
 
 #ifdef CONFIG_SLUB_DEBUG
 	/*
@@ -3579,16 +3597,21 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 		 *
 		 * This is the case if we do RCU, have a constructor or
 		 * destructor or are poisoning the objects.
+		 *
+		 * The assumption that s->offset >= s->inuse means free
+		 * pointer is outside of the object is used in the
+		 * freeptr_outside_object() function. If that is no
+		 * longer true, the function needs to be modified.
 		 */
 		s->offset = size;
 		size += sizeof(void *);
-	} else if (size > sizeof(void *)) {
+	} else if (freepointer_area > sizeof(void *)) {
 		/*
 		 * Store freelist pointer near middle of object to keep
 		 * it away from the edges of the object to avoid small
 		 * sized over/underflows from neighboring allocations.
 		 */
-		s->offset = ALIGN(size / 2, sizeof(void *));
+		s->offset = ALIGN(freepointer_area / 2, sizeof(void *));
 	}
 
 #ifdef CONFIG_SLUB_DEBUG
diff --git a/mm/swap.c b/mm/swap.c
index bf9a79fed62d..0ac463d44cff 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -35,6 +35,7 @@
 #include <linux/uio.h>
 #include <linux/hugetlb.h>
 #include <linux/page_idle.h>
+#include <linux/local_lock.h>
 
 #include "internal.h"
 
@@ -44,14 +45,32 @@
 /* How many pages do we try to swap or page in/out together? */
 int page_cluster;
 
-static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
-static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs);
+/* Protecting only lru_rotate.pvec which requires disabling interrupts */
+struct lru_rotate {
+	local_lock_t lock;
+	struct pagevec pvec;
+};
+static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = {
+	.lock = INIT_LOCAL_LOCK(lock),
+};
+
+/*
+ * The following struct pagevec are grouped together because they are protected
+ * by disabling preemption (and interrupts remain enabled).
+ */
+struct lru_pvecs {
+	local_lock_t lock;
+	struct pagevec lru_add;
+	struct pagevec lru_deactivate_file;
+	struct pagevec lru_deactivate;
+	struct pagevec lru_lazyfree;
 #ifdef CONFIG_SMP
-static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
+	struct pagevec activate_page;
 #endif
+};
+static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
+	.lock = INIT_LOCAL_LOCK(lock),
+};
 
 /*
  * This path almost never happens for VM activity - pages are normally
@@ -254,11 +273,11 @@ void rotate_reclaimable_page(struct page *page)
 		unsigned long flags;
 
 		get_page(page);
-		local_irq_save(flags);
-		pvec = this_cpu_ptr(&lru_rotate_pvecs);
+		local_lock_irqsave(&lru_rotate.lock, flags);
+		pvec = this_cpu_ptr(&lru_rotate.pvec);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_move_tail(pvec);
-		local_irq_restore(flags);
+		local_unlock_irqrestore(&lru_rotate.lock, flags);
 	}
 }
 
@@ -293,7 +312,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec,
 #ifdef CONFIG_SMP
 static void activate_page_drain(int cpu)
 {
-	struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);
+	struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu);
 
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, __activate_page, NULL);
@@ -301,19 +320,21 @@ static void activate_page_drain(int cpu)
 
 static bool need_activate_page_drain(int cpu)
 {
-	return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0;
+	return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0;
 }
 
 void activate_page(struct page *page)
 {
 	page = compound_head(page);
 	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
-		struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
+		struct pagevec *pvec;
 
+		local_lock(&lru_pvecs.lock);
+		pvec = this_cpu_ptr(&lru_pvecs.activate_page);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, __activate_page, NULL);
-		put_cpu_var(activate_page_pvecs);
+		local_unlock(&lru_pvecs.lock);
 	}
 }
 
@@ -335,9 +356,12 @@ void activate_page(struct page *page)
 
 static void __lru_cache_activate_page(struct page *page)
 {
-	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
+	struct pagevec *pvec;
 	int i;
 
+	local_lock(&lru_pvecs.lock);
+	pvec = this_cpu_ptr(&lru_pvecs.lru_add);
+
 	/*
 	 * Search backwards on the optimistic assumption that the page being
 	 * activated has just been added to this pagevec. Note that only
@@ -357,7 +381,7 @@ static void __lru_cache_activate_page(struct page *page)
 		}
 	}
 
-	put_cpu_var(lru_add_pvec);
+	local_unlock(&lru_pvecs.lock);
 }
 
 /*
@@ -385,7 +409,7 @@ void mark_page_accessed(struct page *page)
 	} else if (!PageActive(page)) {
 		/*
 		 * If the page is on the LRU, queue it for activation via
-		 * activate_page_pvecs. Otherwise, assume the page is on a
+		 * lru_pvecs.activate_page. Otherwise, assume the page is on a
 		 * pagevec, mark it active and it'll be moved to the active
 		 * LRU on the next drain.
 		 */
@@ -404,12 +428,14 @@ EXPORT_SYMBOL(mark_page_accessed);
 
 static void __lru_cache_add(struct page *page)
 {
-	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
+	struct pagevec *pvec;
 
+	local_lock(&lru_pvecs.lock);
+	pvec = this_cpu_ptr(&lru_pvecs.lru_add);
 	get_page(page);
 	if (!pagevec_add(pvec, page) || PageCompound(page))
 		__pagevec_lru_add(pvec);
-	put_cpu_var(lru_add_pvec);
+	local_unlock(&lru_pvecs.lock);
 }
 
 /**
@@ -593,30 +619,30 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec,
  */
 void lru_add_drain_cpu(int cpu)
 {
-	struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu);
+	struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add, cpu);
 
 	if (pagevec_count(pvec))
 		__pagevec_lru_add(pvec);
 
-	pvec = &per_cpu(lru_rotate_pvecs, cpu);
+	pvec = &per_cpu(lru_rotate.pvec, cpu);
 	if (pagevec_count(pvec)) {
 		unsigned long flags;
 
 		/* No harm done if a racing interrupt already did this */
-		local_irq_save(flags);
+		local_lock_irqsave(&lru_rotate.lock, flags);
 		pagevec_move_tail(pvec);
-		local_irq_restore(flags);
+		local_unlock_irqrestore(&lru_rotate.lock, flags);
 	}
 
-	pvec = &per_cpu(lru_deactivate_file_pvecs, cpu);
+	pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu);
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
 
-	pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+	pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu);
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
 
-	pvec = &per_cpu(lru_lazyfree_pvecs, cpu);
+	pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu);
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
 
@@ -641,11 +667,14 @@ void deactivate_file_page(struct page *page)
 		return;
 
 	if (likely(get_page_unless_zero(page))) {
-		struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
+		struct pagevec *pvec;
+
+		local_lock(&lru_pvecs.lock);
+		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
 
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
-		put_cpu_var(lru_deactivate_file_pvecs);
+		local_unlock(&lru_pvecs.lock);
 	}
 }
 
@@ -660,12 +689,14 @@ void deactivate_file_page(struct page *page)
 void deactivate_page(struct page *page)
 {
 	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
-		struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
+		struct pagevec *pvec;
 
+		local_lock(&lru_pvecs.lock);
+		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
-		put_cpu_var(lru_deactivate_pvecs);
+		local_unlock(&lru_pvecs.lock);
 	}
 }
 
@@ -680,19 +711,30 @@ void mark_page_lazyfree(struct page *page)
 {
 	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
 	    !PageSwapCache(page) && !PageUnevictable(page)) {
-		struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs);
+		struct pagevec *pvec;
 
+		local_lock(&lru_pvecs.lock);
+		pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
-		put_cpu_var(lru_lazyfree_pvecs);
+		local_unlock(&lru_pvecs.lock);
 	}
 }
 
 void lru_add_drain(void)
 {
-	lru_add_drain_cpu(get_cpu());
-	put_cpu();
+	local_lock(&lru_pvecs.lock);
+	lru_add_drain_cpu(smp_processor_id());
+	local_unlock(&lru_pvecs.lock);
+}
+
+void lru_add_drain_cpu_zone(struct zone *zone)
+{
+	local_lock(&lru_pvecs.lock);
+	lru_add_drain_cpu(smp_processor_id());
+	drain_local_pages(zone);
+	local_unlock(&lru_pvecs.lock);
 }
 
 #ifdef CONFIG_SMP
@@ -743,11 +785,11 @@ void lru_add_drain_all(void)
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
 
-		if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
-		    pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
-		    pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
-		    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
-		    pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) ||
+		if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) ||
+		    pagevec_count(&per_cpu(lru_rotate.pvec, cpu)) ||
+		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) ||
+		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) ||
+		    pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) ||
 		    need_activate_page_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			queue_work_on(cpu, mm_percpu_wq, work);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 399f219544f7..9a8227afa073 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -34,6 +34,7 @@
 #include <linux/llist.h>
 #include <linux/bitops.h>
 #include <linux/rbtree_augmented.h>
+#include <linux/overflow.h>
 
 #include <linux/uaccess.h>
 #include <asm/tlbflush.h>
@@ -3054,6 +3055,7 @@ finished:
  * @vma:		vma to cover
  * @uaddr:		target user address to start at
  * @kaddr:		virtual address of vmalloc kernel memory
+ * @pgoff:		offset from @kaddr to start at
  * @size:		size of map area
  *
  * Returns:	0 for success, -Exxx on failure
@@ -3066,9 +3068,15 @@ finished:
  * Similar to remap_pfn_range() (see mm/memory.c)
  */
 int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
-				void *kaddr, unsigned long size)
+				void *kaddr, unsigned long pgoff,
+				unsigned long size)
 {
 	struct vm_struct *area;
+	unsigned long off;
+	unsigned long end_index;
+
+	if (check_shl_overflow(pgoff, PAGE_SHIFT, &off))
+		return -EINVAL;
 
 	size = PAGE_ALIGN(size);
 
@@ -3082,8 +3090,10 @@ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
 	if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT)))
 		return -EINVAL;
 
-	if (kaddr + size > area->addr + get_vm_area_size(area))
+	if (check_add_overflow(size, off, &end_index) ||
+	    end_index > get_vm_area_size(area))
 		return -EINVAL;
+	kaddr += off;
 
 	do {
 		struct page *page = vmalloc_to_page(kaddr);
@@ -3122,7 +3132,7 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 						unsigned long pgoff)
 {
 	return remap_vmalloc_range_partial(vma, vma->vm_start,
-					   addr + (pgoff << PAGE_SHIFT),
+					   addr, pgoff,
 					   vma->vm_end - vma->vm_start);
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b06868fc4926..a37c87b5aee2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1625,7 +1625,6 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
  * @dst:	The temp list to put pages on to.
  * @nr_scanned:	The number of pages that were scanned.
  * @sc:		The scan_control struct for this reclaim session
- * @mode:	One of the LRU isolation modes
  * @lru:	LRU list id for isolating
  *
  * returns how many pages were moved onto *@dst.
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 96d21a792b57..2435d2c24657 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1119,6 +1119,9 @@ const char * const vmstat_text[] = {
 	"nr_mlock",
 	"nr_page_table_pages",
 	"nr_kernel_stack",
+#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
+	"nr_shadow_call_stack",
+#endif
 	"nr_bounce",
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	"nr_zspages",
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 42f31c4b53ad..460b0feced26 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -43,6 +43,7 @@
 #include <linux/spinlock.h>
 #include <linux/zpool.h>
 #include <linux/magic.h>
+#include <linux/kmemleak.h>
 
 /*
  * NCHUNKS_ORDER determines the internal allocation granularity, effectively
@@ -215,6 +216,8 @@ static inline struct z3fold_buddy_slots *alloc_slots(struct z3fold_pool *pool,
 				 (gfp & ~(__GFP_HIGHMEM | __GFP_MOVABLE)));
 
 	if (slots) {
+		/* It will be freed separately in free_handle(). */
+		kmemleak_not_leak(slots);
 		memset(slots->slot, 0, sizeof(slots->slot));
 		slots->pool = (unsigned long)pool;
 		rwlock_init(&slots->lock);
@@ -318,16 +321,16 @@ static inline void free_handle(unsigned long handle)
 	slots = handle_to_slots(handle);
 	write_lock(&slots->lock);
 	*(unsigned long *)handle = 0;
-	write_unlock(&slots->lock);
-	if (zhdr->slots == slots)
+	if (zhdr->slots == slots) {
+		write_unlock(&slots->lock);
 		return; /* simple case, nothing else to do */
+	}
 
 	/* we are freeing a foreign handle if we are here */
 	zhdr->foreign_handles--;
 	is_free = true;
-	read_lock(&slots->lock);
 	if (!test_bit(HANDLES_ORPHANED, &slots->pool)) {
-		read_unlock(&slots->lock);
+		write_unlock(&slots->lock);
 		return;
 	}
 	for (i = 0; i <= BUDDY_MASK; i++) {
@@ -336,7 +339,7 @@ static inline void free_handle(unsigned long handle)
 			break;
 		}
 	}
-	read_unlock(&slots->lock);
+	write_unlock(&slots->lock);
 
 	if (is_free) {
 		struct z3fold_pool *pool = slots_to_pool(slots);
@@ -422,6 +425,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page, bool headless,
 	zhdr->start_middle = 0;
 	zhdr->cpu = -1;
 	zhdr->foreign_handles = 0;
+	zhdr->mapped_count = 0;
 	zhdr->slots = slots;
 	zhdr->pool = pool;
 	INIT_LIST_HEAD(&zhdr->buddy);
diff --git a/net/atm/common.c b/net/atm/common.c
index 0ce530af534d..8575f5d52087 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -177,18 +177,18 @@ static void vcc_destroy_socket(struct sock *sk)
 
 	set_bit(ATM_VF_CLOSE, &vcc->flags);
 	clear_bit(ATM_VF_READY, &vcc->flags);
-	if (vcc->dev) {
-		if (vcc->dev->ops->close)
-			vcc->dev->ops->close(vcc);
-		if (vcc->push)
-			vcc->push(vcc, NULL); /* atmarpd has no push */
-		module_put(vcc->owner);
-
-		while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
-			atm_return(vcc, skb->truesize);
-			kfree_skb(skb);
-		}
+	if (vcc->dev && vcc->dev->ops->close)
+		vcc->dev->ops->close(vcc);
+	if (vcc->push)
+		vcc->push(vcc, NULL); /* atmarpd has no push */
+	module_put(vcc->owner);
+
+	while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
+		atm_return(vcc, skb->truesize);
+		kfree_skb(skb);
+	}
 
+	if (vcc->dev && vcc->dev->ops->owner) {
 		module_put(vcc->dev->ops->owner);
 		atm_dev_put(vcc->dev);
 	}
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 25fa3a7b72bd..ca37f5a71f5e 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -1264,6 +1264,12 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry)
 		entry->vcc = NULL;
 	}
 	if (entry->recv_vcc) {
+		struct atm_vcc *vcc = entry->recv_vcc;
+		struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc);
+
+		kfree(vpriv);
+		vcc->user_back = NULL;
+
 		entry->recv_vcc->push = entry->old_recv_push;
 		vcc_release_async(entry->recv_vcc, -EPIPE);
 		entry->recv_vcc = NULL;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index ff57ea89c27e..fd91cd34f25e 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -635,8 +635,10 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_BINDTODEVICE:
-		if (optlen > IFNAMSIZ)
-			optlen = IFNAMSIZ;
+		if (optlen > IFNAMSIZ - 1)
+			optlen = IFNAMSIZ - 1;
+
+		memset(devname, 0, sizeof(devname));
 
 		if (copy_from_user(devname, optval, optlen)) {
 			res = -EFAULT;
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 969466218999..80b87b1f4e3a 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -893,7 +893,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset,
 
 	orig_node = batadv_v_ogm_orig_get(bat_priv, ogm_packet->orig);
 	if (!orig_node)
-		return;
+		goto out;
 
 	neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming,
 						     ethhdr->h_source);
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 8f0717c3f7b5..b0469d15da0e 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -1009,15 +1009,8 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv,
  */
 static u8 batadv_nc_random_weight_tq(u8 tq)
 {
-	u8 rand_val, rand_tq;
-
-	get_random_bytes(&rand_val, sizeof(rand_val));
-
 	/* randomize the estimated packet loss (max TQ - estimated TQ) */
-	rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq);
-
-	/* normalize the randomized packet loss */
-	rand_tq /= BATADV_TQ_MAX_VALUE;
+	u8 rand_tq = prandom_u32_max(BATADV_TQ_MAX_VALUE + 1 - tq);
 
 	/* convert to (randomized) estimated tq again */
 	return BATADV_TQ_MAX_VALUE - rand_tq;
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index c45962d8527b..0f962dcd239e 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -1150,7 +1150,7 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj,
 	ret = batadv_parse_throughput(net_dev, buff, "throughput_override",
 				      &tp_override);
 	if (!ret)
-		return count;
+		goto out;
 
 	old_tp_override = atomic_read(&hard_iface->bat_v.throughput_override);
 	if (old_tp_override == tp_override)
@@ -1190,6 +1190,7 @@ static ssize_t batadv_show_throughput_override(struct kobject *kobj,
 
 	tp_override = atomic_read(&hard_iface->bat_v.throughput_override);
 
+	batadv_hardif_put(hard_iface);
 	return sprintf(buff, "%u.%u MBit\n", tp_override / 10,
 		       tp_override % 10);
 }
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 1476a91ce935..d022f126eb02 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -170,7 +170,6 @@ static int aes_cmac(struct crypto_shash *tfm, const u8 k[16], const u8 *m,
 		    size_t len, u8 mac[16])
 {
 	uint8_t tmp[16], mac_msb[16], msg_msb[CMAC_MSG_MAX];
-	SHASH_DESC_ON_STACK(desc, tfm);
 	int err;
 
 	if (len > CMAC_MSG_MAX)
@@ -181,8 +180,6 @@ static int aes_cmac(struct crypto_shash *tfm, const u8 k[16], const u8 *m,
 		return -EINVAL;
 	}
 
-	desc->tfm = tfm;
-
 	/* Swap key and message from LSB to MSB */
 	swap_buf(k, tmp, 16);
 	swap_buf(m, msg_msb, len);
@@ -196,8 +193,7 @@ static int aes_cmac(struct crypto_shash *tfm, const u8 k[16], const u8 *m,
 		return err;
 	}
 
-	err = crypto_shash_digest(desc, msg_msb, len, mac_msb);
-	shash_desc_zero(desc);
+	err = crypto_shash_tfm_digest(tfm, msg_msb, len, mac_msb);
 	if (err) {
 		BT_ERR("Hash computation error %d", err);
 		return err;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ad12fe3fca8c..83490bf73a13 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -2413,7 +2413,8 @@ void br_multicast_uninit_stats(struct net_bridge *br)
 	free_percpu(br->mcast_stats);
 }
 
-static void mcast_stats_add_dir(u64 *dst, u64 *src)
+/* noinline for https://bugs.llvm.org/show_bug.cgi?id=45802#c9 */
+static noinline_for_stack void mcast_stats_add_dir(u64 *dst, u64 *src)
 {
 	dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX];
 	dst[BR_MCAST_DIR_TX] += src[BR_MCAST_DIR_TX];
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 43dab4066f91..a0f5dbee8f9c 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -612,6 +612,7 @@ int br_process_vlan_info(struct net_bridge *br,
 					       v - 1, rtm_cmd);
 				v_change_start = 0;
 			}
+			cond_resched();
 		}
 		/* v_change_start is set only if the last/whole range changed */
 		if (v_change_start)
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index b325b569e761..f48cf4cfb80f 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -31,6 +31,12 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
 	ether_addr_copy(eth->h_dest, eth_hdr(oldskb)->h_source);
 	eth->h_proto = eth_hdr(oldskb)->h_proto;
 	skb_pull(nskb, ETH_HLEN);
+
+	if (skb_vlan_tag_present(oldskb)) {
+		u16 vid = skb_vlan_tag_get(oldskb);
+
+		__vlan_hwaccel_put_tag(nskb, oldskb->vlan_proto, vid);
+	}
 }
 
 static int nft_bridge_iphdr_validate(struct sk_buff *skb)
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 998e26b75a78..1d4973f8cd7a 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -3649,7 +3649,9 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
 		 * supported.
 		 */
 		req->r_t.target_oloc.pool = m.redirect.oloc.pool;
-		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED;
+		req->r_flags |= CEPH_OSD_FLAG_REDIRECTED |
+				CEPH_OSD_FLAG_IGNORE_OVERLAY |
+				CEPH_OSD_FLAG_IGNORE_CACHE;
 		req->r_tid = 0;
 		__submit_request(req, false);
 		goto out_unlock_osdc;
diff --git a/net/core/dev.c b/net/core/dev.c
index 9c9e763bfe0e..2d8aceee4284 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4140,7 +4140,8 @@ EXPORT_SYMBOL(netdev_max_backlog);
 
 int netdev_tstamp_prequeue __read_mostly = 1;
 int netdev_budget __read_mostly = 300;
-unsigned int __read_mostly netdev_budget_usecs = 2000;
+/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */
+unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ;
 int weight_p __read_mostly = 64;           /* old backlog weight */
 int dev_weight_rx_bias __read_mostly = 1;  /* bias for backlog weight */
 int dev_weight_tx_bias __read_mostly = 1;  /* bias for output_queue quota */
@@ -4987,11 +4988,12 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
 	return 0;
 }
 
-static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
+static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 				    struct packet_type **ppt_prev)
 {
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
+	struct sk_buff *skb = *pskb;
 	struct net_device *orig_dev;
 	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
@@ -5022,8 +5024,10 @@ another_round:
 		ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
 		preempt_enable();
 
-		if (ret2 != XDP_PASS)
-			return NET_RX_DROP;
+		if (ret2 != XDP_PASS) {
+			ret = NET_RX_DROP;
+			goto out;
+		}
 		skb_reset_mac_len(skb);
 	}
 
@@ -5173,6 +5177,13 @@ drop:
 	}
 
 out:
+	/* The invariant here is that if *ppt_prev is not NULL
+	 * then skb should also be non-NULL.
+	 *
+	 * Apparently *ppt_prev assignment above holds this invariant due to
+	 * skb dereferencing near it.
+	 */
+	*pskb = skb;
 	return ret;
 }
 
@@ -5182,7 +5193,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc)
 	struct packet_type *pt_prev = NULL;
 	int ret;
 
-	ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+	ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
 	if (pt_prev)
 		ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb,
 					 skb->dev, pt_prev, orig_dev);
@@ -5260,7 +5271,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
 		struct packet_type *pt_prev = NULL;
 
 		skb_list_del_init(skb);
-		__netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+		__netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
 		if (!pt_prev)
 			continue;
 		if (pt_curr != pt_prev || od_curr != orig_dev) {
@@ -8666,8 +8677,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 	const struct net_device_ops *ops = dev->netdev_ops;
 	enum bpf_netdev_command query;
 	u32 prog_id, expected_id = 0;
-	struct bpf_prog *prog = NULL;
 	bpf_op_t bpf_op, bpf_chk;
+	struct bpf_prog *prog;
 	bool offload;
 	int err;
 
@@ -8733,6 +8744,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 	} else {
 		if (!prog_id)
 			return 0;
+		prog = NULL;
 	}
 
 	err = dev_xdp_install(dev, bpf_op, extack, flags, prog);
@@ -8905,11 +8917,13 @@ static void netdev_sync_lower_features(struct net_device *upper,
 			netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
 				   &feature, lower->name);
 			lower->wanted_features &= ~feature;
-			netdev_update_features(lower);
+			__netdev_update_features(lower);
 
 			if (unlikely(lower->features & feature))
 				netdev_WARN(upper, "failed to disable %pNF on %s!\n",
 					    &feature, lower->name);
+			else
+				netdev_features_change(lower);
 		}
 	}
 }
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 80f97722f31f..899edcee7dab 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4283,6 +4283,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
 		end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
 		dump = false;
+
+		if (start_offset == end_offset) {
+			err = 0;
+			goto nla_put_failure;
+		}
 	}
 
 	err = devlink_nl_region_read_snapshot_fill(skb, devlink,
@@ -5363,6 +5368,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
 {
 	enum devlink_health_reporter_state prev_health_state;
 	struct devlink *devlink = reporter->devlink;
+	unsigned long recover_ts_threshold;
 
 	/* write a log message of the current error */
 	WARN_ON(!msg);
@@ -5373,10 +5379,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
 	devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
 
 	/* abort if the previous error wasn't recovered */
+	recover_ts_threshold = reporter->last_recovery_ts +
+			       msecs_to_jiffies(reporter->graceful_period);
 	if (reporter->auto_recover &&
 	    (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY ||
-	     jiffies - reporter->last_recovery_ts <
-	     msecs_to_jiffies(reporter->graceful_period))) {
+	     (reporter->last_recovery_ts && reporter->recovery_count &&
+	      time_is_after_jiffies(recover_ts_threshold)))) {
 		trace_devlink_health_recover_aborted(devlink,
 						     reporter->ops->name,
 						     reporter->health_state,
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 8e33cec9fc4e..2ee7bc4c9e03 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -213,6 +213,7 @@ static void sched_send_work(struct timer_list *t)
 static void trace_drop_common(struct sk_buff *skb, void *location)
 {
 	struct net_dm_alert_msg *msg;
+	struct net_dm_drop_point *point;
 	struct nlmsghdr *nlh;
 	struct nlattr *nla;
 	int i;
@@ -231,11 +232,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	nlh = (struct nlmsghdr *)dskb->data;
 	nla = genlmsg_data(nlmsg_data(nlh));
 	msg = nla_data(nla);
+	point = msg->points;
 	for (i = 0; i < msg->entries; i++) {
-		if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
-			msg->points[i].count++;
+		if (!memcmp(&location, &point->pc, sizeof(void *))) {
+			point->count++;
 			goto out;
 		}
+		point++;
 	}
 	if (msg->entries == dm_hit_limit)
 		goto out;
@@ -244,8 +247,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	 */
 	__nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point));
 	nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
-	memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
-	msg->points[msg->entries].count = 1;
+	memcpy(point->pc, &location, sizeof(void *));
+	point->count = 1;
 	msg->entries++;
 
 	if (!timer_pending(&data->send_timer)) {
diff --git a/net/core/filter.c b/net/core/filter.c
index 7628b947dbc3..5cc9276f1023 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2590,8 +2590,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
 			}
 			pop = 0;
 		} else if (pop >= sge->length - a) {
-			sge->length = a;
 			pop -= (sge->length - a);
+			sge->length = a;
 		}
 	}
 
@@ -5925,7 +5925,7 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
 		return -EOPNOTSUPP;
 	if (unlikely(dev_net(skb->dev) != sock_net(sk)))
 		return -ENETUNREACH;
-	if (unlikely(sk->sk_reuseport))
+	if (unlikely(sk_fullsock(sk) && sk->sk_reuseport))
 		return -ESOCKTNOSUPPORT;
 	if (sk_is_refcounted(sk) &&
 	    unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 3eff84824c8b..5dceed467f64 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -160,12 +160,10 @@ out:
 	return ret;
 }
 
-int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
+static int flow_dissector_bpf_prog_detach(struct net *net)
 {
 	struct bpf_prog *attached;
-	struct net *net;
 
-	net = current->nsproxy->net_ns;
 	mutex_lock(&flow_dissector_mutex);
 	attached = rcu_dereference_protected(net->flow_dissector_prog,
 					     lockdep_is_held(&flow_dissector_mutex));
@@ -179,6 +177,24 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
 	return 0;
 }
 
+int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
+{
+	return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns);
+}
+
+static void __net_exit flow_dissector_pernet_pre_exit(struct net *net)
+{
+	/* We're not racing with attach/detach because there are no
+	 * references to netns left when pre_exit gets called.
+	 */
+	if (rcu_access_pointer(net->flow_dissector_prog))
+		flow_dissector_bpf_prog_detach(net);
+}
+
+static struct pernet_operations flow_dissector_pernet_ops __net_initdata = {
+	.pre_exit = flow_dissector_pernet_pre_exit,
+};
+
 /**
  * __skb_flow_get_ports - extract the upper layer ports and return them
  * @skb: sk_buff to extract the ports from
@@ -1836,7 +1852,7 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_basic_dissector,
 				flow_keys_basic_dissector_keys,
 				ARRAY_SIZE(flow_keys_basic_dissector_keys));
-	return 0;
-}
 
+	return register_pernet_subsys(&flow_dissector_pernet_ops);
+}
 core_initcall(init_default_flow_dissectors);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 39d37d0ef575..dbe0c6ead773 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1082,8 +1082,8 @@ static void neigh_timer_handler(struct timer_list *t)
 	}
 
 	if (neigh->nud_state & NUD_IN_TIMER) {
-		if (time_before(next, jiffies + HZ/2))
-			next = jiffies + HZ/2;
+		if (time_before(next, jiffies + HZ/100))
+			next = jiffies + HZ/100;
 		if (!mod_timer(&neigh->timer, next))
 			neigh_hold(neigh);
 	}
@@ -1956,6 +1956,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 				   NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
 	}
 
+	if (protocol)
+		neigh->protocol = protocol;
+
 	if (ndm->ndm_flags & NTF_EXT_LEARNED)
 		flags |= NEIGH_UPDATE_F_EXT_LEARNED;
 
@@ -1969,9 +1972,6 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
 				     NETLINK_CB(skb).portid, extack);
 
-	if (protocol)
-		neigh->protocol = protocol;
-
 	neigh_release(neigh);
 
 out:
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index cf0215734ceb..4773ad6ec111 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -80,7 +80,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
 	struct net_device *netdev = to_net_dev(dev);
 	struct net *net = dev_net(netdev);
 	unsigned long new;
-	int ret = -EINVAL;
+	int ret;
 
 	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index b4c87fe31be2..41b24cd31562 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -127,10 +127,8 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
 	cs->classid = (u32)value;
 
 	css_task_iter_start(css, 0, &it);
-	while ((p = css_task_iter_next(&it))) {
+	while ((p = css_task_iter_next(&it)))
 		update_classid_task(p, cs->classid);
-		cond_resched();
-	}
 	css_task_iter_end(&it);
 
 	return 0;
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 8881dd943dd0..9bd4cab7d510 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -236,6 +236,8 @@ static void net_prio_attach(struct cgroup_taskset *tset)
 	struct task_struct *p;
 	struct cgroup_subsys_state *css;
 
+	cgroup_sk_alloc_disable();
+
 	cgroup_taskset_for_each(p, css, tset) {
 		void *v = (void *)(unsigned long)css->id;
 
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 7b6b1d2c3d10..b5bc680d4755 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -5,7 +5,6 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/cryptohash.h>
 #include <linux/module.h>
 #include <linux/cache.h>
 #include <linux/random.h>
diff --git a/net/core/sock.c b/net/core/sock.c
index ce1d8dce9b7a..b714162213ae 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1872,7 +1872,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 * as not suitable for copying when cloning.
 		 */
 		if (sk_user_data_is_nocopy(newsk))
-			RCU_INIT_POINTER(newsk->sk_user_data, NULL);
+			newsk->sk_user_data = NULL;
 
 		newsk->sk_err	   = 0;
 		newsk->sk_err_soft = 0;
@@ -2364,7 +2364,6 @@ static void sk_leave_memory_pressure(struct sock *sk)
 	}
 }
 
-/* On 32bit arches, an skb frag is limited to 2^15 */
 #define SKB_FRAG_PAGE_ORDER	get_order(32768)
 DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 9a271a58a41d..d90665b465b8 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -459,7 +459,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
 	list_for_each_entry(dp, &dst->ports, list) {
 		err = dsa_port_setup(dp);
 		if (err)
-			goto teardown;
+			continue;
 	}
 
 	return 0;
diff --git a/net/dsa/master.c b/net/dsa/master.c
index b5c535af63a3..a621367c6e8c 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -289,7 +289,8 @@ static void dsa_master_ndo_teardown(struct net_device *dev)
 {
 	struct dsa_port *cpu_dp = dev->dsa_ptr;
 
-	dev->netdev_ops = cpu_dp->orig_ndo_ops;
+	if (cpu_dp->orig_ndo_ops)
+		dev->netdev_ops = cpu_dp->orig_ndo_ops;
 	cpu_dp->orig_ndo_ops = NULL;
 }
 
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 231b2d494f1c..a58fdd362574 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -670,11 +670,16 @@ int dsa_port_link_register_of(struct dsa_port *dp)
 {
 	struct dsa_switch *ds = dp->ds;
 	struct device_node *phy_np;
+	int port = dp->index;
 
 	if (!ds->ops->adjust_link) {
 		phy_np = of_parse_phandle(dp->dn, "phy-handle", 0);
-		if (of_phy_is_fixed_link(dp->dn) || phy_np)
+		if (of_phy_is_fixed_link(dp->dn) || phy_np) {
+			if (ds->ops->phylink_mac_link_down)
+				ds->ops->phylink_mac_link_down(ds, port,
+					MLO_AN_FIXED, PHY_INTERFACE_MODE_NA);
 			return dsa_port_phylink_register(dp);
+		}
 		return 0;
 	}
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index e94eb1aac602..d3bcb9afa795 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -856,20 +856,18 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev,
 	struct dsa_port *to_dp;
 	int err;
 
-	act = &cls->rule->action.entries[0];
-
 	if (!ds->ops->port_mirror_add)
 		return -EOPNOTSUPP;
 
-	if (!act->dev)
-		return -EINVAL;
-
 	if (!flow_action_basic_hw_stats_check(&cls->rule->action,
 					      cls->common.extack))
 		return -EOPNOTSUPP;
 
 	act = &cls->rule->action.entries[0];
 
+	if (!act->dev)
+		return -EINVAL;
+
 	if (!dsa_slave_dev_check(act->dev))
 		return -EOPNOTSUPP;
 
@@ -1738,6 +1736,7 @@ int dsa_slave_create(struct dsa_port *port)
 	if (ds->ops->port_vlan_add && ds->ops->port_vlan_del)
 		slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	slave_dev->hw_features |= NETIF_F_HW_TC;
+	slave_dev->features |= NETIF_F_LLTX;
 	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
 	if (!IS_ERR_OR_NULL(port->mac))
 		ether_addr_copy(slave_dev->dev_addr, port->mac);
@@ -1770,11 +1769,9 @@ int dsa_slave_create(struct dsa_port *port)
 	rtnl_lock();
 	ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN);
 	rtnl_unlock();
-	if (ret && ret != -EOPNOTSUPP) {
-		dev_err(ds->dev, "error %d setting MTU on port %d\n",
-			ret, port->index);
-		goto out_free;
-	}
+	if (ret)
+		dev_warn(ds->dev, "nonfatal error %d setting MTU on port %d\n",
+			 ret, port->index);
 
 	netif_carrier_off(slave_dev);
 
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index b5705cba8318..d6619edd53e5 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -15,6 +15,7 @@
 #define MTK_HDR_XMIT_TAGGED_TPID_8100	1
 #define MTK_HDR_RECV_SOURCE_PORT_MASK	GENMASK(2, 0)
 #define MTK_HDR_XMIT_DP_BIT_MASK	GENMASK(5, 0)
+#define MTK_HDR_XMIT_SA_DIS		BIT(6)
 
 static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
@@ -22,6 +23,9 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *mtk_tag;
 	bool is_vlan_skb = true;
+	unsigned char *dest = eth_hdr(skb)->h_dest;
+	bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+				!is_broadcast_ether_addr(dest);
 
 	/* Build the special tag after the MAC Source Address. If VLAN header
 	 * is present, it's required that VLAN header and special tag is
@@ -47,6 +51,10 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 		     MTK_HDR_XMIT_UNTAGGED;
 	mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
 
+	/* Disable SA learning for multicast frames */
+	if (unlikely(is_multicast_skb))
+		mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS;
+
 	/* Tag control information is kept for 802.1Q */
 	if (!is_vlan_skb) {
 		mtk_tag[2] = 0;
@@ -61,6 +69,9 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	int port;
 	__be16 *phdr, hdr;
+	unsigned char *dest = eth_hdr(skb)->h_dest;
+	bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+				!is_broadcast_ether_addr(dest);
 
 	if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN)))
 		return NULL;
@@ -86,6 +97,10 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb->dev)
 		return NULL;
 
+	/* Only unicast or broadcast frames are offloaded */
+	if (likely(!is_multicast_skb))
+		skb->offload_fwd_mark = 1;
+
 	return skb;
 }
 
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 0c772318c023..ed5357210193 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -342,7 +342,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 	ret = ops->reply_size(req_info, reply_data);
 	if (ret < 0)
 		goto err_cleanup;
-	reply_len = ret;
+	reply_len = ret + ethnl_reply_header_size();
 	ret = -ENOMEM;
 	rskb = ethnl_reply_init(reply_len, req_info->dev, ops->reply_cmd,
 				ops->hdr_attr, info, &reply_payload);
@@ -588,7 +588,7 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
 	ret = ops->reply_size(req_info, reply_data);
 	if (ret < 0)
 		goto err_cleanup;
-	reply_len = ret;
+	reply_len = ret + ethnl_reply_header_size();
 	ret = -ENOMEM;
 	skb = genlmsg_new(reply_len, GFP_KERNEL);
 	if (!skb)
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 95eae5c68a52..0eed4e4909ab 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -324,7 +324,6 @@ static int strset_reply_size(const struct ethnl_req_info *req_base,
 	int len = 0;
 	int ret;
 
-	len += ethnl_reply_header_size();
 	for (i = 0; i < ETH_SS_COUNT; i++) {
 		const struct strset_info *set_info = &data->sets[i];
 
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 5465a395da04..1decb25f6764 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -69,10 +69,16 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev,
 	else
 		multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]);
 
-	if (!data[IFLA_HSR_VERSION])
+	if (!data[IFLA_HSR_VERSION]) {
 		hsr_version = 0;
-	else
+	} else {
 		hsr_version = nla_get_u8(data[IFLA_HSR_VERSION]);
+		if (hsr_version > 1) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only versions 0..1 are supported");
+			return -EINVAL;
+		}
+	}
 
 	return hsr_dev_finalize(dev, link, multicast_spec, hsr_version, extack);
 }
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index f4b9f7a3ce51..25b6ffba26cd 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -18,7 +18,7 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
 {
 	struct sk_buff *skb = *pskb;
 	struct hsr_port *port;
-	u16 protocol;
+	__be16 protocol;
 
 	if (!skb_mac_header_was_set(skb)) {
 		WARN_ONCE(1, "%s: skb invalid", __func__);
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 0bd10a1f477f..a23094b050f8 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
@@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 30fa42f5997d..5267b6b191eb 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -276,6 +276,7 @@ static struct in_device *inetdev_init(struct net_device *dev)
 	err = devinet_sysctl_register(in_dev);
 	if (err) {
 		in_dev->dead = 1;
+		neigh_parms_release(&arp_tbl, in_dev->arp_parms);
 		in_dev_put(in_dev);
 		in_dev = NULL;
 		goto out;
@@ -614,12 +615,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
 	return NULL;
 }
 
-static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
+static int ip_mc_autojoin_config(struct net *net, bool join,
+				 const struct in_ifaddr *ifa)
 {
+#if defined(CONFIG_IP_MULTICAST)
 	struct ip_mreqn mreq = {
 		.imr_multiaddr.s_addr = ifa->ifa_address,
 		.imr_ifindex = ifa->ifa_dev->dev->ifindex,
 	};
+	struct sock *sk = net->ipv4.mc_autojoin_sk;
 	int ret;
 
 	ASSERT_RTNL();
@@ -632,6 +636,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
 	release_sock(sk);
 
 	return ret;
+#else
+	return -EOPNOTSUPP;
+#endif
 }
 
 static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -675,7 +682,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			continue;
 
 		if (ipv4_is_multicast(ifa->ifa_address))
-			ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa);
+			ip_mc_autojoin_config(net, false, ifa);
 		__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
 		return 0;
 	}
@@ -940,8 +947,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		 */
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
 		if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) {
-			int ret = ip_mc_config(net->ipv4.mc_autojoin_sk,
-					       true, ifa);
+			int ret = ip_mc_autojoin_config(net, true, ifa);
 
 			if (ret < 0) {
 				inet_free_ifa(ifa);
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 731022cff600..d14133eac476 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -63,10 +63,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 		sp->olen++;
 
 		xo = xfrm_offload(skb);
-		if (!xo) {
-			xfrm_state_put(x);
+		if (!xo)
 			goto out_reset;
-		}
 	}
 
 	xo->flags |= XFRM_GRO;
@@ -139,19 +137,27 @@ static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x,
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
-	int proto = xo->proto;
+	u8 proto = xo->proto;
 
 	skb->transport_header += x->props.header_len;
 
-	if (proto == IPPROTO_BEETPH) {
-		struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data;
+	if (x->sel.family != AF_INET6) {
+		if (proto == IPPROTO_BEETPH) {
+			struct ip_beet_phdr *ph =
+				(struct ip_beet_phdr *)skb->data;
+
+			skb->transport_header += ph->hdrlen * 8;
+			proto = ph->nexthdr;
+		} else {
+			skb->transport_header -= IPV4_BEET_PHMAXLEN;
+		}
+	} else {
+		__be16 frag;
 
-		skb->transport_header += ph->hdrlen * 8;
-		proto = ph->nexthdr;
-	} else if (x->sel.family != AF_INET6) {
-		skb->transport_header -= IPV4_BEET_PHMAXLEN;
-	} else if (proto == IPPROTO_TCP) {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
+		skb->transport_header +=
+			ipv6_skip_exthdr(skb, 0, &proto, &frag);
+		if (proto == IPPROTO_TCP)
+			skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
 	}
 
 	__skb_pull(skb, skb_transport_offset(skb));
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 213be9c050ad..41079490a118 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -309,17 +309,18 @@ bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev)
 {
 	bool dev_match = false;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	int ret;
+	if (unlikely(fi->nh)) {
+		dev_match = nexthop_uses_dev(fi->nh, dev);
+	} else {
+		int ret;
 
-	for (ret = 0; ret < fib_info_num_path(fi); ret++) {
-		const struct fib_nh_common *nhc = fib_info_nhc(fi, ret);
+		for (ret = 0; ret < fib_info_num_path(fi); ret++) {
+			const struct fib_nh_common *nhc = fib_info_nhc(fi, ret);
 
-		if (nhc->nhc_dev == dev) {
-			dev_match = true;
-			break;
-		} else if (l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) {
-			dev_match = true;
-			break;
+			if (nhc_l3mdev_matches_dev(nhc, dev)) {
+				dev_match = true;
+				break;
+			}
 		}
 	}
 #else
@@ -918,7 +919,6 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 	else
 		filter->dump_exceptions = false;
 
-	filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC);
 	filter->flags    = rtm->rtm_flags;
 	filter->protocol = rtm->rtm_protocol;
 	filter->rt_type  = rtm->rtm_type;
@@ -990,7 +990,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (filter.table_id) {
 		tb = fib_get_table(net, filter.table_id);
 		if (!tb) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != PF_INET)
 				return skb->len;
 
 			NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 6ed8c9317179..55ca2e521828 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -2014,7 +2014,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 
 	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
-		struct fib_nh *nh;
+		struct fib_nh_common *nhc;
 
 		if (fa->fa_slen != slen)
 			continue;
@@ -2037,8 +2037,8 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 		    fa->fa_type != RTN_UNICAST)
 			continue;
 
-		nh = fib_info_nh(next_fi, 0);
-		if (!nh->fib_nh_gw4 || nh->fib_nh_scope != RT_SCOPE_LINK)
+		nhc = fib_info_nhc(next_fi, 0);
+		if (!nhc->nhc_gw_family || nhc->nhc_scope != RT_SCOPE_LINK)
 			continue;
 
 		fib_alias_accessed(fa);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 4f334b425538..248f1c1959a6 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1371,6 +1371,26 @@ static inline t_key prefix_mismatch(t_key key, struct key_vector *n)
 	return (key ^ prefix) & (prefix | -prefix);
 }
 
+bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags,
+			 const struct flowi4 *flp)
+{
+	if (nhc->nhc_flags & RTNH_F_DEAD)
+		return false;
+
+	if (ip_ignore_linkdown(nhc->nhc_dev) &&
+	    nhc->nhc_flags & RTNH_F_LINKDOWN &&
+	    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
+		return false;
+
+	if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
+		if (flp->flowi4_oif &&
+		    flp->flowi4_oif != nhc->nhc_oif)
+			return false;
+	}
+
+	return true;
+}
+
 /* should be called with rcu_read_lock */
 int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		     struct fib_result *res, int fib_flags)
@@ -1503,6 +1523,7 @@ found:
 	/* Step 3: Process the leaf, if that fails fall back to backtracing */
 	hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) {
 		struct fib_info *fi = fa->fa_info;
+		struct fib_nh_common *nhc;
 		int nhsel, err;
 
 		if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) {
@@ -1528,26 +1549,25 @@ out_reject:
 		if (fi->fib_flags & RTNH_F_DEAD)
 			continue;
 
-		if (unlikely(fi->nh && nexthop_is_blackhole(fi->nh))) {
-			err = fib_props[RTN_BLACKHOLE].error;
-			goto out_reject;
+		if (unlikely(fi->nh)) {
+			if (nexthop_is_blackhole(fi->nh)) {
+				err = fib_props[RTN_BLACKHOLE].error;
+				goto out_reject;
+			}
+
+			nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp,
+						     &nhsel);
+			if (nhc)
+				goto set_result;
+			goto miss;
 		}
 
 		for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) {
-			struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel);
+			nhc = fib_info_nhc(fi, nhsel);
 
-			if (nhc->nhc_flags & RTNH_F_DEAD)
+			if (!fib_lookup_good_nhc(nhc, fib_flags, flp))
 				continue;
-			if (ip_ignore_linkdown(nhc->nhc_dev) &&
-			    nhc->nhc_flags & RTNH_F_LINKDOWN &&
-			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
-				continue;
-			if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
-				if (flp->flowi4_oif &&
-				    flp->flowi4_oif != nhc->nhc_oif)
-					continue;
-			}
-
+set_result:
 			if (!(fib_flags & FIB_LOOKUP_NOREF))
 				refcount_inc(&fi->fib_clntref);
 
@@ -1568,6 +1588,7 @@ out_reject:
 			return err;
 		}
 	}
+miss:
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 	this_cpu_inc(stats->semantic_match_miss);
 #endif
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5f34eb951627..65c29f2bd89f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -24,17 +24,19 @@
 #include <net/addrconf.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-/* match_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
- *                          only, and any IPv4 addresses if not IPv6 only
- * match_wildcard == false: addresses must be exactly the same, i.e.
- *                          IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
- *                          and 0.0.0.0 equals to 0.0.0.0 only
+/* match_sk*_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses
+ *				if IPv6 only, and any IPv4 addresses
+ *				if not IPv6 only
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ *				IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
+ *				and 0.0.0.0 equals to 0.0.0.0 only
  */
 static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 				 const struct in6_addr *sk2_rcv_saddr6,
 				 __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
 				 bool sk1_ipv6only, bool sk2_ipv6only,
-				 bool match_wildcard)
+				 bool match_sk1_wildcard,
+				 bool match_sk2_wildcard)
 {
 	int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
 	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -44,8 +46,8 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 		if (!sk2_ipv6only) {
 			if (sk1_rcv_saddr == sk2_rcv_saddr)
 				return true;
-			if (!sk1_rcv_saddr || !sk2_rcv_saddr)
-				return match_wildcard;
+			return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+				(match_sk2_wildcard && !sk2_rcv_saddr);
 		}
 		return false;
 	}
@@ -53,11 +55,11 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 	if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
 		return true;
 
-	if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
+	if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard &&
 	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
 		return true;
 
-	if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
+	if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard &&
 	    !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
 		return true;
 
@@ -69,18 +71,19 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 }
 #endif
 
-/* match_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
- * match_wildcard == false: addresses must be exactly the same, i.e.
- *                          0.0.0.0 only equals to 0.0.0.0
+/* match_sk*_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ *				0.0.0.0 only equals to 0.0.0.0
  */
 static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
-				 bool sk2_ipv6only, bool match_wildcard)
+				 bool sk2_ipv6only, bool match_sk1_wildcard,
+				 bool match_sk2_wildcard)
 {
 	if (!sk2_ipv6only) {
 		if (sk1_rcv_saddr == sk2_rcv_saddr)
 			return true;
-		if (!sk1_rcv_saddr || !sk2_rcv_saddr)
-			return match_wildcard;
+		return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+			(match_sk2_wildcard && !sk2_rcv_saddr);
 	}
 	return false;
 }
@@ -96,10 +99,12 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
 					    sk2->sk_rcv_saddr,
 					    ipv6_only_sock(sk),
 					    ipv6_only_sock(sk2),
+					    match_wildcard,
 					    match_wildcard);
 #endif
 	return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
-				    ipv6_only_sock(sk2), match_wildcard);
+				    ipv6_only_sock(sk2), match_wildcard,
+				    match_wildcard);
 }
 EXPORT_SYMBOL(inet_rcv_saddr_equal);
 
@@ -285,10 +290,10 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
 					    tb->fast_rcv_saddr,
 					    sk->sk_rcv_saddr,
 					    tb->fast_ipv6_only,
-					    ipv6_only_sock(sk), true);
+					    ipv6_only_sock(sk), true, false);
 #endif
 	return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr,
-				    ipv6_only_sock(sk), true);
+				    ipv6_only_sock(sk), true, false);
 }
 
 /* Obtain a reference to a local port for the given sock,
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1b4e6f298648..1dda7c155c48 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -93,7 +93,28 @@ static int vti_rcv_proto(struct sk_buff *skb)
 
 static int vti_rcv_tunnel(struct sk_buff *skb)
 {
-	return vti_rcv(skb, ip_hdr(skb)->saddr, true);
+	struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id);
+	const struct iphdr *iph = ip_hdr(skb);
+	struct ip_tunnel *tunnel;
+
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+				  iph->saddr, iph->daddr, 0);
+	if (tunnel) {
+		struct tnl_ptk_info tpi = {
+			.proto = htons(ETH_P_IP),
+		};
+
+		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+			goto drop;
+		if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+			goto drop;
+		return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false);
+	}
+
+	return -EINVAL;
+drop:
+	kfree_skb(skb);
+	return 0;
 }
 
 static int vti_rcv_cb(struct sk_buff *skb, int err)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2f01cf6fa0de..678575adaf3b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -698,7 +698,7 @@ out:
 
 rtnl_link_failed:
 #if IS_ENABLED(CONFIG_MPLS)
-	xfrm4_tunnel_deregister(&mplsip_handler, AF_INET);
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
 xfrm_tunnel_mplsip_failed:
 
 #endif
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9cf83cc85e4a..b2363b82b48d 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -109,8 +109,10 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags);
 static void ipmr_expire_process(struct timer_list *t);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
-#define ipmr_for_each_table(mrt, net) \
-	list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list)
+#define ipmr_for_each_table(mrt, net)					\
+	list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list,	\
+				lockdep_rtnl_is_held() ||		\
+				list_empty(&net->ipv4.mr_tables))
 
 static struct mr_table *ipmr_mr_table_iter(struct net *net,
 					   struct mr_table *mrt)
@@ -2611,7 +2613,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR)
 				return skb->len;
 
 			NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist");
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 3c25a467b3ef..7afde8828b4c 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -166,8 +166,7 @@ pptp_outbound_pkt(struct sk_buff *skb,
 		break;
 	default:
 		pr_debug("unknown outbound packet 0x%04x:%s\n", msg,
-			 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
-					       pptp_msg_name[0]);
+			 pptp_msg_name(msg));
 		fallthrough;
 	case PPTP_SET_LINK_INFO:
 		/* only need to NAT in case PAC is behind NAT box */
@@ -268,9 +267,7 @@ pptp_inbound_pkt(struct sk_buff *skb,
 		pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID);
 		break;
 	default:
-		pr_debug("unknown inbound packet %s\n",
-			 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] :
-					       pptp_msg_name[0]);
+		pr_debug("unknown inbound packet %s\n", pptp_msg_name(msg));
 		fallthrough;
 	case PPTP_START_SESSION_REQUEST:
 	case PPTP_START_SESSION_REPLY:
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index fdfca534d094..563f71bcb2d7 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -63,9 +63,16 @@ static void nexthop_free_mpath(struct nexthop *nh)
 	int i;
 
 	nhg = rcu_dereference_raw(nh->nh_grp);
-	for (i = 0; i < nhg->num_nh; ++i)
-		WARN_ON(nhg->nh_entries[i].nh);
+	for (i = 0; i < nhg->num_nh; ++i) {
+		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+
+		WARN_ON(!list_empty(&nhge->nh_list));
+		nexthop_put(nhge->nh);
+	}
+
+	WARN_ON(nhg->spare == nhg);
 
+	kfree(nhg->spare);
 	kfree(nhg);
 }
 
@@ -276,6 +283,7 @@ out:
 	return 0;
 
 nla_put_failure:
+	nlmsg_cancel(skb, nlh);
 	return -EMSGSIZE;
 }
 
@@ -433,7 +441,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
 		if (!valid_group_nh(nh, len, extack))
 			return -EINVAL;
 	}
-	for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) {
+	for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
 		if (!tb[i])
 			continue;
 
@@ -693,41 +701,56 @@ static void nh_group_rebalance(struct nh_group *nhg)
 	}
 }
 
-static void remove_nh_grp_entry(struct nh_grp_entry *nhge,
-				struct nh_group *nhg,
+static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
 				struct nl_info *nlinfo)
 {
+	struct nh_grp_entry *nhges, *new_nhges;
+	struct nexthop *nhp = nhge->nh_parent;
 	struct nexthop *nh = nhge->nh;
-	struct nh_grp_entry *nhges;
-	bool found = false;
-	int i;
+	struct nh_group *nhg, *newg;
+	int i, j;
 
 	WARN_ON(!nh);
 
-	nhges = nhg->nh_entries;
-	for (i = 0; i < nhg->num_nh; ++i) {
-		if (found) {
-			nhges[i-1].nh = nhges[i].nh;
-			nhges[i-1].weight = nhges[i].weight;
-			list_del(&nhges[i].nh_list);
-			list_add(&nhges[i-1].nh_list, &nhges[i-1].nh->grp_list);
-		} else if (nhg->nh_entries[i].nh == nh) {
-			found = true;
-		}
-	}
+	nhg = rtnl_dereference(nhp->nh_grp);
+	newg = nhg->spare;
 
-	if (WARN_ON(!found))
+	/* last entry, keep it visible and remove the parent */
+	if (nhg->num_nh == 1) {
+		remove_nexthop(net, nhp, nlinfo);
 		return;
+	}
+
+	newg->has_v4 = nhg->has_v4;
+	newg->mpath = nhg->mpath;
+	newg->num_nh = nhg->num_nh;
 
-	nhg->num_nh--;
-	nhg->nh_entries[nhg->num_nh].nh = NULL;
+	/* copy old entries to new except the one getting removed */
+	nhges = nhg->nh_entries;
+	new_nhges = newg->nh_entries;
+	for (i = 0, j = 0; i < nhg->num_nh; ++i) {
+		/* current nexthop getting removed */
+		if (nhg->nh_entries[i].nh == nh) {
+			newg->num_nh--;
+			continue;
+		}
 
-	nh_group_rebalance(nhg);
+		list_del(&nhges[i].nh_list);
+		new_nhges[j].nh_parent = nhges[i].nh_parent;
+		new_nhges[j].nh = nhges[i].nh;
+		new_nhges[j].weight = nhges[i].weight;
+		list_add(&new_nhges[j].nh_list, &new_nhges[j].nh->grp_list);
+		j++;
+	}
 
-	nexthop_put(nh);
+	nh_group_rebalance(newg);
+	rcu_assign_pointer(nhp->nh_grp, newg);
+
+	list_del(&nhge->nh_list);
+	nexthop_put(nhge->nh);
 
 	if (nlinfo)
-		nexthop_notify(RTM_NEWNEXTHOP, nhge->nh_parent, nlinfo);
+		nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo);
 }
 
 static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
@@ -735,17 +758,11 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
 {
 	struct nh_grp_entry *nhge, *tmp;
 
-	list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) {
-		struct nh_group *nhg;
-
-		list_del(&nhge->nh_list);
-		nhg = rtnl_dereference(nhge->nh_parent->nh_grp);
-		remove_nh_grp_entry(nhge, nhg, nlinfo);
+	list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list)
+		remove_nh_grp_entry(net, nhge, nlinfo);
 
-		/* if this group has no more entries then remove it */
-		if (!nhg->num_nh)
-			remove_nexthop(net, nhge->nh_parent, nlinfo);
-	}
+	/* make sure all see the newly published array before releasing rtnl */
+	synchronize_rcu();
 }
 
 static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
@@ -759,10 +776,7 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
 		if (WARN_ON(!nhge->nh))
 			continue;
 
-		list_del(&nhge->nh_list);
-		nexthop_put(nhge->nh);
-		nhge->nh = NULL;
-		nhg->num_nh--;
+		list_del_init(&nhge->nh_list);
 	}
 }
 
@@ -1085,6 +1099,7 @@ static struct nexthop *nexthop_create_group(struct net *net,
 {
 	struct nlattr *grps_attr = cfg->nh_grp;
 	struct nexthop_grp *entry = nla_data(grps_attr);
+	u16 num_nh = nla_len(grps_attr) / sizeof(*entry);
 	struct nh_group *nhg;
 	struct nexthop *nh;
 	int i;
@@ -1095,12 +1110,21 @@ static struct nexthop *nexthop_create_group(struct net *net,
 
 	nh->is_group = 1;
 
-	nhg = nexthop_grp_alloc(nla_len(grps_attr) / sizeof(*entry));
+	nhg = nexthop_grp_alloc(num_nh);
 	if (!nhg) {
 		kfree(nh);
 		return ERR_PTR(-ENOMEM);
 	}
 
+	/* spare group used for removals */
+	nhg->spare = nexthop_grp_alloc(num_nh);
+	if (!nhg) {
+		kfree(nhg);
+		kfree(nh);
+		return NULL;
+	}
+	nhg->spare->spare = nhg;
+
 	for (i = 0; i < nhg->num_nh; ++i) {
 		struct nexthop *nhe;
 		struct nh_info *nhi;
@@ -1132,6 +1156,7 @@ out_no_nh:
 	for (; i >= 0; --i)
 		nexthop_put(nhg->nh_entries[i].nh);
 
+	kfree(nhg->spare);
 	kfree(nhg);
 	kfree(nh);
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 788c69d9bfe0..b73f540fa19b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -491,18 +491,16 @@ u32 ip_idents_reserve(u32 hash, int segs)
 	atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
 	u32 old = READ_ONCE(*p_tstamp);
 	u32 now = (u32)jiffies;
-	u32 new, delta = 0;
+	u32 delta = 0;
 
 	if (old != now && cmpxchg(p_tstamp, old, now) == old)
 		delta = prandom_u32_max(now - old);
 
-	/* Do not use atomic_add_return() as it makes UBSAN unhappy */
-	do {
-		old = (u32)atomic_read(p_id);
-		new = old + delta + segs;
-	} while (atomic_cmpxchg(p_id, old, new) != old);
-
-	return new - segs;
+	/* If UBSAN reports an error there, please make sure your compiler
+	 * supports -fno-strict-overflow before reporting it that was a bug
+	 * in UBSAN, and it has been fixed in GCC-8.
+	 */
+	return atomic_add_return(segs + delta, p_id) - segs;
 }
 EXPORT_SYMBOL(ip_idents_reserve);
 
@@ -915,7 +913,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* Check for load limit; set rate_last to the latest sent
 	 * redirect.
 	 */
-	if (peer->rate_tokens == 0 ||
+	if (peer->n_redirects == 0 ||
 	    time_after(jiffies,
 		       (peer->rate_last +
 			(ip_rt_redirect_load << peer->n_redirects)))) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6d87de434377..dd401757eea1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 					  int target, struct sock *sk)
 {
-	return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
-		(sk->sk_prot->stream_memory_read ?
-		sk->sk_prot->stream_memory_read(sk) : false);
+	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
+
+	if (avail > 0) {
+		if (avail >= target)
+			return true;
+		if (tcp_rmem_pressure(sk))
+			return true;
+	}
+	if (sk->sk_prot->stream_memory_read)
+		return sk->sk_prot->stream_memory_read(sk);
+	return false;
 }
 
 /*
@@ -1756,10 +1764,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
 
 	down_read(&current->mm->mmap_sem);
 
-	ret = -EINVAL;
 	vma = find_vma(current->mm, address);
-	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops)
-		goto out;
+	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) {
+		up_read(&current->mm->mmap_sem);
+		return -EINVAL;
+	}
 	zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
 
 	tp = tcp_sk(sk);
@@ -2154,13 +2163,15 @@ skip_copy:
 			tp->urg_data = 0;
 			tcp_fast_path_check(sk);
 		}
-		if (used + offset < skb->len)
-			continue;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
 			tcp_update_recv_tstamps(skb, &tss);
 			cmsg_flags |= 2;
 		}
+
+		if (used + offset < skb->len)
+			continue;
+
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
 		if (!(flags & MSG_PEEK))
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 5a05327f97c1..629aaa9a1eb9 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -125,7 +125,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 
 	if (!ret) {
 		msg->sg.start = i;
-		msg->sg.size -= apply_bytes;
 		sk_psock_queue_msg(psock, tmp);
 		sk_psock_data_ready(sk, psock);
 	} else {
@@ -262,14 +261,17 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	struct sk_psock *psock;
 	int copied, ret;
 
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
-	if (unlikely(flags & MSG_ERRQUEUE))
-		return inet_recv_error(sk, msg, len, addr_len);
 	if (!skb_queue_empty(&sk->sk_receive_queue) &&
-	    sk_psock_queue_empty(psock))
+	    sk_psock_queue_empty(psock)) {
+		sk_psock_put(sk, psock);
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	}
 	lock_sock(sk);
 msg_bytes_ready:
 	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bf4ced9273e8..29c6fc8c7716 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3926,10 +3926,6 @@ void tcp_parse_options(const struct net *net,
 				 */
 				break;
 #endif
-			case TCPOPT_MPTCP:
-				mptcp_parse_option(skb, ptr, opsize, opt_rx);
-				break;
-
 			case TCPOPT_FASTOPEN:
 				tcp_parse_fastopen_option(
 					opsize - TCPOLEN_FASTOPEN_BASE,
@@ -4761,7 +4757,8 @@ void tcp_data_ready(struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int avail = tp->rcv_nxt - tp->copied_seq;
 
-	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+	if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
+	    !sock_flag(sk, SOCK_DONE))
 		return;
 
 	sk->sk_data_ready(sk);
@@ -5990,9 +5987,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
-		if (sk_is_mptcp(sk))
-			mptcp_rcv_synsent(sk);
-
 		/* Remember, tcp_poll() does not lock socket!
 		 * Change state from SYN-SENT only after copied_seq
 		 * is initialized. */
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 89ba7c87de5d..30ddb9dc9398 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -58,9 +58,7 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
-#ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
-#endif
 
 	return xfrm_output(sk, skb);
 }
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 24e319dfb510..f131cedf5ba6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3222,11 +3222,11 @@ static int ipv6_generate_stable_address(struct in6_addr *address,
 					const struct inet6_dev *idev)
 {
 	static DEFINE_SPINLOCK(lock);
-	static __u32 digest[SHA_DIGEST_WORDS];
-	static __u32 workspace[SHA_WORKSPACE_WORDS];
+	static __u32 digest[SHA1_DIGEST_WORDS];
+	static __u32 workspace[SHA1_WORKSPACE_WORDS];
 
 	static union {
-		char __data[SHA_MESSAGE_BYTES];
+		char __data[SHA1_BLOCK_SIZE];
 		struct {
 			struct in6_addr secret;
 			__be32 prefix[2];
@@ -3251,7 +3251,7 @@ static int ipv6_generate_stable_address(struct in6_addr *address,
 retry:
 	spin_lock_bh(&lock);
 
-	sha_init(digest);
+	sha1_init(digest);
 	memset(&data, 0, sizeof(data));
 	memset(workspace, 0, sizeof(workspace));
 	memcpy(data.hwaddr, idev->dev->perm_addr, idev->dev->addr_len);
@@ -3260,7 +3260,7 @@ retry:
 	data.secret = secret;
 	data.dad_count = dad_count;
 
-	sha_transform(digest, data.__data, workspace);
+	sha1_transform(digest, data.__data, workspace);
 
 	temp = *address;
 	temp.s6_addr32[2] = (__force __be32)digest[0];
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 221c81f85cbf..8d3f66c310db 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1047,7 +1047,8 @@ static int calipso_opt_getattr(const unsigned char *calipso,
 			goto getattr_return;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	secattr->type = NETLBL_NLTYPE_CALIPSO;
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 8eab2c869d61..ab0eea336c70 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -85,10 +85,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 		sp->olen++;
 
 		xo = xfrm_offload(skb);
-		if (!xo) {
-			xfrm_state_put(x);
+		if (!xo)
 			goto out_reset;
-		}
 	}
 
 	xo->flags |= XFRM_GRO;
@@ -123,9 +121,16 @@ static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
 	struct ip_esp_hdr *esph;
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct xfrm_offload *xo = xfrm_offload(skb);
-	int proto = iph->nexthdr;
+	u8 proto = iph->nexthdr;
 
 	skb_push(skb, -skb_network_offset(skb));
+
+	if (x->outer_mode.encap == XFRM_MODE_TRANSPORT) {
+		__be16 frag;
+
+		ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto, &frag);
+	}
+
 	esph = ip_esp_hdr(skb);
 	*skb_mac_header(skb) = IPPROTO_ESP;
 
@@ -166,23 +171,31 @@ static struct sk_buff *xfrm6_beet_gso_segment(struct xfrm_state *x,
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
-	int proto = xo->proto;
+	u8 proto = xo->proto;
 
 	skb->transport_header += x->props.header_len;
 
-	if (proto == IPPROTO_BEETPH) {
-		struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data;
-
-		skb->transport_header += ph->hdrlen * 8;
-		proto = ph->nexthdr;
-	}
-
 	if (x->sel.family != AF_INET6) {
 		skb->transport_header -=
 			(sizeof(struct ipv6hdr) - sizeof(struct iphdr));
 
+		if (proto == IPPROTO_BEETPH) {
+			struct ip_beet_phdr *ph =
+				(struct ip_beet_phdr *)skb->data;
+
+			skb->transport_header += ph->hdrlen * 8;
+			proto = ph->nexthdr;
+		} else {
+			skb->transport_header -= IPV4_BEET_PHMAXLEN;
+		}
+
 		if (proto == IPPROTO_TCP)
 			skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
+	} else {
+		__be16 frag;
+
+		skb->transport_header +=
+			ipv6_skip_exthdr(skb, 0, &proto, &frag);
 	}
 
 	__skb_pull(skb, skb_transport_offset(skb));
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 2688f3e82165..fc5000370030 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -229,6 +229,25 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	return res;
 }
 
+static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type,
+				  struct flowi6 *fl6)
+{
+	struct net *net = sock_net(sk);
+	struct dst_entry *dst;
+	bool res = false;
+
+	dst = ip6_route_output(net, sk, fl6);
+	if (!dst->error) {
+		struct rt6_info *rt = (struct rt6_info *)dst;
+		struct in6_addr prefsrc;
+
+		rt6_get_prefsrc(rt, &prefsrc);
+		res = !ipv6_addr_any(&prefsrc);
+	}
+	dst_release(dst);
+	return res;
+}
+
 /*
  *	an inline helper for the "simple" if statement below
  *	checks if parameter problem report is caused by an
@@ -527,7 +546,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		saddr = force_saddr;
 	if (saddr) {
 		fl6.saddr = *saddr;
-	} else {
+	} else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) {
 		/* select a more meaningful saddr from input if */
 		struct net_device *in_netdev;
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 46ed56719476..20314895509c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -664,7 +664,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (arg.filter.table_id) {
 		tb = fib6_get_table(net, arg.filter.table_id);
 		if (!tb) {
-			if (arg.filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != PF_INET6)
 				goto out;
 
 			NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist");
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 65a54d74acc1..1f4d20e97c07 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -98,7 +98,8 @@ static void ipmr_expire_process(struct timer_list *t);
 #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
 #define ip6mr_for_each_table(mrt, net) \
 	list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \
-				lockdep_rtnl_is_held())
+				lockdep_rtnl_is_held() || \
+				list_empty(&net->ipv6.mr6_tables))
 
 static struct mr_table *ip6mr_mr_table_iter(struct net *net,
 					    struct mr_table *mrt)
@@ -2502,7 +2503,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR)
 				return skb->len;
 
 			NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist");
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index debdaeba5d8c..18d05403d3b5 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -183,15 +183,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 					retv = -EBUSY;
 					break;
 				}
-			} else if (sk->sk_protocol == IPPROTO_TCP) {
-				if (sk->sk_prot != &tcpv6_prot) {
-					retv = -EBUSY;
-					break;
-				}
-				break;
-			} else {
+			}
+			if (sk->sk_protocol == IPPROTO_TCP &&
+			    sk->sk_prot != &tcpv6_prot) {
+				retv = -EBUSY;
 				break;
 			}
+			if (sk->sk_protocol != IPPROTO_TCP)
+				break;
 			if (sk->sk_state != TCP_ESTABLISHED) {
 				retv = -ENOTCONN;
 				break;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 310cbddaa533..ff847a324220 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1385,9 +1385,18 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
 	}
 	ip6_rt_copy_init(pcpu_rt, res);
 	pcpu_rt->rt6i_flags |= RTF_PCPU;
+
+	if (f6i->nh)
+		pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev));
+
 	return pcpu_rt;
 }
 
+static bool rt6_is_valid(const struct rt6_info *rt6)
+{
+	return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev));
+}
+
 /* It should be called with rcu_read_lock() acquired */
 static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 {
@@ -1395,6 +1404,19 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 
 	pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
 
+	if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) {
+		struct rt6_info *prev, **p;
+
+		p = this_cpu_ptr(res->nh->rt6i_pcpu);
+		prev = xchg(p, NULL);
+		if (prev) {
+			dst_dev_put(&prev->dst);
+			dst_release(&prev->dst);
+		}
+
+		pcpu_rt = NULL;
+	}
+
 	return pcpu_rt;
 }
 
@@ -2593,6 +2615,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
 	rt = container_of(dst, struct rt6_info, dst);
 
+	if (rt->sernum)
+		return rt6_is_valid(rt) ? dst : NULL;
+
 	rcu_read_lock();
 
 	/* All IPV6 dsts are created with ->obsolete set to the value
@@ -2697,8 +2722,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 
-	if (dst_metric_locked(dst, RTAX_MTU))
-		return;
+	/* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU)
+	 * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it.
+	 * [see also comment in rt6_mtu_change_route()]
+	 */
 
 	if (iph) {
 		daddr = &iph->daddr;
diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c
index d38b476fc7f2..307f336b5353 100644
--- a/net/ipv6/rpl.c
+++ b/net/ipv6/rpl.c
@@ -8,6 +8,7 @@
 #include <net/rpl.h>
 
 #define IPV6_PFXTAIL_LEN(x) (sizeof(struct in6_addr) - (x))
+#define IPV6_RPL_BEST_ADDR_COMPRESSION 15
 
 static void ipv6_rpl_addr_decompress(struct in6_addr *dst,
 				     const struct in6_addr *daddr,
@@ -73,7 +74,7 @@ static unsigned char ipv6_rpl_srh_calc_cmpri(const struct ipv6_rpl_sr_hdr *inhdr
 		}
 	}
 
-	return plen;
+	return IPV6_RPL_BEST_ADDR_COMPRESSION;
 }
 
 static unsigned char ipv6_rpl_srh_calc_cmpre(const struct in6_addr *daddr,
@@ -83,10 +84,10 @@ static unsigned char ipv6_rpl_srh_calc_cmpre(const struct in6_addr *daddr,
 
 	for (plen = 0; plen < sizeof(*daddr); plen++) {
 		if (daddr->s6_addr[plen] != last_segment->s6_addr[plen])
-			break;
+			return plen;
 	}
 
-	return plen;
+	return IPV6_RPL_BEST_ADDR_COMPRESSION;
 }
 
 void ipv6_rpl_srh_compress(struct ipv6_rpl_sr_hdr *outhdr,
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 75421a472d25..37b434293bda 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -27,8 +27,9 @@
 
 bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len)
 {
-	int trailing;
 	unsigned int tlv_offset;
+	int max_last_entry;
+	int trailing;
 
 	if (srh->type != IPV6_SRCRT_TYPE_4)
 		return false;
@@ -36,7 +37,12 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len)
 	if (((srh->hdrlen + 1) << 3) != len)
 		return false;
 
-	if (srh->segments_left > srh->first_segment)
+	max_last_entry = (srh->hdrlen / 2) - 1;
+
+	if (srh->first_segment > max_last_entry)
+		return false;
+
+	if (srh->segments_left > srh->first_segment + 1)
 		return false;
 
 	tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4);
@@ -434,7 +440,7 @@ static struct genl_family seg6_genl_family __ro_after_init = {
 
 int __init seg6_init(void)
 {
-	int err = -ENOMEM;
+	int err;
 
 	err = genl_register_family(&seg6_genl_family);
 	if (err)
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index ffcfcd2b128f..85dddfe3a2c6 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -34,7 +34,6 @@
 #include <net/addrconf.h>
 #include <net/xfrm.h>
 
-#include <linux/cryptohash.h>
 #include <crypto/hash.h>
 #include <crypto/sha.h>
 #include <net/seg6.h>
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index fbe51d40bd7e..e34167f790e6 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -111,9 +111,7 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 
-#ifdef CONFIG_NETFILTER
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
-#endif
 
 	return xfrm_output(sk, skb);
 }
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fcb53ed1c4fb..6d7ef78c88af 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1458,6 +1458,9 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
 	if (sk->sk_type != SOCK_DGRAM)
 		return -EPROTONOSUPPORT;
 
+	if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)
+		return -EPROTONOSUPPORT;
+
 	if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) ||
 	    (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP))
 		return -EPROTONOSUPPORT;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 0d7c887a2b75..955662a6dee7 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -20,7 +20,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -209,15 +208,31 @@ discard:
 	return 0;
 }
 
-static int l2tp_ip_open(struct sock *sk)
+static int l2tp_ip_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip_lock);
+		sk_add_node(sk, &l2tp_ip_table);
+		write_unlock_bh(&l2tp_ip_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip_lock);
-	sk_add_node(sk, &l2tp_ip_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip_lock);
+}
+
+static int l2tp_ip_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip_hash(sk);
 	return 0;
 }
 
@@ -594,8 +609,8 @@ static struct proto l2tp_ip_prot = {
 	.sendmsg	   = l2tp_ip_sendmsg,
 	.recvmsg	   = l2tp_ip_recvmsg,
 	.backlog_rcv	   = l2tp_ip_backlog_recv,
-	.hash		   = inet_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip_hash,
+	.unhash		   = l2tp_ip_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ip_setsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index d148766f40d1..0fa694bd3f6a 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -20,8 +20,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
-#include <net/inet6_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -222,15 +220,31 @@ discard:
 	return 0;
 }
 
-static int l2tp_ip6_open(struct sock *sk)
+static int l2tp_ip6_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip6_lock);
+		sk_add_node(sk, &l2tp_ip6_table);
+		write_unlock_bh(&l2tp_ip6_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip6_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip6_lock);
-	sk_add_node(sk, &l2tp_ip6_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip6_lock);
+}
+
+static int l2tp_ip6_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip6_hash(sk);
 	return 0;
 }
 
@@ -728,8 +742,8 @@ static struct proto l2tp_ip6_prot = {
 	.sendmsg	   = l2tp_ip6_sendmsg,
 	.recvmsg	   = l2tp_ip6_recvmsg,
 	.backlog_rcv	   = l2tp_ip6_backlog_recv,
-	.hash		   = inet6_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip6_hash,
+	.unhash		   = l2tp_ip6_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip6_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index f5a9bdc4980c..ebb381c3f1b9 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -920,51 +920,51 @@ static const struct genl_ops l2tp_nl_ops[] = {
 		.cmd = L2TP_CMD_TUNNEL_CREATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_create,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_DELETE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_delete,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_MODIFY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_modify,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_get,
 		.dumpit = l2tp_nl_cmd_tunnel_dump,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_CREATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_create,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_DELETE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_delete,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_MODIFY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_modify,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_get,
 		.dumpit = l2tp_nl_cmd_session_dump,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 };
 
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 8345926193de..6423173bb87e 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1069,7 +1069,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC;
 		if (hw->max_signal <= 0) {
 			result = -EINVAL;
-			goto fail_wiphy_register;
+			goto fail_workqueue;
 		}
 	}
 
@@ -1135,7 +1135,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 
 	result = ieee80211_init_cipher_suites(local);
 	if (result < 0)
-		goto fail_wiphy_register;
+		goto fail_workqueue;
 
 	if (!local->ops->remain_on_channel)
 		local->hw.wiphy->max_remain_on_channel_duration = 5000;
@@ -1161,10 +1161,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 
 	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM;
 
-	result = wiphy_register(local->hw.wiphy);
-	if (result < 0)
-		goto fail_wiphy_register;
-
 	/*
 	 * We use the number of queues for feature tests (QoS, HT) internally
 	 * so restrict them appropriately.
@@ -1187,8 +1183,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	local->tx_headroom = max_t(unsigned int , local->hw.extra_tx_headroom,
 				   IEEE80211_TX_STATUS_HEADROOM);
 
-	debugfs_hw_add(local);
-
 	/*
 	 * if the driver doesn't specify a max listen interval we
 	 * use 5 which should be a safe default
@@ -1217,9 +1211,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		goto fail_flows;
 
 	rtnl_lock();
-
 	result = ieee80211_init_rate_ctrl_alg(local,
 					      hw->rate_control_algorithm);
+	rtnl_unlock();
 	if (result < 0) {
 		wiphy_debug(local->hw.wiphy,
 			    "Failed to initialize rate control algorithm\n");
@@ -1273,6 +1267,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		local->sband_allocated |= BIT(band);
 	}
 
+	result = wiphy_register(local->hw.wiphy);
+	if (result < 0)
+		goto fail_wiphy_register;
+
+	debugfs_hw_add(local);
+	rate_control_add_debugfs(local);
+
+	rtnl_lock();
+
 	/* add one default STA interface if supported */
 	if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) &&
 	    !ieee80211_hw_check(hw, NO_AUTO_VIF)) {
@@ -1312,17 +1315,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 #if defined(CONFIG_INET) || defined(CONFIG_IPV6)
  fail_ifa:
 #endif
+	wiphy_unregister(local->hw.wiphy);
+ fail_wiphy_register:
 	rtnl_lock();
 	rate_control_deinitialize(local);
 	ieee80211_remove_interfaces(local);
- fail_rate:
 	rtnl_unlock();
+ fail_rate:
  fail_flows:
 	ieee80211_led_exit(local);
 	destroy_workqueue(local->workqueue);
  fail_workqueue:
-	wiphy_unregister(local->hw.wiphy);
- fail_wiphy_register:
 	if (local->wiphy_ciphers_allocated)
 		kfree(local->hw.wiphy->cipher_suites);
 	kfree(local->int_scan_req);
@@ -1372,8 +1375,8 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw)
 	skb_queue_purge(&local->skb_queue_unreliable);
 	skb_queue_purge(&local->skb_queue_tdls_chsw);
 
-	destroy_workqueue(local->workqueue);
 	wiphy_unregister(local->hw.wiphy);
+	destroy_workqueue(local->workqueue);
 	ieee80211_led_exit(local);
 	kfree(local->int_scan_req);
 }
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index d09b3c789314..36978a0e5000 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -1257,15 +1257,15 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
 		    sdata->u.mesh.mshcfg.rssi_threshold < rx_status->signal)
 			mesh_neighbour_update(sdata, mgmt->sa, &elems,
 					      rx_status);
+
+		if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT &&
+		    !sdata->vif.csa_active)
+			ieee80211_mesh_process_chnswitch(sdata, &elems, true);
 	}
 
 	if (ifmsh->sync_ops)
 		ifmsh->sync_ops->rx_bcn_presp(sdata,
 			stype, mgmt, &elems, rx_status);
-
-	if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT &&
-	    !sdata->vif.csa_active)
-		ieee80211_mesh_process_chnswitch(sdata, &elems, true);
 }
 
 int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata)
@@ -1373,6 +1373,9 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata,
 	ieee802_11_parse_elems(pos, len - baselen, true, &elems,
 			       mgmt->bssid, NULL);
 
+	if (!mesh_matches_local(sdata, &elems))
+		return;
+
 	ifmsh->chsw_ttl = elems.mesh_chansw_params_ie->mesh_ttl;
 	if (!--ifmsh->chsw_ttl)
 		fwd_csa = false;
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 38a0383dfbcf..aa5150929996 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -1103,7 +1103,14 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata)
 	mesh_path_sel_frame_tx(MPATH_PREQ, 0, sdata->vif.addr, ifmsh->sn,
 			       target_flags, mpath->dst, mpath->sn, da, 0,
 			       ttl, lifetime, 0, ifmsh->preq_id++, sdata);
+
+	spin_lock_bh(&mpath->state_lock);
+	if (mpath->flags & MESH_PATH_DELETED) {
+		spin_unlock_bh(&mpath->state_lock);
+		goto enddiscovery;
+	}
 	mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout);
+	spin_unlock_bh(&mpath->state_lock);
 
 enddiscovery:
 	rcu_read_unlock();
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index a1e9fc7878aa..b051f125d3af 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -214,17 +214,16 @@ static ssize_t rcname_read(struct file *file, char __user *userbuf,
 				       ref->ops->name, len);
 }
 
-static const struct file_operations rcname_ops = {
+const struct file_operations rcname_ops = {
 	.read = rcname_read,
 	.open = simple_open,
 	.llseek = default_llseek,
 };
 #endif
 
-static struct rate_control_ref *rate_control_alloc(const char *name,
-					    struct ieee80211_local *local)
+static struct rate_control_ref *
+rate_control_alloc(const char *name, struct ieee80211_local *local)
 {
-	struct dentry *debugfsdir = NULL;
 	struct rate_control_ref *ref;
 
 	ref = kmalloc(sizeof(struct rate_control_ref), GFP_KERNEL);
@@ -234,13 +233,7 @@ static struct rate_control_ref *rate_control_alloc(const char *name,
 	if (!ref->ops)
 		goto free;
 
-#ifdef CONFIG_MAC80211_DEBUGFS
-	debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir);
-	local->debugfs.rcdir = debugfsdir;
-	debugfs_create_file("name", 0400, debugfsdir, ref, &rcname_ops);
-#endif
-
-	ref->priv = ref->ops->alloc(&local->hw, debugfsdir);
+	ref->priv = ref->ops->alloc(&local->hw);
 	if (!ref->priv)
 		goto free;
 	return ref;
diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h
index 5397c6dad056..79b44d3db171 100644
--- a/net/mac80211/rate.h
+++ b/net/mac80211/rate.h
@@ -60,6 +60,29 @@ static inline void rate_control_add_sta_debugfs(struct sta_info *sta)
 #endif
 }
 
+extern const struct file_operations rcname_ops;
+
+static inline void rate_control_add_debugfs(struct ieee80211_local *local)
+{
+#ifdef CONFIG_MAC80211_DEBUGFS
+	struct dentry *debugfsdir;
+
+	if (!local->rate_ctrl)
+		return;
+
+	if (!local->rate_ctrl->ops->add_debugfs)
+		return;
+
+	debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir);
+	local->debugfs.rcdir = debugfsdir;
+	debugfs_create_file("name", 0400, debugfsdir,
+			    local->rate_ctrl, &rcname_ops);
+
+	local->rate_ctrl->ops->add_debugfs(&local->hw, local->rate_ctrl->priv,
+					   debugfsdir);
+#endif
+}
+
 void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata);
 
 /* Get a reference to the rate control algorithm. If `name' is NULL, get the
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 694a31978a04..5dc3e5bc4e64 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -1635,7 +1635,7 @@ minstrel_ht_init_cck_rates(struct minstrel_priv *mp)
 }
 
 static void *
-minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
+minstrel_ht_alloc(struct ieee80211_hw *hw)
 {
 	struct minstrel_priv *mp;
 
@@ -1673,7 +1673,17 @@ minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
 	mp->update_interval = HZ / 10;
 	mp->new_avg = true;
 
+	minstrel_ht_init_cck_rates(mp);
+
+	return mp;
+}
+
 #ifdef CONFIG_MAC80211_DEBUGFS
+static void minstrel_ht_add_debugfs(struct ieee80211_hw *hw, void *priv,
+				    struct dentry *debugfsdir)
+{
+	struct minstrel_priv *mp = priv;
+
 	mp->fixed_rate_idx = (u32) -1;
 	debugfs_create_u32("fixed_rate_idx", S_IRUGO | S_IWUGO, debugfsdir,
 			   &mp->fixed_rate_idx);
@@ -1681,12 +1691,8 @@ minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
 			   &mp->sample_switch);
 	debugfs_create_bool("new_avg", S_IRUGO | S_IWUSR, debugfsdir,
 			   &mp->new_avg);
-#endif
-
-	minstrel_ht_init_cck_rates(mp);
-
-	return mp;
 }
+#endif
 
 static void
 minstrel_ht_free(void *priv)
@@ -1725,6 +1731,7 @@ static const struct rate_control_ops mac80211_minstrel_ht = {
 	.alloc = minstrel_ht_alloc,
 	.free = minstrel_ht_free,
 #ifdef CONFIG_MAC80211_DEBUGFS
+	.add_debugfs = minstrel_ht_add_debugfs,
 	.add_sta_debugfs = minstrel_ht_add_sta_debugfs,
 #endif
 	.get_expected_throughput = minstrel_ht_get_expected_throughput,
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index f8d5c2515829..cd8487bc6fc2 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -231,7 +231,8 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
 	struct sta_info *sta;
 	int i = 0;
 
-	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+	list_for_each_entry_rcu(sta, &local->sta_list, list,
+				lockdep_is_held(&local->sta_mtx)) {
 		if (sdata != sta->sdata)
 			continue;
 		if (i < idx) {
diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c
index c151628bd416..3d980713a9e2 100644
--- a/net/mptcp/crypto.c
+++ b/net/mptcp/crypto.c
@@ -47,8 +47,6 @@ void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn)
 void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac)
 {
 	u8 input[SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE];
-	__be32 mptcp_hashed_key[SHA256_DIGEST_WORDS];
-	__be32 *hash_out = (__force __be32 *)hmac;
 	struct sha256_state state;
 	u8 key1be[8];
 	u8 key2be[8];
@@ -61,7 +59,7 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac)
 	put_unaligned_be64(key2, key2be);
 
 	/* Generate key xored with ipad */
-	memset(input, 0x36, SHA_MESSAGE_BYTES);
+	memset(input, 0x36, SHA256_BLOCK_SIZE);
 	for (i = 0; i < 8; i++)
 		input[i] ^= key1be[i];
 	for (i = 0; i < 8; i++)
@@ -78,7 +76,7 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac)
 	sha256_final(&state, &input[SHA256_BLOCK_SIZE]);
 
 	/* Prepare second part of hmac */
-	memset(input, 0x5C, SHA_MESSAGE_BYTES);
+	memset(input, 0x5C, SHA256_BLOCK_SIZE);
 	for (i = 0; i < 8; i++)
 		input[i] ^= key1be[i];
 	for (i = 0; i < 8; i++)
@@ -86,11 +84,7 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac)
 
 	sha256_init(&state);
 	sha256_update(&state, input, SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE);
-	sha256_final(&state, (u8 *)mptcp_hashed_key);
-
-	/* takes only first 160 bits */
-	for (i = 0; i < 5; i++)
-		hash_out[i] = mptcp_hashed_key[i];
+	sha256_final(&state, (u8 *)hmac);
 }
 
 #ifdef CONFIG_MPTCP_HMAC_TEST
@@ -101,29 +95,29 @@ struct test_cast {
 };
 
 /* we can't reuse RFC 4231 test vectors, as we have constraint on the
- * input and key size, and we truncate the output.
+ * input and key size.
  */
 static struct test_cast tests[] = {
 	{
 		.key = "0b0b0b0b0b0b0b0b",
 		.msg = "48692054",
-		.result = "8385e24fb4235ac37556b6b886db106284a1da67",
+		.result = "8385e24fb4235ac37556b6b886db106284a1da671699f46db1f235ec622dcafa",
 	},
 	{
 		.key = "aaaaaaaaaaaaaaaa",
 		.msg = "dddddddd",
-		.result = "2c5e219164ff1dca1c4a92318d847bb6b9d44492",
+		.result = "2c5e219164ff1dca1c4a92318d847bb6b9d44492984e1eb71aff9022f71046e9",
 	},
 	{
 		.key = "0102030405060708",
 		.msg = "cdcdcdcd",
-		.result = "e73b9ba9969969cefb04aa0d6df18ec2fcc075b6",
+		.result = "e73b9ba9969969cefb04aa0d6df18ec2fcc075b6f23b4d8c4da736a5dbbc6e7d",
 	},
 };
 
 static int __init test_mptcp_crypto(void)
 {
-	char hmac[20], hmac_hex[41];
+	char hmac[32], hmac_hex[65];
 	u32 nonce1, nonce2;
 	u64 key1, key2;
 	u8 msg[8];
@@ -140,11 +134,11 @@ static int __init test_mptcp_crypto(void)
 		put_unaligned_be32(nonce2, &msg[4]);
 
 		mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac);
-		for (j = 0; j < 20; ++j)
+		for (j = 0; j < 32; ++j)
 			sprintf(&hmac_hex[j << 1], "%02x", hmac[j] & 0xff);
-		hmac_hex[40] = 0;
+		hmac_hex[64] = 0;
 
-		if (memcmp(hmac_hex, tests[i].result, 40))
+		if (memcmp(hmac_hex, tests[i].result, 64))
 			pr_err("test %d failed, got %s expected %s", i,
 			       hmac_hex, tests[i].result);
 		else
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index faf57585b892..7793b6011fa7 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -7,6 +7,7 @@
 #define pr_fmt(fmt) "MPTCP: " fmt
 
 #include <linux/kernel.h>
+#include <crypto/sha.h>
 #include <net/tcp.h>
 #include <net/mptcp.h>
 #include "protocol.h"
@@ -16,10 +17,10 @@ static bool mptcp_cap_flag_sha256(u8 flags)
 	return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256;
 }
 
-void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
-			int opsize, struct tcp_options_received *opt_rx)
+static void mptcp_parse_option(const struct sk_buff *skb,
+			       const unsigned char *ptr, int opsize,
+			       struct mptcp_options_received *mp_opt)
 {
-	struct mptcp_options_received *mp_opt = &opt_rx->mptcp;
 	u8 subtype = *ptr >> 4;
 	int expected_opsize;
 	u8 version;
@@ -283,12 +284,20 @@ void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
 }
 
 void mptcp_get_options(const struct sk_buff *skb,
-		       struct tcp_options_received *opt_rx)
+		       struct mptcp_options_received *mp_opt)
 {
-	const unsigned char *ptr;
 	const struct tcphdr *th = tcp_hdr(skb);
-	int length = (th->doff * 4) - sizeof(struct tcphdr);
+	const unsigned char *ptr;
+	int length;
+
+	/* initialize option status */
+	mp_opt->mp_capable = 0;
+	mp_opt->mp_join = 0;
+	mp_opt->add_addr = 0;
+	mp_opt->rm_addr = 0;
+	mp_opt->dss = 0;
 
+	length = (th->doff * 4) - sizeof(struct tcphdr);
 	ptr = (const unsigned char *)(th + 1);
 
 	while (length > 0) {
@@ -308,7 +317,7 @@ void mptcp_get_options(const struct sk_buff *skb,
 			if (opsize > length)
 				return;	/* don't parse partial options */
 			if (opcode == TCPOPT_MPTCP)
-				mptcp_parse_option(skb, ptr, opsize, opt_rx);
+				mptcp_parse_option(skb, ptr, opsize, mp_opt);
 			ptr += opsize - 2;
 			length -= opsize;
 		}
@@ -344,28 +353,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 	return false;
 }
 
-void mptcp_rcv_synsent(struct sock *sk)
-{
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) {
-		subflow->mp_capable = 1;
-		subflow->can_ack = 1;
-		subflow->remote_key = tp->rx_opt.mptcp.sndr_key;
-		pr_debug("subflow=%p, remote_key=%llu", subflow,
-			 subflow->remote_key);
-	} else if (subflow->request_join && tp->rx_opt.mptcp.mp_join) {
-		subflow->mp_join = 1;
-		subflow->thmac = tp->rx_opt.mptcp.thmac;
-		subflow->remote_nonce = tp->rx_opt.mptcp.nonce;
-		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow,
-			 subflow->thmac, subflow->remote_nonce);
-	} else if (subflow->request_mptcp) {
-		tcp_sk(sk)->is_mptcp = 0;
-	}
-}
-
 /* MP_JOIN client subflow must wait for 4th ack before sending any data:
  * TCP can't schedule delack timer before the subflow is fully established.
  * MPTCP uses the delack timer to do 3rd ack retransmissions
@@ -549,7 +536,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 				  struct in_addr *addr)
 {
-	u8 hmac[MPTCP_ADDR_HMAC_LEN];
+	u8 hmac[SHA256_DIGEST_SIZE];
 	u8 msg[7];
 
 	msg[0] = addr_id;
@@ -559,14 +546,14 @@ static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 
 	mptcp_crypto_hmac_sha(key1, key2, msg, 7, hmac);
 
-	return get_unaligned_be64(hmac);
+	return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
 }
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 				   struct in6_addr *addr)
 {
-	u8 hmac[MPTCP_ADDR_HMAC_LEN];
+	u8 hmac[SHA256_DIGEST_SIZE];
 	u8 msg[19];
 
 	msg[0] = addr_id;
@@ -576,7 +563,7 @@ static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 
 	mptcp_crypto_hmac_sha(key1, key2, msg, 19, hmac);
 
-	return get_unaligned_be64(hmac);
+	return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
 }
 #endif
 
@@ -709,7 +696,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk,
 	if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1)
 		return subflow->mp_capable;
 
-	if (mp_opt->use_ack) {
+	if (mp_opt->dss && mp_opt->use_ack) {
 		/* subflows are fully established as soon as we get any
 		 * additional ack.
 		 */
@@ -717,8 +704,6 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk,
 		goto fully_established;
 	}
 
-	WARN_ON_ONCE(subflow->can_ack);
-
 	/* If the first established packet does not contain MP_CAPABLE + data
 	 * then fallback to TCP
 	 */
@@ -728,6 +713,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk,
 		return false;
 	}
 
+	if (unlikely(!READ_ONCE(msk->pm.server_side)))
+		pr_warn_once("bogus mpc option on established client sk");
 	subflow->fully_established = 1;
 	subflow->remote_key = mp_opt->sndr_key;
 	subflow->can_ack = 1;
@@ -819,41 +806,41 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-	struct mptcp_options_received *mp_opt;
+	struct mptcp_options_received mp_opt;
 	struct mptcp_ext *mpext;
 
-	mp_opt = &opt_rx->mptcp;
-	if (!check_fully_established(msk, sk, subflow, skb, mp_opt))
+	mptcp_get_options(skb, &mp_opt);
+	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
 		return;
 
-	if (mp_opt->add_addr && add_addr_hmac_valid(msk, mp_opt)) {
+	if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) {
 		struct mptcp_addr_info addr;
 
-		addr.port = htons(mp_opt->port);
-		addr.id = mp_opt->addr_id;
-		if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
+		addr.port = htons(mp_opt.port);
+		addr.id = mp_opt.addr_id;
+		if (mp_opt.family == MPTCP_ADDR_IPVERSION_4) {
 			addr.family = AF_INET;
-			addr.addr = mp_opt->addr;
+			addr.addr = mp_opt.addr;
 		}
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-		else if (mp_opt->family == MPTCP_ADDR_IPVERSION_6) {
+		else if (mp_opt.family == MPTCP_ADDR_IPVERSION_6) {
 			addr.family = AF_INET6;
-			addr.addr6 = mp_opt->addr6;
+			addr.addr6 = mp_opt.addr6;
 		}
 #endif
-		if (!mp_opt->echo)
+		if (!mp_opt.echo)
 			mptcp_pm_add_addr_received(msk, &addr);
-		mp_opt->add_addr = 0;
+		mp_opt.add_addr = 0;
 	}
 
-	if (!mp_opt->dss)
+	if (!mp_opt.dss)
 		return;
 
 	/* we can't wait for recvmsg() to update the ack_seq, otherwise
 	 * monodirectional flows will stuck
 	 */
-	if (mp_opt->use_ack)
-		update_una(msk, mp_opt);
+	if (mp_opt.use_ack)
+		update_una(msk, &mp_opt);
 
 	mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
 	if (!mpext)
@@ -861,8 +848,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 
 	memset(mpext, 0, sizeof(*mpext));
 
-	if (mp_opt->use_map) {
-		if (mp_opt->mpc_map) {
+	if (mp_opt.use_map) {
+		if (mp_opt.mpc_map) {
 			/* this is an MP_CAPABLE carrying MPTCP data
 			 * we know this map the first chunk of data
 			 */
@@ -872,16 +859,16 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 			mpext->subflow_seq = 1;
 			mpext->dsn64 = 1;
 			mpext->mpc_map = 1;
+			mpext->data_fin = 0;
 		} else {
-			mpext->data_seq = mp_opt->data_seq;
-			mpext->subflow_seq = mp_opt->subflow_seq;
-			mpext->dsn64 = mp_opt->dsn64;
+			mpext->data_seq = mp_opt.data_seq;
+			mpext->subflow_seq = mp_opt.subflow_seq;
+			mpext->dsn64 = mp_opt.dsn64;
+			mpext->data_fin = mp_opt.data_fin;
 		}
-		mpext->data_len = mp_opt->data_len;
+		mpext->data_len = mp_opt.data_len;
 		mpext->use_map = 1;
 	}
-
-	mpext->data_fin = mp_opt->data_fin;
 }
 
 void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 86d61ab34c7c..b78edf237ba0 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -599,12 +599,14 @@ static int mptcp_nl_fill_addr(struct sk_buff *skb,
 	    nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->ifindex))
 		goto nla_put_failure;
 
-	if (addr->family == AF_INET)
-		nla_put_in_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR4,
-				addr->addr.s_addr);
+	if (addr->family == AF_INET &&
+	    nla_put_in_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR4,
+			    addr->addr.s_addr))
+		goto nla_put_failure;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	else if (addr->family == AF_INET6)
-		nla_put_in6_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR6, &addr->addr6);
+	else if (addr->family == AF_INET6 &&
+		 nla_put_in6_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR6, &addr->addr6))
+		goto nla_put_failure;
 #endif
 	nla_nest_end(skb, attr);
 	return 0;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 939a5045181a..34dd0e278a82 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -97,12 +97,7 @@ static struct socket *__mptcp_tcp_fallback(struct mptcp_sock *msk)
 	if (likely(!__mptcp_needs_tcp_fallback(msk)))
 		return NULL;
 
-	if (msk->subflow) {
-		release_sock((struct sock *)msk);
-		return msk->subflow;
-	}
-
-	return NULL;
+	return msk->subflow;
 }
 
 static bool __mptcp_can_create_subflow(const struct mptcp_sock *msk)
@@ -734,9 +729,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			goto out;
 	}
 
+fallback:
 	ssock = __mptcp_tcp_fallback(msk);
 	if (unlikely(ssock)) {
-fallback:
+		release_sock(sk);
 		pr_debug("fallback passthrough");
 		ret = sock_sendmsg(ssock, msg);
 		return ret >= 0 ? ret + copied : (copied ? copied : ret);
@@ -769,8 +765,14 @@ fallback:
 		if (ret < 0)
 			break;
 		if (ret == 0 && unlikely(__mptcp_needs_tcp_fallback(msk))) {
+			/* Can happen for passive sockets:
+			 * 3WHS negotiated MPTCP, but first packet after is
+			 * plain TCP (e.g. due to middlebox filtering unknown
+			 * options).
+			 *
+			 * Fall back to TCP.
+			 */
 			release_sock(ssk);
-			ssock = __mptcp_tcp_fallback(msk);
 			goto fallback;
 		}
 
@@ -883,6 +885,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	ssock = __mptcp_tcp_fallback(msk);
 	if (unlikely(ssock)) {
 fallback:
+		release_sock(sk);
 		pr_debug("fallback-read subflow=%p",
 			 mptcp_subflow_ctx(ssock->sk));
 		copied = sock_recvmsg(ssock, msg, flags);
@@ -951,7 +954,8 @@ fallback:
 
 		pr_debug("block timeout %ld", timeo);
 		mptcp_wait_data(sk, &timeo);
-		if (unlikely(__mptcp_tcp_fallback(msk)))
+		ssock = __mptcp_tcp_fallback(msk);
+		if (unlikely(ssock))
 			goto fallback;
 	}
 
@@ -1259,11 +1263,14 @@ static void mptcp_close(struct sock *sk, long timeout)
 
 	lock_sock(sk);
 
-	mptcp_token_destroy(msk->token);
 	inet_sk_state_store(sk, TCP_CLOSE);
 
-	__mptcp_flush_join_list(msk);
-
+	/* be sure to always acquire the join list lock, to sync vs
+	 * mptcp_finish_join().
+	 */
+	spin_lock_bh(&msk->join_list_lock);
+	list_splice_tail_init(&msk->join_list, &msk->conn_list);
+	spin_unlock_bh(&msk->join_list_lock);
 	list_splice_init(&msk->conn_list, &conn_list);
 
 	data_fin_tx_seq = msk->write_seq;
@@ -1313,11 +1320,12 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
 
 static int mptcp_disconnect(struct sock *sk, int flags)
 {
-	lock_sock(sk);
-	__mptcp_clear_xmit(sk);
-	release_sock(sk);
-	mptcp_cancel_work(sk);
-	return tcp_disconnect(sk, flags);
+	/* Should never be called.
+	 * inet_stream_connect() calls ->disconnect, but that
+	 * refers to the subflow socket, not the mptcp one.
+	 */
+	WARN_ON_ONCE(1);
+	return 0;
 }
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -1329,7 +1337,9 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
 }
 #endif
 
-struct sock *mptcp_sk_clone(const struct sock *sk, struct request_sock *req)
+struct sock *mptcp_sk_clone(const struct sock *sk,
+			    const struct mptcp_options_received *mp_opt,
+			    struct request_sock *req)
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
 	struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
@@ -1352,26 +1362,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk, struct request_sock *req)
 	msk->subflow = NULL;
 
 	if (unlikely(mptcp_token_new_accept(subflow_req->token, nsk))) {
+		nsk->sk_state = TCP_CLOSE;
 		bh_unlock_sock(nsk);
 
 		/* we can't call into mptcp_close() here - possible BH context
-		 * free the sock directly
+		 * free the sock directly.
+		 * sk_clone_lock() sets nsk refcnt to two, hence call sk_free()
+		 * too.
 		 */
-		nsk->sk_prot->destroy(nsk);
+		sk_common_release(nsk);
 		sk_free(nsk);
 		return NULL;
 	}
 
 	msk->write_seq = subflow_req->idsn + 1;
 	atomic64_set(&msk->snd_una, msk->write_seq);
-	if (subflow_req->remote_key_valid) {
+	if (mp_opt->mp_capable) {
 		msk->can_ack = true;
-		msk->remote_key = subflow_req->remote_key;
+		msk->remote_key = mp_opt->sndr_key;
 		mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
 		ack_seq++;
 		msk->ack_seq = ack_seq;
 	}
 
+	sock_reset_flag(nsk, SOCK_RCU_FREE);
 	/* will be fully established after successful MPC subflow creation */
 	inet_sk_state_store(nsk, TCP_SYN_RECV);
 	bh_unlock_sock(nsk);
@@ -1428,6 +1442,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 		newsk = new_mptcp_sock;
 		mptcp_copy_inaddrs(newsk, ssk);
 		list_add(&subflow->node, &msk->conn_list);
+		inet_sk_state_store(newsk, TCP_ESTABLISHED);
 
 		bh_unlock_sock(new_mptcp_sock);
 
@@ -1445,6 +1460,7 @@ static void mptcp_destroy(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
+	mptcp_token_destroy(msk->token);
 	if (msk->cached_ext)
 		__skb_ext_put(msk->cached_ext);
 
@@ -1467,12 +1483,11 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname,
 	 */
 	lock_sock(sk);
 	ssock = __mptcp_tcp_fallback(msk);
+	release_sock(sk);
 	if (ssock)
 		return tcp_setsockopt(ssock->sk, level, optname, optval,
 				      optlen);
 
-	release_sock(sk);
-
 	return -EOPNOTSUPP;
 }
 
@@ -1492,12 +1507,11 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname,
 	 */
 	lock_sock(sk);
 	ssock = __mptcp_tcp_fallback(msk);
+	release_sock(sk);
 	if (ssock)
 		return tcp_getsockopt(ssock->sk, level, optname, optval,
 				      option);
 
-	release_sock(sk);
-
 	return -EOPNOTSUPP;
 }
 
@@ -1613,20 +1627,30 @@ bool mptcp_finish_join(struct sock *sk)
 	if (!msk->pm.server_side)
 		return true;
 
-	/* passive connection, attach to msk socket */
+	if (!mptcp_pm_allow_new_subflow(msk))
+		return false;
+
+	/* active connections are already on conn_list, and we can't acquire
+	 * msk lock here.
+	 * use the join list lock as synchronization point and double-check
+	 * msk status to avoid racing with mptcp_close()
+	 */
+	spin_lock_bh(&msk->join_list_lock);
+	ret = inet_sk_state_load(parent) == TCP_ESTABLISHED;
+	if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node)))
+		list_add_tail(&subflow->node, &msk->join_list);
+	spin_unlock_bh(&msk->join_list_lock);
+	if (!ret)
+		return false;
+
+	/* attach to msk socket only after we are sure he will deal with us
+	 * at close time
+	 */
 	parent_sock = READ_ONCE(parent->sk_socket);
 	if (parent_sock && !sk->sk_socket)
 		mptcp_sock_graft(sk, parent_sock);
-
-	ret = mptcp_pm_allow_new_subflow(msk);
-	if (ret) {
-		/* active connections are already on conn_list */
-		spin_lock_bh(&msk->join_list_lock);
-		if (!WARN_ON_ONCE(!list_empty(&subflow->node)))
-			list_add_tail(&subflow->node, &msk->join_list);
-		spin_unlock_bh(&msk->join_list_lock);
-	}
-	return ret;
+	subflow->map_seq = msk->ack_seq;
+	return true;
 }
 
 bool mptcp_sk_is_subflow(const struct sock *sk)
@@ -1700,6 +1724,14 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	int err;
 
 	lock_sock(sock->sk);
+	if (sock->state != SS_UNCONNECTED && msk->subflow) {
+		/* pending connection or invalid state, let existing subflow
+		 * cope with that
+		 */
+		ssock = msk->subflow;
+		goto do_connect;
+	}
+
 	ssock = __mptcp_socket_create(msk, TCP_SYN_SENT);
 	if (IS_ERR(ssock)) {
 		err = PTR_ERR(ssock);
@@ -1714,9 +1746,17 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		mptcp_subflow_ctx(ssock->sk)->request_mptcp = 0;
 #endif
 
+do_connect:
 	err = ssock->ops->connect(ssock, uaddr, addr_len, flags);
-	inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk));
-	mptcp_copy_inaddrs(sock->sk, ssock->sk);
+	sock->state = ssock->state;
+
+	/* on successful connect, the msk state will be moved to established by
+	 * subflow_finish_connect()
+	 */
+	if (!err || err == EINPROGRESS)
+		mptcp_copy_inaddrs(sock->sk, ssock->sk);
+	else
+		inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk));
 
 unlock:
 	release_sock(sock->sk);
@@ -1774,6 +1814,8 @@ static int mptcp_listen(struct socket *sock, int backlog)
 		goto unlock;
 	}
 
+	sock_set_flag(sock->sk, SOCK_RCU_FREE);
+
 	err = ssock->ops->listen(ssock, backlog);
 	inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk));
 	if (!err)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 67448002a2d7..d0803dfb8108 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -81,7 +81,6 @@
 
 /* MPTCP ADD_ADDR flags */
 #define MPTCP_ADDR_ECHO		BIT(0)
-#define MPTCP_ADDR_HMAC_LEN	20
 #define MPTCP_ADDR_IPVERSION_4	4
 #define MPTCP_ADDR_IPVERSION_6	6
 
@@ -91,6 +90,45 @@
 #define MPTCP_WORK_RTX		2
 #define MPTCP_WORK_EOF		3
 
+struct mptcp_options_received {
+	u64	sndr_key;
+	u64	rcvr_key;
+	u64	data_ack;
+	u64	data_seq;
+	u32	subflow_seq;
+	u16	data_len;
+	u16	mp_capable : 1,
+		mp_join : 1,
+		dss : 1,
+		add_addr : 1,
+		rm_addr : 1,
+		family : 4,
+		echo : 1,
+		backup : 1;
+	u32	token;
+	u32	nonce;
+	u64	thmac;
+	u8	hmac[20];
+	u8	join_id;
+	u8	use_map:1,
+		dsn64:1,
+		data_fin:1,
+		use_ack:1,
+		ack64:1,
+		mpc_map:1,
+		__unused:2;
+	u8	addr_id;
+	u8	rm_id;
+	union {
+		struct in_addr	addr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		struct in6_addr	addr6;
+#endif
+	};
+	u64	ahmac;
+	u16	port;
+};
+
 static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
 {
 	return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) |
@@ -206,12 +244,10 @@ struct mptcp_subflow_request_sock {
 	struct	tcp_request_sock sk;
 	u16	mp_capable : 1,
 		mp_join : 1,
-		backup : 1,
-		remote_key_valid : 1;
+		backup : 1;
 	u8	local_id;
 	u8	remote_id;
 	u64	local_key;
-	u64	remote_key;
 	u64	idsn;
 	u32	token;
 	u32	ssn_offset;
@@ -332,9 +368,11 @@ void mptcp_proto_init(void);
 int mptcp_proto_v6_init(void);
 #endif
 
-struct sock *mptcp_sk_clone(const struct sock *sk, struct request_sock *req);
+struct sock *mptcp_sk_clone(const struct sock *sk,
+			    const struct mptcp_options_received *mp_opt,
+			    struct request_sock *req);
 void mptcp_get_options(const struct sk_buff *skb,
-		       struct tcp_options_received *opt_rx);
+		       struct mptcp_options_received *mp_opt);
 
 void mptcp_finish_connect(struct sock *sk);
 void mptcp_data_ready(struct sock *sk, struct sock *ssk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 50a8bea987c6..8968b2c065e7 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <crypto/algapi.h>
+#include <crypto/sha.h>
 #include <net/sock.h>
 #include <net/inet_common.h>
 #include <net/inet_hashtables.h>
@@ -89,7 +90,7 @@ static bool subflow_token_join_request(struct request_sock *req,
 				       const struct sk_buff *skb)
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
-	u8 hmac[MPTCPOPT_HMAC_LEN];
+	u8 hmac[SHA256_DIGEST_SIZE];
 	struct mptcp_sock *msk;
 	int local_id;
 
@@ -124,16 +125,14 @@ static void subflow_init_req(struct request_sock *req,
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
-	struct tcp_options_received rx_opt;
+	struct mptcp_options_received mp_opt;
 
 	pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
 
-	memset(&rx_opt.mptcp, 0, sizeof(rx_opt.mptcp));
-	mptcp_get_options(skb, &rx_opt);
+	mptcp_get_options(skb, &mp_opt);
 
 	subflow_req->mp_capable = 0;
 	subflow_req->mp_join = 0;
-	subflow_req->remote_key_valid = 0;
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
@@ -143,16 +142,16 @@ static void subflow_init_req(struct request_sock *req,
 		return;
 #endif
 
-	if (rx_opt.mptcp.mp_capable) {
+	if (mp_opt.mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
-		if (rx_opt.mptcp.mp_join)
+		if (mp_opt.mp_join)
 			return;
-	} else if (rx_opt.mptcp.mp_join) {
+	} else if (mp_opt.mp_join) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
 	}
 
-	if (rx_opt.mptcp.mp_capable && listener->request_mptcp) {
+	if (mp_opt.mp_capable && listener->request_mptcp) {
 		int err;
 
 		err = mptcp_token_new_request(req);
@@ -160,13 +159,13 @@ static void subflow_init_req(struct request_sock *req,
 			subflow_req->mp_capable = 1;
 
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
-	} else if (rx_opt.mptcp.mp_join && listener->request_mptcp) {
+	} else if (mp_opt.mp_join && listener->request_mptcp) {
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
 		subflow_req->mp_join = 1;
-		subflow_req->backup = rx_opt.mptcp.backup;
-		subflow_req->remote_id = rx_opt.mptcp.join_id;
-		subflow_req->token = rx_opt.mptcp.token;
-		subflow_req->remote_nonce = rx_opt.mptcp.nonce;
+		subflow_req->backup = mp_opt.backup;
+		subflow_req->remote_id = mp_opt.join_id;
+		subflow_req->token = mp_opt.token;
+		subflow_req->remote_nonce = mp_opt.nonce;
 		pr_debug("token=%u, remote_nonce=%u", subflow_req->token,
 			 subflow_req->remote_nonce);
 		if (!subflow_token_join_request(req, skb)) {
@@ -203,7 +202,7 @@ static void subflow_v6_init_req(struct request_sock *req,
 /* validate received truncated hmac and create hmac for third ACK */
 static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
 {
-	u8 hmac[MPTCPOPT_HMAC_LEN];
+	u8 hmac[SHA256_DIGEST_SIZE];
 	u64 thmac;
 
 	subflow_generate_hmac(subflow->remote_key, subflow->local_key,
@@ -222,29 +221,55 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_options_received mp_opt;
 	struct sock *parent = subflow->conn;
+	struct tcp_sock *tp = tcp_sk(sk);
 
 	subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);
 
-	if (inet_sk_state_load(parent) != TCP_ESTABLISHED) {
+	if (inet_sk_state_load(parent) == TCP_SYN_SENT) {
 		inet_sk_state_store(parent, TCP_ESTABLISHED);
 		parent->sk_state_change(parent);
 	}
 
-	if (subflow->conn_finished || !tcp_sk(sk)->is_mptcp)
+	/* be sure no special action on any packet other than syn-ack */
+	if (subflow->conn_finished)
+		return;
+
+	subflow->conn_finished = 1;
+
+	mptcp_get_options(skb, &mp_opt);
+	if (subflow->request_mptcp && mp_opt.mp_capable) {
+		subflow->mp_capable = 1;
+		subflow->can_ack = 1;
+		subflow->remote_key = mp_opt.sndr_key;
+		pr_debug("subflow=%p, remote_key=%llu", subflow,
+			 subflow->remote_key);
+	} else if (subflow->request_join && mp_opt.mp_join) {
+		subflow->mp_join = 1;
+		subflow->thmac = mp_opt.thmac;
+		subflow->remote_nonce = mp_opt.nonce;
+		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow,
+			 subflow->thmac, subflow->remote_nonce);
+	} else if (subflow->request_mptcp) {
+		tp->is_mptcp = 0;
+	}
+
+	if (!tp->is_mptcp)
 		return;
 
 	if (subflow->mp_capable) {
 		pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk),
 			 subflow->remote_key);
 		mptcp_finish_connect(sk);
-		subflow->conn_finished = 1;
 
 		if (skb) {
 			pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq);
 			subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
 		}
 	} else if (subflow->mp_join) {
+		u8 hmac[SHA256_DIGEST_SIZE];
+
 		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u",
 			 subflow, subflow->thmac,
 			 subflow->remote_nonce);
@@ -257,7 +282,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow_generate_hmac(subflow->local_key, subflow->remote_key,
 				      subflow->local_nonce,
 				      subflow->remote_nonce,
-				      subflow->hmac);
+				      hmac);
+
+		memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN);
 
 		if (skb)
 			subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
@@ -265,7 +292,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		if (!mptcp_finish_join(sk))
 			goto do_reset;
 
-		subflow->conn_finished = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
 	} else {
 do_reset:
@@ -323,10 +349,10 @@ drop:
 
 /* validate hmac received in third ACK */
 static bool subflow_hmac_valid(const struct request_sock *req,
-			       const struct tcp_options_received *rx_opt)
+			       const struct mptcp_options_received *mp_opt)
 {
 	const struct mptcp_subflow_request_sock *subflow_req;
-	u8 hmac[MPTCPOPT_HMAC_LEN];
+	u8 hmac[SHA256_DIGEST_SIZE];
 	struct mptcp_sock *msk;
 	bool ret;
 
@@ -340,13 +366,53 @@ static bool subflow_hmac_valid(const struct request_sock *req,
 			      subflow_req->local_nonce, hmac);
 
 	ret = true;
-	if (crypto_memneq(hmac, rx_opt->mptcp.hmac, sizeof(hmac)))
+	if (crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN))
 		ret = false;
 
 	sock_put((struct sock *)msk);
 	return ret;
 }
 
+static void mptcp_sock_destruct(struct sock *sk)
+{
+	/* if new mptcp socket isn't accepted, it is free'd
+	 * from the tcp listener sockets request queue, linked
+	 * from req->sk.  The tcp socket is released.
+	 * This calls the ULP release function which will
+	 * also remove the mptcp socket, via
+	 * sock_put(ctx->conn).
+	 *
+	 * Problem is that the mptcp socket will not be in
+	 * SYN_RECV state and doesn't have SOCK_DEAD flag.
+	 * Both result in warnings from inet_sock_destruct.
+	 */
+
+	if (sk->sk_state == TCP_SYN_RECV) {
+		sk->sk_state = TCP_CLOSE;
+		WARN_ON_ONCE(sk->sk_socket);
+		sock_orphan(sk);
+	}
+
+	inet_sock_destruct(sk);
+}
+
+static void mptcp_force_close(struct sock *sk)
+{
+	inet_sk_state_store(sk, TCP_CLOSE);
+	sk_common_release(sk);
+}
+
+static void subflow_ulp_fallback(struct sock *sk,
+				 struct mptcp_subflow_context *old_ctx)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	mptcp_subflow_tcp_fallback(sk, old_ctx);
+	icsk->icsk_ulp_ops = NULL;
+	rcu_assign_pointer(icsk->icsk_ulp_data, NULL);
+	tcp_sk(sk)->is_mptcp = 0;
+}
+
 static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 					  struct sk_buff *skb,
 					  struct request_sock *req,
@@ -356,13 +422,18 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
 	struct mptcp_subflow_request_sock *subflow_req;
-	struct tcp_options_received opt_rx;
+	struct mptcp_options_received mp_opt;
 	bool fallback_is_fatal = false;
 	struct sock *new_msk = NULL;
+	bool fallback = false;
 	struct sock *child;
 
 	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
 
+	/* we need later a valid 'mp_capable' value even when options are not
+	 * parsed
+	 */
+	mp_opt.mp_capable = 0;
 	if (tcp_rsk(req)->is_mptcp == 0)
 		goto create_child;
 
@@ -377,26 +448,21 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			goto create_msk;
 		}
 
-		opt_rx.mptcp.mp_capable = 0;
-		mptcp_get_options(skb, &opt_rx);
-		if (opt_rx.mptcp.mp_capable) {
-			subflow_req->remote_key = opt_rx.mptcp.sndr_key;
-			subflow_req->remote_key_valid = 1;
-		} else {
-			subflow_req->mp_capable = 0;
+		mptcp_get_options(skb, &mp_opt);
+		if (!mp_opt.mp_capable) {
+			fallback = true;
 			goto create_child;
 		}
 
 create_msk:
-		new_msk = mptcp_sk_clone(listener->conn, req);
+		new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req);
 		if (!new_msk)
-			subflow_req->mp_capable = 0;
+			fallback = true;
 	} else if (subflow_req->mp_join) {
 		fallback_is_fatal = true;
-		opt_rx.mptcp.mp_join = 0;
-		mptcp_get_options(skb, &opt_rx);
-		if (!opt_rx.mptcp.mp_join ||
-		    !subflow_hmac_valid(req, &opt_rx)) {
+		mptcp_get_options(skb, &mp_opt);
+		if (!mp_opt.mp_join ||
+		    !subflow_hmac_valid(req, &mp_opt)) {
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
 			return NULL;
 		}
@@ -409,12 +475,18 @@ create_child:
 	if (child && *own_req) {
 		struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);
 
-		/* we have null ctx on TCP fallback, which is fatal on
-		 * MPJ handshake
+		/* we need to fallback on ctx allocation failure and on pre-reqs
+		 * checking above. In the latter scenario we additionally need
+		 * to reset the context to non MPTCP status.
 		 */
-		if (!ctx) {
+		if (!ctx || fallback) {
 			if (fallback_is_fatal)
 				goto close_child;
+
+			if (ctx) {
+				subflow_ulp_fallback(child, ctx);
+				kfree_rcu(ctx, rcu);
+			}
 			goto out;
 		}
 
@@ -422,10 +494,17 @@ create_child:
 			/* new mpc subflow takes ownership of the newly
 			 * created mptcp socket
 			 */
-			inet_sk_state_store(new_msk, TCP_ESTABLISHED);
+			new_msk->sk_destruct = mptcp_sock_destruct;
 			mptcp_pm_new_connection(mptcp_sk(new_msk), 1);
 			ctx->conn = new_msk;
 			new_msk = NULL;
+
+			/* with OoO packets we can reach here without ingress
+			 * mpc option
+			 */
+			ctx->remote_key = mp_opt.sndr_key;
+			ctx->fully_established = mp_opt.mp_capable;
+			ctx->can_ack = mp_opt.mp_capable;
 		} else if (ctx->mp_join) {
 			struct mptcp_sock *owner;
 
@@ -444,7 +523,14 @@ create_child:
 out:
 	/* dispose of the left over mptcp master, if any */
 	if (unlikely(new_msk))
-		sock_put(new_msk);
+		mptcp_force_close(new_msk);
+
+	/* check for expected invariant - should never trigger, just help
+	 * catching eariler subtle bugs
+	 */
+	WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp &&
+		     (!mptcp_subflow_ctx(child) ||
+		      !mptcp_subflow_ctx(child)->conn));
 	return child;
 
 close_child:
@@ -931,6 +1017,16 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 	if (err)
 		return err;
 
+	/* the newly created socket really belongs to the owning MPTCP master
+	 * socket, even if for additional subflows the allocation is performed
+	 * by a kernel workqueue. Adjust inode references, so that the
+	 * procfs/diag interaces really show this one belonging to the correct
+	 * user.
+	 */
+	SOCK_INODE(sf)->i_ino = SOCK_INODE(sk->sk_socket)->i_ino;
+	SOCK_INODE(sf)->i_uid = SOCK_INODE(sk->sk_socket)->i_uid;
+	SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid;
+
 	subflow = mptcp_subflow_ctx(sf->sk);
 	pr_debug("subflow=%p", subflow);
 
@@ -1047,17 +1143,6 @@ static void subflow_ulp_release(struct sock *sk)
 	kfree_rcu(ctx, rcu);
 }
 
-static void subflow_ulp_fallback(struct sock *sk,
-				 struct mptcp_subflow_context *old_ctx)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-
-	mptcp_subflow_tcp_fallback(sk, old_ctx);
-	icsk->icsk_ulp_ops = NULL;
-	rcu_assign_pointer(icsk->icsk_ulp_data, NULL);
-	tcp_sk(sk)->is_mptcp = 0;
-}
-
 static void subflow_ulp_clone(const struct request_sock *req,
 			      struct sock *newsk,
 			      const gfp_t priority)
@@ -1091,9 +1176,6 @@ static void subflow_ulp_clone(const struct request_sock *req,
 		 * is fully established only after we receive the remote key
 		 */
 		new_ctx->mp_capable = 1;
-		new_ctx->fully_established = subflow_req->remote_key_valid;
-		new_ctx->can_ack = subflow_req->remote_key_valid;
-		new_ctx->remote_key = subflow_req->remote_key;
 		new_ctx->local_key = subflow_req->local_key;
 		new_ctx->token = subflow_req->token;
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 8dd17589217d..340cb955af25 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -86,7 +86,8 @@ find_set_type(const char *name, u8 family, u8 revision)
 {
 	struct ip_set_type *type;
 
-	list_for_each_entry_rcu(type, &ip_set_type_list, list)
+	list_for_each_entry_rcu(type, &ip_set_type_list, list,
+				lockdep_is_held(&ip_set_type_mutex))
 		if (STRNCMP(type->name, name) &&
 		    (type->family == family ||
 		     type->family == NFPROTO_UNSPEC) &&
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index cd747c0962fd..5a67f7966574 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -59,7 +59,7 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
 	/* Don't lookup sub-counters at all */
 	opt->cmdflags &= ~IPSET_FLAG_MATCH_COUNTERS;
 	if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE)
-		opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE;
+		opt->cmdflags |= IPSET_FLAG_SKIP_COUNTER_UPDATE;
 	list_for_each_entry_rcu(e, &map->members, list) {
 		ret = ip_set_test(e->id, skb, par, opt);
 		if (ret <= 0)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index c4582eb71766..bb72ca5f3999 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1519,9 +1519,9 @@ __nf_conntrack_alloc(struct net *net,
 	ct->status = 0;
 	ct->timeout = 0;
 	write_pnet(&ct->ct_net, net);
-	memset(&ct->__nfct_init_offset[0], 0,
+	memset(&ct->__nfct_init_offset, 0,
 	       offsetof(struct nf_conn, proto) -
-	       offsetof(struct nf_conn, __nfct_init_offset[0]));
+	       offsetof(struct nf_conn, __nfct_init_offset));
 
 	nf_ct_zone_add(ct, zone);
 
@@ -2016,22 +2016,18 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
 	nf_conntrack_get(skb_nfct(nskb));
 }
 
-static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
+static int __nf_conntrack_update(struct net *net, struct sk_buff *skb,
+				 struct nf_conn *ct,
+				 enum ip_conntrack_info ctinfo)
 {
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conntrack_tuple tuple;
-	enum ip_conntrack_info ctinfo;
 	struct nf_nat_hook *nat_hook;
 	unsigned int status;
-	struct nf_conn *ct;
 	int dataoff;
 	u16 l3num;
 	u8 l4num;
 
-	ct = nf_ct_get(skb, &ctinfo);
-	if (!ct || nf_ct_is_confirmed(ct))
-		return 0;
-
 	l3num = nf_ct_l3num(ct);
 
 	dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num);
@@ -2088,6 +2084,76 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
 	return 0;
 }
 
+/* This packet is coming from userspace via nf_queue, complete the packet
+ * processing after the helper invocation in nf_confirm().
+ */
+static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct,
+			       enum ip_conntrack_info ctinfo)
+{
+	const struct nf_conntrack_helper *helper;
+	const struct nf_conn_help *help;
+	int protoff;
+
+	help = nfct_help(ct);
+	if (!help)
+		return 0;
+
+	helper = rcu_dereference(help->helper);
+	if (!(helper->flags & NF_CT_HELPER_F_USERSPACE))
+		return 0;
+
+	switch (nf_ct_l3num(ct)) {
+	case NFPROTO_IPV4:
+		protoff = skb_network_offset(skb) + ip_hdrlen(skb);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case NFPROTO_IPV6: {
+		__be16 frag_off;
+		u8 pnum;
+
+		pnum = ipv6_hdr(skb)->nexthdr;
+		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
+					   &frag_off);
+		if (protoff < 0 || (frag_off & htons(~0x7)) != 0)
+			return 0;
+		break;
+	}
+#endif
+	default:
+		return 0;
+	}
+
+	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
+	    !nf_is_loopback_packet(skb)) {
+		if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) {
+			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
+			return -1;
+		}
+	}
+
+	/* We've seen it coming out the other side: confirm it */
+	return nf_conntrack_confirm(skb) == NF_DROP ? - 1 : 0;
+}
+
+static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
+{
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+	int err;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct)
+		return 0;
+
+	if (!nf_ct_is_confirmed(ct)) {
+		err = __nf_conntrack_update(net, skb, ct, ctinfo);
+		if (err < 0)
+			return err;
+	}
+
+	return nf_confirm_cthelper(skb, ct, ctinfo);
+}
+
 static bool nf_conntrack_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
 				       const struct sk_buff *skb)
 {
@@ -2139,8 +2205,19 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data),
 		nf_conntrack_lock(lockp);
 		if (*bucket < nf_conntrack_htable_size) {
 			hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) {
-				if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+				if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY)
 					continue;
+				/* All nf_conn objects are added to hash table twice, one
+				 * for original direction tuple, once for the reply tuple.
+				 *
+				 * Exception: In the IPS_NAT_CLASH case, only the reply
+				 * tuple is added (the original tuple already existed for
+				 * a different object).
+				 *
+				 * We only need to call the iterator once for each
+				 * conntrack, so we just use the 'reply' direction
+				 * tuple while iterating.
+				 */
 				ct = nf_ct_tuplehash_to_ctrack(h);
 				if (iter(ct, data))
 					goto found;
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index a971183f11af..1f44d523b512 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -72,24 +72,32 @@ EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn);
 
 #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
 /* PptpControlMessageType names */
-const char *const pptp_msg_name[] = {
-	"UNKNOWN_MESSAGE",
-	"START_SESSION_REQUEST",
-	"START_SESSION_REPLY",
-	"STOP_SESSION_REQUEST",
-	"STOP_SESSION_REPLY",
-	"ECHO_REQUEST",
-	"ECHO_REPLY",
-	"OUT_CALL_REQUEST",
-	"OUT_CALL_REPLY",
-	"IN_CALL_REQUEST",
-	"IN_CALL_REPLY",
-	"IN_CALL_CONNECT",
-	"CALL_CLEAR_REQUEST",
-	"CALL_DISCONNECT_NOTIFY",
-	"WAN_ERROR_NOTIFY",
-	"SET_LINK_INFO"
+static const char *const pptp_msg_name_array[PPTP_MSG_MAX + 1] = {
+	[0]				= "UNKNOWN_MESSAGE",
+	[PPTP_START_SESSION_REQUEST]	= "START_SESSION_REQUEST",
+	[PPTP_START_SESSION_REPLY]	= "START_SESSION_REPLY",
+	[PPTP_STOP_SESSION_REQUEST]	= "STOP_SESSION_REQUEST",
+	[PPTP_STOP_SESSION_REPLY]	= "STOP_SESSION_REPLY",
+	[PPTP_ECHO_REQUEST]		= "ECHO_REQUEST",
+	[PPTP_ECHO_REPLY]		= "ECHO_REPLY",
+	[PPTP_OUT_CALL_REQUEST]		= "OUT_CALL_REQUEST",
+	[PPTP_OUT_CALL_REPLY]		= "OUT_CALL_REPLY",
+	[PPTP_IN_CALL_REQUEST]		= "IN_CALL_REQUEST",
+	[PPTP_IN_CALL_REPLY]		= "IN_CALL_REPLY",
+	[PPTP_IN_CALL_CONNECT]		= "IN_CALL_CONNECT",
+	[PPTP_CALL_CLEAR_REQUEST]	= "CALL_CLEAR_REQUEST",
+	[PPTP_CALL_DISCONNECT_NOTIFY]	= "CALL_DISCONNECT_NOTIFY",
+	[PPTP_WAN_ERROR_NOTIFY]		= "WAN_ERROR_NOTIFY",
+	[PPTP_SET_LINK_INFO]		= "SET_LINK_INFO"
 };
+
+const char *pptp_msg_name(u_int16_t msg)
+{
+	if (msg > PPTP_MSG_MAX)
+		return pptp_msg_name_array[0];
+
+	return pptp_msg_name_array[msg];
+}
 EXPORT_SYMBOL(pptp_msg_name);
 #endif
 
@@ -276,7 +284,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound;
 
 	msg = ntohs(ctlh->messageType);
-	pr_debug("inbound control message %s\n", pptp_msg_name[msg]);
+	pr_debug("inbound control message %s\n", pptp_msg_name(msg));
 
 	switch (msg) {
 	case PPTP_START_SESSION_REPLY:
@@ -311,7 +319,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		pcid = pptpReq->ocack.peersCallID;
 		if (info->pns_call_id != pcid)
 			goto invalid;
-		pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name[msg],
+		pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name(msg),
 			 ntohs(cid), ntohs(pcid));
 
 		if (pptpReq->ocack.resultCode == PPTP_OUTCALL_CONNECT) {
@@ -328,7 +336,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 			goto invalid;
 
 		cid = pptpReq->icreq.callID;
-		pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid));
+		pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid));
 		info->cstate = PPTP_CALL_IN_REQ;
 		info->pac_call_id = cid;
 		break;
@@ -347,7 +355,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		if (info->pns_call_id != pcid)
 			goto invalid;
 
-		pr_debug("%s, PCID=%X\n", pptp_msg_name[msg], ntohs(pcid));
+		pr_debug("%s, PCID=%X\n", pptp_msg_name(msg), ntohs(pcid));
 		info->cstate = PPTP_CALL_IN_CONF;
 
 		/* we expect a GRE connection from PAC to PNS */
@@ -357,7 +365,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	case PPTP_CALL_DISCONNECT_NOTIFY:
 		/* server confirms disconnect */
 		cid = pptpReq->disc.callID;
-		pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid));
+		pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid));
 		info->cstate = PPTP_CALL_NONE;
 
 		/* untrack this call id, unexpect GRE packets */
@@ -384,7 +392,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff,
 invalid:
 	pr_debug("invalid %s: type=%d cid=%u pcid=%u "
 		 "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n",
-		 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0],
+		 pptp_msg_name(msg),
 		 msg, ntohs(cid), ntohs(pcid),  info->cstate, info->sstate,
 		 ntohs(info->pns_call_id), ntohs(info->pac_call_id));
 	return NF_ACCEPT;
@@ -404,7 +412,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 	typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound;
 
 	msg = ntohs(ctlh->messageType);
-	pr_debug("outbound control message %s\n", pptp_msg_name[msg]);
+	pr_debug("outbound control message %s\n", pptp_msg_name(msg));
 
 	switch (msg) {
 	case PPTP_START_SESSION_REQUEST:
@@ -426,7 +434,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		info->cstate = PPTP_CALL_OUT_REQ;
 		/* track PNS call id */
 		cid = pptpReq->ocreq.callID;
-		pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid));
+		pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid));
 		info->pns_call_id = cid;
 		break;
 
@@ -440,7 +448,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 		pcid = pptpReq->icack.peersCallID;
 		if (info->pac_call_id != pcid)
 			goto invalid;
-		pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name[msg],
+		pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name(msg),
 			 ntohs(cid), ntohs(pcid));
 
 		if (pptpReq->icack.resultCode == PPTP_INCALL_ACCEPT) {
@@ -480,7 +488,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff,
 invalid:
 	pr_debug("invalid %s: type=%d cid=%u pcid=%u "
 		 "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n",
-		 msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0],
+		 pptp_msg_name(msg),
 		 msg, ntohs(cid), ntohs(pcid),  info->cstate, info->sstate,
 		 ntohs(info->pns_call_id), ntohs(info->pac_call_id));
 	return NF_ACCEPT;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index c0cb79495c35..42da6e337276 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -284,7 +284,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 
 	if (nf_flow_has_expired(flow))
 		flow_offload_fixup_ct(flow->ct);
-	else if (test_bit(NF_FLOW_TEARDOWN, &flow->flags))
+	else
 		flow_offload_fixup_ct_timeout(flow->ct);
 
 	flow_offload_free(flow);
@@ -361,8 +361,10 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
 {
 	struct nf_flowtable *flow_table = data;
 
-	if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) ||
-	    test_bit(NF_FLOW_TEARDOWN, &flow->flags)) {
+	if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct))
+		set_bit(NF_FLOW_TEARDOWN, &flow->flags);
+
+	if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) {
 		if (test_bit(NF_FLOW_HW, &flow->flags)) {
 			if (!test_bit(NF_FLOW_HW_DYING, &flow->flags))
 				nf_flow_offload_del(flow_table, flow);
@@ -421,10 +423,12 @@ void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
 
 	down_write(&flow_table->flow_block_lock);
 	block_cb = flow_block_cb_lookup(block, cb, cb_priv);
-	if (block_cb)
+	if (block_cb) {
 		list_del(&block_cb->list);
-	else
+		flow_block_cb_free(block_cb);
+	} else {
 		WARN_ON(true);
+	}
 	up_write(&flow_table->flow_block_lock);
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_offload_del_cb);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index e3b099c14eff..2276a73ccba2 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -817,6 +817,7 @@ static void flow_offload_work_handler(struct work_struct *work)
 			WARN_ON_ONCE(1);
 	}
 
+	clear_bit(NF_FLOW_HW_PENDING, &offload->flow->flags);
 	kfree(offload);
 }
 
@@ -831,9 +832,14 @@ nf_flow_offload_work_alloc(struct nf_flowtable *flowtable,
 {
 	struct flow_offload_work *offload;
 
+	if (test_and_set_bit(NF_FLOW_HW_PENDING, &flow->flags))
+		return NULL;
+
 	offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC);
-	if (!offload)
+	if (!offload) {
+		clear_bit(NF_FLOW_HW_PENDING, &flow->flags);
 		return NULL;
+	}
 
 	offload->cmd = cmd;
 	offload->flow = flow;
@@ -1056,7 +1062,7 @@ static struct flow_indr_block_entry block_ing_entry = {
 int nf_flow_table_offload_init(void)
 {
 	nf_flow_offload_wq  = alloc_workqueue("nf_flow_table_offload",
-					      WQ_UNBOUND | WQ_MEM_RECLAIM, 0);
+					      WQ_UNBOUND, 0);
 	if (!nf_flow_offload_wq)
 		return -ENOMEM;
 
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 64eedc17037a..59151dc07fdc 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -68,15 +68,13 @@ static bool udp_manip_pkt(struct sk_buff *skb,
 			  enum nf_nat_manip_type maniptype)
 {
 	struct udphdr *hdr;
-	bool do_csum;
 
 	if (skb_ensure_writable(skb, hdroff + sizeof(*hdr)))
 		return false;
 
 	hdr = (struct udphdr *)(skb->data + hdroff);
-	do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL;
+	__udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check);
 
-	__udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, do_csum);
 	return true;
 }
 
@@ -1035,8 +1033,8 @@ int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops)
 	ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops,
 				 ARRAY_SIZE(nf_nat_ipv4_ops));
 	if (ret)
-		nf_nat_ipv6_unregister_fn(net, ops);
-
+		nf_nat_unregister_fn(net, NFPROTO_IPV6, ops,
+					ARRAY_SIZE(nf_nat_ipv6_ops));
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4471393da6d8..9780bd93b7e4 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3542,6 +3542,7 @@ cont:
 			continue;
 		if (!strcmp(set->name, i->name)) {
 			kfree(set->name);
+			set->name = NULL;
 			return -ENFILE;
 		}
 	}
@@ -3961,8 +3962,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 		if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT |
 			      NFT_SET_INTERVAL | NFT_SET_TIMEOUT |
 			      NFT_SET_MAP | NFT_SET_EVAL |
-			      NFT_SET_OBJECT))
-			return -EINVAL;
+			      NFT_SET_OBJECT | NFT_SET_CONCAT))
+			return -EOPNOTSUPP;
 		/* Only one of these operations is supported */
 		if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) ==
 			     (NFT_SET_MAP | NFT_SET_OBJECT))
@@ -4000,7 +4001,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 		objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
 		if (objtype == NFT_OBJECT_UNSPEC ||
 		    objtype > NFT_OBJECT_MAX)
-			return -EINVAL;
+			return -EOPNOTSUPP;
 	} else if (flags & NFT_SET_OBJECT)
 		return -EINVAL;
 	else
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index a5f294aa8e4c..5b0d0a77379c 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -103,7 +103,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 	if (help->helper->data_len == 0)
 		return -EINVAL;
 
-	nla_memcpy(help->data, nla_data(attr), sizeof(help->data));
+	nla_memcpy(help->data, attr, sizeof(help->data));
 	return 0;
 }
 
@@ -240,6 +240,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 		ret = -ENOMEM;
 		goto err2;
 	}
+	helper->data_len = size;
 
 	helper->flags |= NF_CT_HELPER_F_USERSPACE;
 	memcpy(&helper->tuple, tuple, sizeof(struct nf_conntrack_tuple));
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 9f5dea0064ea..916a3c7f9eaf 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -165,12 +165,12 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
 static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx,
 						const struct sk_buff *skb,
 						const struct iphdr *ip,
-						unsigned char *opts)
+						unsigned char *opts,
+						struct tcphdr *_tcph)
 {
 	const struct tcphdr *tcp;
-	struct tcphdr _tcph;
 
-	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
+	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), _tcph);
 	if (!tcp)
 		return NULL;
 
@@ -205,10 +205,11 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 	int fmatch = FMATCH_WRONG;
 	struct nf_osf_hdr_ctx ctx;
 	const struct tcphdr *tcp;
+	struct tcphdr _tcph;
 
 	memset(&ctx, 0, sizeof(ctx));
 
-	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
+	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph);
 	if (!tcp)
 		return false;
 
@@ -265,10 +266,11 @@ bool nf_osf_find(const struct sk_buff *skb,
 	const struct nf_osf_finger *kf;
 	struct nf_osf_hdr_ctx ctx;
 	const struct tcphdr *tcp;
+	struct tcphdr _tcph;
 
 	memset(&ctx, 0, sizeof(ctx));
 
-	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
+	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph);
 	if (!tcp)
 		return false;
 
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 1e70359d633c..f1363b8aabba 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -29,7 +29,7 @@ void nft_lookup_eval(const struct nft_expr *expr,
 {
 	const struct nft_lookup *priv = nft_expr_priv(expr);
 	const struct nft_set *set = priv->set;
-	const struct nft_set_ext *ext;
+	const struct nft_set_ext *ext = NULL;
 	bool found;
 
 	found = set->ops->lookup(nft_net(pkt), set, &regs->data[priv->sreg],
@@ -39,11 +39,13 @@ void nft_lookup_eval(const struct nft_expr *expr,
 		return;
 	}
 
-	if (set->flags & NFT_SET_MAP)
-		nft_data_copy(&regs->data[priv->dreg],
-			      nft_set_ext_data(ext), set->dlen);
+	if (ext) {
+		if (set->flags & NFT_SET_MAP)
+			nft_data_copy(&regs->data[priv->dreg],
+				      nft_set_ext_data(ext), set->dlen);
 
-	nft_set_elem_update_expr(ext, regs, pkt);
+		nft_set_elem_update_expr(ext, regs, pkt);
+	}
 }
 
 static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = {
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 32f0fc8be3a4..2a81ea421819 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -81,7 +81,6 @@ static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set,
 	u32 idx, off;
 
 	nft_bitmap_location(set, key, &idx, &off);
-	*ext = NULL;
 
 	return nft_bitmap_active(priv->bitmap, idx, off, genmask);
 }
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 3a5552e14f75..62f416bc0579 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -79,6 +79,10 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 				parent = rcu_dereference_raw(parent->rb_left);
 				continue;
 			}
+
+			if (nft_set_elem_expired(&rbe->ext))
+				return false;
+
 			if (nft_rbtree_interval_end(rbe)) {
 				if (nft_set_is_anonymous(set))
 					return false;
@@ -94,6 +98,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
+	    !nft_set_elem_expired(&interval->ext) &&
 	    nft_rbtree_interval_start(interval)) {
 		*ext = &interval->ext;
 		return true;
@@ -154,6 +159,9 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,
 				continue;
 			}
 
+			if (nft_set_elem_expired(&rbe->ext))
+				return false;
+
 			if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) ||
 			    (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) ==
 			    (flags & NFT_SET_ELEM_INTERVAL_END)) {
@@ -170,6 +178,7 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
+	    !nft_set_elem_expired(&interval->ext) &&
 	    ((!nft_rbtree_interval_end(interval) &&
 	      !(flags & NFT_SET_ELEM_INTERVAL_END)) ||
 	     (nft_rbtree_interval_end(interval) &&
@@ -218,27 +227,26 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 
 	/* Detect overlaps as we descend the tree. Set the flag in these cases:
 	 *
-	 * a1. |__ _ _?  >|__ _ _  (insert start after existing start)
-	 * a2. _ _ __>|  ?_ _ __|  (insert end before existing end)
-	 * a3. _ _ ___|  ?_ _ _>|  (insert end after existing end)
-	 * a4. >|__ _ _   _ _ __|  (insert start before existing end)
+	 * a1. _ _ __>|  ?_ _ __|  (insert end before existing end)
+	 * a2. _ _ ___|  ?_ _ _>|  (insert end after existing end)
+	 * a3. _ _ ___? >|_ _ __|  (insert start before existing end)
 	 *
 	 * and clear it later on, as we eventually reach the points indicated by
 	 * '?' above, in the cases described below. We'll always meet these
 	 * later, locally, due to tree ordering, and overlaps for the intervals
 	 * that are the closest together are always evaluated last.
 	 *
-	 * b1. |__ _ _!  >|__ _ _  (insert start after existing end)
-	 * b2. _ _ __>|  !_ _ __|  (insert end before existing start)
-	 * b3. !_____>|            (insert end after existing start)
+	 * b1. _ _ __>|  !_ _ __|  (insert end before existing start)
+	 * b2. _ _ ___|  !_ _ _>|  (insert end after existing start)
+	 * b3. _ _ ___! >|_ _ __|  (insert start after existing end)
 	 *
-	 * Case a4. resolves to b1.:
+	 * Case a3. resolves to b3.:
 	 * - if the inserted start element is the leftmost, because the '0'
 	 *   element in the tree serves as end element
 	 * - otherwise, if an existing end is found. Note that end elements are
 	 *   always inserted after corresponding start elements.
 	 *
-	 * For a new, rightmost pair of elements, we'll hit cases b1. and b3.,
+	 * For a new, rightmost pair of elements, we'll hit cases b3. and b2.,
 	 * in that order.
 	 *
 	 * The flag is also cleared in two special cases:
@@ -262,9 +270,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			p = &parent->rb_left;
 
 			if (nft_rbtree_interval_start(new)) {
-				overlap = nft_rbtree_interval_start(rbe) &&
-					  nft_set_elem_active(&rbe->ext,
-							      genmask);
+				if (nft_rbtree_interval_end(rbe) &&
+				    nft_set_elem_active(&rbe->ext, genmask))
+					overlap = false;
 			} else {
 				overlap = nft_rbtree_interval_end(rbe) &&
 					  nft_set_elem_active(&rbe->ext,
@@ -419,6 +427,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		if (iter->count < iter->skip)
 			goto cont;
+		if (nft_set_elem_expired(&rbe->ext))
+			goto cont;
 		if (!nft_set_elem_active(&rbe->ext, iter->genmask))
 			goto cont;
 
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 75bd0e5dd312..7b2f359bfce4 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -346,6 +346,9 @@ static int idletimer_tg_checkentry_v1(const struct xt_tgchk_param *par)
 
 	pr_debug("checkentry targinfo%s\n", info->label);
 
+	if (info->send_nl_msg)
+		return -EOPNOTSUPP;
+
 	ret = idletimer_tg_helper((struct idletimer_tg_info *)info);
 	if(ret < 0)
 	{
diff --git a/net/netlabel/Kconfig b/net/netlabel/Kconfig
index 64280a1d3906..07b03c306f28 100644
--- a/net/netlabel/Kconfig
+++ b/net/netlabel/Kconfig
@@ -14,6 +14,6 @@ config NETLABEL
 	  Documentation/netlabel as well as the NetLabel SourceForge project
 	  for configuration tools and additional documentation.
 
-	   * http://netlabel.sf.net
+	   * https://github.com/netlabel/netlabel_tools
 
 	  If you are unsure, say N.
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 409a3ae47ce2..5e1239cef000 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -734,6 +734,12 @@ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap,
 	if ((off & (BITS_PER_LONG - 1)) != 0)
 		return -EINVAL;
 
+	/* a null catmap is equivalent to an empty one */
+	if (!catmap) {
+		*offset = (u32)-1;
+		return 0;
+	}
+
 	if (off < catmap->startbit) {
 		off = catmap->startbit;
 		*offset = off;
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index 79f12d8c7b86..0891ee02ca4f 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -208,6 +208,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 		/* refcount initialized at 1 */
 		spin_unlock_bh(&nr_node_list_lock);
 
+		nr_neigh_put(nr_neigh);
 		return 0;
 	}
 	nr_node_lock(nr_node);
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e726159cfcfa..4340f25fe390 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1895,7 +1895,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net)
 		struct hlist_head *head = &info->limits[i];
 		struct ovs_ct_limit *ct_limit;
 
-		hlist_for_each_entry_rcu(ct_limit, head, hlist_node)
+		hlist_for_each_entry_rcu(ct_limit, head, hlist_node,
+					 lockdep_ovsl_is_held())
 			kfree_rcu(ct_limit, rcu);
 	}
 	kfree(ovs_net->ct_limit_info->limits);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index d8ae541d22a8..94b024534987 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2466,8 +2466,10 @@ static void __net_exit ovs_exit_net(struct net *dnet)
 	struct net *net;
 	LIST_HEAD(head);
 
-	ovs_ct_exit(dnet);
 	ovs_lock();
+
+	ovs_ct_exit(dnet);
+
 	list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node)
 		__dp_destroy(dp);
 
diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index e7d0fe3f4330..c5b3202a14ca 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -712,6 +712,10 @@ void qrtr_ns_init(void)
 		goto err_sock;
 	}
 
+	qrtr_ns.workqueue = alloc_workqueue("qrtr_ns_handler", WQ_UNBOUND, 1);
+	if (!qrtr_ns.workqueue)
+		goto err_sock;
+
 	qrtr_ns.sock->sk->sk_data_ready = qrtr_ns_data_ready;
 
 	sq.sq_port = QRTR_PORT_CTRL;
@@ -720,17 +724,13 @@ void qrtr_ns_init(void)
 	ret = kernel_bind(qrtr_ns.sock, (struct sockaddr *)&sq, sizeof(sq));
 	if (ret < 0) {
 		pr_err("failed to bind to socket\n");
-		goto err_sock;
+		goto err_wq;
 	}
 
 	qrtr_ns.bcast_sq.sq_family = AF_QIPCRTR;
 	qrtr_ns.bcast_sq.sq_node = QRTR_NODE_BCAST;
 	qrtr_ns.bcast_sq.sq_port = QRTR_PORT_CTRL;
 
-	qrtr_ns.workqueue = alloc_workqueue("qrtr_ns_handler", WQ_UNBOUND, 1);
-	if (!qrtr_ns.workqueue)
-		goto err_sock;
-
 	ret = say_hello(&qrtr_ns.bcast_sq);
 	if (ret < 0)
 		goto err_wq;
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index e22092e4a783..2d8d6131bc5f 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -854,7 +854,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	}
 	mutex_unlock(&qrtr_node_lock);
 
-	qrtr_local_enqueue(node, skb, type, from, to);
+	qrtr_local_enqueue(NULL, skb, type, from, to);
 
 	return 0;
 }
@@ -906,20 +906,21 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	node = NULL;
 	if (addr->sq_node == QRTR_NODE_BCAST) {
-		enqueue_fn = qrtr_bcast_enqueue;
-		if (addr->sq_port != QRTR_PORT_CTRL) {
+		if (addr->sq_port != QRTR_PORT_CTRL &&
+		    qrtr_local_nid != QRTR_NODE_BCAST) {
 			release_sock(sk);
 			return -ENOTCONN;
 		}
+		enqueue_fn = qrtr_bcast_enqueue;
 	} else if (addr->sq_node == ipc->us.sq_node) {
 		enqueue_fn = qrtr_local_enqueue;
 	} else {
-		enqueue_fn = qrtr_node_enqueue;
 		node = qrtr_node_lookup(addr->sq_node);
 		if (!node) {
 			release_sock(sk);
 			return -ECONNRESET;
 		}
+		enqueue_fn = qrtr_node_enqueue;
 	}
 
 	plen = (len + 3) & ~3;
diff --git a/net/rds/message.c b/net/rds/message.c
index 50f13f1d4ae0..071a261fdaab 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2020 Oracle and/or its affiliates.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -162,12 +162,12 @@ static void rds_message_purge(struct rds_message *rm)
 	if (rm->rdma.op_active)
 		rds_rdma_free_op(&rm->rdma);
 	if (rm->rdma.op_rdma_mr)
-		rds_mr_put(rm->rdma.op_rdma_mr);
+		kref_put(&rm->rdma.op_rdma_mr->r_kref, __rds_put_mr_final);
 
 	if (rm->atomic.op_active)
 		rds_atomic_free_op(&rm->atomic);
 	if (rm->atomic.op_rdma_mr)
-		rds_mr_put(rm->atomic.op_rdma_mr);
+		kref_put(&rm->atomic.op_rdma_mr->r_kref, __rds_put_mr_final);
 }
 
 void rds_message_put(struct rds_message *rm)
@@ -308,26 +308,20 @@ out:
 /*
  * RDS ops use this to grab SG entries from the rm's sg pool.
  */
-struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents,
-					  int *ret)
+struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents)
 {
 	struct scatterlist *sg_first = (struct scatterlist *) &rm[1];
 	struct scatterlist *sg_ret;
 
-	if (WARN_ON(!ret))
-		return NULL;
-
 	if (nents <= 0) {
 		pr_warn("rds: alloc sgs failed! nents <= 0\n");
-		*ret = -EINVAL;
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	}
 
 	if (rm->m_used_sgs + nents > rm->m_total_sgs) {
 		pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n",
 			rm->m_total_sgs, rm->m_used_sgs, nents);
-		*ret = -ENOMEM;
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	sg_ret = &sg_first[rm->m_used_sgs];
@@ -343,7 +337,6 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in
 	unsigned int i;
 	int num_sgs = DIV_ROUND_UP(total_len, PAGE_SIZE);
 	int extra_bytes = num_sgs * sizeof(struct scatterlist);
-	int ret;
 
 	rm = rds_message_alloc(extra_bytes, GFP_NOWAIT);
 	if (!rm)
@@ -352,10 +345,10 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in
 	set_bit(RDS_MSG_PAGEVEC, &rm->m_flags);
 	rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len);
 	rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE);
-	rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret);
-	if (!rm->data.op_sg) {
+	rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs);
+	if (IS_ERR(rm->data.op_sg)) {
 		rds_message_put(rm);
-		return ERR_PTR(ret);
+		return ERR_CAST(rm->data.op_sg);
 	}
 
 	for (i = 0; i < rm->data.op_nents; ++i) {
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 585e6b3b69ce..a7ae11846cd7 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2007, 2020 Oracle and/or its affiliates.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -84,7 +84,7 @@ static struct rds_mr *rds_mr_tree_walk(struct rb_root *root, u64 key,
 	if (insert) {
 		rb_link_node(&insert->r_rb_node, parent, p);
 		rb_insert_color(&insert->r_rb_node, root);
-		refcount_inc(&insert->r_refcount);
+		kref_get(&insert->r_kref);
 	}
 	return NULL;
 }
@@ -99,10 +99,7 @@ static void rds_destroy_mr(struct rds_mr *mr)
 	unsigned long flags;
 
 	rdsdebug("RDS: destroy mr key is %x refcnt %u\n",
-			mr->r_key, refcount_read(&mr->r_refcount));
-
-	if (test_and_set_bit(RDS_MR_DEAD, &mr->r_state))
-		return;
+		 mr->r_key, kref_read(&mr->r_kref));
 
 	spin_lock_irqsave(&rs->rs_rdma_lock, flags);
 	if (!RB_EMPTY_NODE(&mr->r_rb_node))
@@ -115,8 +112,10 @@ static void rds_destroy_mr(struct rds_mr *mr)
 		mr->r_trans->free_mr(trans_private, mr->r_invalidate);
 }
 
-void __rds_put_mr_final(struct rds_mr *mr)
+void __rds_put_mr_final(struct kref *kref)
 {
+	struct rds_mr *mr = container_of(kref, struct rds_mr, r_kref);
+
 	rds_destroy_mr(mr);
 	kfree(mr);
 }
@@ -140,8 +139,7 @@ void rds_rdma_drop_keys(struct rds_sock *rs)
 		rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys);
 		RB_CLEAR_NODE(&mr->r_rb_node);
 		spin_unlock_irqrestore(&rs->rs_rdma_lock, flags);
-		rds_destroy_mr(mr);
-		rds_mr_put(mr);
+		kref_put(&mr->r_kref, __rds_put_mr_final);
 		spin_lock_irqsave(&rs->rs_rdma_lock, flags);
 	}
 	spin_unlock_irqrestore(&rs->rs_rdma_lock, flags);
@@ -242,7 +240,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 		goto out;
 	}
 
-	refcount_set(&mr->r_refcount, 1);
+	kref_init(&mr->r_kref);
 	RB_CLEAR_NODE(&mr->r_rb_node);
 	mr->r_trans = rs->rs_transport;
 	mr->r_sock = rs;
@@ -343,7 +341,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 
 	rdsdebug("RDS: get_mr key is %x\n", mr->r_key);
 	if (mr_ret) {
-		refcount_inc(&mr->r_refcount);
+		kref_get(&mr->r_kref);
 		*mr_ret = mr;
 	}
 
@@ -351,7 +349,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 out:
 	kfree(pages);
 	if (mr)
-		rds_mr_put(mr);
+		kref_put(&mr->r_kref, __rds_put_mr_final);
 	return ret;
 }
 
@@ -434,13 +432,7 @@ int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen)
 	if (!mr)
 		return -EINVAL;
 
-	/*
-	 * call rds_destroy_mr() ourselves so that we're sure it's done by the time
-	 * we return.  If we let rds_mr_put() do it it might not happen until
-	 * someone else drops their ref.
-	 */
-	rds_destroy_mr(mr);
-	rds_mr_put(mr);
+	kref_put(&mr->r_kref, __rds_put_mr_final);
 	return 0;
 }
 
@@ -464,6 +456,14 @@ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force)
 		return;
 	}
 
+	/* Get a reference so that the MR won't go away before calling
+	 * sync_mr() below.
+	 */
+	kref_get(&mr->r_kref);
+
+	/* If it is going to be freed, remove it from the tree now so
+	 * that no other thread can find it and free it.
+	 */
 	if (mr->r_use_once || force) {
 		rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys);
 		RB_CLEAR_NODE(&mr->r_rb_node);
@@ -477,12 +477,13 @@ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force)
 	if (mr->r_trans->sync_mr)
 		mr->r_trans->sync_mr(mr->r_trans_private, DMA_FROM_DEVICE);
 
+	/* Release the reference held above. */
+	kref_put(&mr->r_kref, __rds_put_mr_final);
+
 	/* If the MR was marked as invalidate, this will
 	 * trigger an async flush. */
-	if (zot_me) {
-		rds_destroy_mr(mr);
-		rds_mr_put(mr);
-	}
+	if (zot_me)
+		kref_put(&mr->r_kref, __rds_put_mr_final);
 }
 
 void rds_rdma_free_op(struct rm_rdma_op *ro)
@@ -490,7 +491,7 @@ void rds_rdma_free_op(struct rm_rdma_op *ro)
 	unsigned int i;
 
 	if (ro->op_odp_mr) {
-		rds_mr_put(ro->op_odp_mr);
+		kref_put(&ro->op_odp_mr->r_kref, __rds_put_mr_final);
 	} else {
 		for (i = 0; i < ro->op_nents; i++) {
 			struct page *page = sg_page(&ro->op_sg[i]);
@@ -664,9 +665,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
 	op->op_odp_mr = NULL;
 
 	WARN_ON(!nr_pages);
-	op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret);
-	if (!op->op_sg)
+	op->op_sg = rds_message_alloc_sgs(rm, nr_pages);
+	if (IS_ERR(op->op_sg)) {
+		ret = PTR_ERR(op->op_sg);
 		goto out_pages;
+	}
 
 	if (op->op_notify || op->op_recverr) {
 		/* We allocate an uninitialized notifier here, because
@@ -730,7 +733,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
 				goto out_pages;
 			}
 			RB_CLEAR_NODE(&local_odp_mr->r_rb_node);
-			refcount_set(&local_odp_mr->r_refcount, 1);
+			kref_init(&local_odp_mr->r_kref);
 			local_odp_mr->r_trans = rs->rs_transport;
 			local_odp_mr->r_sock = rs;
 			local_odp_mr->r_trans_private =
@@ -827,7 +830,7 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm,
 	if (!mr)
 		err = -EINVAL;	/* invalid r_key */
 	else
-		refcount_inc(&mr->r_refcount);
+		kref_get(&mr->r_kref);
 	spin_unlock_irqrestore(&rs->rs_rdma_lock, flags);
 
 	if (mr) {
@@ -905,9 +908,11 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm,
 	rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT);
 	rm->atomic.op_active = 1;
 	rm->atomic.op_recverr = rs->rs_recverr;
-	rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1, &ret);
-	if (!rm->atomic.op_sg)
+	rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1);
+	if (IS_ERR(rm->atomic.op_sg)) {
+		ret = PTR_ERR(rm->atomic.op_sg);
 		goto err;
+	}
 
 	/* verify 8 byte-aligned */
 	if (args->local_addr & 0x7) {
diff --git a/net/rds/rds.h b/net/rds/rds.h
index e4a603523083..6019b0c004a9 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -291,7 +291,7 @@ struct rds_incoming {
 
 struct rds_mr {
 	struct rb_node		r_rb_node;
-	refcount_t		r_refcount;
+	struct kref		r_kref;
 	u32			r_key;
 
 	/* A copy of the creation flags */
@@ -299,19 +299,11 @@ struct rds_mr {
 	unsigned int		r_invalidate:1;
 	unsigned int		r_write:1;
 
-	/* This is for RDS_MR_DEAD.
-	 * It would be nice & consistent to make this part of the above
-	 * bit field here, but we need to use test_and_set_bit.
-	 */
-	unsigned long		r_state;
 	struct rds_sock		*r_sock; /* back pointer to the socket that owns us */
 	struct rds_transport	*r_trans;
 	void			*r_trans_private;
 };
 
-/* Flags for mr->r_state */
-#define RDS_MR_DEAD		0
-
 static inline rds_rdma_cookie_t rds_rdma_make_cookie(u32 r_key, u32 offset)
 {
 	return r_key | (((u64) offset) << 32);
@@ -852,8 +844,7 @@ rds_conn_connecting(struct rds_connection *conn)
 
 /* message.c */
 struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp);
-struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents,
-					  int *ret);
+struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents);
 int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from,
 			       bool zcopy);
 struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len);
@@ -946,12 +937,7 @@ void rds_atomic_send_complete(struct rds_message *rm, int wc_status);
 int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm,
 		    struct cmsghdr *cmsg);
 
-void __rds_put_mr_final(struct rds_mr *mr);
-static inline void rds_mr_put(struct rds_mr *mr)
-{
-	if (refcount_dec_and_test(&mr->r_refcount))
-		__rds_put_mr_final(mr);
-}
+void __rds_put_mr_final(struct kref *kref);
 
 static inline bool rds_destroy_pending(struct rds_connection *conn)
 {
diff --git a/net/rds/send.c b/net/rds/send.c
index 82dcd8b84fe7..68e2bdb08fd0 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1274,9 +1274,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 
 	/* Attach data to the rm */
 	if (payload_len) {
-		rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret);
-		if (!rm->data.op_sg)
+		rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs);
+		if (IS_ERR(rm->data.op_sg)) {
+			ret = PTR_ERR(rm->data.op_sg);
 			goto out;
+		}
 		ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy);
 		if (ret)
 			goto out;
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index 6ffb7e9887ce..ddd0f95713a9 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -25,6 +25,7 @@ rxrpc-y := \
 	peer_event.o \
 	peer_object.o \
 	recvmsg.o \
+	rtt.o \
 	security.o \
 	sendmsg.o \
 	skbuff.o \
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 3eb1ab40ca5c..9fe264bec70c 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -7,6 +7,7 @@
 
 #include <linux/atomic.h>
 #include <linux/seqlock.h>
+#include <linux/win_minmax.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/sock.h>
@@ -311,11 +312,14 @@ struct rxrpc_peer {
 #define RXRPC_RTT_CACHE_SIZE 32
 	spinlock_t		rtt_input_lock;	/* RTT lock for input routine */
 	ktime_t			rtt_last_req;	/* Time of last RTT request */
-	u64			rtt;		/* Current RTT estimate (in nS) */
-	u64			rtt_sum;	/* Sum of cache contents */
-	u64			rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* Determined RTT cache */
-	u8			rtt_cursor;	/* next entry at which to insert */
-	u8			rtt_usage;	/* amount of cache actually used */
+	unsigned int		rtt_count;	/* Number of samples we've got */
+
+	u32			srtt_us;	/* smoothed round trip time << 3 in usecs */
+	u32			mdev_us;	/* medium deviation			*/
+	u32			mdev_max_us;	/* maximal mdev for the last rtt period	*/
+	u32			rttvar_us;	/* smoothed mdev_max			*/
+	u32			rto_j;		/* Retransmission timeout in jiffies */
+	u8			backoff;	/* Backoff timeout */
 
 	u8			cong_cwnd;	/* Congestion window size */
 };
@@ -1041,7 +1045,6 @@ extern unsigned long rxrpc_idle_ack_delay;
 extern unsigned int rxrpc_rx_window_size;
 extern unsigned int rxrpc_rx_mtu;
 extern unsigned int rxrpc_rx_jumbo_max;
-extern unsigned long rxrpc_resend_timeout;
 
 extern const s8 rxrpc_ack_priority[];
 
@@ -1069,8 +1072,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
  * peer_event.c
  */
 void rxrpc_error_report(struct sock *);
-void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
-			rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
 void rxrpc_peer_keepalive_worker(struct work_struct *);
 
 /*
@@ -1103,6 +1104,14 @@ void rxrpc_notify_socket(struct rxrpc_call *);
 int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
 
 /*
+ * rtt.c
+ */
+void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
+			rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
+unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool);
+void rxrpc_peer_init_rtt(struct rxrpc_peer *);
+
+/*
  * rxkad.c
  */
 #ifdef CONFIG_RXKAD
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 70e44abf106c..b7611cc159e5 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -248,7 +248,7 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb)
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	ktime_t now = skb->tstamp;
 
-	if (call->peer->rtt_usage < 3 ||
+	if (call->peer->rtt_count < 3 ||
 	    ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now))
 		rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
 				  true, true,
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index cedbbb3a7c2e..2a65ac41055f 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -111,8 +111,8 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 	} else {
 		unsigned long now = jiffies, ack_at;
 
-		if (call->peer->rtt_usage > 0)
-			ack_at = nsecs_to_jiffies(call->peer->rtt);
+		if (call->peer->srtt_us != 0)
+			ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3);
 		else
 			ack_at = expiry;
 
@@ -157,24 +157,18 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
 static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 {
 	struct sk_buff *skb;
-	unsigned long resend_at;
+	unsigned long resend_at, rto_j;
 	rxrpc_seq_t cursor, seq, top;
-	ktime_t now, max_age, oldest, ack_ts, timeout, min_timeo;
+	ktime_t now, max_age, oldest, ack_ts;
 	int ix;
 	u8 annotation, anno_type, retrans = 0, unacked = 0;
 
 	_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
 
-	if (call->peer->rtt_usage > 1)
-		timeout = ns_to_ktime(call->peer->rtt * 3 / 2);
-	else
-		timeout = ms_to_ktime(rxrpc_resend_timeout);
-	min_timeo = ns_to_ktime((1000000000 / HZ) * 4);
-	if (ktime_before(timeout, min_timeo))
-		timeout = min_timeo;
+	rto_j = call->peer->rto_j;
 
 	now = ktime_get_real();
-	max_age = ktime_sub(now, timeout);
+	max_age = ktime_sub(now, jiffies_to_usecs(rto_j));
 
 	spin_lock_bh(&call->lock);
 
@@ -219,7 +213,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 	}
 
 	resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest)));
-	resend_at += jiffies + rxrpc_resend_timeout;
+	resend_at += jiffies + rto_j;
 	WRITE_ONCE(call->resend_at, resend_at);
 
 	if (unacked)
@@ -234,7 +228,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 					rxrpc_timer_set_for_resend);
 		spin_unlock_bh(&call->lock);
 		ack_ts = ktime_sub(now, call->acks_latest_ts);
-		if (ktime_to_ns(ack_ts) < call->peer->rtt)
+		if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3))
 			goto out;
 		rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
 				  rxrpc_propose_ack_ping_for_lost_ack);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 69e09d69c896..3be4177baf70 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -91,11 +91,11 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
 		/* We analyse the number of packets that get ACK'd per RTT
 		 * period and increase the window if we managed to fill it.
 		 */
-		if (call->peer->rtt_usage == 0)
+		if (call->peer->rtt_count == 0)
 			goto out;
 		if (ktime_before(skb->tstamp,
-				 ktime_add_ns(call->cong_tstamp,
-					      call->peer->rtt)))
+				 ktime_add_us(call->cong_tstamp,
+					      call->peer->srtt_us >> 3)))
 			goto out_no_clear_ca;
 		change = rxrpc_cong_rtt_window_end;
 		call->cong_tstamp = skb->tstamp;
@@ -803,6 +803,30 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
 }
 
 /*
+ * Return true if the ACK is valid - ie. it doesn't appear to have regressed
+ * with respect to the ack state conveyed by preceding ACKs.
+ */
+static bool rxrpc_is_ack_valid(struct rxrpc_call *call,
+			       rxrpc_seq_t first_pkt, rxrpc_seq_t prev_pkt)
+{
+	rxrpc_seq_t base = READ_ONCE(call->ackr_first_seq);
+
+	if (after(first_pkt, base))
+		return true; /* The window advanced */
+
+	if (before(first_pkt, base))
+		return false; /* firstPacket regressed */
+
+	if (after_eq(prev_pkt, call->ackr_prev_seq))
+		return true; /* previousPacket hasn't regressed. */
+
+	/* Some rx implementations put a serial number in previousPacket. */
+	if (after_eq(prev_pkt, base + call->tx_winsize))
+		return false;
+	return true;
+}
+
+/*
  * Process an ACK packet.
  *
  * ack.firstPacket is the sequence number of the first soft-ACK'd/NAK'd packet
@@ -865,9 +889,12 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	}
 
 	/* Discard any out-of-order or duplicate ACKs (outside lock). */
-	if (before(first_soft_ack, call->ackr_first_seq) ||
-	    before(prev_pkt, call->ackr_prev_seq))
+	if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
+		trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial,
+					   first_soft_ack, call->ackr_first_seq,
+					   prev_pkt, call->ackr_prev_seq);
 		return;
+	}
 
 	buf.info.rxMTU = 0;
 	ioffset = offset + nr_acks + 3;
@@ -878,9 +905,12 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	spin_lock(&call->input_lock);
 
 	/* Discard any out-of-order or duplicate ACKs (inside lock). */
-	if (before(first_soft_ack, call->ackr_first_seq) ||
-	    before(prev_pkt, call->ackr_prev_seq))
+	if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) {
+		trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial,
+					   first_soft_ack, call->ackr_first_seq,
+					   prev_pkt, call->ackr_prev_seq);
 		goto out;
+	}
 	call->acks_latest_ts = skb->tstamp;
 
 	call->ackr_first_seq = first_soft_ack;
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index a6c1349e965d..01135e54d95d 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -165,15 +165,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 			goto error;
 		}
 
-		/* we want to set the don't fragment bit */
-		opt = IPV6_PMTUDISC_DO;
-		ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
-					(char *) &opt, sizeof(opt));
-		if (ret < 0) {
-			_debug("setsockopt failed");
-			goto error;
-		}
-
 		/* Fall through and set IPv4 options too otherwise we don't get
 		 * errors from IPv4 packets sent through the IPv6 socket.
 		 */
diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c
index 214405f75346..d4144fd86f84 100644
--- a/net/rxrpc/misc.c
+++ b/net/rxrpc/misc.c
@@ -63,11 +63,6 @@ unsigned int rxrpc_rx_mtu = 5692;
  */
 unsigned int rxrpc_rx_jumbo_max = 4;
 
-/*
- * Time till packet resend (in milliseconds).
- */
-unsigned long rxrpc_resend_timeout = 4 * HZ;
-
 const s8 rxrpc_ack_priority[] = {
 	[0]				= 0,
 	[RXRPC_ACK_DELAY]		= 1,
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index bad3d2420344..f8b632a5c619 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -369,7 +369,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	    (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
 	     retrans ||
 	     call->cong_mode == RXRPC_CALL_SLOW_START ||
-	     (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) ||
+	     (call->peer->rtt_count < 3 && sp->hdr.seq & 1) ||
 	     ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000),
 			  ktime_get_real())))
 		whdr.flags |= RXRPC_REQUEST_ACK;
@@ -423,13 +423,10 @@ done:
 		if (whdr.flags & RXRPC_REQUEST_ACK) {
 			call->peer->rtt_last_req = skb->tstamp;
 			trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
-			if (call->peer->rtt_usage > 1) {
+			if (call->peer->rtt_count > 1) {
 				unsigned long nowj = jiffies, ack_lost_at;
 
-				ack_lost_at = nsecs_to_jiffies(2 * call->peer->rtt);
-				if (ack_lost_at < 1)
-					ack_lost_at = 1;
-
+				ack_lost_at = rxrpc_get_rto_backoff(call->peer, retrans);
 				ack_lost_at += nowj;
 				WRITE_ONCE(call->ack_lost_at, ack_lost_at);
 				rxrpc_reduce_call_timer(call, ack_lost_at, nowj,
@@ -474,41 +471,21 @@ send_fragmentable:
 	skb->tstamp = ktime_get_real();
 
 	switch (conn->params.local->srx.transport.family) {
+	case AF_INET6:
 	case AF_INET:
 		opt = IP_PMTUDISC_DONT;
-		ret = kernel_setsockopt(conn->params.local->socket,
-					SOL_IP, IP_MTU_DISCOVER,
-					(char *)&opt, sizeof(opt));
-		if (ret == 0) {
-			ret = kernel_sendmsg(conn->params.local->socket, &msg,
-					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_seconds();
-
-			opt = IP_PMTUDISC_DO;
-			kernel_setsockopt(conn->params.local->socket, SOL_IP,
-					  IP_MTU_DISCOVER,
-					  (char *)&opt, sizeof(opt));
-		}
-		break;
-
-#ifdef CONFIG_AF_RXRPC_IPV6
-	case AF_INET6:
-		opt = IPV6_PMTUDISC_DONT;
-		ret = kernel_setsockopt(conn->params.local->socket,
-					SOL_IPV6, IPV6_MTU_DISCOVER,
-					(char *)&opt, sizeof(opt));
-		if (ret == 0) {
-			ret = kernel_sendmsg(conn->params.local->socket, &msg,
-					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_seconds();
-
-			opt = IPV6_PMTUDISC_DO;
-			kernel_setsockopt(conn->params.local->socket,
-					  SOL_IPV6, IPV6_MTU_DISCOVER,
-					  (char *)&opt, sizeof(opt));
-		}
+		kernel_setsockopt(conn->params.local->socket,
+				  SOL_IP, IP_MTU_DISCOVER,
+				  (char *)&opt, sizeof(opt));
+		ret = kernel_sendmsg(conn->params.local->socket, &msg,
+				     iov, 2, len);
+		conn->params.peer->last_tx_at = ktime_get_seconds();
+
+		opt = IP_PMTUDISC_DO;
+		kernel_setsockopt(conn->params.local->socket,
+				  SOL_IP, IP_MTU_DISCOVER,
+				  (char *)&opt, sizeof(opt));
 		break;
-#endif
 
 	default:
 		BUG();
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 923b263c401b..b1449d971883 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -296,52 +296,6 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
 }
 
 /*
- * Add RTT information to cache.  This is called in softirq mode and has
- * exclusive access to the peer RTT data.
- */
-void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
-			rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
-			ktime_t send_time, ktime_t resp_time)
-{
-	struct rxrpc_peer *peer = call->peer;
-	s64 rtt;
-	u64 sum = peer->rtt_sum, avg;
-	u8 cursor = peer->rtt_cursor, usage = peer->rtt_usage;
-
-	rtt = ktime_to_ns(ktime_sub(resp_time, send_time));
-	if (rtt < 0)
-		return;
-
-	spin_lock(&peer->rtt_input_lock);
-
-	/* Replace the oldest datum in the RTT buffer */
-	sum -= peer->rtt_cache[cursor];
-	sum += rtt;
-	peer->rtt_cache[cursor] = rtt;
-	peer->rtt_cursor = (cursor + 1) & (RXRPC_RTT_CACHE_SIZE - 1);
-	peer->rtt_sum = sum;
-	if (usage < RXRPC_RTT_CACHE_SIZE) {
-		usage++;
-		peer->rtt_usage = usage;
-	}
-
-	spin_unlock(&peer->rtt_input_lock);
-
-	/* Now recalculate the average */
-	if (usage == RXRPC_RTT_CACHE_SIZE) {
-		avg = sum / RXRPC_RTT_CACHE_SIZE;
-	} else {
-		avg = sum;
-		do_div(avg, usage);
-	}
-
-	/* Don't need to update this under lock */
-	peer->rtt = avg;
-	trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
-			   usage, avg);
-}
-
-/*
  * Perform keep-alive pings.
  */
 static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 452163eadb98..ca29976bb193 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -225,6 +225,8 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
 		spin_lock_init(&peer->rtt_input_lock);
 		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
 
+		rxrpc_peer_init_rtt(peer);
+
 		if (RXRPC_TX_SMSS > 2190)
 			peer->cong_cwnd = 2;
 		else if (RXRPC_TX_SMSS > 1095)
@@ -497,14 +499,14 @@ void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call,
 EXPORT_SYMBOL(rxrpc_kernel_get_peer);
 
 /**
- * rxrpc_kernel_get_rtt - Get a call's peer RTT
+ * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT
  * @sock: The socket on which the call is in progress.
  * @call: The call to query
  *
- * Get the call's peer RTT.
+ * Get the call's peer smoothed RTT.
  */
-u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call)
+u32 rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call)
 {
-	return call->peer->rtt;
+	return call->peer->srtt_us >> 3;
 }
-EXPORT_SYMBOL(rxrpc_kernel_get_rtt);
+EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index b9d053e42821..8b179e3c802a 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -222,7 +222,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
 		seq_puts(seq,
 			 "Proto Local                                          "
 			 " Remote                                         "
-			 " Use CW  MTU   LastUse          RTT Rc\n"
+			 " Use  CW   MTU LastUse      RTT      RTO\n"
 			 );
 		return 0;
 	}
@@ -236,15 +236,15 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
 	now = ktime_get_seconds();
 	seq_printf(seq,
 		   "UDP   %-47.47s %-47.47s %3u"
-		   " %3u %5u %6llus %12llu %2u\n",
+		   " %3u %5u %6llus %8u %8u\n",
 		   lbuff,
 		   rbuff,
 		   atomic_read(&peer->usage),
 		   peer->cong_cwnd,
 		   peer->mtu,
 		   now - peer->last_tx_at,
-		   peer->rtt,
-		   peer->rtt_cursor);
+		   peer->srtt_us >> 3,
+		   jiffies_to_usecs(peer->rto_j));
 
 	return 0;
 }
diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c
new file mode 100644
index 000000000000..928d8b34a3ee
--- /dev/null
+++ b/net/rxrpc/rtt.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* RTT/RTO calculation.
+ *
+ * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com)
+ *
+ * https://tools.ietf.org/html/rfc6298
+ * https://tools.ietf.org/html/rfc1122#section-4.2.3.1
+ * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf
+ */
+
+#include <linux/net.h>
+#include "ar-internal.h"
+
+#define RXRPC_RTO_MAX	((unsigned)(120 * HZ))
+#define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ))	/* RFC6298 2.1 initial RTO value	*/
+#define rxrpc_jiffies32 ((u32)jiffies)		/* As rxrpc_jiffies32 */
+#define rxrpc_min_rtt_wlen 300			/* As sysctl_tcp_min_rtt_wlen */
+
+static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer)
+{
+	return 200;
+}
+
+static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer)
+{
+	return _usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us);
+}
+
+static u32 rxrpc_bound_rto(u32 rto)
+{
+	return min(rto, RXRPC_RTO_MAX);
+}
+
+/*
+ * Called to compute a smoothed rtt estimate. The data fed to this
+ * routine either comes from timestamps, or from segments that were
+ * known _not_ to have been retransmitted [see Karn/Partridge
+ * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88
+ * piece by Van Jacobson.
+ * NOTE: the next three routines used to be one big routine.
+ * To save cycles in the RFC 1323 implementation it was better to break
+ * it up into three procedures. -- erics
+ */
+static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us)
+{
+	long m = sample_rtt_us; /* RTT */
+	u32 srtt = peer->srtt_us;
+
+	/*	The following amusing code comes from Jacobson's
+	 *	article in SIGCOMM '88.  Note that rtt and mdev
+	 *	are scaled versions of rtt and mean deviation.
+	 *	This is designed to be as fast as possible
+	 *	m stands for "measurement".
+	 *
+	 *	On a 1990 paper the rto value is changed to:
+	 *	RTO = rtt + 4 * mdev
+	 *
+	 * Funny. This algorithm seems to be very broken.
+	 * These formulae increase RTO, when it should be decreased, increase
+	 * too slowly, when it should be increased quickly, decrease too quickly
+	 * etc. I guess in BSD RTO takes ONE value, so that it is absolutely
+	 * does not matter how to _calculate_ it. Seems, it was trap
+	 * that VJ failed to avoid. 8)
+	 */
+	if (srtt != 0) {
+		m -= (srtt >> 3);	/* m is now error in rtt est */
+		srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
+		if (m < 0) {
+			m = -m;		/* m is now abs(error) */
+			m -= (peer->mdev_us >> 2);   /* similar update on mdev */
+			/* This is similar to one of Eifel findings.
+			 * Eifel blocks mdev updates when rtt decreases.
+			 * This solution is a bit different: we use finer gain
+			 * for mdev in this case (alpha*beta).
+			 * Like Eifel it also prevents growth of rto,
+			 * but also it limits too fast rto decreases,
+			 * happening in pure Eifel.
+			 */
+			if (m > 0)
+				m >>= 3;
+		} else {
+			m -= (peer->mdev_us >> 2);   /* similar update on mdev */
+		}
+
+		peer->mdev_us += m;		/* mdev = 3/4 mdev + 1/4 new */
+		if (peer->mdev_us > peer->mdev_max_us) {
+			peer->mdev_max_us = peer->mdev_us;
+			if (peer->mdev_max_us > peer->rttvar_us)
+				peer->rttvar_us = peer->mdev_max_us;
+		}
+	} else {
+		/* no previous measure. */
+		srtt = m << 3;		/* take the measured time to be rtt */
+		peer->mdev_us = m << 1;	/* make sure rto = 3*rtt */
+		peer->rttvar_us = max(peer->mdev_us, rxrpc_rto_min_us(peer));
+		peer->mdev_max_us = peer->rttvar_us;
+	}
+
+	peer->srtt_us = max(1U, srtt);
+}
+
+/*
+ * Calculate rto without backoff.  This is the second half of Van Jacobson's
+ * routine referred to above.
+ */
+static void rxrpc_set_rto(struct rxrpc_peer *peer)
+{
+	u32 rto;
+
+	/* 1. If rtt variance happened to be less 50msec, it is hallucination.
+	 *    It cannot be less due to utterly erratic ACK generation made
+	 *    at least by solaris and freebsd. "Erratic ACKs" has _nothing_
+	 *    to do with delayed acks, because at cwnd>2 true delack timeout
+	 *    is invisible. Actually, Linux-2.4 also generates erratic
+	 *    ACKs in some circumstances.
+	 */
+	rto = __rxrpc_set_rto(peer);
+
+	/* 2. Fixups made earlier cannot be right.
+	 *    If we do not estimate RTO correctly without them,
+	 *    all the algo is pure shit and should be replaced
+	 *    with correct one. It is exactly, which we pretend to do.
+	 */
+
+	/* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo
+	 * guarantees that rto is higher.
+	 */
+	peer->rto_j = rxrpc_bound_rto(rto);
+}
+
+static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us)
+{
+	if (rtt_us < 0)
+		return;
+
+	//rxrpc_update_rtt_min(peer, rtt_us);
+	rxrpc_rtt_estimator(peer, rtt_us);
+	rxrpc_set_rto(peer);
+
+	/* RFC6298: only reset backoff on valid RTT measurement. */
+	peer->backoff = 0;
+}
+
+/*
+ * Add RTT information to cache.  This is called in softirq mode and has
+ * exclusive access to the peer RTT data.
+ */
+void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
+			rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
+			ktime_t send_time, ktime_t resp_time)
+{
+	struct rxrpc_peer *peer = call->peer;
+	s64 rtt_us;
+
+	rtt_us = ktime_to_us(ktime_sub(resp_time, send_time));
+	if (rtt_us < 0)
+		return;
+
+	spin_lock(&peer->rtt_input_lock);
+	rxrpc_ack_update_rtt(peer, rtt_us);
+	if (peer->rtt_count < 3)
+		peer->rtt_count++;
+	spin_unlock(&peer->rtt_input_lock);
+
+	trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial,
+			   peer->srtt_us >> 3, peer->rto_j);
+}
+
+/*
+ * Get the retransmission timeout to set in jiffies, backing it off each time
+ * we retransmit.
+ */
+unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans)
+{
+	u64 timo_j;
+	u8 backoff = READ_ONCE(peer->backoff);
+
+	timo_j = peer->rto_j;
+	timo_j <<= backoff;
+	if (retrans && timo_j * 2 <= RXRPC_RTO_MAX)
+		WRITE_ONCE(peer->backoff, backoff + 1);
+
+	if (timo_j < 1)
+		timo_j = 1;
+
+	return timo_j;
+}
+
+void rxrpc_peer_init_rtt(struct rxrpc_peer *peer)
+{
+	peer->rto_j	= RXRPC_TIMEOUT_INIT;
+	peer->mdev_us	= jiffies_to_usecs(RXRPC_TIMEOUT_INIT);
+	peer->backoff	= 0;
+	//minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U);
+}
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 098f1f9ec53b..52a24d4ef5d8 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -1148,7 +1148,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key,
 				   &expiry, _abort_code);
 	if (ret < 0)
-		goto temporary_error_free_resp;
+		goto temporary_error_free_ticket;
 
 	/* use the session key from inside the ticket to decrypt the
 	 * response */
@@ -1230,7 +1230,6 @@ protocol_error:
 
 temporary_error_free_ticket:
 	kfree(ticket);
-temporary_error_free_resp:
 	kfree(response);
 temporary_error:
 	/* Ignore the response packet if we got a temporary error such as
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 0fcf157aa09f..5e9c43d4a314 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -66,15 +66,14 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
 					    struct rxrpc_call *call)
 {
 	rxrpc_seq_t tx_start, tx_win;
-	signed long rtt2, timeout;
-	u64 rtt;
+	signed long rtt, timeout;
 
-	rtt = READ_ONCE(call->peer->rtt);
-	rtt2 = nsecs_to_jiffies64(rtt) * 2;
-	if (rtt2 < 2)
-		rtt2 = 2;
+	rtt = READ_ONCE(call->peer->srtt_us) >> 3;
+	rtt = usecs_to_jiffies(rtt) * 2;
+	if (rtt < 2)
+		rtt = 2;
 
-	timeout = rtt2;
+	timeout = rtt;
 	tx_start = READ_ONCE(call->tx_hard_ack);
 
 	for (;;) {
@@ -92,7 +91,7 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
 			return -EINTR;
 
 		if (tx_win != tx_start) {
-			timeout = rtt2;
+			timeout = rtt;
 			tx_start = tx_win;
 		}
 
@@ -271,16 +270,9 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 		_debug("need instant resend %d", ret);
 		rxrpc_instant_resend(call, ix);
 	} else {
-		unsigned long now = jiffies, resend_at;
+		unsigned long now = jiffies;
+		unsigned long resend_at = now + call->peer->rto_j;
 
-		if (call->peer->rtt_usage > 1)
-			resend_at = nsecs_to_jiffies(call->peer->rtt * 3 / 2);
-		else
-			resend_at = rxrpc_resend_timeout;
-		if (resend_at < 1)
-			resend_at = 1;
-
-		resend_at += now;
 		WRITE_ONCE(call->resend_at, resend_at);
 		rxrpc_reduce_call_timer(call, resend_at, now,
 					rxrpc_timer_set_for_send);
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index 2bbb38161851..18dade4e6f9a 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -71,15 +71,6 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.extra1		= (void *)&one_jiffy,
 		.extra2		= (void *)&max_jiffies,
 	},
-	{
-		.procname	= "resend_timeout",
-		.data		= &rxrpc_resend_timeout,
-		.maxlen		= sizeof(unsigned long),
-		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_ms_jiffies_minmax,
-		.extra1		= (void *)&one_jiffy,
-		.extra2		= (void *)&max_jiffies,
-	},
 
 	/* Non-time values */
 	{
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 1a766393be62..20577355235a 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -199,6 +199,9 @@ static int tcf_ct_flow_table_add_action_nat(struct net *net,
 	const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
 	struct nf_conntrack_tuple target;
 
+	if (!(ct->status & IPS_NAT_MASK))
+		return 0;
+
 	nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);
 
 	switch (tuple->src.l3num) {
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index f6a3b969ead0..0a7ecc292bd3 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1667,6 +1667,7 @@ int tcf_classify_ingress(struct sk_buff *skb,
 		skb_ext_del(skb, TC_SKB_EXT);
 
 		tp = rcu_dereference_bh(fchain->filter_chain);
+		last_executed_chain = fchain->index;
 	}
 
 	ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode,
@@ -2069,6 +2070,7 @@ replay:
 		err = PTR_ERR(block);
 		goto errout;
 	}
+	block->classid = parent;
 
 	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
 	if (chain_index > TC_ACT_EXT_VAL_MASK) {
@@ -2611,12 +2613,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 			return skb->len;
 
 		parent = tcm->tcm_parent;
-		if (!parent) {
+		if (!parent)
 			q = dev->qdisc;
-			parent = q->handle;
-		} else {
+		else
 			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
-		}
 		if (!q)
 			goto out;
 		cops = q->ops->cl_ops;
@@ -2632,6 +2632,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		block = cops->tcf_block(q, cl, NULL);
 		if (!block)
 			goto out;
+		parent = block->classid;
 		if (tcf_block_shared(block))
 			q = NULL;
 	}
@@ -3522,6 +3523,16 @@ static void tcf_sample_get_group(struct flow_action_entry *entry,
 #endif
 }
 
+static enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats)
+{
+	if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY))
+		return FLOW_ACTION_HW_STATS_DONT_CARE;
+	else if (!hw_stats)
+		return FLOW_ACTION_HW_STATS_DISABLED;
+
+	return hw_stats;
+}
+
 int tc_setup_flow_action(struct flow_action *flow_action,
 			 const struct tcf_exts *exts)
 {
@@ -3545,7 +3556,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 		if (err)
 			goto err_out_locked;
 
-		entry->hw_stats = act->hw_stats;
+		entry->hw_stats = tc_act_hw_stats(act->hw_stats);
 
 		if (is_tcf_gact_ok(act)) {
 			entry->id = FLOW_ACTION_ACCEPT;
@@ -3613,7 +3624,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 				entry->mangle.mask = tcf_pedit_mask(act, k);
 				entry->mangle.val = tcf_pedit_val(act, k);
 				entry->mangle.offset = tcf_pedit_offset(act, k);
-				entry->hw_stats = act->hw_stats;
+				entry->hw_stats = tc_act_hw_stats(act->hw_stats);
 				entry = &flow_action->entries[++j];
 			}
 		} else if (is_tcf_csum(act)) {
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index a36974e9c601..1bcf8fbfd40e 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -323,7 +323,8 @@ static void choke_reset(struct Qdisc *sch)
 
 	sch->q.qlen = 0;
 	sch->qstats.backlog = 0;
-	memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
+	if (q->tab)
+		memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
 	q->head = q->tail = 0;
 	red_restart(&q->vars);
 }
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index b1da5589a0c6..c48f91075b5c 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -82,7 +82,7 @@ static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
 	if (q->skip_sock_check)
 		goto skip;
 
-	if (!sk)
+	if (!sk || !sk_fullsock(sk))
 		return false;
 
 	if (!sock_flag(sk, SOCK_TXTIME))
@@ -137,8 +137,9 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 	struct sock_exterr_skb *serr;
 	struct sk_buff *clone;
 	ktime_t txtime = skb->tstamp;
+	struct sock *sk = skb->sk;
 
-	if (!skb->sk || !(skb->sk->sk_txtime_report_errors))
+	if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors))
 		return;
 
 	clone = skb_clone(skb, GFP_ATOMIC);
@@ -154,7 +155,7 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 	serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
 	serr->ee.ee_info = txtime; /* low part of tstamp */
 
-	if (sock_queue_err_skb(skb->sk, clone))
+	if (sock_queue_err_skb(sk, clone))
 		kfree_skb(clone);
 }
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 968519ff36e9..436160be9c18 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -416,7 +416,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 		q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
 
 	if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])
-		q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
+		q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
 
 	if (tb[TCA_FQ_CODEL_MEMORY_LIMIT])
 		q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT]));
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index a9da8776bf5b..fb760cee824e 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -297,9 +297,9 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
 			goto flow_error;
 		}
 		q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]);
-		if (!q->flows_cnt || q->flows_cnt > 65536) {
+		if (!q->flows_cnt || q->flows_cnt >= 65536) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Number of flows must be < 65536");
+					   "Number of flows must range in [1..65535]");
 			goto flow_error;
 		}
 	}
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index c787d4d46017..5a6def5e4e6d 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -637,6 +637,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	if (ctl->divisor &&
 	    (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536))
 		return -EINVAL;
+
+	/* slot->allot is a short, make sure quantum is not too big. */
+	if (ctl->quantum) {
+		unsigned int scaled = SFQ_ALLOT_SIZE(ctl->quantum);
+
+		if (scaled <= 0 || scaled > SHRT_MAX)
+			return -EINVAL;
+	}
+
 	if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
 					ctl_v1->Wlog))
 		return -EINVAL;
diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
index 0fb10abf7579..7a5e4c454715 100644
--- a/net/sched/sch_skbprio.c
+++ b/net/sched/sch_skbprio.c
@@ -169,6 +169,9 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct tc_skbprio_qopt *ctl = nla_data(opt);
 
+	if (opt->nla_len != nla_attr_size(sizeof(*ctl)))
+		return -EINVAL;
+
 	sch->limit = ctl->limit;
 	return 0;
 }
diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
index 6e2eb1dd64ed..68934438ee19 100644
--- a/net/sctp/Kconfig
+++ b/net/sctp/Kconfig
@@ -31,7 +31,7 @@ menuconfig IP_SCTP
 	  homing at either or both ends of an association."
 
 	  To compile this protocol support as a module, choose M here: the
-	  module will be called sctp. Debug messages are handeled by the
+	  module will be called sctp. Debug messages are handled by the
 	  kernel's dynamic debugging framework.
 
 	  If in doubt, say N.
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 4278764d82b8..83e97e8892e0 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -741,14 +741,8 @@ void sctp_auth_calculate_hmac(const struct sctp_association *asoc,
 	if (crypto_shash_setkey(tfm, &asoc_key->data[0], asoc_key->len))
 		goto free;
 
-	{
-		SHASH_DESC_ON_STACK(desc, tfm);
-
-		desc->tfm = tfm;
-		crypto_shash_digest(desc, (u8 *)auth,
-				    end - (unsigned char *)auth, digest);
-		shash_desc_zero(desc);
-	}
+	crypto_shash_tfm_digest(tfm, (u8 *)auth, end - (unsigned char *)auth,
+				digest);
 
 free:
 	if (free_key)
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 09050c1d5517..47910470e532 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -858,7 +858,11 @@ struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc,
 	struct sctp_chunk *retval;
 	__u32 ctsn;
 
-	ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map);
+	if (chunk && chunk->asoc)
+		ctsn = sctp_tsnmap_get_ctsn(&chunk->asoc->peer.tsn_map);
+	else
+		ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map);
+
 	shut.cum_tsn_ack = htonl(ctsn);
 
 	retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN, 0,
@@ -1666,17 +1670,14 @@ static struct sctp_cookie_param *sctp_pack_cookie(
 	       ntohs(init_chunk->chunk_hdr->length), raw_addrs, addrs_len);
 
 	if (sctp_sk(ep->base.sk)->hmac) {
-		SHASH_DESC_ON_STACK(desc, sctp_sk(ep->base.sk)->hmac);
+		struct crypto_shash *tfm = sctp_sk(ep->base.sk)->hmac;
 		int err;
 
 		/* Sign the message.  */
-		desc->tfm = sctp_sk(ep->base.sk)->hmac;
-
-		err = crypto_shash_setkey(desc->tfm, ep->secret_key,
+		err = crypto_shash_setkey(tfm, ep->secret_key,
 					  sizeof(ep->secret_key)) ?:
-		      crypto_shash_digest(desc, (u8 *)&cookie->c, bodysize,
-					  cookie->signature);
-		shash_desc_zero(desc);
+		      crypto_shash_tfm_digest(tfm, (u8 *)&cookie->c, bodysize,
+					      cookie->signature);
 		if (err)
 			goto free_cookie;
 	}
@@ -1737,17 +1738,13 @@ struct sctp_association *sctp_unpack_cookie(
 
 	/* Check the signature.  */
 	{
-		SHASH_DESC_ON_STACK(desc, sctp_sk(ep->base.sk)->hmac);
+		struct crypto_shash *tfm = sctp_sk(ep->base.sk)->hmac;
 		int err;
 
-		desc->tfm = sctp_sk(ep->base.sk)->hmac;
-
-		err = crypto_shash_setkey(desc->tfm, ep->secret_key,
+		err = crypto_shash_setkey(tfm, ep->secret_key,
 					  sizeof(ep->secret_key)) ?:
-		      crypto_shash_digest(desc, (u8 *)bear_cookie, bodysize,
-					  digest);
-		shash_desc_zero(desc);
-
+		      crypto_shash_tfm_digest(tfm, (u8 *)bear_cookie, bodysize,
+					      digest);
 		if (err) {
 			*error = -SCTP_IERROR_NOMEM;
 			goto fail;
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 2bc29463e1dc..9f36fe911d08 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1523,9 +1523,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			timeout = asoc->timeouts[cmd->obj.to];
 			BUG_ON(!timeout);
 
-			timer->expires = jiffies + timeout;
-			sctp_association_hold(asoc);
-			add_timer(timer);
+			/*
+			 * SCTP has a hard time with timer starts.  Because we process
+			 * timer starts as side effects, it can be hard to tell if we
+			 * have already started a timer or not, which leads to BUG
+			 * halts when we call add_timer. So here, instead of just starting
+			 * a timer, if the timer is already started, and just mod
+			 * the timer with the shorter of the two expiration times
+			 */
+			if (!timer_pending(timer))
+				sctp_association_hold(asoc);
+			timer_reduce(timer, jiffies + timeout);
 			break;
 
 		case SCTP_CMD_TIMER_RESTART:
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 6a16af4b1ef6..e86620fbd90f 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1856,16 +1856,17 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
 	/* Update the content of current association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
-	if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+	if ((sctp_state(asoc, SHUTDOWN_PENDING) ||
+	     sctp_state(asoc, SHUTDOWN_SENT)) &&
 	    (sctp_sstate(asoc->base.sk, CLOSING) ||
 	     sock_flag(asoc->base.sk, SOCK_DEAD))) {
-		/* if were currently in SHUTDOWN_PENDING, but the socket
-		 * has been closed by user, don't transition to ESTABLISHED.
-		 * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+		/* If the socket has been closed by user, don't
+		 * transition to ESTABLISHED. Instead trigger SHUTDOWN
+		 * bundled with COOKIE_ACK.
 		 */
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
 		return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
-						     SCTP_ST_CHUNK(0), NULL,
+						     SCTP_ST_CHUNK(0), repl,
 						     commands);
 	} else {
 		sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
@@ -5470,7 +5471,7 @@ enum sctp_disposition sctp_sf_do_9_2_start_shutdown(
 	 * in the Cumulative TSN Ack field the last sequential TSN it
 	 * has received from the peer.
 	 */
-	reply = sctp_make_shutdown(asoc, NULL);
+	reply = sctp_make_shutdown(asoc, arg);
 	if (!reply)
 		goto nomem;
 
@@ -6068,7 +6069,7 @@ enum sctp_disposition sctp_sf_autoclose_timer_expire(
 	disposition = SCTP_DISPOSITION_CONSUME;
 	if (sctp_outq_is_empty(&asoc->outqueue)) {
 		disposition = sctp_sf_do_9_2_start_shutdown(net, ep, asoc, type,
-							    arg, commands);
+							    NULL, commands);
 	}
 
 	return disposition;
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index c82dbdcf13f2..77d5c36a8991 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -343,6 +343,9 @@ void sctp_ulpevent_nofity_peer_addr_change(struct sctp_transport *transport,
 	struct sockaddr_storage addr;
 	struct sctp_ulpevent *event;
 
+	if (asoc->state < SCTP_STATE_ESTABLISHED)
+		return;
+
 	memset(&addr, 0, sizeof(struct sockaddr_storage));
 	memcpy(&addr, &transport->ipaddr, transport->af_specific->sockaddr_len);
 
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 25fbd8d9de74..ac5cac0dd24b 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -2032,7 +2032,6 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred,
 	struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf;
 	struct kvec *head = rqstp->rq_rcv_buf.head;
 	struct rpc_auth *auth = cred->cr_auth;
-	unsigned int savedlen = rcv_buf->len;
 	u32 offset, opaque_len, maj_stat;
 	__be32 *p;
 
@@ -2043,9 +2042,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred,
 	offset = (u8 *)(p) - (u8 *)head->iov_base;
 	if (offset + opaque_len > rcv_buf->len)
 		goto unwrap_failed;
-	rcv_buf->len = offset + opaque_len;
 
-	maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, rcv_buf);
+	maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset,
+			      offset + opaque_len, rcv_buf);
 	if (maj_stat == GSS_S_CONTEXT_EXPIRED)
 		clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
 	if (maj_stat != GSS_S_COMPLETE)
@@ -2059,10 +2058,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred,
 	 */
 	xdr_init_decode(xdr, rcv_buf, p, rqstp);
 
-	auth->au_rslack = auth->au_verfsize + 2 +
-			  XDR_QUADLEN(savedlen - rcv_buf->len);
-	auth->au_ralign = auth->au_verfsize + 2 +
-			  XDR_QUADLEN(savedlen - rcv_buf->len);
+	auth->au_rslack = auth->au_verfsize + 2 + ctx->gc_gss_ctx->slack;
+	auth->au_ralign = auth->au_verfsize + 2 + ctx->gc_gss_ctx->align;
+
 	return 0;
 unwrap_failed:
 	trace_rpcgss_unwrap_failed(task);
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 6f2d30d7b766..e7180da1fc6a 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -851,8 +851,8 @@ out_err:
 }
 
 u32
-gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf,
-		     u32 *headskip, u32 *tailskip)
+gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len,
+		     struct xdr_buf *buf, u32 *headskip, u32 *tailskip)
 {
 	struct xdr_buf subbuf;
 	u32 ret = 0;
@@ -881,7 +881,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf,
 
 	/* create a segment skipping the header and leaving out the checksum */
 	xdr_buf_subsegment(buf, &subbuf, offset + GSS_KRB5_TOK_HDR_LEN,
-				    (buf->len - offset - GSS_KRB5_TOK_HDR_LEN -
+				    (len - offset - GSS_KRB5_TOK_HDR_LEN -
 				     kctx->gk5e->cksumlength));
 
 	nblocks = (subbuf.len + blocksize - 1) / blocksize;
@@ -926,7 +926,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf,
 		goto out_err;
 
 	/* Get the packet's hmac value */
-	ret = read_bytes_from_xdr_buf(buf, buf->len - kctx->gk5e->cksumlength,
+	ret = read_bytes_from_xdr_buf(buf, len - kctx->gk5e->cksumlength,
 				      pkt_hmac, kctx->gk5e->cksumlength);
 	if (ret)
 		goto out_err;
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 6c1920eed771..cf0fd170ac18 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -261,7 +261,9 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 }
 
 static u32
-gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
+gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len,
+		       struct xdr_buf *buf, unsigned int *slack,
+		       unsigned int *align)
 {
 	int			signalg;
 	int			sealalg;
@@ -279,12 +281,13 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	u32			conflen = kctx->gk5e->conflen;
 	int			crypt_offset;
 	u8			*cksumkey;
+	unsigned int		saved_len = buf->len;
 
 	dprintk("RPC:       gss_unwrap_kerberos\n");
 
 	ptr = (u8 *)buf->head[0].iov_base + offset;
 	if (g_verify_token_header(&kctx->mech_used, &bodysize, &ptr,
-					buf->len - offset))
+					len - offset))
 		return GSS_S_DEFECTIVE_TOKEN;
 
 	if ((ptr[0] != ((KG_TOK_WRAP_MSG >> 8) & 0xff)) ||
@@ -324,6 +327,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	    (!kctx->initiate && direction != 0))
 		return GSS_S_BAD_SIG;
 
+	buf->len = len;
 	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
 		struct crypto_sync_skcipher *cipher;
 		int err;
@@ -376,11 +380,15 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	data_len = (buf->head[0].iov_base + buf->head[0].iov_len) - data_start;
 	memmove(orig_start, data_start, data_len);
 	buf->head[0].iov_len -= (data_start - orig_start);
-	buf->len -= (data_start - orig_start);
+	buf->len = len - (data_start - orig_start);
 
 	if (gss_krb5_remove_padding(buf, blocksize))
 		return GSS_S_DEFECTIVE_TOKEN;
 
+	/* slack must include room for krb5 padding */
+	*slack = XDR_QUADLEN(saved_len - buf->len);
+	/* The GSS blob always precedes the RPC message payload */
+	*align = *slack;
 	return GSS_S_COMPLETE;
 }
 
@@ -486,7 +494,9 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset,
 }
 
 static u32
-gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
+gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len,
+		       struct xdr_buf *buf, unsigned int *slack,
+		       unsigned int *align)
 {
 	time64_t	now;
 	u8		*ptr;
@@ -532,7 +542,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	if (rrc != 0)
 		rotate_left(offset + 16, buf, rrc);
 
-	err = (*kctx->gk5e->decrypt_v2)(kctx, offset, buf,
+	err = (*kctx->gk5e->decrypt_v2)(kctx, offset, len, buf,
 					&headskip, &tailskip);
 	if (err)
 		return GSS_S_FAILURE;
@@ -542,7 +552,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	 * it against the original
 	 */
 	err = read_bytes_from_xdr_buf(buf,
-				buf->len - GSS_KRB5_TOK_HDR_LEN - tailskip,
+				len - GSS_KRB5_TOK_HDR_LEN - tailskip,
 				decrypted_hdr, GSS_KRB5_TOK_HDR_LEN);
 	if (err) {
 		dprintk("%s: error %u getting decrypted_hdr\n", __func__, err);
@@ -568,18 +578,19 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	 * Note that buf->head[0].iov_len may indicate the available
 	 * head buffer space rather than that actually occupied.
 	 */
-	movelen = min_t(unsigned int, buf->head[0].iov_len, buf->len);
+	movelen = min_t(unsigned int, buf->head[0].iov_len, len);
 	movelen -= offset + GSS_KRB5_TOK_HDR_LEN + headskip;
-	if (offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen >
-	    buf->head[0].iov_len)
-		return GSS_S_FAILURE;
+	BUG_ON(offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen >
+							buf->head[0].iov_len);
 	memmove(ptr, ptr + GSS_KRB5_TOK_HDR_LEN + headskip, movelen);
 	buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip;
-	buf->len -= GSS_KRB5_TOK_HDR_LEN + headskip;
+	buf->len = len - GSS_KRB5_TOK_HDR_LEN + headskip;
 
 	/* Trim off the trailing "extra count" and checksum blob */
-	buf->len -= ec + GSS_KRB5_TOK_HDR_LEN + tailskip;
+	xdr_buf_trim(buf, ec + GSS_KRB5_TOK_HDR_LEN + tailskip);
 
+	*align = XDR_QUADLEN(GSS_KRB5_TOK_HDR_LEN + headskip);
+	*slack = *align + XDR_QUADLEN(ec + GSS_KRB5_TOK_HDR_LEN + tailskip);
 	return GSS_S_COMPLETE;
 }
 
@@ -603,7 +614,8 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset,
 }
 
 u32
-gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf)
+gss_unwrap_kerberos(struct gss_ctx *gctx, int offset,
+		    int len, struct xdr_buf *buf)
 {
 	struct krb5_ctx	*kctx = gctx->internal_ctx_id;
 
@@ -613,9 +625,11 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf)
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
 	case ENCTYPE_ARCFOUR_HMAC:
-		return gss_unwrap_kerberos_v1(kctx, offset, buf);
+		return gss_unwrap_kerberos_v1(kctx, offset, len, buf,
+					      &gctx->slack, &gctx->align);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
-		return gss_unwrap_kerberos_v2(kctx, offset, buf);
+		return gss_unwrap_kerberos_v2(kctx, offset, len, buf,
+					      &gctx->slack, &gctx->align);
 	}
 }
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index db550bfc2642..69316ab1b9fa 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -411,10 +411,11 @@ gss_wrap(struct gss_ctx	*ctx_id,
 u32
 gss_unwrap(struct gss_ctx	*ctx_id,
 	   int			offset,
+	   int			len,
 	   struct xdr_buf	*buf)
 {
 	return ctx_id->mech_type->gm_ops
-		->gss_unwrap(ctx_id, offset, buf);
+		->gss_unwrap(ctx_id, offset, len, buf);
 }
 
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 54ae5be62f6a..50d93c49ef1a 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -906,7 +906,7 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g
 	if (svc_getnl(&buf->head[0]) != seq)
 		goto out;
 	/* trim off the mic and padding at the end before returning */
-	buf->len -= 4 + round_up_to_quad(mic.len);
+	xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4);
 	stat = 0;
 out:
 	kfree(mic.data);
@@ -934,7 +934,7 @@ static int
 unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx)
 {
 	u32 priv_len, maj_stat;
-	int pad, saved_len, remaining_len, offset;
+	int pad, remaining_len, offset;
 
 	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
@@ -954,12 +954,8 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs
 	buf->len -= pad;
 	fix_priv_head(buf, pad);
 
-	/* Maybe it would be better to give gss_unwrap a length parameter: */
-	saved_len = buf->len;
-	buf->len = priv_len;
-	maj_stat = gss_unwrap(ctx, 0, buf);
+	maj_stat = gss_unwrap(ctx, 0, priv_len, buf);
 	pad = priv_len - buf->len;
-	buf->len = saved_len;
 	buf->len -= pad;
 	/* The upper layers assume the buffer is aligned on 4-byte boundaries.
 	 * In the krb5p case, at least, the data ends up offset, so we need to
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index af0ddd28b081..baef5ee43dbb 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -529,7 +529,6 @@ void cache_purge(struct cache_detail *detail)
 {
 	struct cache_head *ch = NULL;
 	struct hlist_head *head = NULL;
-	struct hlist_node *tmp = NULL;
 	int i = 0;
 
 	spin_lock(&detail->hash_lock);
@@ -541,7 +540,9 @@ void cache_purge(struct cache_detail *detail)
 	dprintk("RPC: %d entries in %s cache\n", detail->entries, detail->name);
 	for (i = 0; i < detail->hash_size; i++) {
 		head = &detail->hash_table[i];
-		hlist_for_each_entry_safe(ch, tmp, head, cache_list) {
+		while (!hlist_empty(head)) {
+			ch = hlist_entry(head->first, struct cache_head,
+					 cache_list);
 			sunrpc_begin_cache_remove_entry(ch, detail);
 			spin_unlock(&detail->hash_lock);
 			sunrpc_end_cache_remove_entry(ch, detail);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 325a0858700f..61b21dafd7c0 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -880,6 +880,22 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client);
 /*
  * Free an RPC client
  */
+static void rpc_free_client_work(struct work_struct *work)
+{
+	struct rpc_clnt *clnt = container_of(work, struct rpc_clnt, cl_work);
+
+	/* These might block on processes that might allocate memory,
+	 * so they cannot be called in rpciod, so they are handled separately
+	 * here.
+	 */
+	rpc_clnt_debugfs_unregister(clnt);
+	rpc_free_clid(clnt);
+	rpc_clnt_remove_pipedir(clnt);
+	xprt_put(rcu_dereference_raw(clnt->cl_xprt));
+
+	kfree(clnt);
+	rpciod_down();
+}
 static struct rpc_clnt *
 rpc_free_client(struct rpc_clnt *clnt)
 {
@@ -890,17 +906,14 @@ rpc_free_client(struct rpc_clnt *clnt)
 			rcu_dereference(clnt->cl_xprt)->servername);
 	if (clnt->cl_parent != clnt)
 		parent = clnt->cl_parent;
-	rpc_clnt_debugfs_unregister(clnt);
-	rpc_clnt_remove_pipedir(clnt);
 	rpc_unregister_client(clnt);
 	rpc_free_iostats(clnt->cl_metrics);
 	clnt->cl_metrics = NULL;
-	xprt_put(rcu_dereference_raw(clnt->cl_xprt));
 	xprt_iter_destroy(&clnt->cl_xpi);
-	rpciod_down();
 	put_cred(clnt->cl_cred);
-	rpc_free_clid(clnt);
-	kfree(clnt);
+
+	INIT_WORK(&clnt->cl_work, rpc_free_client_work);
+	schedule_work(&clnt->cl_work);
 	return parent;
 }
 
@@ -2420,6 +2433,11 @@ rpc_check_timeout(struct rpc_task *task)
 {
 	struct rpc_clnt	*clnt = task->tk_client;
 
+	if (RPC_SIGNALLED(task)) {
+		rpc_call_rpcerror(task, -ERESTARTSYS);
+		return;
+	}
+
 	if (xprt_adjust_timeout(task->tk_rqstp) == 0)
 		return;
 
@@ -2808,8 +2826,7 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt,
 	task = rpc_call_null_helper(clnt, xprt, NULL,
 			RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC|RPC_TASK_NULLCREDS,
 			&rpc_cb_add_xprt_call_ops, data);
-	if (IS_ERR(task))
-		return PTR_ERR(task);
+
 	rpc_put_task(task);
 success:
 	return 1;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index e27e3532ec75..2284ff038dad 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -908,9 +908,6 @@ int svc_send(struct svc_rqst *rqstp)
 	if (!xprt)
 		goto out;
 
-	/* release the receive skb before sending the reply */
-	xprt->xpt_ops->xpo_release_rqst(rqstp);
-
 	/* calculate over-all length */
 	xb = &rqstp->rq_res;
 	xb->len = xb->head[0].iov_len +
@@ -1040,6 +1037,8 @@ static void svc_delete_xprt(struct svc_xprt *xprt)
 
 	dprintk("svc: svc_delete_xprt(%p)\n", xprt);
 	xprt->xpt_ops->xpo_detach(xprt);
+	if (xprt->xpt_bc_xprt)
+		xprt->xpt_bc_xprt->ops->close(xprt->xpt_bc_xprt);
 
 	spin_lock_bh(&serv->sv_lock);
 	list_del_init(&xprt->xpt_list);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 519cf9c4f8fd..023514e392b3 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -527,6 +527,8 @@ static int svc_udp_sendto(struct svc_rqst *rqstp)
 	unsigned int uninitialized_var(sent);
 	int err;
 
+	svc_release_udp_skb(rqstp);
+
 	svc_set_cmsg_data(rqstp, cmh);
 
 	err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent);
@@ -1076,6 +1078,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	unsigned int uninitialized_var(sent);
 	int err;
 
+	svc_release_skb(rqstp);
+
 	err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, marker, &sent);
 	xdr_free_bvec(xdr);
 	if (err < 0 || sent != (xdr->len + sizeof(marker)))
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 15b58c5144f9..6f7d82fb1eb0 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -1150,6 +1150,47 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 }
 EXPORT_SYMBOL_GPL(xdr_buf_subsegment);
 
+/**
+ * xdr_buf_trim - lop at most "len" bytes off the end of "buf"
+ * @buf: buf to be trimmed
+ * @len: number of bytes to reduce "buf" by
+ *
+ * Trim an xdr_buf by the given number of bytes by fixing up the lengths. Note
+ * that it's possible that we'll trim less than that amount if the xdr_buf is
+ * too small, or if (for instance) it's all in the head and the parser has
+ * already read too far into it.
+ */
+void xdr_buf_trim(struct xdr_buf *buf, unsigned int len)
+{
+	size_t cur;
+	unsigned int trim = len;
+
+	if (buf->tail[0].iov_len) {
+		cur = min_t(size_t, buf->tail[0].iov_len, trim);
+		buf->tail[0].iov_len -= cur;
+		trim -= cur;
+		if (!trim)
+			goto fix_len;
+	}
+
+	if (buf->page_len) {
+		cur = min_t(unsigned int, buf->page_len, trim);
+		buf->page_len -= cur;
+		trim -= cur;
+		if (!trim)
+			goto fix_len;
+	}
+
+	if (buf->head[0].iov_len) {
+		cur = min_t(size_t, buf->head[0].iov_len, trim);
+		buf->head[0].iov_len -= cur;
+		trim -= cur;
+	}
+fix_len:
+	buf->len -= (len - trim);
+}
+EXPORT_SYMBOL_GPL(xdr_buf_trim);
+
 static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len)
 {
 	unsigned int this_len;
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 4a81e6995d3e..3c627dc685cc 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -388,7 +388,9 @@ static int rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt,
 	} while (nsegs);
 
 done:
-	return xdr_stream_encode_item_absent(xdr);
+	if (xdr_stream_encode_item_absent(xdr) < 0)
+		return -EMSGSIZE;
+	return 0;
 }
 
 /* Register and XDR encode the Write list. Supports encoding a list
@@ -454,7 +456,9 @@ static int rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt,
 	*segcount = cpu_to_be32(nchunks);
 
 done:
-	return xdr_stream_encode_item_absent(xdr);
+	if (xdr_stream_encode_item_absent(xdr) < 0)
+		return -EMSGSIZE;
+	return 0;
 }
 
 /* Register and XDR encode the Reply chunk. Supports encoding an array
@@ -480,8 +484,11 @@ static int rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt,
 	int nsegs, nchunks;
 	__be32 *segcount;
 
-	if (wtype != rpcrdma_replych)
-		return xdr_stream_encode_item_absent(xdr);
+	if (wtype != rpcrdma_replych) {
+		if (xdr_stream_encode_item_absent(xdr) < 0)
+			return -EMSGSIZE;
+		return 0;
+	}
 
 	seg = req->rl_segments;
 	nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf, 0, wtype, seg);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index d510a3a15d4b..af7eb8d202ae 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -244,6 +244,8 @@ static void
 xprt_rdma_bc_close(struct rpc_xprt *xprt)
 {
 	dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
+
+	xprt_disconnect_done(xprt);
 	xprt->cwnd = RPC_CWNDSHIFT;
 }
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 54469b72b25f..efa5fcb5793f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -223,6 +223,26 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 		svc_rdma_recv_ctxt_destroy(rdma, ctxt);
 }
 
+/**
+ * svc_rdma_release_rqst - Release transport-specific per-rqst resources
+ * @rqstp: svc_rqst being released
+ *
+ * Ensure that the recv_ctxt is released whether or not a Reply
+ * was sent. For example, the client could close the connection,
+ * or svc_process could drop an RPC, before the Reply is sent.
+ */
+void svc_rdma_release_rqst(struct svc_rqst *rqstp)
+{
+	struct svc_rdma_recv_ctxt *ctxt = rqstp->rq_xprt_ctxt;
+	struct svc_xprt *xprt = rqstp->rq_xprt;
+	struct svcxprt_rdma *rdma =
+		container_of(xprt, struct svcxprt_rdma, sc_xprt);
+
+	rqstp->rq_xprt_ctxt = NULL;
+	if (ctxt)
+		svc_rdma_recv_ctxt_put(rdma, ctxt);
+}
+
 static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma,
 				struct svc_rdma_recv_ctxt *ctxt)
 {
@@ -820,6 +840,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	__be32 *p;
 	int ret;
 
+	rqstp->rq_xprt_ctxt = NULL;
+
 	spin_lock(&rdma_xprt->sc_rq_dto_lock);
 	ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_read_complete_q);
 	if (ctxt) {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index bd7c195d872e..23c2d3ce0dc9 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -323,8 +323,6 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
 		if (atomic_sub_return(cc->cc_sqecount,
 				      &rdma->sc_sq_avail) > 0) {
 			ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr);
-			trace_svcrdma_post_rw(&cc->cc_cqe,
-					      cc->cc_sqecount, ret);
 			if (ret)
 				break;
 			return 0;
@@ -337,6 +335,7 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
 		trace_svcrdma_sq_retry(rdma);
 	} while (1);
 
+	trace_svcrdma_sq_post_err(rdma, ret);
 	set_bit(XPT_CLOSE, &xprt->xpt_flags);
 
 	/* If even one was posted, there will be a completion. */
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 90cba3058f04..b6c8643867f2 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -322,15 +322,17 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr)
 		}
 
 		svc_xprt_get(&rdma->sc_xprt);
+		trace_svcrdma_post_send(wr);
 		ret = ib_post_send(rdma->sc_qp, wr, NULL);
-		trace_svcrdma_post_send(wr, ret);
-		if (ret) {
-			set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
-			svc_xprt_put(&rdma->sc_xprt);
-			wake_up(&rdma->sc_send_wait);
-		}
-		break;
+		if (ret)
+			break;
+		return 0;
 	}
+
+	trace_svcrdma_sq_post_err(rdma, ret);
+	set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
+	svc_xprt_put(&rdma->sc_xprt);
+	wake_up(&rdma->sc_send_wait);
 	return ret;
 }
 
@@ -924,12 +926,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 	ret = svc_rdma_send_reply_msg(rdma, sctxt, rctxt, rqstp);
 	if (ret < 0)
 		goto err1;
-	ret = 0;
-
-out:
-	rqstp->rq_xprt_ctxt = NULL;
-	svc_rdma_recv_ctxt_put(rdma, rctxt);
-	return ret;
+	return 0;
 
  err2:
 	if (ret != -E2BIG && ret != -EINVAL)
@@ -938,16 +935,14 @@ out:
 	ret = svc_rdma_send_error_msg(rdma, sctxt, rqstp);
 	if (ret < 0)
 		goto err1;
-	ret = 0;
-	goto out;
+	return 0;
 
  err1:
 	svc_rdma_send_ctxt_put(rdma, sctxt);
  err0:
 	trace_svcrdma_send_failed(rqstp, ret);
 	set_bit(XPT_CLOSE, &xprt->xpt_flags);
-	ret = -ENOTCONN;
-	goto out;
+	return -ENOTCONN;
 }
 
 /**
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 8bb99980ae85..ea54785db4f8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -71,7 +71,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 					struct sockaddr *sa, int salen,
 					int flags);
 static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt);
-static void svc_rdma_release_rqst(struct svc_rqst *);
 static void svc_rdma_detach(struct svc_xprt *xprt);
 static void svc_rdma_free(struct svc_xprt *xprt);
 static int svc_rdma_has_wspace(struct svc_xprt *xprt);
@@ -552,10 +551,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	return NULL;
 }
 
-static void svc_rdma_release_rqst(struct svc_rqst *rqstp)
-{
-}
-
 /*
  * When connected, an svc_xprt has at least two references:
  *
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index cdd84c09df10..05c4d3a9cda2 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -289,6 +289,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_DISCONNECTED:
 		ep->re_connect_status = -ECONNABORTED;
 disconnected:
+		xprt_force_disconnect(xprt);
 		return rpcrdma_ep_destroy(ep);
 	default:
 		break;
@@ -1355,8 +1356,8 @@ int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 		--ep->re_send_count;
 	}
 
+	trace_xprtrdma_post_send(req);
 	rc = frwr_send(r_xprt, req);
-	trace_xprtrdma_post_send(req, rc);
 	if (rc)
 		return -ENOTCONN;
 	return 0;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 0bda8a73e8a8..845d0be805ec 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2584,6 +2584,7 @@ static int bc_send_request(struct rpc_rqst *req)
 
 static void bc_close(struct rpc_xprt *xprt)
 {
+	xprt_disconnect_done(xprt);
 }
 
 /*
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index c8c47fc72653..8c47ded2edb6 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -1712,6 +1712,7 @@ exit:
 	case -EBUSY:
 		this_cpu_inc(stats->stat[STAT_ASYNC]);
 		*skb = NULL;
+		tipc_aead_put(aead);
 		return rc;
 	default:
 		this_cpu_inc(stats->stat[STAT_NOK]);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 467c53a1fb5c..d4675e922a8f 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1065,7 +1065,7 @@ static void tipc_link_update_cwin(struct tipc_link *l, int released,
 	/* Enter fast recovery */
 	if (unlikely(retransmitted)) {
 		l->ssthresh = max_t(u16, l->window / 2, 300);
-		l->window = l->ssthresh;
+		l->window = min_t(u16, l->ssthresh, l->window);
 		return;
 	}
 	/* Enter slow start */
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 10292c942384..803a3a6d0f50 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2038,6 +2038,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 		n = tipc_node_find_by_id(net, ehdr->id);
 	}
 	tipc_crypto_rcv(net, (n) ? n->crypto_rx : NULL, &skb, b);
+	tipc_node_put(n);
 	if (!skb)
 		return;
 
@@ -2090,7 +2091,7 @@ rcv:
 	/* Check/update node state before receiving */
 	if (unlikely(skb)) {
 		if (unlikely(skb_linearize(skb)))
-			goto discard;
+			goto out_node_put;
 		tipc_node_write_lock(n);
 		if (tipc_node_check_state(n, skb, bearer_id, &xmitq)) {
 			if (le->link) {
@@ -2119,6 +2120,7 @@ rcv:
 	if (!skb_queue_empty(&xmitq))
 		tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr, n);
 
+out_node_put:
 	tipc_node_put(n);
 discard:
 	kfree_skb(skb);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 87466607097f..e370ad0edd76 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1739,22 +1739,21 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
 	return 0;
 }
 
-static void tipc_sk_send_ack(struct tipc_sock *tsk)
+static struct sk_buff *tipc_sk_build_ack(struct tipc_sock *tsk)
 {
 	struct sock *sk = &tsk->sk;
-	struct net *net = sock_net(sk);
 	struct sk_buff *skb = NULL;
 	struct tipc_msg *msg;
 	u32 peer_port = tsk_peer_port(tsk);
 	u32 dnode = tsk_peer_node(tsk);
 
 	if (!tipc_sk_connected(sk))
-		return;
+		return NULL;
 	skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0,
 			      dnode, tsk_own_node(tsk), peer_port,
 			      tsk->portid, TIPC_OK);
 	if (!skb)
-		return;
+		return NULL;
 	msg = buf_msg(skb);
 	msg_set_conn_ack(msg, tsk->rcv_unacked);
 	tsk->rcv_unacked = 0;
@@ -1764,7 +1763,19 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk)
 		tsk->rcv_win = tsk_adv_blocks(tsk->sk.sk_rcvbuf);
 		msg_set_adv_win(msg, tsk->rcv_win);
 	}
-	tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg));
+	return skb;
+}
+
+static void tipc_sk_send_ack(struct tipc_sock *tsk)
+{
+	struct sk_buff *skb;
+
+	skb = tipc_sk_build_ack(tsk);
+	if (!skb)
+		return;
+
+	tipc_node_xmit_skb(sock_net(&tsk->sk), skb, tsk_peer_node(tsk),
+			   msg_link_selector(buf_msg(skb)));
 }
 
 static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
@@ -1938,7 +1949,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
 	bool peek = flags & MSG_PEEK;
 	int offset, required, copy, copied = 0;
 	int hlen, dlen, err, rc;
-	bool ack = false;
 	long timeout;
 
 	/* Catch invalid receive attempts */
@@ -1983,7 +1993,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
 
 		/* Copy data if msg ok, otherwise return error/partial data */
 		if (likely(!err)) {
-			ack = msg_ack_required(hdr);
 			offset = skb_cb->bytes_read;
 			copy = min_t(int, dlen - offset, buflen - copied);
 			rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy);
@@ -2011,7 +2020,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
 
 		/* Send connection flow control advertisement when applicable */
 		tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen);
-		if (ack || tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)
+		if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)
 			tipc_sk_send_ack(tsk);
 
 		/* Exit if all requested data or FIN/error received */
@@ -2105,9 +2114,11 @@ static void tipc_sk_proto_rcv(struct sock *sk,
  * tipc_sk_filter_connect - check incoming message for a connection-based socket
  * @tsk: TIPC socket
  * @skb: pointer to message buffer.
+ * @xmitq: for Nagle ACK if any
  * Returns true if message should be added to receive queue, false otherwise
  */
-static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
+static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb,
+				   struct sk_buff_head *xmitq)
 {
 	struct sock *sk = &tsk->sk;
 	struct net *net = sock_net(sk);
@@ -2171,8 +2182,17 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
 		if (!skb_queue_empty(&sk->sk_write_queue))
 			tipc_sk_push_backlog(tsk);
 		/* Accept only connection-based messages sent by peer */
-		if (likely(con_msg && !err && pport == oport && pnode == onode))
+		if (likely(con_msg && !err && pport == oport &&
+			   pnode == onode)) {
+			if (msg_ack_required(hdr)) {
+				struct sk_buff *skb;
+
+				skb = tipc_sk_build_ack(tsk);
+				if (skb)
+					__skb_queue_tail(xmitq, skb);
+			}
 			return true;
+		}
 		if (!tsk_peer_msg(tsk, hdr))
 			return false;
 		if (!err)
@@ -2267,7 +2287,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
 	while ((skb = __skb_dequeue(&inputq))) {
 		hdr = buf_msg(skb);
 		limit = rcvbuf_limit(sk, skb);
-		if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) ||
+		if ((sk_conn && !tipc_sk_filter_connect(tsk, skb, xmitq)) ||
 		    (!sk_conn && msg_connected(hdr)) ||
 		    (!grp && msg_in_group(hdr)))
 			err = TIPC_ERR_NO_PORT;
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index aa015c233898..6ebbec1bedd1 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -96,6 +96,16 @@ void tipc_sub_get(struct tipc_subscription *subscription);
 		(swap_ ? swab32(val__) : val__);			\
 	})
 
+/* tipc_sub_write - write val_ to field_ of struct sub_ in user endian format
+ */
+#define tipc_sub_write(sub_, field_, val_)				\
+	({								\
+		struct tipc_subscr *sub__ = sub_;			\
+		u32 val__ = val_;					\
+		int swap_ = !((sub__)->filter & TIPC_FILTER_MASK);	\
+		(sub__)->field_ = swap_ ? swab32(val__) : val__;	\
+	})
+
 /* tipc_evt_write - write val_ to field_ of struct evt_ in user endian format
  */
 #define tipc_evt_write(evt_, field_, val_)				\
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 3a12fc18239b..446af7bbd13e 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -237,8 +237,8 @@ static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s)
 		if (!s || !memcmp(s, &sub->evt.s, sizeof(*s))) {
 			tipc_sub_unsubscribe(sub);
 			atomic_dec(&tn->subscription_count);
-		} else if (s) {
-			break;
+			if (s)
+				break;
 		}
 	}
 	spin_unlock_bh(&con->sub_lock);
@@ -362,9 +362,10 @@ static int tipc_conn_rcv_sub(struct tipc_topsrv *srv,
 {
 	struct tipc_net *tn = tipc_net(srv->net);
 	struct tipc_subscription *sub;
+	u32 s_filter = tipc_sub_read(s, filter);
 
-	if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) {
-		s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL);
+	if (s_filter & TIPC_SUB_CANCEL) {
+		tipc_sub_write(s, filter, s_filter & ~TIPC_SUB_CANCEL);
 		tipc_conn_delete_sub(con, s);
 		return 0;
 	}
@@ -400,12 +401,15 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
 		return -EWOULDBLOCK;
 	if (ret == sizeof(s)) {
 		read_lock_bh(&sk->sk_callback_lock);
-		ret = tipc_conn_rcv_sub(srv, con, &s);
+		/* RACE: the connection can be closed in the meantime */
+		if (likely(connected(con)))
+			ret = tipc_conn_rcv_sub(srv, con, &s);
 		read_unlock_bh(&sk->sk_callback_lock);
+		if (!ret)
+			return 0;
 	}
-	if (ret < 0)
-		tipc_conn_close(con);
 
+	tipc_conn_close(con);
 	return ret;
 }
 
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index d6620ad53546..28a283f26a8d 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -161,9 +161,11 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 			 struct udp_bearer *ub, struct udp_media_addr *src,
 			 struct udp_media_addr *dst, struct dst_cache *cache)
 {
-	struct dst_entry *ndst = dst_cache_get(cache);
+	struct dst_entry *ndst;
 	int ttl, err = 0;
 
+	local_bh_disable();
+	ndst = dst_cache_get(cache);
 	if (dst->proto == htons(ETH_P_IP)) {
 		struct rtable *rt = (struct rtable *)ndst;
 
@@ -210,9 +212,11 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 					   src->port, dst->port, false);
 #endif
 	}
+	local_bh_enable();
 	return err;
 
 tx_error:
+	local_bh_enable();
 	kfree_skb(skb);
 	return err;
 }
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 156efce50dbd..0e989005bdc2 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -56,9 +56,9 @@ enum {
 	TLS_NUM_PROTS,
 };
 
-static struct proto *saved_tcpv6_prot;
+static const struct proto *saved_tcpv6_prot;
 static DEFINE_MUTEX(tcpv6_prot_mutex);
-static struct proto *saved_tcpv4_prot;
+static const struct proto *saved_tcpv4_prot;
 static DEFINE_MUTEX(tcpv4_prot_mutex);
 static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG];
 static struct proto_ops tls_sw_proto_ops;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index c98e602a1a2d..8c2763eb6aae 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -206,10 +206,12 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err)
 
 	kfree(aead_req);
 
+	spin_lock_bh(&ctx->decrypt_compl_lock);
 	pending = atomic_dec_return(&ctx->decrypt_pending);
 
-	if (!pending && READ_ONCE(ctx->async_notify))
+	if (!pending && ctx->async_notify)
 		complete(&ctx->async_wait.completion);
+	spin_unlock_bh(&ctx->decrypt_compl_lock);
 }
 
 static int tls_do_decryption(struct sock *sk,
@@ -467,10 +469,12 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err)
 			ready = true;
 	}
 
+	spin_lock_bh(&ctx->encrypt_compl_lock);
 	pending = atomic_dec_return(&ctx->encrypt_pending);
 
-	if (!pending && READ_ONCE(ctx->async_notify))
+	if (!pending && ctx->async_notify)
 		complete(&ctx->async_wait.completion);
+	spin_unlock_bh(&ctx->encrypt_compl_lock);
 
 	if (!ready)
 		return;
@@ -780,7 +784,7 @@ static int tls_push_record(struct sock *sk, int flags,
 
 static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 			       bool full_record, u8 record_type,
-			       size_t *copied, int flags)
+			       ssize_t *copied, int flags)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
@@ -796,10 +800,13 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 	psock = sk_psock_get(sk);
 	if (!psock || !policy) {
 		err = tls_push_record(sk, flags, record_type);
-		if (err && err != -EINPROGRESS) {
+		if (err && sk->sk_err == EBADMSG) {
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
+			err = -sk->sk_err;
 		}
+		if (psock)
+			sk_psock_put(sk, psock);
 		return err;
 	}
 more_data:
@@ -822,9 +829,10 @@ more_data:
 	switch (psock->eval) {
 	case __SK_PASS:
 		err = tls_push_record(sk, flags, record_type);
-		if (err && err != -EINPROGRESS) {
+		if (err && sk->sk_err == EBADMSG) {
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
+			err = -sk->sk_err;
 			goto out_err;
 		}
 		break;
@@ -914,7 +922,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	unsigned char record_type = TLS_RECORD_TYPE_DATA;
 	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool eor = !(msg->msg_flags & MSG_MORE);
-	size_t try_to_copy, copied = 0;
+	size_t try_to_copy;
+	ssize_t copied = 0;
 	struct sk_msg *msg_pl, *msg_en;
 	struct tls_rec *rec;
 	int required_size;
@@ -924,6 +933,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int num_zc = 0;
 	int orig_size;
 	int ret = 0;
+	int pending;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -EOPNOTSUPP;
@@ -1090,13 +1100,19 @@ trim_sgl:
 		goto send_end;
 	} else if (num_zc) {
 		/* Wait for pending encryptions to get completed */
-		smp_store_mb(ctx->async_notify, true);
+		spin_lock_bh(&ctx->encrypt_compl_lock);
+		ctx->async_notify = true;
 
-		if (atomic_read(&ctx->encrypt_pending))
+		pending = atomic_read(&ctx->encrypt_pending);
+		spin_unlock_bh(&ctx->encrypt_compl_lock);
+		if (pending)
 			crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 		else
 			reinit_completion(&ctx->async_wait.completion);
 
+		/* There can be no concurrent accesses, since we have no
+		 * pending encrypt operations
+		 */
 		WRITE_ONCE(ctx->async_notify, false);
 
 		if (ctx->async_wait.err) {
@@ -1116,7 +1132,7 @@ send_end:
 
 	release_sock(sk);
 	mutex_unlock(&tls_ctx->tx_lock);
-	return copied ? copied : ret;
+	return copied > 0 ? copied : ret;
 }
 
 static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
@@ -1130,7 +1146,7 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 	struct sk_msg *msg_pl;
 	struct tls_rec *rec;
 	int num_async = 0;
-	size_t copied = 0;
+	ssize_t copied = 0;
 	bool full_record;
 	int record_room;
 	int ret = 0;
@@ -1232,7 +1248,7 @@ wait_for_memory:
 	}
 sendpage_end:
 	ret = sk_stream_error(sk, flags, ret);
-	return copied ? copied : ret;
+	return copied > 0 ? copied : ret;
 }
 
 int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
@@ -1727,6 +1743,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool is_peek = flags & MSG_PEEK;
 	int num_async = 0;
+	int pending;
 
 	flags |= nonblock;
 
@@ -1889,8 +1906,11 @@ pick_next_record:
 recv_end:
 	if (num_async) {
 		/* Wait for all previously submitted records to be decrypted */
-		smp_store_mb(ctx->async_notify, true);
-		if (atomic_read(&ctx->decrypt_pending)) {
+		spin_lock_bh(&ctx->decrypt_compl_lock);
+		ctx->async_notify = true;
+		pending = atomic_read(&ctx->decrypt_pending);
+		spin_unlock_bh(&ctx->decrypt_compl_lock);
+		if (pending) {
 			err = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 			if (err) {
 				/* one of async decrypt failed */
@@ -1902,6 +1922,10 @@ recv_end:
 		} else {
 			reinit_completion(&ctx->async_wait.completion);
 		}
+
+		/* There can be no concurrent accesses, since we have no
+		 * pending decrypt operations
+		 */
 		WRITE_ONCE(ctx->async_notify, false);
 
 		/* Drain records from the rx_list & copy if required */
@@ -2081,8 +2105,9 @@ static void tls_data_ready(struct sock *sk)
 	strp_data_ready(&ctx->strp);
 
 	psock = sk_psock_get(sk);
-	if (psock && !list_empty(&psock->ingress_msg)) {
-		ctx->saved_data_ready(sk);
+	if (psock) {
+		if (!list_empty(&psock->ingress_msg))
+			ctx->saved_data_ready(sk);
 		sk_psock_put(sk, psock);
 	}
 }
@@ -2287,6 +2312,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 
 	if (tx) {
 		crypto_init_wait(&sw_ctx_tx->async_wait);
+		spin_lock_init(&sw_ctx_tx->encrypt_compl_lock);
 		crypto_info = &ctx->crypto_send.info;
 		cctx = &ctx->tx;
 		aead = &sw_ctx_tx->aead_send;
@@ -2295,6 +2321,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		sw_ctx_tx->tx_work.sk = sk;
 	} else {
 		crypto_init_wait(&sw_ctx_rx->async_wait);
+		spin_lock_init(&sw_ctx_rx->decrypt_compl_lock);
 		crypto_info = &ctx->crypto_recv.info;
 		cctx = &ctx->rx;
 		skb_queue_head_init(&sw_ctx_rx->rx_list);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index a5f28708e0e7..626bf9044418 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1408,7 +1408,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 	/* Wait for children sockets to appear; these are the new sockets
 	 * created upon connection establishment.
 	 */
-	timeout = sock_sndtimeo(listener, flags & O_NONBLOCK);
+	timeout = sock_rcvtimeo(listener, flags & O_NONBLOCK);
 	prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
 
 	while ((connected = vsock_dequeue_accept(listener)) == NULL &&
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 709038a4783e..0edda1edf988 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -157,7 +157,11 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
 
 void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt)
 {
+	if (pkt->tap_delivered)
+		return;
+
 	vsock_deliver_tap(virtio_transport_build_skb, pkt);
+	pkt->tap_delivered = true;
 }
 EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);
 
@@ -1128,6 +1132,14 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 
 	lock_sock(sk);
 
+	/* Check if sk has been released before lock_sock */
+	if (sk->sk_shutdown == SHUTDOWN_MASK) {
+		(void)virtio_transport_reset_no_sock(t, pkt);
+		release_sock(sk);
+		sock_put(sk);
+		goto free_pkt;
+	}
+
 	/* Update CID in case it has changed after a transport reset event */
 	vsk->local_addr.svm_cid = dst.svm_cid;
 
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 341402b4f178..ce024440fa51 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -142,7 +142,7 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
 	if (result)
 		return result;
 
-	if (rdev->wiphy.debugfsdir)
+	if (!IS_ERR_OR_NULL(rdev->wiphy.debugfsdir))
 		debugfs_rename(rdev->wiphy.debugfsdir->d_parent,
 			       rdev->wiphy.debugfsdir,
 			       rdev->wiphy.debugfsdir->d_parent, newname);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5fa402144cda..692bcd35f809 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -644,10 +644,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY,
 					 .len = NL80211_HE_MAX_CAPABILITY_LEN },
 
-	[NL80211_ATTR_FTM_RESPONDER] = {
-		.type = NLA_NESTED,
-		.validation_data = nl80211_ftm_responder_policy,
-	},
+	[NL80211_ATTR_FTM_RESPONDER] =
+		NLA_POLICY_NESTED(nl80211_ftm_responder_policy),
 	[NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1),
 	[NL80211_ATTR_PEER_MEASUREMENTS] =
 		NLA_POLICY_NESTED(nl80211_pmsr_attr_policy),
diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index 00e782335cb0..25bf72ee6cad 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -115,8 +115,10 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 	}
 
-	if (!pskb_may_pull(skb, 1))
+	if (!pskb_may_pull(skb, 1)) {
+		x25_neigh_put(nb);
 		return 0;
+	}
 
 	switch (skb->data[0]) {
 
diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c
index 8aa415a38814..0285aaa1e93c 100644
--- a/net/x25/x25_subr.c
+++ b/net/x25/x25_subr.c
@@ -357,6 +357,12 @@ void x25_disconnect(struct sock *sk, int reason, unsigned char cause,
 		sk->sk_state_change(sk);
 		sock_set_flag(sk, SOCK_DEAD);
 	}
+	if (x25->neighbour) {
+		read_lock_bh(&x25_list_lock);
+		x25_neigh_put(x25->neighbour);
+		x25->neighbour = NULL;
+		read_unlock_bh(&x25_list_lock);
+	}
 }
 
 /*
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index fa7bb5e060d0..3889bd9aec46 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -341,9 +341,9 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 {
 	bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
 	u32 chunk_size = mr->chunk_size, headroom = mr->headroom;
+	u64 npgs, addr = mr->addr, size = mr->len;
 	unsigned int chunks, chunks_per_page;
-	u64 addr = mr->addr, size = mr->len;
-	int size_chk, err;
+	int err;
 
 	if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) {
 		/* Strictly speaking we could support this, if:
@@ -372,6 +372,10 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if ((addr + size) < addr)
 		return -EINVAL;
 
+	npgs = div_u64(size, PAGE_SIZE);
+	if (npgs > U32_MAX)
+		return -EINVAL;
+
 	chunks = (unsigned int)div_u64(size, chunk_size);
 	if (chunks == 0)
 		return -EINVAL;
@@ -382,8 +386,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 			return -EINVAL;
 	}
 
-	size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM;
-	if (size_chk < 0)
+	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
 
 	umem->address = (unsigned long)addr;
@@ -392,7 +395,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->size = size;
 	umem->headroom = headroom;
 	umem->chunk_size_nohr = chunk_size - headroom;
-	umem->npgs = size / PAGE_SIZE;
+	umem->npgs = (u32)npgs;
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 356f90e4522b..c350108aa38d 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -131,8 +131,9 @@ static void __xsk_rcv_memcpy(struct xdp_umem *umem, u64 addr, void *from_buf,
 		u64 page_start = addr & ~(PAGE_SIZE - 1);
 		u64 first_len = PAGE_SIZE - (addr - page_start);
 
-		memcpy(to_buf, from_buf, first_len + metalen);
-		memcpy(next_pg_addr, from_buf + first_len, len - first_len);
+		memcpy(to_buf, from_buf, first_len);
+		memcpy(next_pg_addr, from_buf + first_len,
+		       len + metalen - first_len);
 
 		return;
 	}
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index 037ea156d2f9..5a0ff665b71a 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -379,6 +379,7 @@ static void espintcp_destruct(struct sock *sk)
 {
 	struct espintcp_ctx *ctx = espintcp_getctx(sk);
 
+	ctx->saved_destruct(sk);
 	kfree(ctx);
 }
 
@@ -419,6 +420,7 @@ static int espintcp_init_sk(struct sock *sk)
 	sk->sk_socket->ops = &espintcp_ops;
 	ctx->saved_data_ready = sk->sk_data_ready;
 	ctx->saved_write_space = sk->sk_write_space;
+	ctx->saved_destruct = sk->sk_destruct;
 	sk->sk_data_ready = espintcp_data_ready;
 	sk->sk_write_space = espintcp_write_space;
 	sk->sk_destruct = espintcp_destruct;
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 6cc7f7f1dd68..f50d1f97cf8e 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -25,12 +25,10 @@ static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb,
 	struct xfrm_offload *xo = xfrm_offload(skb);
 
 	skb_reset_mac_len(skb);
-	pskb_pull(skb, skb->mac_len + hsize + x->props.header_len);
-
-	if (xo->flags & XFRM_GSO_SEGMENT) {
-		skb_reset_transport_header(skb);
+	if (xo->flags & XFRM_GSO_SEGMENT)
 		skb->transport_header -= x->props.header_len;
-	}
+
+	pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len);
 }
 
 static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index aa35f23c4912..8a202c44f89a 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -644,7 +644,7 @@ resume:
 		dev_put(skb->dev);
 
 		spin_lock(&x->lock);
-		if (nexthdr <= 0) {
+		if (nexthdr < 0) {
 			if (nexthdr == -EBADMSG) {
 				xfrm_audit_state_icvfail(x, skb,
 							 x->type->proto);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 3361e3ac5714..1e115cbf21d3 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -750,7 +750,28 @@ static struct rtnl_link_ops xfrmi_link_ops __read_mostly = {
 	.get_link_net	= xfrmi_get_link_net,
 };
 
+static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list)
+{
+	struct net *net;
+	LIST_HEAD(list);
+
+	rtnl_lock();
+	list_for_each_entry(net, net_exit_list, exit_list) {
+		struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+		struct xfrm_if __rcu **xip;
+		struct xfrm_if *xi;
+
+		for (xip = &xfrmn->xfrmi[0];
+		     (xi = rtnl_dereference(*xip)) != NULL;
+		     xip = &xi->next)
+			unregister_netdevice_queue(xi->dev, &list);
+	}
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+}
+
 static struct pernet_operations xfrmi_net_ops = {
+	.exit_batch = xfrmi_exit_batch_net,
 	.id   = &xfrmi_net_id,
 	.size = sizeof(struct xfrmi_net),
 };
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 2fd3d990d992..69c4900db817 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -583,18 +583,20 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 		xfrm_state_hold(x);
 
 		if (skb_is_gso(skb)) {
-			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+			if (skb->inner_protocol)
+				return xfrm_output_gso(net, sk, skb);
 
-			return xfrm_output2(net, sk, skb);
+			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
+			goto out;
 		}
 
 		if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
 			goto out;
+	} else {
+		if (skb_is_gso(skb))
+			return xfrm_output_gso(net, sk, skb);
 	}
 
-	if (skb_is_gso(skb))
-		return xfrm_output_gso(net, sk, skb);
-
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		err = skb_checksum_help(skb);
 		if (err) {
@@ -640,7 +642,8 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 
 	if (skb->protocol == htons(ETH_P_IP))
 		proto = AF_INET;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+	else if (skb->protocol == htons(ETH_P_IPV6) &&
+		 skb->sk->sk_family == AF_INET6)
 		proto = AF_INET6;
 	else
 		return;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 297b2fdb3c29..564aa6492e7c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1436,12 +1436,7 @@ static void xfrm_policy_requeue(struct xfrm_policy *old,
 static bool xfrm_policy_mark_match(struct xfrm_policy *policy,
 				   struct xfrm_policy *pol)
 {
-	u32 mark = policy->mark.v & policy->mark.m;
-
-	if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m)
-		return true;
-
-	if ((mark & pol->mark.m) == pol->mark.v &&
+	if (policy->mark.v == pol->mark.v &&
 	    policy->priority == pol->priority)
 		return true;
 
diff --git a/samples/bpf/lwt_len_hist_user.c b/samples/bpf/lwt_len_hist_user.c
index 587b68b1f8dd..430a4b7e353e 100644
--- a/samples/bpf/lwt_len_hist_user.c
+++ b/samples/bpf/lwt_len_hist_user.c
@@ -15,8 +15,6 @@
 #define MAX_INDEX 64
 #define MAX_STARS 38
 
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
-
 static void stars(char *str, long val, long max, int width)
 {
 	int i;
diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c
index e04229d21475..c13a5bc5095b 100644
--- a/samples/ftrace/ftrace-direct-modify.c
+++ b/samples/ftrace/ftrace-direct-modify.c
@@ -20,18 +20,22 @@ static unsigned long my_ip = (unsigned long)schedule;
 
 asm (
 "	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
 "   my_tramp1:"
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
 "	call my_direct_func1\n"
 "	leave\n"
+"	.size		my_tramp1, .-my_tramp1\n"
 "	ret\n"
+"	.type		my_tramp2, @function\n"
 "   my_tramp2:"
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
 "	call my_direct_func2\n"
 "	leave\n"
 "	ret\n"
+"	.size		my_tramp2, .-my_tramp2\n"
 "	.popsection\n"
 );
 
diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c
index 27efa5f6ff52..d5c5022be664 100644
--- a/samples/ftrace/ftrace-direct-too.c
+++ b/samples/ftrace/ftrace-direct-too.c
@@ -15,6 +15,7 @@ extern void my_tramp(void *);
 
 asm (
 "	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
 "   my_tramp:"
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
@@ -27,6 +28,7 @@ asm (
 "	popq %rdi\n"
 "	leave\n"
 "	ret\n"
+"	.size		my_tramp, .-my_tramp\n"
 "	.popsection\n"
 );
 
diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c
index a2e3063bd306..63ca06d42c80 100644
--- a/samples/ftrace/ftrace-direct.c
+++ b/samples/ftrace/ftrace-direct.c
@@ -13,6 +13,7 @@ extern void my_tramp(void *);
 
 asm (
 "	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
 "   my_tramp:"
 "	pushq %rbp\n"
 "	movq %rsp, %rbp\n"
@@ -21,6 +22,7 @@ asm (
 "	popq %rdi\n"
 "	leave\n"
 "	ret\n"
+"	.size		my_tramp, .-my_tramp\n"
 "	.popsection\n"
 );
 
diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c
index d693c23a85e8..501911d1b327 100644
--- a/samples/kprobes/kprobe_example.c
+++ b/samples/kprobes/kprobe_example.c
@@ -25,7 +25,7 @@ static struct kprobe kp = {
 };
 
 /* kprobe pre_handler: called just before the probed instruction is executed */
-static int handler_pre(struct kprobe *p, struct pt_regs *regs)
+static int __kprobes handler_pre(struct kprobe *p, struct pt_regs *regs)
 {
 #ifdef CONFIG_X86
 	pr_info("<%s> pre_handler: p->addr = 0x%p, ip = %lx, flags = 0x%lx\n",
@@ -54,7 +54,7 @@ static int handler_pre(struct kprobe *p, struct pt_regs *regs)
 }
 
 /* kprobe post_handler: called after the probed instruction is executed */
-static void handler_post(struct kprobe *p, struct pt_regs *regs,
+static void __kprobes handler_post(struct kprobe *p, struct pt_regs *regs,
 				unsigned long flags)
 {
 #ifdef CONFIG_X86
@@ -90,6 +90,8 @@ static int handler_fault(struct kprobe *p, struct pt_regs *regs, int trapnr)
 	/* Return 0 because we don't handle the fault. */
 	return 0;
 }
+/* NOKPROBE_SYMBOL() is also available */
+NOKPROBE_SYMBOL(handler_fault);
 
 static int __init kprobe_init(void)
 {
diff --git a/samples/kprobes/kretprobe_example.c b/samples/kprobes/kretprobe_example.c
index 186315ca88b3..013e8e6ebae9 100644
--- a/samples/kprobes/kretprobe_example.c
+++ b/samples/kprobes/kretprobe_example.c
@@ -48,6 +48,7 @@ static int entry_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
 	data->entry_stamp = ktime_get();
 	return 0;
 }
+NOKPROBE_SYMBOL(entry_handler);
 
 /*
  * Return-probe handler: Log the return value and duration. Duration may turn
@@ -67,6 +68,7 @@ static int ret_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
 			func_name, retval, (long long)delta);
 	return 0;
 }
+NOKPROBE_SYMBOL(ret_handler);
 
 static struct kretprobe my_kretprobe = {
 	.handler		= ret_handler,
diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h
index 80b4a70315b6..13a35f7cbe66 100644
--- a/samples/trace_events/trace-events-sample.h
+++ b/samples/trace_events/trace-events-sample.h
@@ -416,7 +416,7 @@ TRACE_EVENT_FN(foo_bar_with_fn,
  * Note, TRACE_EVENT() itself is simply defined as:
  *
  * #define TRACE_EVENT(name, proto, args, tstruct, assign, printk)  \
- *  DEFINE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \
+ *  DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \
  *  DEFINE_EVENT(name, name, proto, args)
  *
  * The DEFINE_EVENT() also can be declared with conditions and reg functions:
diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c
index cc86bf6566e4..9894693f3be1 100644
--- a/samples/vfio-mdev/mdpy.c
+++ b/samples/vfio-mdev/mdpy.c
@@ -418,7 +418,7 @@ static int mdpy_mmap(struct mdev_device *mdev, struct vm_area_struct *vma)
 		return -EINVAL;
 
 	return remap_vmalloc_range_partial(vma, vma->vm_start,
-					   mdev_state->memblk,
+					   mdev_state->memblk, 0,
 					   vma->vm_end - vma->vm_start);
 }
 
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 97547108ee7f..4b799737722c 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -309,7 +309,7 @@ define rule_dtc
 endef
 
 $(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE
-	$(call if_changed_rule,dtc)
+	$(call if_changed_rule,dtc,yaml)
 
 dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp)
 
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index d64c67b67e3c..b83be177edf0 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -51,7 +51,7 @@ my %ignore_type = ();
 my @ignore = ();
 my $help = 0;
 my $configuration_file = ".checkpatch.conf";
-my $max_line_length = 80;
+my $max_line_length = 100;
 my $ignore_perl_version = 0;
 my $minimum_perl_version = 5.10.0;
 my $min_conf_desc_length = 4;
@@ -97,9 +97,11 @@ Options:
   --types TYPE(,TYPE2...)    show only these comma separated message types
   --ignore TYPE(,TYPE2...)   ignore various comma separated message types
   --show-types               show the specific message type in the output
-  --max-line-length=n        set the maximum line length, if exceeded, warn
+  --max-line-length=n        set the maximum line length, (default $max_line_length)
+                             if exceeded, warn on patches
+                             requires --strict for use with --file
   --min-conf-desc-length=n   set the min description length, if shorter, warn
-  --tab-size=n               set the number of spaces for tab (default 8)
+  --tab-size=n               set the number of spaces for tab (default $tabsize)
   --root=PATH                PATH to the kernel tree root
   --no-summary               suppress the per-file summary
   --mailback                 only produce a report in case of warnings/errors
@@ -479,7 +481,7 @@ our $allocFunctions = qr{(?x:
 		(?:kv|k|v)[czm]alloc(?:_node|_array)? |
 		kstrdup(?:_const)? |
 		kmemdup(?:_nul)?) |
-	(?:\w+)?alloc_skb(?:ip_align)? |
+	(?:\w+)?alloc_skb(?:_ip_align)? |
 				# dev_alloc_skb/netdev_alloc_skb, et al
 	dma_alloc_coherent
 )};
@@ -3240,8 +3242,10 @@ sub process {
 
 			if ($msg_type ne "" &&
 			    (show_type("LONG_LINE") || show_type($msg_type))) {
-				WARN($msg_type,
-				     "line over $max_line_length characters\n" . $herecurr);
+				my $msg_level = \&WARN;
+				$msg_level = \&CHK if ($file);
+				&{$msg_level}($msg_type,
+					      "line length of $length exceeds $max_line_length columns\n" . $herecurr);
 			}
 		}
 
diff --git a/scripts/config b/scripts/config
index e0e39826dae9..eee5b7f3a092 100755
--- a/scripts/config
+++ b/scripts/config
@@ -7,6 +7,9 @@ myname=${0##*/}
 # If no prefix forced, use the default CONFIG_
 CONFIG_="${CONFIG_-CONFIG_}"
 
+# We use an uncommon delimiter for sed substitutions
+SED_DELIM=$(echo -en "\001")
+
 usage() {
 	cat >&2 <<EOL
 Manipulate options in a .config file from the command line.
@@ -83,7 +86,7 @@ txt_subst() {
 	local infile="$3"
 	local tmpfile="$infile.swp"
 
-	sed -e "s:$before:$after:" "$infile" >"$tmpfile"
+	sed -e "s$SED_DELIM$before$SED_DELIM$after$SED_DELIM" "$infile" >"$tmpfile"
 	# replace original file with the edited one
 	mv "$tmpfile" "$infile"
 }
diff --git a/scripts/decodecode b/scripts/decodecode
index ba8b8d5834e6..fbdb325cdf4f 100755
--- a/scripts/decodecode
+++ b/scripts/decodecode
@@ -126,7 +126,7 @@ faultlinenum=$(( $(wc -l $T.oo  | cut -d" " -f1) - \
 faultline=`cat $T.dis | head -1 | cut -d":" -f2-`
 faultline=`echo "$faultline" | sed -e 's/\[/\\\[/g; s/\]/\\\]/g'`
 
-cat $T.oo | sed -e "${faultlinenum}s/^\(.*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/"
+cat $T.oo | sed -e "${faultlinenum}s/^\([^:]*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/"
 echo
 cat $T.aa
 cleanup
diff --git a/scripts/dtc/Makefile b/scripts/dtc/Makefile
index 2f3c3a7e1620..ef85f8b7d4a7 100644
--- a/scripts/dtc/Makefile
+++ b/scripts/dtc/Makefile
@@ -13,7 +13,7 @@ dtc-objs	+= dtc-lexer.lex.o dtc-parser.tab.o
 HOST_EXTRACFLAGS := -I $(srctree)/$(src)/libfdt
 
 ifeq ($(shell pkg-config --exists yaml-0.1 2>/dev/null && echo yes),)
-ifneq ($(CHECK_DTBS),)
+ifneq ($(CHECK_DT_BINDING)$(CHECK_DTBS),)
 $(error dtc needs libyaml for DT schema validation support. \
 	Install the necessary libyaml development package.)
 endif
diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile
index f22858b2c3d6..80f354289eeb 100644
--- a/scripts/gcc-plugins/Makefile
+++ b/scripts/gcc-plugins/Makefile
@@ -4,6 +4,7 @@ GCC_PLUGINS_DIR := $(shell $(CC) -print-file-name=plugin)
 HOST_EXTRACXXFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu++98 -fno-rtti
 HOST_EXTRACXXFLAGS += -fno-exceptions -fasynchronous-unwind-tables -ggdb
 HOST_EXTRACXXFLAGS += -Wno-narrowing -Wno-unused-variable -Wno-c++11-compat
+HOST_EXTRACXXFLAGS += -Wno-format-diag
 
 $(obj)/randomize_layout_plugin.o: $(objtree)/$(obj)/randomize_layout_seed.h
 quiet_cmd_create_randomize_layout_seed = GENSEED $@
diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h
index 17f06079a712..9ad76b7f3f10 100644
--- a/scripts/gcc-plugins/gcc-common.h
+++ b/scripts/gcc-plugins/gcc-common.h
@@ -35,7 +35,9 @@
 #include "ggc.h"
 #include "timevar.h"
 
+#if BUILDING_GCC_VERSION < 10000
 #include "params.h"
+#endif
 
 #if BUILDING_GCC_VERSION <= 4009
 #include "pointer-set.h"
@@ -847,6 +849,7 @@ static inline gimple gimple_build_assign_with_ops(enum tree_code subcode, tree l
 	return gimple_build_assign(lhs, subcode, op1, op2 PASS_MEM_STAT);
 }
 
+#if BUILDING_GCC_VERSION < 10000
 template <>
 template <>
 inline bool is_a_helper<const ggoto *>::test(const_gimple gs)
@@ -860,6 +863,7 @@ inline bool is_a_helper<const greturn *>::test(const_gimple gs)
 {
 	return gs->code == GIMPLE_RETURN;
 }
+#endif
 
 static inline gasm *as_a_gasm(gimple stmt)
 {
diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c
index dbd37460c573..cc75eeba0be1 100644
--- a/scripts/gcc-plugins/stackleak_plugin.c
+++ b/scripts/gcc-plugins/stackleak_plugin.c
@@ -51,7 +51,6 @@ static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after)
 	gimple stmt;
 	gcall *stackleak_track_stack;
 	cgraph_node_ptr node;
-	int frequency;
 	basic_block bb;
 
 	/* Insert call to void stackleak_track_stack(void) */
@@ -68,9 +67,9 @@ static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after)
 	bb = gimple_bb(stackleak_track_stack);
 	node = cgraph_get_create_node(track_function_decl);
 	gcc_assert(node);
-	frequency = compute_call_stmt_bb_frequency(current_function_decl, bb);
 	cgraph_create_edge(cgraph_get_node(current_function_decl), node,
-			stackleak_track_stack, bb->count, frequency);
+			stackleak_track_stack, bb->count,
+			compute_call_stmt_bb_frequency(current_function_decl, bb));
 }
 
 static bool is_alloca(gimple stmt)
diff --git a/scripts/gdb/linux/rbtree.py b/scripts/gdb/linux/rbtree.py
index 39db889b874c..c4b991607917 100644
--- a/scripts/gdb/linux/rbtree.py
+++ b/scripts/gdb/linux/rbtree.py
@@ -12,7 +12,7 @@ rb_node_type = utils.CachedType("struct rb_node")
 
 def rb_first(root):
     if root.type == rb_root_type.get_type():
-        node = node.address.cast(rb_root_type.get_type().pointer())
+        node = root.address.cast(rb_root_type.get_type().pointer())
     elif root.type != rb_root_type.get_type().pointer():
         raise gdb.GdbError("Must be struct rb_root not {}".format(root.type))
 
@@ -28,7 +28,7 @@ def rb_first(root):
 
 def rb_last(root):
     if root.type == rb_root_type.get_type():
-        node = node.address.cast(rb_root_type.get_type().pointer())
+        node = root.address.cast(rb_root_type.get_type().pointer())
     elif root.type != rb_root_type.get_type().pointer():
         raise gdb.GdbError("Must be struct rb_root not {}".format(root.type))
 
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 3e8dea6e0a95..6dc3078649fa 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -34,7 +34,7 @@ struct sym_entry {
 	unsigned int len;
 	unsigned int start_pos;
 	unsigned int percpu_absolute;
-	unsigned char sym[0];
+	unsigned char sym[];
 };
 
 struct addr_range {
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index d09ab4afbda4..3adef49250af 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -55,6 +55,29 @@ modpost_link()
 	${LD} ${KBUILD_LDFLAGS} -r -o ${1} ${objects}
 }
 
+objtool_link()
+{
+	local objtoolopt;
+
+	if [ -n "${CONFIG_VMLINUX_VALIDATION}" ]; then
+		objtoolopt="check"
+		if [ -z "${CONFIG_FRAME_POINTER}" ]; then
+			objtoolopt="${objtoolopt} --no-fp"
+		fi
+		if [ -n "${CONFIG_GCOV_KERNEL}" ]; then
+			objtoolopt="${objtoolopt} --no-unreachable"
+		fi
+		if [ -n "${CONFIG_RETPOLINE}" ]; then
+			objtoolopt="${objtoolopt} --retpoline"
+		fi
+		if [ -n "${CONFIG_X86_SMAP}" ]; then
+			objtoolopt="${objtoolopt} --uaccess"
+		fi
+		info OBJTOOL ${1}
+		tools/objtool/objtool ${objtoolopt} ${1}
+	fi
+}
+
 # Link of vmlinux
 # ${1} - output file
 # ${2}, ${3}, ... - optional extra .o files
@@ -251,6 +274,7 @@ ${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init need-builtin=1
 #link vmlinux.o
 info LD vmlinux.o
 modpost_link vmlinux.o
+objtool_link vmlinux.o
 
 # modpost vmlinux.o to check for section mismatches
 ${MAKE} -f "${srctree}/scripts/Makefile.modpost" MODPOST_VMLINUX=1
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 5c3c50c5ec52..0053d4fea847 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -948,7 +948,7 @@ static void check_section(const char *modname, struct elf_info *elf,
 
 #define DATA_SECTIONS ".data", ".data.rel"
 #define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \
-		".kprobes.text", ".cpuidle.text"
+		".kprobes.text", ".cpuidle.text", ".noinstr.text"
 #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \
 		".fixup", ".entry.text", ".exception.text", ".text.*", \
 		".coldtext"
diff --git a/security/Makefile b/security/Makefile
index 22e73a3482bd..3baf435de541 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -30,7 +30,7 @@ obj-$(CONFIG_SECURITY_YAMA)		+= yama/
 obj-$(CONFIG_SECURITY_LOADPIN)		+= loadpin/
 obj-$(CONFIG_SECURITY_SAFESETID)       += safesetid/
 obj-$(CONFIG_SECURITY_LOCKDOWN_LSM)	+= lockdown/
-obj-$(CONFIG_CGROUP_DEVICE)		+= device_cgroup.o
+obj-$(CONFIG_CGROUPS)			+= device_cgroup.o
 obj-$(CONFIG_BPF_LSM)			+= bpf/
 
 # Object integrity file lists
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 280741fc0f5f..f6a3ecfadf80 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -454,7 +454,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
 	 */
 	error = aa_may_manage_policy(label, ns, mask);
 	if (error)
-		return error;
+		goto end_section;
 
 	data = aa_simple_write_to_buffer(buf, size, size, pos);
 	error = PTR_ERR(data);
@@ -462,6 +462,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
 		error = aa_replace_profiles(ns, label, mask, data);
 		aa_put_loaddata(data);
 	}
+end_section:
 	end_current_label_crit_section(label);
 
 	return error;
diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c
index 5a98661a8b46..597732503815 100644
--- a/security/apparmor/audit.c
+++ b/security/apparmor/audit.c
@@ -197,8 +197,9 @@ int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule)
 	rule->label = aa_label_parse(&root_ns->unconfined->label, rulestr,
 				     GFP_KERNEL, true, false);
 	if (IS_ERR(rule->label)) {
+		int err = PTR_ERR(rule->label);
 		aa_audit_rule_free(rule);
-		return PTR_ERR(rule->label);
+		return err;
 	}
 
 	*vrule = rule;
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 6ceb74e0f789..a84ef030fbd7 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -1328,6 +1328,7 @@ int aa_change_profile(const char *fqname, int flags)
 		ctx->nnp = aa_get_label(label);
 
 	if (!fqname || !*fqname) {
+		aa_put_label(label);
 		AA_DEBUG("no profile name");
 		return -EINVAL;
 	}
@@ -1346,8 +1347,6 @@ int aa_change_profile(const char *fqname, int flags)
 			op = OP_CHANGE_PROFILE;
 	}
 
-	label = aa_get_current_label();
-
 	if (*fqname == '&') {
 		stack = true;
 		/* don't have label_parse() do stacking */
diff --git a/security/commoncap.c b/security/commoncap.c
index f4ee0ae106b2..0ca31c8bc0b1 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -812,6 +812,7 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 	int ret;
 	kuid_t root_uid;
 
+	new->cap_ambient = old->cap_ambient;
 	if (WARN_ON(!cap_ambient_invariant_ok(old)))
 		return -EPERM;
 
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 7d0f8f7431ff..43ab0ad45c1b 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -15,6 +15,8 @@
 #include <linux/rcupdate.h>
 #include <linux/mutex.h>
 
+#ifdef CONFIG_CGROUP_DEVICE
+
 static DEFINE_MUTEX(devcgroup_mutex);
 
 enum devcg_behavior {
@@ -792,7 +794,7 @@ struct cgroup_subsys devices_cgrp_subsys = {
 };
 
 /**
- * __devcgroup_check_permission - checks if an inode operation is permitted
+ * devcgroup_legacy_check_permission - checks if an inode operation is permitted
  * @dev_cgroup: the dev cgroup to be tested against
  * @type: device type
  * @major: device major number
@@ -801,7 +803,7 @@ struct cgroup_subsys devices_cgrp_subsys = {
  *
  * returns 0 on success, -EPERM case the operation is not permitted
  */
-static int __devcgroup_check_permission(short type, u32 major, u32 minor,
+static int devcgroup_legacy_check_permission(short type, u32 major, u32 minor,
 					short access)
 {
 	struct dev_cgroup *dev_cgroup;
@@ -825,6 +827,10 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor,
 	return 0;
 }
 
+#endif /* CONFIG_CGROUP_DEVICE */
+
+#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
+
 int devcgroup_check_permission(short type, u32 major, u32 minor, short access)
 {
 	int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
@@ -832,6 +838,13 @@ int devcgroup_check_permission(short type, u32 major, u32 minor, short access)
 	if (rc)
 		return -EPERM;
 
-	return __devcgroup_check_permission(type, major, minor, access);
+	#ifdef CONFIG_CGROUP_DEVICE
+	return devcgroup_legacy_check_permission(type, major, minor, access);
+
+	#else /* CONFIG_CGROUP_DEVICE */
+	return 0;
+
+	#endif /* CONFIG_CGROUP_DEVICE */
 }
 EXPORT_SYMBOL(devcgroup_check_permission);
+#endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index 35682852ddea..764b896cd628 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -73,7 +73,7 @@ static struct shash_desc *init_desc(char type, uint8_t hash_algo)
 {
 	long rc;
 	const char *algo;
-	struct crypto_shash **tfm;
+	struct crypto_shash **tfm, *tmp_tfm;
 	struct shash_desc *desc;
 
 	if (type == EVM_XATTR_HMAC) {
@@ -91,31 +91,31 @@ static struct shash_desc *init_desc(char type, uint8_t hash_algo)
 		algo = hash_algo_name[hash_algo];
 	}
 
-	if (*tfm == NULL) {
-		mutex_lock(&mutex);
-		if (*tfm)
-			goto out;
-		*tfm = crypto_alloc_shash(algo, 0, CRYPTO_NOLOAD);
-		if (IS_ERR(*tfm)) {
-			rc = PTR_ERR(*tfm);
-			pr_err("Can not allocate %s (reason: %ld)\n", algo, rc);
-			*tfm = NULL;
+	if (*tfm)
+		goto alloc;
+	mutex_lock(&mutex);
+	if (*tfm)
+		goto unlock;
+
+	tmp_tfm = crypto_alloc_shash(algo, 0, CRYPTO_NOLOAD);
+	if (IS_ERR(tmp_tfm)) {
+		pr_err("Can not allocate %s (reason: %ld)\n", algo,
+		       PTR_ERR(tmp_tfm));
+		mutex_unlock(&mutex);
+		return ERR_CAST(tmp_tfm);
+	}
+	if (type == EVM_XATTR_HMAC) {
+		rc = crypto_shash_setkey(tmp_tfm, evmkey, evmkey_len);
+		if (rc) {
+			crypto_free_shash(tmp_tfm);
 			mutex_unlock(&mutex);
 			return ERR_PTR(rc);
 		}
-		if (type == EVM_XATTR_HMAC) {
-			rc = crypto_shash_setkey(*tfm, evmkey, evmkey_len);
-			if (rc) {
-				crypto_free_shash(*tfm);
-				*tfm = NULL;
-				mutex_unlock(&mutex);
-				return ERR_PTR(rc);
-			}
-		}
-out:
-		mutex_unlock(&mutex);
 	}
-
+	*tfm = tmp_tfm;
+unlock:
+	mutex_unlock(&mutex);
+alloc:
 	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(*tfm),
 			GFP_KERNEL);
 	if (!desc)
@@ -207,7 +207,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
 	data->hdr.length = crypto_shash_digestsize(desc->tfm);
 
 	error = -ENODATA;
-	list_for_each_entry_rcu(xattr, &evm_config_xattrnames, list) {
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
 		bool is_ima = false;
 
 		if (strcmp(xattr->name, XATTR_NAME_IMA) == 0)
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index d361d7fdafc4..0d36259b690d 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -97,7 +97,7 @@ static int evm_find_protected_xattrs(struct dentry *dentry)
 	if (!(inode->i_opflags & IOP_XATTR))
 		return -EOPNOTSUPP;
 
-	list_for_each_entry_rcu(xattr, &evm_config_xattrnames, list) {
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
 		error = __vfs_getxattr(dentry, inode, xattr->name, NULL, 0);
 		if (error < 0) {
 			if (error == -ENODATA)
@@ -228,7 +228,7 @@ static int evm_protected_xattr(const char *req_xattr_name)
 	struct xattr_list *xattr;
 
 	namelen = strlen(req_xattr_name);
-	list_for_each_entry_rcu(xattr, &evm_config_xattrnames, list) {
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
 		if ((strlen(xattr->name) == namelen)
 		    && (strncmp(req_xattr_name, xattr->name, namelen) == 0)) {
 			found = 1;
diff --git a/security/integrity/evm/evm_secfs.c b/security/integrity/evm/evm_secfs.c
index 39ad1038d45d..cfc3075769bb 100644
--- a/security/integrity/evm/evm_secfs.c
+++ b/security/integrity/evm/evm_secfs.c
@@ -232,7 +232,14 @@ static ssize_t evm_write_xattrs(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	/* Guard against races in evm_read_xattrs */
+	/*
+	 * xattr_list_mutex guards against races in evm_read_xattrs().
+	 * Entries are only added to the evm_config_xattrnames list
+	 * and never deleted. Therefore, the list is traversed
+	 * using list_for_each_entry_lockless() without holding
+	 * the mutex in evm_calc_hmac_or_hash(), evm_find_protected_xattrs()
+	 * and evm_protected_xattr().
+	 */
 	mutex_lock(&xattr_list_mutex);
 	list_for_each_entry(tmp, &evm_config_xattrnames, list) {
 		if (strcmp(xattr->name, tmp->name) == 0) {
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 423c84f95a14..88b5e288f241 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -411,7 +411,7 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
 	loff_t i_size;
 	int rc;
 	struct file *f = file;
-	bool new_file_instance = false, modified_flags = false;
+	bool new_file_instance = false, modified_mode = false;
 
 	/*
 	 * For consistency, fail file's opened with the O_DIRECT flag on
@@ -431,13 +431,13 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
 		f = dentry_open(&file->f_path, flags, file->f_cred);
 		if (IS_ERR(f)) {
 			/*
-			 * Cannot open the file again, lets modify f_flags
+			 * Cannot open the file again, lets modify f_mode
 			 * of original and continue
 			 */
 			pr_info_ratelimited("Unable to reopen file for reading.\n");
 			f = file;
-			f->f_flags |= FMODE_READ;
-			modified_flags = true;
+			f->f_mode |= FMODE_READ;
+			modified_mode = true;
 		} else {
 			new_file_instance = true;
 		}
@@ -455,8 +455,8 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
 out:
 	if (new_file_instance)
 		fput(f);
-	else if (modified_flags)
-		f->f_flags &= ~FMODE_READ;
+	else if (modified_mode)
+		f->f_mode &= ~FMODE_READ;
 	return rc;
 }
 
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index a71e822a6e92..3efc8308ad26 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -338,8 +338,7 @@ static ssize_t ima_write_policy(struct file *file, const char __user *buf,
 		integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL, NULL,
 				    "policy_update", "signed policy required",
 				    1, 0);
-		if (ima_appraise & IMA_APPRAISE_ENFORCE)
-			result = -EACCES;
+		result = -EACCES;
 	} else {
 		result = ima_parse_add_rule(data);
 	}
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index f6797ba44bf7..14cf81d1a30b 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -323,19 +323,6 @@ error:
 	return ukey;
 }
 
-static int calc_hash(struct crypto_shash *tfm, u8 *digest,
-		     const u8 *buf, unsigned int buflen)
-{
-	SHASH_DESC_ON_STACK(desc, tfm);
-	int err;
-
-	desc->tfm = tfm;
-
-	err = crypto_shash_digest(desc, buf, buflen, digest);
-	shash_desc_zero(desc);
-	return err;
-}
-
 static int calc_hmac(u8 *digest, const u8 *key, unsigned int keylen,
 		     const u8 *buf, unsigned int buflen)
 {
@@ -351,7 +338,7 @@ static int calc_hmac(u8 *digest, const u8 *key, unsigned int keylen,
 
 	err = crypto_shash_setkey(tfm, key, keylen);
 	if (!err)
-		err = calc_hash(tfm, digest, buf, buflen);
+		err = crypto_shash_tfm_digest(tfm, buf, buflen, digest);
 	crypto_free_shash(tfm);
 	return err;
 }
@@ -381,7 +368,8 @@ static int get_derived_key(u8 *derived_key, enum derived_key_type key_type,
 
 	memcpy(derived_buf + strlen(derived_buf) + 1, master_key,
 	       master_keylen);
-	ret = calc_hash(hash_tfm, derived_key, derived_buf, derived_buf_len);
+	ret = crypto_shash_tfm_digest(hash_tfm, derived_buf, derived_buf_len,
+				      derived_key);
 	kzfree(derived_buf);
 	return ret;
 }
diff --git a/security/keys/proc.c b/security/keys/proc.c
index 415f3f1c2da0..d0cde6685627 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -139,6 +139,8 @@ static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos)
 	n = key_serial_next(p, v);
 	if (n)
 		*_pos = key_node_serial(n);
+	else
+		(*_pos)++;
 	return n;
 }
 
diff --git a/security/security.c b/security/security.c
index 7fed24b9d57e..51de970fbb1e 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1965,8 +1965,20 @@ EXPORT_SYMBOL(security_ismaclabel);
 
 int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
 {
-	return call_int_hook(secid_to_secctx, -EOPNOTSUPP, secid, secdata,
-				seclen);
+	struct security_hook_list *hp;
+	int rc;
+
+	/*
+	 * Currently, only one LSM can implement secid_to_secctx (i.e this
+	 * LSM hook is not "stackable").
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.secid_to_secctx, list) {
+		rc = hp->hook.secid_to_secctx(secid, secdata, seclen);
+		if (rc != LSM_RET_DEFAULT(secid_to_secctx))
+			return rc;
+	}
+
+	return LSM_RET_DEFAULT(secid_to_secctx);
 }
 EXPORT_SYMBOL(security_secid_to_secctx);
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 0b4e32161b77..4c037c2545c1 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5842,40 +5842,60 @@ static unsigned int selinux_ipv6_postroute(void *priv,
 
 static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
-	int err = 0;
-	u32 perm;
+	int rc = 0;
+	unsigned int msg_len;
+	unsigned int data_len = skb->len;
+	unsigned char *data = skb->data;
 	struct nlmsghdr *nlh;
 	struct sk_security_struct *sksec = sk->sk_security;
+	u16 sclass = sksec->sclass;
+	u32 perm;
 
-	if (skb->len < NLMSG_HDRLEN) {
-		err = -EINVAL;
-		goto out;
-	}
-	nlh = nlmsg_hdr(skb);
+	while (data_len >= nlmsg_total_size(0)) {
+		nlh = (struct nlmsghdr *)data;
+
+		/* NOTE: the nlmsg_len field isn't reliably set by some netlink
+		 *       users which means we can't reject skb's with bogus
+		 *       length fields; our solution is to follow what
+		 *       netlink_rcv_skb() does and simply skip processing at
+		 *       messages with length fields that are clearly junk
+		 */
+		if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len)
+			return 0;
 
-	err = selinux_nlmsg_lookup(sksec->sclass, nlh->nlmsg_type, &perm);
-	if (err) {
-		if (err == -EINVAL) {
+		rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm);
+		if (rc == 0) {
+			rc = sock_has_perm(sk, perm);
+			if (rc)
+				return rc;
+		} else if (rc == -EINVAL) {
+			/* -EINVAL is a missing msg/perm mapping */
 			pr_warn_ratelimited("SELinux: unrecognized netlink"
-			       " message: protocol=%hu nlmsg_type=%hu sclass=%s"
-			       " pid=%d comm=%s\n",
-			       sk->sk_protocol, nlh->nlmsg_type,
-			       secclass_map[sksec->sclass - 1].name,
-			       task_pid_nr(current), current->comm);
-			if (!enforcing_enabled(&selinux_state) ||
-			    security_get_allow_unknown(&selinux_state))
-				err = 0;
+				" message: protocol=%hu nlmsg_type=%hu sclass=%s"
+				" pid=%d comm=%s\n",
+				sk->sk_protocol, nlh->nlmsg_type,
+				secclass_map[sclass - 1].name,
+				task_pid_nr(current), current->comm);
+			if (enforcing_enabled(&selinux_state) &&
+			    !security_get_allow_unknown(&selinux_state))
+				return rc;
+			rc = 0;
+		} else if (rc == -ENOENT) {
+			/* -ENOENT is a missing socket/class mapping, ignore */
+			rc = 0;
+		} else {
+			return rc;
 		}
 
-		/* Ignore */
-		if (err == -ENOENT)
-			err = 0;
-		goto out;
+		/* move to the next message after applying netlink padding */
+		msg_len = NLMSG_ALIGN(nlh->nlmsg_len);
+		if (msg_len >= data_len)
+			return 0;
+		data_len -= msg_len;
+		data += msg_len;
 	}
 
-	err = sock_has_perm(sk, perm);
-out:
-	return err;
+	return rc;
 }
 
 static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass)
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index 986f3ac14282..d233ab3f1533 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -27,9 +27,9 @@
 	    "audit_control", "setfcap"
 
 #define COMMON_CAP2_PERMS  "mac_override", "mac_admin", "syslog", \
-		"wake_alarm", "block_suspend", "audit_read"
+		"wake_alarm", "block_suspend", "audit_read", "perfmon"
 
-#if CAP_LAST_CAP > CAP_AUDIT_READ
+#if CAP_LAST_CAP > CAP_PERFMON
 #error New capability defined, please update COMMON_CAP2_PERMS.
 #endif
 
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index 939a74fd8fb4..da94a1b4bfda 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -429,7 +429,7 @@ int cond_read_list(struct policydb *p, void *fp)
 
 	p->cond_list = kcalloc(len, sizeof(*p->cond_list), GFP_KERNEL);
 	if (!p->cond_list)
-		return rc;
+		return -ENOMEM;
 
 	rc = avtab_alloc(&(p->te_cond_avtab), p->te_avtab.nel);
 	if (rc)
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 70ecdc78efbd..c21b922e5ebe 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -1035,14 +1035,14 @@ static int str_read(char **strp, gfp_t flags, void *fp, u32 len)
 	if (!str)
 		return -ENOMEM;
 
-	/* it's expected the caller should free the str */
-	*strp = str;
-
 	rc = next_entry(str, fp, len);
-	if (rc)
+	if (rc) {
+		kfree(str);
 		return rc;
+	}
 
 	str[len] = '\0';
+	*strp = str;
 	return 0;
 }
 
diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c
index b412d3b3d5ff..21edb8ac95eb 100644
--- a/sound/core/hwdep.c
+++ b/sound/core/hwdep.c
@@ -216,12 +216,12 @@ static int snd_hwdep_dsp_load(struct snd_hwdep *hw,
 	if (info.index >= 32)
 		return -EINVAL;
 	/* check whether the dsp was already loaded */
-	if (hw->dsp_loaded & (1 << info.index))
+	if (hw->dsp_loaded & (1u << info.index))
 		return -EBUSY;
 	err = hw->ops.dsp_load(hw, &info);
 	if (err < 0)
 		return err;
-	hw->dsp_loaded |= (1 << info.index);
+	hw->dsp_loaded |= (1u << info.index);
 	return 0;
 }
 
diff --git a/sound/core/oss/pcm_plugin.c b/sound/core/oss/pcm_plugin.c
index 59d62f05658f..1545f8fdb4db 100644
--- a/sound/core/oss/pcm_plugin.c
+++ b/sound/core/oss/pcm_plugin.c
@@ -205,13 +205,14 @@ static snd_pcm_sframes_t calc_dst_frames(struct snd_pcm_substream *plug,
 	plugin = snd_pcm_plug_first(plug);
 	while (plugin && frames > 0) {
 		plugin_next = plugin->next;
+		if (check_size && plugin->buf_frames &&
+		    frames > plugin->buf_frames)
+			frames = plugin->buf_frames;
 		if (plugin->dst_frames) {
 			frames = plugin->dst_frames(plugin, frames);
 			if (frames < 0)
 				return frames;
 		}
-		if (check_size && frames > plugin->buf_frames)
-			frames = plugin->buf_frames;
 		plugin = plugin_next;
 	}
 	return frames;
@@ -225,14 +226,15 @@ static snd_pcm_sframes_t calc_src_frames(struct snd_pcm_substream *plug,
 
 	plugin = snd_pcm_plug_last(plug);
 	while (plugin && frames > 0) {
-		if (check_size && frames > plugin->buf_frames)
-			frames = plugin->buf_frames;
 		plugin_prev = plugin->prev;
 		if (plugin->src_frames) {
 			frames = plugin->src_frames(plugin, frames);
 			if (frames < 0)
 				return frames;
 		}
+		if (check_size && plugin->buf_frames &&
+		    frames > plugin->buf_frames)
+			frames = plugin->buf_frames;
 		plugin = plugin_prev;
 	}
 	return frames;
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 872a852de75c..d531e1bc2b81 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -433,6 +433,7 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 
  no_delta_check:
 	if (runtime->status->hw_ptr == new_hw_ptr) {
+		runtime->hw_ptr_jiffies = curr_jiffies;
 		update_audio_tstamp(substream, &curr_tstamp, &audio_tstamp);
 		return 0;
 	}
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 20dd08e1f675..2a688b711a9a 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -120,6 +120,17 @@ static void snd_rawmidi_input_event_work(struct work_struct *work)
 		runtime->event(runtime->substream);
 }
 
+/* buffer refcount management: call with runtime->lock held */
+static inline void snd_rawmidi_buffer_ref(struct snd_rawmidi_runtime *runtime)
+{
+	runtime->buffer_ref++;
+}
+
+static inline void snd_rawmidi_buffer_unref(struct snd_rawmidi_runtime *runtime)
+{
+	runtime->buffer_ref--;
+}
+
 static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream)
 {
 	struct snd_rawmidi_runtime *runtime;
@@ -669,6 +680,11 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime,
 		if (!newbuf)
 			return -ENOMEM;
 		spin_lock_irq(&runtime->lock);
+		if (runtime->buffer_ref) {
+			spin_unlock_irq(&runtime->lock);
+			kvfree(newbuf);
+			return -EBUSY;
+		}
 		oldbuf = runtime->buffer;
 		runtime->buffer = newbuf;
 		runtime->buffer_size = params->buffer_size;
@@ -1019,8 +1035,10 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream,
 	long result = 0, count1;
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 	unsigned long appl_ptr;
+	int err = 0;
 
 	spin_lock_irqsave(&runtime->lock, flags);
+	snd_rawmidi_buffer_ref(runtime);
 	while (count > 0 && runtime->avail) {
 		count1 = runtime->buffer_size - runtime->appl_ptr;
 		if (count1 > count)
@@ -1039,16 +1057,19 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream,
 		if (userbuf) {
 			spin_unlock_irqrestore(&runtime->lock, flags);
 			if (copy_to_user(userbuf + result,
-					 runtime->buffer + appl_ptr, count1)) {
-				return result > 0 ? result : -EFAULT;
-			}
+					 runtime->buffer + appl_ptr, count1))
+				err = -EFAULT;
 			spin_lock_irqsave(&runtime->lock, flags);
+			if (err)
+				goto out;
 		}
 		result += count1;
 		count -= count1;
 	}
+ out:
+	snd_rawmidi_buffer_unref(runtime);
 	spin_unlock_irqrestore(&runtime->lock, flags);
-	return result;
+	return result > 0 ? result : err;
 }
 
 long snd_rawmidi_kernel_read(struct snd_rawmidi_substream *substream,
@@ -1342,6 +1363,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream,
 			return -EAGAIN;
 		}
 	}
+	snd_rawmidi_buffer_ref(runtime);
 	while (count > 0 && runtime->avail > 0) {
 		count1 = runtime->buffer_size - runtime->appl_ptr;
 		if (count1 > count)
@@ -1373,6 +1395,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream,
 	}
       __end:
 	count1 = runtime->avail < runtime->buffer_size;
+	snd_rawmidi_buffer_unref(runtime);
 	spin_unlock_irqrestore(&runtime->lock, flags);
 	if (count1)
 		snd_rawmidi_output_trigger(substream, 1);
diff --git a/sound/firewire/amdtp-stream-trace.h b/sound/firewire/amdtp-stream-trace.h
index 16c7f6605511..26e7cb555d3c 100644
--- a/sound/firewire/amdtp-stream-trace.h
+++ b/sound/firewire/amdtp-stream-trace.h
@@ -66,8 +66,7 @@ TRACE_EVENT(amdtp_packet,
 		__entry->irq,
 		__entry->index,
 		__print_array(__get_dynamic_array(cip_header),
-			      __get_dynamic_array_len(cip_header),
-			      sizeof(u8)))
+			      __get_dynamic_array_len(cip_header), 1))
 );
 
 #endif
diff --git a/sound/hda/Kconfig b/sound/hda/Kconfig
index 4ca6b09056f3..3bc9224d5e4f 100644
--- a/sound/hda/Kconfig
+++ b/sound/hda/Kconfig
@@ -21,16 +21,17 @@ config SND_HDA_EXT_CORE
        select SND_HDA_CORE
 
 config SND_HDA_PREALLOC_SIZE
-	int "Pre-allocated buffer size for HD-audio driver" if !SND_DMA_SGBUF
+	int "Pre-allocated buffer size for HD-audio driver"
 	range 0 32768
-	default 0 if SND_DMA_SGBUF
+	default 2048 if SND_DMA_SGBUF
 	default 64 if !SND_DMA_SGBUF
 	help
 	  Specifies the default pre-allocated buffer-size in kB for the
 	  HD-audio driver.  A larger buffer (e.g. 2048) is preferred
 	  for systems using PulseAudio.  The default 64 is chosen just
 	  for compatibility reasons.
-	  On x86 systems, the default is zero as we need no preallocation.
+	  On x86 systems, the default is 2048 as a reasonable value for
+	  most of modern systems.
 
 	  Note that the pre-allocation size can be changed dynamically
 	  via a proc file (/proc/asound/card*/pcm*/sub*/prealloc), too.
diff --git a/sound/isa/opti9xx/miro.c b/sound/isa/opti9xx/miro.c
index e764816a8f7a..b039429e6871 100644
--- a/sound/isa/opti9xx/miro.c
+++ b/sound/isa/opti9xx/miro.c
@@ -867,10 +867,13 @@ static void snd_miro_write(struct snd_miro *chip, unsigned char reg,
 	spin_unlock_irqrestore(&chip->lock, flags);
 }
 
+static inline void snd_miro_write_mask(struct snd_miro *chip,
+		unsigned char reg, unsigned char value, unsigned char mask)
+{
+	unsigned char oldval = snd_miro_read(chip, reg);
 
-#define snd_miro_write_mask(chip, reg, value, mask)	\
-	snd_miro_write(chip, reg,			\
-		(snd_miro_read(chip, reg) & ~(mask)) | ((value) & (mask)))
+	snd_miro_write(chip, reg, (oldval & ~mask) | (value & mask));
+}
 
 /*
  *  Proc Interface
diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c
index d06b29693c85..0e6d20e49158 100644
--- a/sound/isa/opti9xx/opti92x-ad1848.c
+++ b/sound/isa/opti9xx/opti92x-ad1848.c
@@ -317,10 +317,13 @@ static void snd_opti9xx_write(struct snd_opti9xx *chip, unsigned char reg,
 }
 
 
-#define snd_opti9xx_write_mask(chip, reg, value, mask)	\
-	snd_opti9xx_write(chip, reg,			\
-		(snd_opti9xx_read(chip, reg) & ~(mask)) | ((value) & (mask)))
+static inline void snd_opti9xx_write_mask(struct snd_opti9xx *chip,
+		unsigned char reg, unsigned char value, unsigned char mask)
+{
+	unsigned char oldval = snd_opti9xx_read(chip, reg);
 
+	snd_opti9xx_write(chip, reg, (oldval & ~mask) | (value & mask));
+}
 
 static int snd_opti9xx_configure(struct snd_opti9xx *chip,
 					   long port,
diff --git a/sound/pci/ctxfi/cthw20k1.c b/sound/pci/ctxfi/cthw20k1.c
index 6e3177bcc709..015c0d676897 100644
--- a/sound/pci/ctxfi/cthw20k1.c
+++ b/sound/pci/ctxfi/cthw20k1.c
@@ -168,7 +168,7 @@ static int src_get_rsc_ctrl_blk(void **rblk)
 
 static int src_put_rsc_ctrl_blk(void *blk)
 {
-	kfree((struct src_rsc_ctrl_blk *)blk);
+	kfree(blk);
 
 	return 0;
 }
@@ -494,7 +494,7 @@ static int src_mgr_get_ctrl_blk(void **rblk)
 
 static int src_mgr_put_ctrl_blk(void *blk)
 {
-	kfree((struct src_mgr_ctrl_blk *)blk);
+	kfree(blk);
 
 	return 0;
 }
@@ -515,7 +515,7 @@ static int srcimp_mgr_get_ctrl_blk(void **rblk)
 
 static int srcimp_mgr_put_ctrl_blk(void *blk)
 {
-	kfree((struct srcimp_mgr_ctrl_blk *)blk);
+	kfree(blk);
 
 	return 0;
 }
@@ -702,7 +702,7 @@ static int amixer_rsc_get_ctrl_blk(void **rblk)
 
 static int amixer_rsc_put_ctrl_blk(void *blk)
 {
-	kfree((struct amixer_rsc_ctrl_blk *)blk);
+	kfree(blk);
 
 	return 0;
 }
@@ -909,7 +909,7 @@ static int dai_get_ctrl_blk(void **rblk)
 
 static int dai_put_ctrl_blk(void *blk)
 {
-	kfree((struct dai_ctrl_blk *)blk);
+	kfree(blk);
 
 	return 0;
 }
@@ -958,7 +958,7 @@ static int dao_get_ctrl_blk(void **rblk)
 
 static int dao_put_ctrl_blk(void *blk)
 {
-	kfree((struct dao_ctrl_blk *)blk);
+	kfree(blk);
 
 	return 0;
 }
@@ -1156,7 +1156,7 @@ static int daio_mgr_get_ctrl_blk(struct hw *hw, void **rblk)
 
 static int daio_mgr_put_ctrl_blk(void *blk)
 {
-	kfree((struct daio_mgr_ctrl_blk *)blk);
+	kfree(blk);
 
 	return 0;
 }
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index a34a2c9f4bcf..7e3ae4534df9 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -641,8 +641,18 @@ static void hda_jackpoll_work(struct work_struct *work)
 	struct hda_codec *codec =
 		container_of(work, struct hda_codec, jackpoll_work.work);
 
-	snd_hda_jack_set_dirty_all(codec);
-	snd_hda_jack_poll_all(codec);
+	/* for non-polling trigger: we need nothing if already powered on */
+	if (!codec->jackpoll_interval && snd_hdac_is_power_on(&codec->core))
+		return;
+
+	/* the power-up/down sequence triggers the runtime resume */
+	snd_hda_power_up_pm(codec);
+	/* update jacks manually if polling is required, too */
+	if (codec->jackpoll_interval) {
+		snd_hda_jack_set_dirty_all(codec);
+		snd_hda_jack_poll_all(codec);
+	}
+	snd_hda_power_down_pm(codec);
 
 	if (!codec->jackpoll_interval)
 		return;
@@ -2951,18 +2961,14 @@ static int hda_codec_runtime_resume(struct device *dev)
 static int hda_codec_force_resume(struct device *dev)
 {
 	struct hda_codec *codec = dev_to_hda_codec(dev);
-	bool forced_resume = !codec->relaxed_resume && codec->jacktbl.used;
 	int ret;
 
-	/* The get/put pair below enforces the runtime resume even if the
-	 * device hasn't been used at suspend time.  This trick is needed to
-	 * update the jack state change during the sleep.
-	 */
-	if (forced_resume)
-		pm_runtime_get_noresume(dev);
 	ret = pm_runtime_force_resume(dev);
-	if (forced_resume)
-		pm_runtime_put(dev);
+	/* schedule jackpoll work for jack detection update */
+	if (codec->jackpoll_interval ||
+	    (pm_runtime_suspended(dev) && hda_codec_need_resume(codec)))
+		schedule_delayed_work(&codec->jackpoll_work,
+				      codec->jackpoll_interval);
 	return ret;
 }
 
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index bd093593f8fb..0310193ea1bd 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1004,7 +1004,8 @@ static void __azx_runtime_resume(struct azx *chip, bool from_rt)
 
 	if (status && from_rt) {
 		list_for_each_codec(codec, &chip->bus)
-			if (status & (1 << codec->addr))
+			if (!codec->relaxed_resume &&
+			    (status & (1 << codec->addr)))
 				schedule_delayed_work(&codec->jackpoll_work,
 						      codec->jackpoll_interval);
 	}
@@ -1027,7 +1028,7 @@ static int azx_suspend(struct device *dev)
 	chip = card->private_data;
 	bus = azx_bus(chip);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
-	__azx_runtime_suspend(chip);
+	pm_runtime_force_suspend(dev);
 	if (bus->irq >= 0) {
 		free_irq(bus->irq, chip);
 		bus->irq = -1;
@@ -1055,7 +1056,8 @@ static int azx_resume(struct device *dev)
 			chip->msi = 0;
 	if (azx_acquire_irq(chip, 1) < 0)
 		return -EIO;
-	__azx_runtime_resume(chip, false);
+
+	pm_runtime_force_resume(dev);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 
 	trace_azx_resume(chip);
@@ -1071,6 +1073,8 @@ static int azx_freeze_noirq(struct device *dev)
 	struct azx *chip = card->private_data;
 	struct pci_dev *pci = to_pci_dev(dev);
 
+	if (!azx_is_pm_ready(card))
+		return 0;
 	if (chip->driver_type == AZX_DRIVER_SKL)
 		pci_set_power_state(pci, PCI_D3hot);
 
@@ -1083,6 +1087,8 @@ static int azx_thaw_noirq(struct device *dev)
 	struct azx *chip = card->private_data;
 	struct pci_dev *pci = to_pci_dev(dev);
 
+	if (!azx_is_pm_ready(card))
+		return 0;
 	if (chip->driver_type == AZX_DRIVER_SKL)
 		pci_set_power_state(pci, PCI_D0);
 
@@ -1098,12 +1104,12 @@ static int azx_runtime_suspend(struct device *dev)
 	if (!azx_is_pm_ready(card))
 		return 0;
 	chip = card->private_data;
-	if (!azx_has_pm_runtime(chip))
-		return 0;
 
 	/* enable controller wake up event */
-	azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) |
-		  STATESTS_INT_MASK);
+	if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0) {
+		azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) |
+			   STATESTS_INT_MASK);
+	}
 
 	__azx_runtime_suspend(chip);
 	trace_azx_runtime_suspend(chip);
@@ -1114,17 +1120,18 @@ static int azx_runtime_resume(struct device *dev)
 {
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip;
+	bool from_rt = snd_power_get_state(card) == SNDRV_CTL_POWER_D0;
 
 	if (!azx_is_pm_ready(card))
 		return 0;
 	chip = card->private_data;
-	if (!azx_has_pm_runtime(chip))
-		return 0;
-	__azx_runtime_resume(chip, true);
+	__azx_runtime_resume(chip, from_rt);
 
 	/* disable controller Wake Up event*/
-	azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
-			~STATESTS_INT_MASK);
+	if (from_rt) {
+		azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
+			   ~STATESTS_INT_MASK);
+	}
 
 	trace_azx_runtime_resume(chip);
 	return 0;
@@ -1199,10 +1206,8 @@ static void azx_vs_set_state(struct pci_dev *pci,
 		if (!disabled) {
 			dev_info(chip->card->dev,
 				 "Start delayed initialization\n");
-			if (azx_probe_continue(chip) < 0) {
+			if (azx_probe_continue(chip) < 0)
 				dev_err(chip->card->dev, "initialization error\n");
-				hda->init_failed = true;
-			}
 		}
 	} else {
 		dev_info(chip->card->dev, "%s via vga_switcheroo\n",
@@ -1335,12 +1340,15 @@ static int register_vga_switcheroo(struct azx *chip)
 /*
  * destructor
  */
-static int azx_free(struct azx *chip)
+static void azx_free(struct azx *chip)
 {
 	struct pci_dev *pci = chip->pci;
 	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
 	struct hdac_bus *bus = azx_bus(chip);
 
+	if (hda->freed)
+		return;
+
 	if (azx_has_pm_runtime(chip) && chip->running)
 		pm_runtime_get_noresume(&pci->dev);
 	chip->running = 0;
@@ -1384,9 +1392,8 @@ static int azx_free(struct azx *chip)
 
 	if (chip->driver_caps & AZX_DCAPS_I915_COMPONENT)
 		snd_hdac_i915_exit(bus);
-	kfree(hda);
 
-	return 0;
+	hda->freed = 1;
 }
 
 static int azx_dev_disconnect(struct snd_device *device)
@@ -1402,7 +1409,8 @@ static int azx_dev_disconnect(struct snd_device *device)
 
 static int azx_dev_free(struct snd_device *device)
 {
-	return azx_free(device->device_data);
+	azx_free(device->device_data);
+	return 0;
 }
 
 #ifdef SUPPORT_VGA_SWITCHEROO
@@ -1769,7 +1777,7 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 	if (err < 0)
 		return err;
 
-	hda = kzalloc(sizeof(*hda), GFP_KERNEL);
+	hda = devm_kzalloc(&pci->dev, sizeof(*hda), GFP_KERNEL);
 	if (!hda) {
 		pci_disable_device(pci);
 		return -ENOMEM;
@@ -1810,7 +1818,6 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 
 	err = azx_bus_init(chip, model[dev]);
 	if (err < 0) {
-		kfree(hda);
 		pci_disable_device(pci);
 		return err;
 	}
@@ -2005,7 +2012,7 @@ static int azx_first_init(struct azx *chip)
 	/* codec detection */
 	if (!azx_bus(chip)->codec_mask) {
 		dev_err(card->dev, "no codecs found!\n");
-		return -ENODEV;
+		/* keep running the rest for the runtime PM */
 	}
 
 	if (azx_acquire_irq(chip, 0) < 0)
@@ -2027,24 +2034,15 @@ static void azx_firmware_cb(const struct firmware *fw, void *context)
 {
 	struct snd_card *card = context;
 	struct azx *chip = card->private_data;
-	struct pci_dev *pci = chip->pci;
-
-	if (!fw) {
-		dev_err(card->dev, "Cannot load firmware, aborting\n");
-		goto error;
-	}
 
-	chip->fw = fw;
+	if (fw)
+		chip->fw = fw;
+	else
+		dev_err(card->dev, "Cannot load firmware, continue without patching\n");
 	if (!chip->disabled) {
 		/* continue probing */
-		if (azx_probe_continue(chip))
-			goto error;
+		azx_probe_continue(chip);
 	}
-	return; /* OK */
-
- error:
-	snd_card_free(card);
-	pci_set_drvdata(pci, NULL);
 }
 #endif
 
@@ -2080,10 +2078,10 @@ static void pcm_mmap_prepare(struct snd_pcm_substream *substream,
  * some HD-audio PCI entries are exposed without any codecs, and such devices
  * should be ignored from the beginning.
  */
-static const struct snd_pci_quirk driver_blacklist[] = {
-	SND_PCI_QUIRK(0x1043, 0x874f, "ASUS ROG Zenith II / Strix", 0),
-	SND_PCI_QUIRK(0x1462, 0xcb59, "MSI TRX40 Creator", 0),
-	SND_PCI_QUIRK(0x1462, 0xcb60, "MSI TRX40", 0),
+static const struct pci_device_id driver_blacklist[] = {
+	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1043, 0x874f) }, /* ASUS ROG Zenith II / Strix */
+	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb59) }, /* MSI TRX40 Creator */
+	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb60) }, /* MSI TRX40 */
 	{}
 };
 
@@ -2103,7 +2101,7 @@ static int azx_probe(struct pci_dev *pci,
 	bool schedule_probe;
 	int err;
 
-	if (snd_pci_quirk_lookup(pci, driver_blacklist)) {
+	if (pci_match_id(driver_blacklist, pci)) {
 		dev_info(&pci->dev, "Skipping the blacklisted device\n");
 		return -ENODEV;
 	}
@@ -2308,9 +2306,11 @@ static int azx_probe_continue(struct azx *chip)
 #endif
 
 	/* create codec instances */
-	err = azx_probe_codecs(chip, azx_max_codecs[chip->driver_type]);
-	if (err < 0)
-		goto out_free;
+	if (bus->codec_mask) {
+		err = azx_probe_codecs(chip, azx_max_codecs[chip->driver_type]);
+		if (err < 0)
+			goto out_free;
+	}
 
 #ifdef CONFIG_SND_HDA_PATCH_LOADER
 	if (chip->fw) {
@@ -2324,7 +2324,7 @@ static int azx_probe_continue(struct azx *chip)
 #endif
 	}
 #endif
-	if ((probe_only[dev] & 1) == 0) {
+	if (bus->codec_mask && !(probe_only[dev] & 1)) {
 		err = azx_codec_configure(chip);
 		if (err < 0)
 			goto out_free;
@@ -2341,17 +2341,23 @@ static int azx_probe_continue(struct azx *chip)
 
 	set_default_power_save(chip);
 
-	if (azx_has_pm_runtime(chip))
+	if (azx_has_pm_runtime(chip)) {
+		pm_runtime_use_autosuspend(&pci->dev);
+		pm_runtime_allow(&pci->dev);
 		pm_runtime_put_autosuspend(&pci->dev);
+	}
 
 out_free:
-	if (err < 0 || !hda->need_i915_power)
+	if (err < 0) {
+		azx_free(chip);
+		return err;
+	}
+
+	if (!hda->need_i915_power)
 		display_power(chip, false);
-	if (err < 0)
-		hda->init_failed = 1;
 	complete_all(&hda->probe_wait);
 	to_hda_bus(bus)->bus_probing = 0;
-	return err;
+	return 0;
 }
 
 static void azx_remove(struct pci_dev *pci)
diff --git a/sound/pci/hda/hda_intel.h b/sound/pci/hda/hda_intel.h
index 2acfff3da1a0..3fb119f09040 100644
--- a/sound/pci/hda/hda_intel.h
+++ b/sound/pci/hda/hda_intel.h
@@ -27,6 +27,7 @@ struct hda_intel {
 	unsigned int use_vga_switcheroo:1;
 	unsigned int vga_switcheroo_registered:1;
 	unsigned int init_failed:1; /* delayed init failed */
+	unsigned int freed:1; /* resources already released */
 
 	bool need_i915_power:1; /* the hda controller needs i915 power */
 };
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index bb287a916dae..93760a3564cf 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -38,6 +38,10 @@ static bool static_hdmi_pcm;
 module_param(static_hdmi_pcm, bool, 0644);
 MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info");
 
+static bool enable_acomp = true;
+module_param(enable_acomp, bool, 0444);
+MODULE_PARM_DESC(enable_acomp, "Enable audio component binding (default=yes)");
+
 struct hdmi_spec_per_cvt {
 	hda_nid_t cvt_nid;
 	int assigned;
@@ -1844,8 +1848,10 @@ static bool check_non_pcm_per_cvt(struct hda_codec *codec, hda_nid_t cvt_nid)
 	/* Add sanity check to pass klockwork check.
 	 * This should never happen.
 	 */
-	if (WARN_ON(spdif == NULL))
+	if (WARN_ON(spdif == NULL)) {
+		mutex_unlock(&codec->spdif_mutex);
 		return true;
+	}
 	non_pcm = !!(spdif->status & IEC958_AES0_NONAUDIO);
 	mutex_unlock(&codec->spdif_mutex);
 	return non_pcm;
@@ -2194,7 +2200,9 @@ static int generic_hdmi_build_controls(struct hda_codec *codec)
 
 	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
+		struct hdmi_eld *pin_eld = &per_pin->sink_eld;
 
+		pin_eld->eld_valid = false;
 		hdmi_present_sense(per_pin, 0);
 	}
 
@@ -2505,6 +2513,11 @@ static void generic_acomp_init(struct hda_codec *codec,
 {
 	struct hdmi_spec *spec = codec->spec;
 
+	if (!enable_acomp) {
+		codec_info(codec, "audio component disabled by module option\n");
+		return;
+	}
+
 	spec->port2pin = port2pin;
 	setup_drm_audio_ops(codec, ops);
 	if (!snd_hdac_acomp_init(&codec->bus->core, &spec->drm_audio_ops,
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index de2826f90d34..e62d58872b6e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -377,12 +377,14 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0233:
 	case 0x10ec0235:
 	case 0x10ec0236:
+	case 0x10ec0245:
 	case 0x10ec0255:
 	case 0x10ec0256:
 	case 0x10ec0257:
 	case 0x10ec0282:
 	case 0x10ec0283:
 	case 0x10ec0286:
+	case 0x10ec0287:
 	case 0x10ec0288:
 	case 0x10ec0285:
 	case 0x10ec0298:
@@ -797,9 +799,11 @@ static void alc_ssid_check(struct hda_codec *codec, const hda_nid_t *ports)
 {
 	if (!alc_subsystem_id(codec, ports)) {
 		struct alc_spec *spec = codec->spec;
-		codec_dbg(codec,
-			  "realtek: Enable default setup for auto mode as fallback\n");
-		spec->init_amp = ALC_INIT_DEFAULT;
+		if (spec->init_amp == ALC_INIT_UNDEFINED) {
+			codec_dbg(codec,
+				  "realtek: Enable default setup for auto mode as fallback\n");
+			spec->init_amp = ALC_INIT_DEFAULT;
+		}
 	}
 }
 
@@ -2454,6 +2458,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1458, 0xa0cd, "Gigabyte X570 Aorus Master", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1458, 0xa0ce, "Gigabyte X570 Aorus Xtreme", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1275, "MSI-GL63", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
@@ -2469,6 +2474,9 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x97e1, "Clevo P970[ER][CDFN]", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
 	SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+	SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+	SND_PCI_QUIRK(0x1558, 0x70d1, "Clevo PC70[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+	SND_PCI_QUIRK(0x1558, 0x7714, "Clevo X170", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530),
@@ -5477,18 +5485,9 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec,
 		{ 0x19, 0x21a11010 }, /* dock mic */
 		{ }
 	};
-	/* Assure the speaker pin to be coupled with DAC NID 0x03; otherwise
-	 * the speaker output becomes too low by some reason on Thinkpads with
-	 * ALC298 codec
-	 */
-	static const hda_nid_t preferred_pairs[] = {
-		0x14, 0x03, 0x17, 0x02, 0x21, 0x02,
-		0
-	};
 	struct alc_spec *spec = codec->spec;
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.preferred_dacs = preferred_pairs;
 		spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP;
 		snd_hda_apply_pincfgs(codec, pincfgs);
 	} else if (action == HDA_FIXUP_ACT_INIT) {
@@ -5501,6 +5500,23 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec,
 	}
 }
 
+static void alc_fixup_tpt470_dacs(struct hda_codec *codec,
+				  const struct hda_fixup *fix, int action)
+{
+	/* Assure the speaker pin to be coupled with DAC NID 0x03; otherwise
+	 * the speaker output becomes too low by some reason on Thinkpads with
+	 * ALC298 codec
+	 */
+	static const hda_nid_t preferred_pairs[] = {
+		0x14, 0x03, 0x17, 0x02, 0x21, 0x02,
+		0
+	};
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		spec->gen.preferred_dacs = preferred_pairs;
+}
+
 static void alc_shutup_dell_xps13(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
@@ -5853,6 +5869,15 @@ static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec,
 	}
 }
 
+static void alc225_fixup_s3_pop_noise(struct hda_codec *codec,
+				      const struct hda_fixup *fix, int action)
+{
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+
+	codec->power_save_node = 1;
+}
+
 /* Forcibly assign NID 0x03 to HP/LO while NID 0x02 to SPK for EQ */
 static void alc274_fixup_bind_dacs(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
@@ -5957,6 +5982,7 @@ enum {
 	ALC269_FIXUP_HP_LINE1_MIC1_LED,
 	ALC269_FIXUP_INV_DMIC,
 	ALC269_FIXUP_LENOVO_DOCK,
+	ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST,
 	ALC269_FIXUP_NO_SHUTUP,
 	ALC286_FIXUP_SONY_MIC_NO_PRESENCE,
 	ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT,
@@ -6042,9 +6068,11 @@ enum {
 	ALC233_FIXUP_ACER_HEADSET_MIC,
 	ALC294_FIXUP_LENOVO_MIC_LOCATION,
 	ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE,
+	ALC225_FIXUP_S3_POP_NOISE,
 	ALC700_FIXUP_INTEL_REFERENCE,
 	ALC274_FIXUP_DELL_BIND_DACS,
 	ALC274_FIXUP_DELL_AIO_LINEOUT_VERB,
+	ALC298_FIXUP_TPT470_DOCK_FIX,
 	ALC298_FIXUP_TPT470_DOCK,
 	ALC255_FIXUP_DUMMY_LINEOUT_VERB,
 	ALC255_FIXUP_DELL_HEADSET_MIC,
@@ -6077,9 +6105,12 @@ enum {
 	ALC294_FIXUP_ASUS_DUAL_SPK,
 	ALC285_FIXUP_THINKPAD_HEADSET_JACK,
 	ALC294_FIXUP_ASUS_HPE,
+	ALC294_FIXUP_ASUS_COEF_1B,
 	ALC285_FIXUP_HP_GPIO_LED,
 	ALC285_FIXUP_HP_MUTE_LED,
 	ALC236_FIXUP_HP_MUTE_LED,
+	ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
+	ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -6277,6 +6308,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT
 	},
+	[ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_limit_int_mic_boost,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_LENOVO_DOCK,
+	},
 	[ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
@@ -6929,6 +6966,12 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ }
 		},
 		.chained = true,
+		.chain_id = ALC225_FIXUP_S3_POP_NOISE
+	},
+	[ALC225_FIXUP_S3_POP_NOISE] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc225_fixup_s3_pop_noise,
+		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
 	},
 	[ALC700_FIXUP_INTEL_REFERENCE] = {
@@ -6961,12 +7004,18 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC274_FIXUP_DELL_BIND_DACS
 	},
-	[ALC298_FIXUP_TPT470_DOCK] = {
+	[ALC298_FIXUP_TPT470_DOCK_FIX] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_tpt470_dock,
 		.chained = true,
 		.chain_id = ALC293_FIXUP_LENOVO_SPK_NOISE
 	},
+	[ALC298_FIXUP_TPT470_DOCK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_tpt470_dacs,
+		.chained = true,
+		.chain_id = ALC298_FIXUP_TPT470_DOCK_FIX
+	},
 	[ALC255_FIXUP_DUMMY_LINEOUT_VERB] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -7201,6 +7250,17 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC
 	},
+	[ALC294_FIXUP_ASUS_COEF_1B] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* Set bit 10 to correct noisy output after reboot from
+			 * Windows 10 (due to pop noise reduction?)
+			 */
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x1b },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x4e4b },
+			{ }
+		},
+	},
 	[ALC285_FIXUP_HP_GPIO_LED] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc285_fixup_hp_gpio_led,
@@ -7213,6 +7273,22 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc236_fixup_hp_mute_led,
 	},
+	[ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			{ 0x1a, AC_VERB_SET_PIN_WIDGET_CONTROL, 0xc5 },
+			{ }
+		},
+	},
+	[ALC295_FIXUP_ASUS_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -7378,9 +7454,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE),
+	SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
 	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B),
 	SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -7406,6 +7485,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
 	SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
+	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
 	SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
@@ -7416,12 +7497,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1558, 0x8561, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS),
+	SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21ca, "Thinkpad L412", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21e9, "Thinkpad Edge 15", ALC269_FIXUP_SKU_IGNORE),
-	SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x21fa, "Thinkpad X230", ALC269_FIXUP_LENOVO_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x21f3, "Thinkpad T430", ALC269_FIXUP_LENOVO_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x21fb, "Thinkpad T430s", ALC269_FIXUP_LENOVO_DOCK),
@@ -7560,6 +7642,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC269_FIXUP_HEADSET_MODE, .name = "headset-mode"},
 	{.id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, .name = "headset-mode-no-hp-mic"},
 	{.id = ALC269_FIXUP_LENOVO_DOCK, .name = "lenovo-dock"},
+	{.id = ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST, .name = "lenovo-dock-limit-boost"},
 	{.id = ALC269_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"},
 	{.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"},
 	{.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
@@ -7571,6 +7654,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"},
 	{.id = ALC292_FIXUP_TPT440, .name = "tpt440"},
 	{.id = ALC292_FIXUP_TPT460, .name = "tpt460"},
+	{.id = ALC298_FIXUP_TPT470_DOCK_FIX, .name = "tpt470-dock-fix"},
 	{.id = ALC298_FIXUP_TPT470_DOCK, .name = "tpt470-dock"},
 	{.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
 	{.id = ALC700_FIXUP_INTEL_REFERENCE, .name = "alc700-ref"},
@@ -7988,6 +8072,18 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60130},
 		{0x17, 0x90170110},
 		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
+		{0x12, 0x90a60120},
+		{0x17, 0x90170110},
+		{0x21, 0x04211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
+		{0x12, 0x90a60130},
+		{0x17, 0x90170110},
+		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
+		{0x12, 0x90a60130},
+		{0x17, 0x90170110},
+		{0x21, 0x03211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 		{0x14, 0x90170110},
 		{0x21, 0x04211020}),
@@ -8195,7 +8291,9 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->gen.mixer_nid = 0;
 		break;
 	case 0x10ec0215:
+	case 0x10ec0245:
 	case 0x10ec0285:
+	case 0x10ec0287:
 	case 0x10ec0289:
 		spec->codec_variant = ALC269_TYPE_ALC215;
 		spec->shutup = alc225_shutup;
@@ -8203,8 +8301,6 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->gen.mixer_nid = 0;
 		break;
 	case 0x10ec0225:
-		codec->power_save_node = 1;
-		/* fall through */
 	case 0x10ec0295:
 	case 0x10ec0299:
 		spec->codec_variant = ALC269_TYPE_ALC225;
@@ -9456,6 +9552,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0234, "ALC234", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0235, "ALC233", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0236, "ALC236", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0245, "ALC245", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0255, "ALC255", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0256, "ALC256", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0257, "ALC257", patch_alc269),
@@ -9475,6 +9572,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0284, "ALC284", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0285, "ALC285", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0286, "ALC286", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0287, "ALC287", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0288, "ALC288", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0289, "ALC289", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0290, "ALC290", patch_alc269),
diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c
index 884d0cdec08c..73e1e5400506 100644
--- a/sound/pci/ice1712/ice1712.c
+++ b/sound/pci/ice1712/ice1712.c
@@ -2332,7 +2332,8 @@ static int snd_ice1712_chip_init(struct snd_ice1712 *ice)
 	pci_write_config_byte(ice->pci, 0x61, ice->eeprom.data[ICE_EEP1_ACLINK]);
 	pci_write_config_byte(ice->pci, 0x62, ice->eeprom.data[ICE_EEP1_I2SID]);
 	pci_write_config_byte(ice->pci, 0x63, ice->eeprom.data[ICE_EEP1_SPDIF]);
-	if (ice->eeprom.subvendor != ICE1712_SUBDEVICE_STDSP24) {
+	if (ice->eeprom.subvendor != ICE1712_SUBDEVICE_STDSP24 &&
+	    ice->eeprom.subvendor != ICE1712_SUBDEVICE_STAUDIO_ADCIII) {
 		ice->gpio.write_mask = ice->eeprom.gpiomask;
 		ice->gpio.direction = ice->eeprom.gpiodir;
 		snd_ice1712_write(ice, ICE1712_IREG_GPIO_WRITE_MASK,
diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c
index 024a7ee54cd5..e499c00e0c66 100644
--- a/sound/soc/amd/acp3x-rt5682-max9836.c
+++ b/sound/soc/amd/acp3x-rt5682-max9836.c
@@ -89,9 +89,9 @@ static int acp3x_5682_init(struct snd_soc_pcm_runtime *rtd)
 	}
 
 	snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_0, KEY_PLAYPAUSE);
-	snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_1, KEY_VOLUMEUP);
-	snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_2, KEY_VOLUMEDOWN);
-	snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_3, KEY_VOICECOMMAND);
+	snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_1, KEY_VOICECOMMAND);
+	snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_2, KEY_VOLUMEUP);
+	snd_jack_set_key(pco_jack.jack, SND_JACK_BTN_3, KEY_VOLUMEDOWN);
 
 	ret = snd_soc_component_set_jack(component, &pco_jack, NULL);
 	if (ret) {
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index e6a0c5d05fa5..e60e0b6a689c 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -1525,6 +1525,7 @@ config SND_SOC_WM8804_SPI
 
 config SND_SOC_WM8900
 	tristate
+	depends on SND_SOC_I2C_AND_SPI
 
 config SND_SOC_WM8903
 	tristate "Wolfson Microelectronics WM8903 CODEC"
@@ -1576,6 +1577,7 @@ config SND_SOC_WM8985
 
 config SND_SOC_WM8988
 	tristate
+	depends on SND_SOC_I2C_AND_SPI
 
 config SND_SOC_WM8990
 	tristate
@@ -1594,6 +1596,7 @@ config SND_SOC_WM8994
 
 config SND_SOC_WM8995
 	tristate
+	depends on SND_SOC_I2C_AND_SPI
 
 config SND_SOC_WM8996
 	tristate
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index fba9b749839d..f26b77faed59 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -142,14 +142,14 @@ static struct hdac_hdmi_pcm *
 hdac_hdmi_get_pcm_from_cvt(struct hdac_hdmi_priv *hdmi,
 			   struct hdac_hdmi_cvt *cvt)
 {
-	struct hdac_hdmi_pcm *pcm = NULL;
+	struct hdac_hdmi_pcm *pcm;
 
 	list_for_each_entry(pcm, &hdmi->pcm_list, head) {
 		if (pcm->cvt == cvt)
-			break;
+			return pcm;
 	}
 
-	return pcm;
+	return NULL;
 }
 
 static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm,
diff --git a/sound/soc/codecs/madera.c b/sound/soc/codecs/madera.c
index 40de9d7811d1..a448d2a2918a 100644
--- a/sound/soc/codecs/madera.c
+++ b/sound/soc/codecs/madera.c
@@ -1903,7 +1903,6 @@ const struct soc_enum madera_isrc_fsh[] = {
 			      MADERA_ISRC4_FSH_SHIFT, 0xf,
 			      MADERA_RATE_ENUM_SIZE,
 			      madera_rate_text, madera_rate_val),
-
 };
 EXPORT_SYMBOL_GPL(madera_isrc_fsh);
 
@@ -1924,7 +1923,6 @@ const struct soc_enum madera_isrc_fsl[] = {
 			      MADERA_ISRC4_FSL_SHIFT, 0xf,
 			      MADERA_RATE_ENUM_SIZE,
 			      madera_rate_text, madera_rate_val),
-
 };
 EXPORT_SYMBOL_GPL(madera_isrc_fsl);
 
@@ -1938,7 +1936,6 @@ const struct soc_enum madera_asrc1_rate[] = {
 			      MADERA_ASYNC_RATE_ENUM_SIZE,
 			      madera_rate_text + MADERA_SYNC_RATE_ENUM_SIZE,
 			      madera_rate_val + MADERA_SYNC_RATE_ENUM_SIZE),
-
 };
 EXPORT_SYMBOL_GPL(madera_asrc1_rate);
 
@@ -1964,7 +1961,6 @@ const struct soc_enum madera_asrc2_rate[] = {
 			      MADERA_ASYNC_RATE_ENUM_SIZE,
 			      madera_rate_text + MADERA_SYNC_RATE_ENUM_SIZE,
 			      madera_rate_val + MADERA_SYNC_RATE_ENUM_SIZE),
-
 };
 EXPORT_SYMBOL_GPL(madera_asrc2_rate);
 
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index d5130193b4a2..e8a8bf7b4ffe 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1653,6 +1653,40 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 		dev_err(&client->dev,
 			"Error %d initializing CHIP_CLK_CTRL\n", ret);
 
+	/* Mute everything to avoid pop from the following power-up */
+	ret = regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_CTRL,
+			   SGTL5000_CHIP_ANA_CTRL_DEFAULT);
+	if (ret) {
+		dev_err(&client->dev,
+			"Error %d muting outputs via CHIP_ANA_CTRL\n", ret);
+		goto disable_clk;
+	}
+
+	/*
+	 * If VAG is powered-on (e.g. from previous boot), it would be disabled
+	 * by the write to ANA_POWER in later steps of the probe code. This
+	 * may create a loud pop even with all outputs muted. The proper way
+	 * to circumvent this is disabling the bit first and waiting the proper
+	 * cool-down time.
+	 */
+	ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, &value);
+	if (ret) {
+		dev_err(&client->dev, "Failed to read ANA_POWER: %d\n", ret);
+		goto disable_clk;
+	}
+	if (value & SGTL5000_VAG_POWERUP) {
+		ret = regmap_update_bits(sgtl5000->regmap,
+					 SGTL5000_CHIP_ANA_POWER,
+					 SGTL5000_VAG_POWERUP,
+					 0);
+		if (ret) {
+			dev_err(&client->dev, "Error %d disabling VAG\n", ret);
+			goto disable_clk;
+		}
+
+		msleep(SGTL5000_VAG_POWERDOWN_DELAY);
+	}
+
 	/* Follow section 2.2.1.1 of AN3663 */
 	ana_pwr = SGTL5000_ANA_POWER_DEFAULT;
 	if (sgtl5000->num_supplies <= VDDD) {
diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h
index a4bf4bca95bf..56ec5863f250 100644
--- a/sound/soc/codecs/sgtl5000.h
+++ b/sound/soc/codecs/sgtl5000.h
@@ -233,6 +233,7 @@
 /*
  * SGTL5000_CHIP_ANA_CTRL
  */
+#define SGTL5000_CHIP_ANA_CTRL_DEFAULT		0x0133
 #define SGTL5000_LINE_OUT_MUTE			0x0100
 #define SGTL5000_HP_SEL_MASK			0x0040
 #define SGTL5000_HP_SEL_SHIFT			6
diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c
index 1554631cb397..5b7f9fcf6cbf 100644
--- a/sound/soc/codecs/tas571x.c
+++ b/sound/soc/codecs/tas571x.c
@@ -820,8 +820,10 @@ static int tas571x_i2c_probe(struct i2c_client *client,
 
 	priv->regmap = devm_regmap_init(dev, NULL, client,
 					priv->chip->regmap_config);
-	if (IS_ERR(priv->regmap))
-		return PTR_ERR(priv->regmap);
+	if (IS_ERR(priv->regmap)) {
+		ret = PTR_ERR(priv->regmap);
+		goto disable_regs;
+	}
 
 	priv->pdn_gpio = devm_gpiod_get_optional(dev, "pdn", GPIOD_OUT_LOW);
 	if (IS_ERR(priv->pdn_gpio)) {
@@ -845,7 +847,7 @@ static int tas571x_i2c_probe(struct i2c_client *client,
 
 	ret = regmap_write(priv->regmap, TAS571X_OSC_TRIM_REG, 0);
 	if (ret)
-		return ret;
+		goto disable_regs;
 
 	usleep_range(50000, 60000);
 
@@ -861,12 +863,20 @@ static int tas571x_i2c_probe(struct i2c_client *client,
 		 */
 		ret = regmap_update_bits(priv->regmap, TAS571X_MVOL_REG, 1, 0);
 		if (ret)
-			return ret;
+			goto disable_regs;
 	}
 
-	return devm_snd_soc_register_component(&client->dev,
+	ret = devm_snd_soc_register_component(&client->dev,
 				      &priv->component_driver,
 				      &tas571x_dai, 1);
+	if (ret)
+		goto disable_regs;
+
+	return ret;
+
+disable_regs:
+	regulator_bulk_disable(priv->chip->num_supply_names, priv->supplies);
+	return ret;
 }
 
 static int tas571x_i2c_remove(struct i2c_client *client)
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index 55112c1bba5e..6cf0f6612bda 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -860,8 +860,7 @@ static int wm8960_hw_params(struct snd_pcm_substream *substream,
 
 	wm8960->is_stream_in_use[tx] = true;
 
-	if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_ON &&
-	    !wm8960->is_stream_in_use[!tx])
+	if (!wm8960->is_stream_in_use[!tx])
 		return wm8960_configure_clocking(component);
 
 	return 0;
diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c
index f2d6f2f81f14..d39d479e2378 100644
--- a/sound/soc/codecs/wsa881x.c
+++ b/sound/soc/codecs/wsa881x.c
@@ -394,6 +394,7 @@ static struct sdw_dpn_prop wsa_sink_dpn_prop[WSA881X_MAX_SWR_PORTS] = {
 		.min_ch = 1,
 		.max_ch = 1,
 		.simple_ch_prep_sm = true,
+		.read_only_wordlength = true,
 	}, {
 		/* COMP */
 		.num = 2,
@@ -401,6 +402,7 @@ static struct sdw_dpn_prop wsa_sink_dpn_prop[WSA881X_MAX_SWR_PORTS] = {
 		.min_ch = 1,
 		.max_ch = 1,
 		.simple_ch_prep_sm = true,
+		.read_only_wordlength = true,
 	}, {
 		/* BOOST */
 		.num = 3,
@@ -408,6 +410,7 @@ static struct sdw_dpn_prop wsa_sink_dpn_prop[WSA881X_MAX_SWR_PORTS] = {
 		.min_ch = 1,
 		.max_ch = 1,
 		.simple_ch_prep_sm = true,
+		.read_only_wordlength = true,
 	}, {
 		/* VISENSE */
 		.num = 4,
@@ -415,6 +418,7 @@ static struct sdw_dpn_prop wsa_sink_dpn_prop[WSA881X_MAX_SWR_PORTS] = {
 		.min_ch = 1,
 		.max_ch = 1,
 		.simple_ch_prep_sm = true,
+		.read_only_wordlength = true,
 	}
 };
 
diff --git a/sound/soc/intel/common/soc-acpi-intel-cml-match.c b/sound/soc/intel/common/soc-acpi-intel-cml-match.c
index bcedec6c6117..7d85bd5aff9f 100644
--- a/sound/soc/intel/common/soc-acpi-intel-cml-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-cml-match.c
@@ -113,14 +113,6 @@ static const struct snd_soc_acpi_adr_device rt1308_1_adr[] = {
 	}
 };
 
-static const struct snd_soc_acpi_adr_device rt1308_2_adr[] = {
-	{
-		.adr = 0x000210025D130800,
-		.num_endpoints = 1,
-		.endpoints = &single_endpoint,
-	}
-};
-
 static const struct snd_soc_acpi_adr_device rt1308_1_group1_adr[] = {
 	{
 		.adr = 0x000110025D130800,
diff --git a/sound/soc/intel/common/soc-acpi-intel-icl-match.c b/sound/soc/intel/common/soc-acpi-intel-icl-match.c
index ef8500349f2f..16ec9f382b0f 100644
--- a/sound/soc/intel/common/soc-acpi-intel-icl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-icl-match.c
@@ -87,14 +87,6 @@ static const struct snd_soc_acpi_adr_device rt1308_1_adr[] = {
 	}
 };
 
-static const struct snd_soc_acpi_adr_device rt1308_2_adr[] = {
-	{
-		.adr = 0x000210025D130800,
-		.num_endpoints = 1,
-		.endpoints = &single_endpoint,
-	}
-};
-
 static const struct snd_soc_acpi_adr_device rt1308_1_group1_adr[] = {
 	{
 		.adr = 0x000110025D130800,
diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c
index af46845f4ef2..89f7f64747cd 100644
--- a/sound/soc/meson/axg-card.c
+++ b/sound/soc/meson/axg-card.c
@@ -338,8 +338,10 @@ static int axg_card_add_link(struct snd_soc_card *card, struct device_node *np,
 
 	if (axg_card_cpu_is_tdm_iface(dai_link->cpus->of_node))
 		ret = axg_card_parse_tdm(card, np, index);
-	else if (axg_card_cpu_is_codec(dai_link->cpus->of_node))
+	else if (axg_card_cpu_is_codec(dai_link->cpus->of_node)) {
 		dai_link->params = &codec_params;
+		dai_link->no_pcm = 0; /* link is not a DPCM BE */
+	}
 
 	return ret;
 }
diff --git a/sound/soc/meson/gx-card.c b/sound/soc/meson/gx-card.c
index 7b01dcb73e5e..4abf7efb7eac 100644
--- a/sound/soc/meson/gx-card.c
+++ b/sound/soc/meson/gx-card.c
@@ -108,8 +108,10 @@ static int gx_card_add_link(struct snd_soc_card *card, struct device_node *np,
 		ret = gx_card_parse_i2s(card, np, index);
 
 	/* Or apply codec to codec params if necessary */
-	else if (gx_card_cpu_identify(dai_link->cpus, "CODEC CTRL"))
+	else if (gx_card_cpu_identify(dai_link->cpus, "CODEC CTRL")) {
 		dai_link->params = &codec_params;
+		dai_link->no_pcm = 0; /* link is not a DPCM BE */
+	}
 
 	return ret;
 }
diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
index d55e3ad96716..287ad2aa27f3 100644
--- a/sound/soc/qcom/apq8096.c
+++ b/sound/soc/qcom/apq8096.c
@@ -116,10 +116,8 @@ static int apq8096_platform_probe(struct platform_device *pdev)
 	card->dev = dev;
 	dev_set_drvdata(dev, card);
 	ret = qcom_snd_parse_of(card);
-	if (ret) {
-		dev_err(dev, "Error parsing OF data\n");
+	if (ret)
 		goto err;
-	}
 
 	apq8096_add_be_ops(card);
 	ret = snd_soc_register_card(card);
diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index c1a7624eaf17..2a5302f1db98 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -902,6 +902,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -917,6 +919,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -931,6 +935,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -946,6 +952,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -960,6 +968,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -975,6 +985,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -989,6 +1001,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
@@ -1004,6 +1018,8 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 				 SNDRV_PCM_RATE_16000,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE |
 				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
 			.rate_min =     8000,
 			.rate_max =     48000,
 		},
diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index b2de65c7f95c..68e9388ff46f 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -559,10 +559,8 @@ static int sdm845_snd_platform_probe(struct platform_device *pdev)
 	card->dev = dev;
 	dev_set_drvdata(dev, card);
 	ret = qcom_snd_parse_of(card);
-	if (ret) {
-		dev_err(dev, "Error parsing OF data\n");
+	if (ret)
 		goto parse_dt_fail;
-	}
 
 	data->card = card;
 	snd_soc_card_set_drvdata(card, data);
diff --git a/sound/soc/samsung/s3c-i2s-v2.c b/sound/soc/samsung/s3c-i2s-v2.c
index 358887848293..5e95c30fb2ba 100644
--- a/sound/soc/samsung/s3c-i2s-v2.c
+++ b/sound/soc/samsung/s3c-i2s-v2.c
@@ -656,60 +656,6 @@ void s3c_i2sv2_cleanup(struct snd_soc_dai *dai,
 }
 EXPORT_SYMBOL_GPL(s3c_i2sv2_cleanup);
 
-#ifdef CONFIG_PM
-static int s3c2412_i2s_suspend(struct snd_soc_dai *dai)
-{
-	struct s3c_i2sv2_info *i2s = to_info(dai);
-	u32 iismod;
-
-	if (dai->active) {
-		i2s->suspend_iismod = readl(i2s->regs + S3C2412_IISMOD);
-		i2s->suspend_iiscon = readl(i2s->regs + S3C2412_IISCON);
-		i2s->suspend_iispsr = readl(i2s->regs + S3C2412_IISPSR);
-
-		/* some basic suspend checks */
-
-		iismod = readl(i2s->regs + S3C2412_IISMOD);
-
-		if (iismod & S3C2412_IISCON_RXDMA_ACTIVE)
-			pr_warn("%s: RXDMA active?\n", __func__);
-
-		if (iismod & S3C2412_IISCON_TXDMA_ACTIVE)
-			pr_warn("%s: TXDMA active?\n", __func__);
-
-		if (iismod & S3C2412_IISCON_IIS_ACTIVE)
-			pr_warn("%s: IIS active\n", __func__);
-	}
-
-	return 0;
-}
-
-static int s3c2412_i2s_resume(struct snd_soc_dai *dai)
-{
-	struct s3c_i2sv2_info *i2s = to_info(dai);
-
-	pr_info("dai_active %d, IISMOD %08x, IISCON %08x\n",
-		dai->active, i2s->suspend_iismod, i2s->suspend_iiscon);
-
-	if (dai->active) {
-		writel(i2s->suspend_iiscon, i2s->regs + S3C2412_IISCON);
-		writel(i2s->suspend_iismod, i2s->regs + S3C2412_IISMOD);
-		writel(i2s->suspend_iispsr, i2s->regs + S3C2412_IISPSR);
-
-		writel(S3C2412_IISFIC_RXFLUSH | S3C2412_IISFIC_TXFLUSH,
-		       i2s->regs + S3C2412_IISFIC);
-
-		ndelay(250);
-		writel(0x0, i2s->regs + S3C2412_IISFIC);
-	}
-
-	return 0;
-}
-#else
-#define s3c2412_i2s_suspend NULL
-#define s3c2412_i2s_resume  NULL
-#endif
-
 int s3c_i2sv2_register_component(struct device *dev, int id,
 			   const struct snd_soc_component_driver *cmp_drv,
 			   struct snd_soc_dai_driver *dai_drv)
@@ -727,9 +673,6 @@ int s3c_i2sv2_register_component(struct device *dev, int id,
 	if (!ops->delay)
 		ops->delay = s3c2412_i2s_delay;
 
-	dai_drv->suspend = s3c2412_i2s_suspend;
-	dai_drv->resume = s3c2412_i2s_resume;
-
 	return devm_snd_soc_register_component(dev, cmp_drv, dai_drv, 1);
 }
 EXPORT_SYMBOL_GPL(s3c_i2sv2_register_component);
diff --git a/sound/soc/samsung/s3c2412-i2s.c b/sound/soc/samsung/s3c2412-i2s.c
index 787a3f6e9f24..b35d828c1cfe 100644
--- a/sound/soc/samsung/s3c2412-i2s.c
+++ b/sound/soc/samsung/s3c2412-i2s.c
@@ -117,6 +117,60 @@ static int s3c2412_i2s_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int s3c2412_i2s_suspend(struct snd_soc_component *component)
+{
+	struct s3c_i2sv2_info *i2s = snd_soc_component_get_drvdata(component);
+	u32 iismod;
+
+	if (component->active) {
+		i2s->suspend_iismod = readl(i2s->regs + S3C2412_IISMOD);
+		i2s->suspend_iiscon = readl(i2s->regs + S3C2412_IISCON);
+		i2s->suspend_iispsr = readl(i2s->regs + S3C2412_IISPSR);
+
+		/* some basic suspend checks */
+
+		iismod = readl(i2s->regs + S3C2412_IISMOD);
+
+		if (iismod & S3C2412_IISCON_RXDMA_ACTIVE)
+			pr_warn("%s: RXDMA active?\n", __func__);
+
+		if (iismod & S3C2412_IISCON_TXDMA_ACTIVE)
+			pr_warn("%s: TXDMA active?\n", __func__);
+
+		if (iismod & S3C2412_IISCON_IIS_ACTIVE)
+			pr_warn("%s: IIS active\n", __func__);
+	}
+
+	return 0;
+}
+
+static int s3c2412_i2s_resume(struct snd_soc_component *component)
+{
+	struct s3c_i2sv2_info *i2s = snd_soc_component_get_drvdata(component);
+
+	pr_info("component_active %d, IISMOD %08x, IISCON %08x\n",
+		component->active, i2s->suspend_iismod, i2s->suspend_iiscon);
+
+	if (component->active) {
+		writel(i2s->suspend_iiscon, i2s->regs + S3C2412_IISCON);
+		writel(i2s->suspend_iismod, i2s->regs + S3C2412_IISMOD);
+		writel(i2s->suspend_iispsr, i2s->regs + S3C2412_IISPSR);
+
+		writel(S3C2412_IISFIC_RXFLUSH | S3C2412_IISFIC_TXFLUSH,
+		       i2s->regs + S3C2412_IISFIC);
+
+		ndelay(250);
+		writel(0x0, i2s->regs + S3C2412_IISFIC);
+	}
+
+	return 0;
+}
+#else
+#define s3c2412_i2s_suspend NULL
+#define s3c2412_i2s_resume  NULL
+#endif
+
 #define S3C2412_I2S_RATES \
 	(SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_11025 | SNDRV_PCM_RATE_16000 | \
 	SNDRV_PCM_RATE_22050 | SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 | \
@@ -146,6 +200,8 @@ static struct snd_soc_dai_driver s3c2412_i2s_dai = {
 
 static const struct snd_soc_component_driver s3c2412_i2s_component = {
 	.name		= "s3c2412-i2s",
+	.suspend	= s3c2412_i2s_suspend,
+	.resume		= s3c2412_i2s_resume,
 };
 
 static int s3c2412_iis_dev_probe(struct platform_device *pdev)
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index fc5d089868df..4a7d3413917f 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -594,10 +594,16 @@ static int rsnd_ssi_stop(struct rsnd_mod *mod,
 	 * Capture:  It might not receave data. Do nothing
 	 */
 	if (rsnd_io_is_play(io)) {
-		rsnd_mod_write(mod, SSICR, cr | EN);
+		rsnd_mod_write(mod, SSICR, cr | ssi->cr_en);
 		rsnd_ssi_status_check(mod, DIRQ);
 	}
 
+	/* In multi-SSI mode, stop is performed by setting ssi0129 in
+	 * SSI_CONTROL to 0 (in rsnd_ssio_stop_gen2). Do nothing here.
+	 */
+	if (rsnd_ssi_multi_slaves_runtime(io))
+		return 0;
+
 	/*
 	 * disable SSI,
 	 * and, wait idle state
@@ -737,6 +743,9 @@ static void rsnd_ssi_parent_attach(struct rsnd_mod *mod,
 	if (!rsnd_rdai_is_clk_master(rdai))
 		return;
 
+	if (rsnd_ssi_is_multi_slave(mod, io))
+		return;
+
 	switch (rsnd_mod_id(mod)) {
 	case 1:
 	case 2:
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index f35d88211887..9c7c3e7539c9 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -221,7 +221,7 @@ static int rsnd_ssiu_init_gen2(struct rsnd_mod *mod,
 			i;
 
 		for_each_rsnd_mod_array(i, pos, io, rsnd_ssi_array) {
-			shift	= (i * 4) + 16;
+			shift	= (i * 4) + 20;
 			val	= (val & ~(0xF << shift)) |
 				rsnd_mod_id(pos) << shift;
 		}
diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c
index 8f3cad8db89a..31c41559034b 100644
--- a/sound/soc/soc-dai.c
+++ b/sound/soc/soc-dai.c
@@ -295,24 +295,17 @@ int snd_soc_dai_startup(struct snd_soc_dai *dai,
 {
 	int ret = 0;
 
-	if (!dai->started[substream->stream] &&
-	    dai->driver->ops->startup)
+	if (dai->driver->ops->startup)
 		ret = dai->driver->ops->startup(substream, dai);
 
-	if (ret == 0)
-		dai->started[substream->stream] = 1;
-
 	return ret;
 }
 
 void snd_soc_dai_shutdown(struct snd_soc_dai *dai,
 			 struct snd_pcm_substream *substream)
 {
-	if (dai->started[substream->stream] &&
-	    dai->driver->ops->shutdown)
+	if (dai->driver->ops->shutdown)
 		dai->driver->ops->shutdown(substream, dai);
-
-	dai->started[substream->stream] = 0;
 }
 
 int snd_soc_dai_prepare(struct snd_soc_dai *dai,
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 679ed60d850e..e2632841b321 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -423,7 +423,7 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 
 			memset(&template, 0, sizeof(template));
 			template.reg = e->reg;
-			template.mask = e->mask << e->shift_l;
+			template.mask = e->mask;
 			template.shift = e->shift_l;
 			template.off_val = snd_soc_enum_item_to_val(e, 0);
 			template.on_val = template.off_val;
@@ -546,8 +546,22 @@ static bool dapm_kcontrol_set_value(const struct snd_kcontrol *kcontrol,
 	if (data->value == value)
 		return false;
 
-	if (data->widget)
-		data->widget->on_val = value;
+	if (data->widget) {
+		switch (dapm_kcontrol_get_wlist(kcontrol)->widgets[0]->id) {
+		case snd_soc_dapm_switch:
+		case snd_soc_dapm_mixer:
+		case snd_soc_dapm_mixer_named_ctl:
+			data->widget->on_val = value & data->widget->mask;
+			break;
+		case snd_soc_dapm_demux:
+		case snd_soc_dapm_mux:
+			data->widget->on_val = value >> data->widget->shift;
+			break;
+		default:
+			data->widget->on_val = value;
+			break;
+		}
+	}
 
 	data->value = value;
 
@@ -4165,6 +4179,8 @@ snd_soc_dapm_new_dai(struct snd_soc_card *card,
 	w = snd_soc_dapm_new_control_unlocked(&card->dapm, &template);
 	if (IS_ERR(w)) {
 		ret = PTR_ERR(w);
+		dev_err(rtd->dev, "ASoC: Failed to create %s widget: %d\n",
+			link_name, ret);
 		goto outfree_kcontrol_news;
 	}
 
@@ -4283,52 +4299,58 @@ int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card)
 	return 0;
 }
 
-static void dapm_add_valid_dai_widget(struct snd_soc_card *card,
-				      struct snd_soc_pcm_runtime *rtd,
-				      struct snd_soc_dai *codec_dai,
-				      struct snd_soc_dai *cpu_dai)
+static void dapm_connect_dai_routes(struct snd_soc_dapm_context *dapm,
+				    struct snd_soc_dai *src_dai,
+				    struct snd_soc_dapm_widget *src,
+				    struct snd_soc_dapm_widget *dai,
+				    struct snd_soc_dai *sink_dai,
+				    struct snd_soc_dapm_widget *sink)
 {
-	struct snd_soc_dapm_widget *playback = NULL, *capture = NULL;
-	struct snd_soc_dapm_widget *codec, *playback_cpu, *capture_cpu;
+	dev_dbg(dapm->dev, "connected DAI link %s:%s -> %s:%s\n",
+		src_dai->component->name, src->name,
+		sink_dai->component->name, sink->name);
+
+	if (dai) {
+		snd_soc_dapm_add_path(dapm, src, dai, NULL, NULL);
+		src = dai;
+	}
+
+	snd_soc_dapm_add_path(dapm, src, sink, NULL, NULL);
+}
+
+static void dapm_connect_dai_pair(struct snd_soc_card *card,
+				  struct snd_soc_pcm_runtime *rtd,
+				  struct snd_soc_dai *codec_dai,
+				  struct snd_soc_dai *cpu_dai)
+{
+	struct snd_soc_dai_link *dai_link = rtd->dai_link;
+	struct snd_soc_dapm_widget *dai, *codec, *playback_cpu, *capture_cpu;
 	struct snd_pcm_substream *substream;
 	struct snd_pcm_str *streams = rtd->pcm->streams;
 
-	if (rtd->dai_link->params) {
+	if (dai_link->params) {
 		playback_cpu = cpu_dai->capture_widget;
 		capture_cpu = cpu_dai->playback_widget;
 	} else {
-		playback = cpu_dai->playback_widget;
-		capture = cpu_dai->capture_widget;
-		playback_cpu = playback;
-		capture_cpu = capture;
+		playback_cpu = cpu_dai->playback_widget;
+		capture_cpu = cpu_dai->capture_widget;
 	}
 
 	/* connect BE DAI playback if widgets are valid */
 	codec = codec_dai->playback_widget;
 
 	if (playback_cpu && codec) {
-		if (!playback) {
+		if (dai_link->params && !dai_link->playback_widget) {
 			substream = streams[SNDRV_PCM_STREAM_PLAYBACK].substream;
-			playback = snd_soc_dapm_new_dai(card, substream,
-							"playback");
-			if (IS_ERR(playback)) {
-				dev_err(rtd->dev,
-					"ASoC: Failed to create DAI %s: %ld\n",
-					codec_dai->name,
-					PTR_ERR(playback));
+			dai = snd_soc_dapm_new_dai(card, substream, "playback");
+			if (IS_ERR(dai))
 				goto capture;
-			}
-
-			snd_soc_dapm_add_path(&card->dapm, playback_cpu,
-					      playback, NULL, NULL);
+			dai_link->playback_widget = dai;
 		}
 
-		dev_dbg(rtd->dev, "connected DAI link %s:%s -> %s:%s\n",
-			cpu_dai->component->name, playback_cpu->name,
-			codec_dai->component->name, codec->name);
-
-		snd_soc_dapm_add_path(&card->dapm, playback, codec,
-				      NULL, NULL);
+		dapm_connect_dai_routes(&card->dapm, cpu_dai, playback_cpu,
+					dai_link->playback_widget,
+					codec_dai, codec);
 	}
 
 capture:
@@ -4336,50 +4358,18 @@ capture:
 	codec = codec_dai->capture_widget;
 
 	if (codec && capture_cpu) {
-		if (!capture) {
+		if (dai_link->params && !dai_link->capture_widget) {
 			substream = streams[SNDRV_PCM_STREAM_CAPTURE].substream;
-			capture = snd_soc_dapm_new_dai(card, substream,
-						       "capture");
-			if (IS_ERR(capture)) {
-				dev_err(rtd->dev,
-					"ASoC: Failed to create DAI %s: %ld\n",
-					codec_dai->name,
-					PTR_ERR(capture));
+			dai = snd_soc_dapm_new_dai(card, substream, "capture");
+			if (IS_ERR(dai))
 				return;
-			}
-
-			snd_soc_dapm_add_path(&card->dapm, capture,
-					      capture_cpu, NULL, NULL);
+			dai_link->capture_widget = dai;
 		}
 
-		dev_dbg(rtd->dev, "connected DAI link %s:%s -> %s:%s\n",
-			codec_dai->component->name, codec->name,
-			cpu_dai->component->name, capture_cpu->name);
-
-		snd_soc_dapm_add_path(&card->dapm, codec, capture,
-				      NULL, NULL);
-	}
-}
-
-static void dapm_connect_dai_link_widgets(struct snd_soc_card *card,
-					  struct snd_soc_pcm_runtime *rtd)
-{
-	struct snd_soc_dai *codec_dai;
-	int i;
-
-	if (rtd->num_cpus == 1) {
-		for_each_rtd_codec_dais(rtd, i, codec_dai)
-			dapm_add_valid_dai_widget(card, rtd, codec_dai,
-						  rtd->cpu_dais[0]);
-	} else if (rtd->num_codecs == rtd->num_cpus) {
-		for_each_rtd_codec_dais(rtd, i, codec_dai)
-			dapm_add_valid_dai_widget(card, rtd, codec_dai,
-						  rtd->cpu_dais[i]);
-	} else {
-		dev_err(card->dev,
-			"N cpus to M codecs link is not supported yet\n");
+		dapm_connect_dai_routes(&card->dapm, codec_dai, codec,
+					dai_link->capture_widget,
+					cpu_dai, capture_cpu);
 	}
-
 }
 
 static void soc_dapm_dai_stream_event(struct snd_soc_dai *dai, int stream,
@@ -4422,6 +4412,8 @@ static void soc_dapm_dai_stream_event(struct snd_soc_dai *dai, int stream,
 void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card)
 {
 	struct snd_soc_pcm_runtime *rtd;
+	struct snd_soc_dai *codec_dai;
+	int i;
 
 	/* for each BE DAI link... */
 	for_each_card_rtds(card, rtd)  {
@@ -4432,7 +4424,18 @@ void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card)
 		if (rtd->dai_link->dynamic)
 			continue;
 
-		dapm_connect_dai_link_widgets(card, rtd);
+		if (rtd->num_cpus == 1) {
+			for_each_rtd_codec_dais(rtd, i, codec_dai)
+				dapm_connect_dai_pair(card, rtd, codec_dai,
+						      rtd->cpu_dais[0]);
+		} else if (rtd->num_codecs == rtd->num_cpus) {
+			for_each_rtd_codec_dais(rtd, i, codec_dai)
+				dapm_connect_dai_pair(card, rtd, codec_dai,
+						      rtd->cpu_dais[i]);
+		} else {
+			dev_err(card->dev,
+				"N cpus to M codecs link is not supported yet\n");
+		}
 	}
 }
 
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 289aebc15529..1f302de44052 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -2911,8 +2911,17 @@ int soc_new_pcm(struct snd_soc_pcm_runtime *rtd, int num)
 	int i;
 
 	if (rtd->dai_link->dynamic || rtd->dai_link->no_pcm) {
-		playback = rtd->dai_link->dpcm_playback;
-		capture = rtd->dai_link->dpcm_capture;
+		cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+		if (rtd->num_cpus > 1) {
+			dev_err(rtd->dev,
+				"DPCM doesn't support Multi CPU yet\n");
+			return -EINVAL;
+		}
+
+		playback = rtd->dai_link->dpcm_playback &&
+			   snd_soc_dai_stream_valid(cpu_dai, SNDRV_PCM_STREAM_PLAYBACK);
+		capture = rtd->dai_link->dpcm_capture &&
+			  snd_soc_dai_stream_valid(cpu_dai, SNDRV_PCM_STREAM_CAPTURE);
 	} else {
 		/* Adapt stream for codec2codec links */
 		int cpu_capture = rtd->dai_link->params ?
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 87f75edba3dc..6df3b0d12d87 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -894,7 +894,13 @@ static int soc_tplg_dmixer_create(struct soc_tplg *tplg, unsigned int count,
 		}
 
 		/* create any TLV data */
-		soc_tplg_create_tlv(tplg, &kc, &mc->hdr);
+		err = soc_tplg_create_tlv(tplg, &kc, &mc->hdr);
+		if (err < 0) {
+			dev_err(tplg->dev, "ASoC: failed to create TLV %s\n",
+				mc->hdr.name);
+			kfree(sm);
+			continue;
+		}
 
 		/* pass control to driver for optional further init */
 		err = soc_tplg_init_kcontrol(tplg, &kc,
@@ -1118,6 +1124,7 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg,
 	struct snd_soc_tplg_hdr *hdr)
 {
 	struct snd_soc_tplg_ctl_hdr *control_hdr;
+	int ret;
 	int i;
 
 	if (tplg->pass != SOC_TPLG_PASS_MIXER) {
@@ -1146,25 +1153,30 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg,
 		case SND_SOC_TPLG_CTL_RANGE:
 		case SND_SOC_TPLG_DAPM_CTL_VOLSW:
 		case SND_SOC_TPLG_DAPM_CTL_PIN:
-			soc_tplg_dmixer_create(tplg, 1,
-					       le32_to_cpu(hdr->payload_size));
+			ret = soc_tplg_dmixer_create(tplg, 1,
+					le32_to_cpu(hdr->payload_size));
 			break;
 		case SND_SOC_TPLG_CTL_ENUM:
 		case SND_SOC_TPLG_CTL_ENUM_VALUE:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_DOUBLE:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_VIRT:
 		case SND_SOC_TPLG_DAPM_CTL_ENUM_VALUE:
-			soc_tplg_denum_create(tplg, 1,
-					      le32_to_cpu(hdr->payload_size));
+			ret = soc_tplg_denum_create(tplg, 1,
+					le32_to_cpu(hdr->payload_size));
 			break;
 		case SND_SOC_TPLG_CTL_BYTES:
-			soc_tplg_dbytes_create(tplg, 1,
-					       le32_to_cpu(hdr->payload_size));
+			ret = soc_tplg_dbytes_create(tplg, 1,
+					le32_to_cpu(hdr->payload_size));
 			break;
 		default:
 			soc_bind_err(tplg, control_hdr, i);
 			return -EINVAL;
 		}
+		if (ret < 0) {
+			dev_err(tplg->dev, "ASoC: invalid control\n");
+			return ret;
+		}
+
 	}
 
 	return 0;
@@ -1272,7 +1284,9 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg,
 		routes[i]->dobj.index = tplg->index;
 		list_add(&routes[i]->dobj.list, &tplg->comp->dobj_list);
 
-		soc_tplg_add_route(tplg, routes[i]);
+		ret = soc_tplg_add_route(tplg, routes[i]);
+		if (ret < 0)
+			break;
 
 		/* add route, but keep going if some fail */
 		snd_soc_dapm_add_routes(dapm, routes[i], 1);
@@ -1355,7 +1369,13 @@ static struct snd_kcontrol_new *soc_tplg_dapm_widget_dmixer_create(
 		}
 
 		/* create any TLV data */
-		soc_tplg_create_tlv(tplg, &kc[i], &mc->hdr);
+		err = soc_tplg_create_tlv(tplg, &kc[i], &mc->hdr);
+		if (err < 0) {
+			dev_err(tplg->dev, "ASoC: failed to create TLV %s\n",
+				mc->hdr.name);
+			kfree(sm);
+			continue;
+		}
 
 		/* pass control to driver for optional further init */
 		err = soc_tplg_init_kcontrol(tplg, &kc[i],
@@ -1766,10 +1786,13 @@ static int soc_tplg_dapm_complete(struct soc_tplg *tplg)
 	return 0;
 }
 
-static void set_stream_info(struct snd_soc_pcm_stream *stream,
+static int set_stream_info(struct snd_soc_pcm_stream *stream,
 	struct snd_soc_tplg_stream_caps *caps)
 {
 	stream->stream_name = kstrdup(caps->name, GFP_KERNEL);
+	if (!stream->stream_name)
+		return -ENOMEM;
+
 	stream->channels_min = le32_to_cpu(caps->channels_min);
 	stream->channels_max = le32_to_cpu(caps->channels_max);
 	stream->rates = le32_to_cpu(caps->rates);
@@ -1777,6 +1800,8 @@ static void set_stream_info(struct snd_soc_pcm_stream *stream,
 	stream->rate_max = le32_to_cpu(caps->rate_max);
 	stream->formats = le64_to_cpu(caps->formats);
 	stream->sig_bits = le32_to_cpu(caps->sig_bits);
+
+	return 0;
 }
 
 static void set_dai_flags(struct snd_soc_dai_driver *dai_drv,
@@ -1812,20 +1837,29 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg,
 	if (dai_drv == NULL)
 		return -ENOMEM;
 
-	if (strlen(pcm->dai_name))
+	if (strlen(pcm->dai_name)) {
 		dai_drv->name = kstrdup(pcm->dai_name, GFP_KERNEL);
+		if (!dai_drv->name) {
+			ret = -ENOMEM;
+			goto err;
+		}
+	}
 	dai_drv->id = le32_to_cpu(pcm->dai_id);
 
 	if (pcm->playback) {
 		stream = &dai_drv->playback;
 		caps = &pcm->caps[SND_SOC_TPLG_STREAM_PLAYBACK];
-		set_stream_info(stream, caps);
+		ret = set_stream_info(stream, caps);
+		if (ret < 0)
+			goto err;
 	}
 
 	if (pcm->capture) {
 		stream = &dai_drv->capture;
 		caps = &pcm->caps[SND_SOC_TPLG_STREAM_CAPTURE];
-		set_stream_info(stream, caps);
+		ret = set_stream_info(stream, caps);
+		if (ret < 0)
+			goto err;
 	}
 
 	if (pcm->compress)
@@ -1835,11 +1869,7 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg,
 	ret = soc_tplg_dai_load(tplg, dai_drv, pcm, NULL);
 	if (ret < 0) {
 		dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n");
-		kfree(dai_drv->playback.stream_name);
-		kfree(dai_drv->capture.stream_name);
-		kfree(dai_drv->name);
-		kfree(dai_drv);
-		return ret;
+		goto err;
 	}
 
 	dai_drv->dobj.index = tplg->index;
@@ -1860,6 +1890,14 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg,
 		return ret;
 	}
 
+	return 0;
+
+err:
+	kfree(dai_drv->playback.stream_name);
+	kfree(dai_drv->capture.stream_name);
+	kfree(dai_drv->name);
+	kfree(dai_drv);
+
 	return ret;
 }
 
@@ -1916,11 +1954,20 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg,
 	if (strlen(pcm->pcm_name)) {
 		link->name = kstrdup(pcm->pcm_name, GFP_KERNEL);
 		link->stream_name = kstrdup(pcm->pcm_name, GFP_KERNEL);
+		if (!link->name || !link->stream_name) {
+			ret = -ENOMEM;
+			goto err;
+		}
 	}
 	link->id = le32_to_cpu(pcm->pcm_id);
 
-	if (strlen(pcm->dai_name))
+	if (strlen(pcm->dai_name)) {
 		link->cpus->dai_name = kstrdup(pcm->dai_name, GFP_KERNEL);
+		if (!link->cpus->dai_name) {
+			ret = -ENOMEM;
+			goto err;
+		}
+	}
 
 	link->codecs->name = "snd-soc-dummy";
 	link->codecs->dai_name = "snd-soc-dummy-dai";
@@ -2088,7 +2135,9 @@ static int soc_tplg_pcm_elems_load(struct soc_tplg *tplg,
 			_pcm = pcm;
 		} else {
 			abi_match = false;
-			pcm_new_ver(tplg, pcm, &_pcm);
+			ret = pcm_new_ver(tplg, pcm, &_pcm);
+			if (ret < 0)
+				return ret;
 		}
 
 		/* create the FE DAIs and DAI links */
@@ -2436,13 +2485,17 @@ static int soc_tplg_dai_config(struct soc_tplg *tplg,
 	if (d->playback) {
 		stream = &dai_drv->playback;
 		caps = &d->caps[SND_SOC_TPLG_STREAM_PLAYBACK];
-		set_stream_info(stream, caps);
+		ret = set_stream_info(stream, caps);
+		if (ret < 0)
+			goto err;
 	}
 
 	if (d->capture) {
 		stream = &dai_drv->capture;
 		caps = &d->caps[SND_SOC_TPLG_STREAM_CAPTURE];
-		set_stream_info(stream, caps);
+		ret = set_stream_info(stream, caps);
+		if (ret < 0)
+			goto err;
 	}
 
 	if (d->flag_mask)
@@ -2454,10 +2507,15 @@ static int soc_tplg_dai_config(struct soc_tplg *tplg,
 	ret = soc_tplg_dai_load(tplg, dai_drv, NULL, dai);
 	if (ret < 0) {
 		dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n");
-		return ret;
+		goto err;
 	}
 
 	return 0;
+
+err:
+	kfree(dai_drv->playback.stream_name);
+	kfree(dai_drv->capture.stream_name);
+	return ret;
 }
 
 /* load physical DAI elements */
@@ -2466,7 +2524,7 @@ static int soc_tplg_dai_elems_load(struct soc_tplg *tplg,
 {
 	struct snd_soc_tplg_dai *dai;
 	int count;
-	int i;
+	int i, ret;
 
 	count = le32_to_cpu(hdr->count);
 
@@ -2481,7 +2539,12 @@ static int soc_tplg_dai_elems_load(struct soc_tplg *tplg,
 			return -EINVAL;
 		}
 
-		soc_tplg_dai_config(tplg, dai);
+		ret = soc_tplg_dai_config(tplg, dai);
+		if (ret < 0) {
+			dev_err(tplg->dev, "ASoC: failed to configure DAI\n");
+			return ret;
+		}
+
 		tplg->pos += (sizeof(*dai) + le32_to_cpu(dai->priv.size));
 	}
 
@@ -2589,7 +2652,7 @@ static int soc_valid_header(struct soc_tplg *tplg,
 	}
 
 	/* big endian firmware objects not supported atm */
-	if (hdr->magic == SOC_TPLG_MAGIC_BIG_ENDIAN) {
+	if (le32_to_cpu(hdr->magic) == SOC_TPLG_MAGIC_BIG_ENDIAN) {
 		dev_err(tplg->dev,
 			"ASoC: pass %d big endian not supported header got %x at offset 0x%lx size 0x%zx.\n",
 			tplg->pass, hdr->magic,
diff --git a/sound/soc/sof/intel/bdw.c b/sound/soc/sof/intel/bdw.c
index 6c23c5769330..a32a3ef78ec5 100644
--- a/sound/soc/sof/intel/bdw.c
+++ b/sound/soc/sof/intel/bdw.c
@@ -567,9 +567,25 @@ static void bdw_set_mach_params(const struct snd_soc_acpi_mach *mach,
 static struct snd_soc_dai_driver bdw_dai[] = {
 {
 	.name = "ssp0-port",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
 },
 {
 	.name = "ssp1-port",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
 },
 };
 
diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c
index f84391294f12..29fd1d86156c 100644
--- a/sound/soc/sof/intel/byt.c
+++ b/sound/soc/sof/intel/byt.c
@@ -459,21 +459,69 @@ static void byt_set_mach_params(const struct snd_soc_acpi_mach *mach,
 static struct snd_soc_dai_driver byt_dai[] = {
 {
 	.name = "ssp0-port",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
 },
 {
 	.name = "ssp1-port",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
 },
 {
 	.name = "ssp2-port",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 8,
+	}
 },
 {
 	.name = "ssp3-port",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
 },
 {
 	.name = "ssp4-port",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
 },
 {
 	.name = "ssp5-port",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 8,
+	},
 },
 };
 
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index 0d0c9afd8791..41f01c3e639e 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -837,7 +837,7 @@ static int stm32_sai_set_config(struct snd_soc_dai *cpu_dai,
 		cr1 = SAI_XCR1_DS_SET(SAI_DATASIZE_32);
 		break;
 	default:
-		dev_err(cpu_dai->dev, "Data format not supported");
+		dev_err(cpu_dai->dev, "Data format not supported\n");
 		return -EINVAL;
 	}
 
@@ -1547,6 +1547,9 @@ static int stm32_sai_sub_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	if (STM_SAI_PROTOCOL_IS_SPDIF(sai))
+		conf = &stm32_sai_pcm_config_spdif;
+
 	ret = snd_dmaengine_pcm_register(&pdev->dev, conf, 0);
 	if (ret) {
 		if (ret != -EPROBE_DEFER)
@@ -1556,15 +1559,10 @@ static int stm32_sai_sub_probe(struct platform_device *pdev)
 
 	ret = snd_soc_register_component(&pdev->dev, &stm32_component,
 					 &sai->cpu_dai_drv, 1);
-	if (ret) {
+	if (ret)
 		snd_dmaengine_pcm_unregister(&pdev->dev);
-		return ret;
-	}
-
-	if (STM_SAI_PROTOCOL_IS_SPDIF(sai))
-		conf = &stm32_sai_pcm_config_spdif;
 
-	return 0;
+	return ret;
 }
 
 static int stm32_sai_sub_remove(struct platform_device *pdev)
diff --git a/sound/usb/format.c b/sound/usb/format.c
index 50e1874c847c..5ffb457cc88c 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -278,6 +278,52 @@ static bool s1810c_valid_sample_rate(struct audioformat *fp,
 }
 
 /*
+ * Many Focusrite devices supports a limited set of sampling rates per
+ * altsetting. Maximum rate is exposed in the last 4 bytes of Format Type
+ * descriptor which has a non-standard bLength = 10.
+ */
+static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
+					struct audioformat *fp,
+					unsigned int rate)
+{
+	struct usb_interface *iface;
+	struct usb_host_interface *alts;
+	unsigned char *fmt;
+	unsigned int max_rate;
+
+	iface = usb_ifnum_to_if(chip->dev, fp->iface);
+	if (!iface)
+		return true;
+
+	alts = &iface->altsetting[fp->altset_idx];
+	fmt = snd_usb_find_csint_desc(alts->extra, alts->extralen,
+				      NULL, UAC_FORMAT_TYPE);
+	if (!fmt)
+		return true;
+
+	if (fmt[0] == 10) { /* bLength */
+		max_rate = combine_quad(&fmt[6]);
+
+		/* Validate max rate */
+		if (max_rate != 48000 &&
+		    max_rate != 96000 &&
+		    max_rate != 192000 &&
+		    max_rate != 384000) {
+
+			usb_audio_info(chip,
+				"%u:%d : unexpected max rate: %u\n",
+				fp->iface, fp->altsetting, max_rate);
+
+			return true;
+		}
+
+		return rate <= max_rate;
+	}
+
+	return true;
+}
+
+/*
  * Helper function to walk the array of sample rate triplets reported by
  * the device. The problem is that we need to parse whole array first to
  * get to know how many sample rates we have to expect.
@@ -319,6 +365,11 @@ static int parse_uac2_sample_rate_range(struct snd_usb_audio *chip,
 			    !s1810c_valid_sample_rate(fp, rate))
 				goto skip_rate;
 
+			/* Filter out invalid rates on Focusrite devices */
+			if (USB_ID_VENDOR(chip->usb_id) == 0x1235 &&
+			    !focusrite_valid_sample_rate(chip, fp, rate))
+				goto skip_rate;
+
 			if (fp->rate_table)
 				fp->rate_table[nr_rates] = rate;
 			if (!fp->rate_min || rate < fp->rate_min)
diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c
index d37db32ecd3b..e39dc85c355a 100644
--- a/sound/usb/line6/podhd.c
+++ b/sound/usb/line6/podhd.c
@@ -21,8 +21,7 @@
 enum {
 	LINE6_PODHD300,
 	LINE6_PODHD400,
-	LINE6_PODHD500_0,
-	LINE6_PODHD500_1,
+	LINE6_PODHD500,
 	LINE6_PODX3,
 	LINE6_PODX3LIVE,
 	LINE6_PODHD500X,
@@ -318,8 +317,7 @@ static const struct usb_device_id podhd_id_table[] = {
 	/* TODO: no need to alloc data interfaces when only audio is used */
 	{ LINE6_DEVICE(0x5057),    .driver_info = LINE6_PODHD300 },
 	{ LINE6_DEVICE(0x5058),    .driver_info = LINE6_PODHD400 },
-	{ LINE6_IF_NUM(0x414D, 0), .driver_info = LINE6_PODHD500_0 },
-	{ LINE6_IF_NUM(0x414D, 1), .driver_info = LINE6_PODHD500_1 },
+	{ LINE6_IF_NUM(0x414D, 0), .driver_info = LINE6_PODHD500 },
 	{ LINE6_IF_NUM(0x414A, 0), .driver_info = LINE6_PODX3 },
 	{ LINE6_IF_NUM(0x414B, 0), .driver_info = LINE6_PODX3LIVE },
 	{ LINE6_IF_NUM(0x4159, 0), .driver_info = LINE6_PODHD500X },
@@ -352,23 +350,13 @@ static const struct line6_properties podhd_properties_table[] = {
 		.ep_audio_r = 0x82,
 		.ep_audio_w = 0x01,
 	},
-	[LINE6_PODHD500_0] = {
+	[LINE6_PODHD500] = {
 		.id = "PODHD500",
 		.name = "POD HD500",
-		.capabilities	= LINE6_CAP_PCM
+		.capabilities	= LINE6_CAP_PCM | LINE6_CAP_CONTROL
 				| LINE6_CAP_HWMON,
 		.altsetting = 1,
-		.ep_ctrl_r = 0x81,
-		.ep_ctrl_w = 0x01,
-		.ep_audio_r = 0x86,
-		.ep_audio_w = 0x02,
-	},
-	[LINE6_PODHD500_1] = {
-		.id = "PODHD500",
-		.name = "POD HD500",
-		.capabilities	= LINE6_CAP_PCM
-				| LINE6_CAP_HWMON,
-		.altsetting = 0,
+		.ctrl_if = 1,
 		.ep_ctrl_r = 0x81,
 		.ep_ctrl_w = 0x01,
 		.ep_audio_r = 0x86,
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 721d12130d0c..15769f266790 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -1182,6 +1182,14 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
 			cval->res = 384;
 		}
 		break;
+	case USB_ID(0x0495, 0x3042): /* ESS Technology Asus USB DAC */
+		if ((strstr(kctl->id.name, "Playback Volume") != NULL) ||
+			strstr(kctl->id.name, "Capture Volume") != NULL) {
+			cval->min >>= 8;
+			cval->max = 0;
+			cval->res = 1;
+		}
+		break;
 	}
 }
 
@@ -1457,7 +1465,7 @@ error:
 		usb_audio_err(chip,
 			"cannot get connectors status: req = %#x, wValue = %#x, wIndex = %#x, type = %d\n",
 			UAC_GET_CUR, validx, idx, cval->val_type);
-		return ret;
+		return filter_error(cval, ret);
 	}
 
 	ucontrol->value.integer.value[0] = val;
@@ -1771,10 +1779,16 @@ static void get_connector_control_name(struct usb_mixer_interface *mixer,
 
 /* Build a mixer control for a UAC connector control (jack-detect) */
 static void build_connector_control(struct usb_mixer_interface *mixer,
+				    const struct usbmix_name_map *imap,
 				    struct usb_audio_term *term, bool is_input)
 {
 	struct snd_kcontrol *kctl;
 	struct usb_mixer_elem_info *cval;
+	const struct usbmix_name_map *map;
+
+	map = find_map(imap, term->id, 0);
+	if (check_ignored_ctl(map))
+		return;
 
 	cval = kzalloc(sizeof(*cval), GFP_KERNEL);
 	if (!cval)
@@ -1805,8 +1819,12 @@ static void build_connector_control(struct usb_mixer_interface *mixer,
 		usb_mixer_elem_info_free(cval);
 		return;
 	}
-	get_connector_control_name(mixer, term, is_input, kctl->id.name,
-				   sizeof(kctl->id.name));
+
+	if (check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name)))
+		strlcat(kctl->id.name, " Jack", sizeof(kctl->id.name));
+	else
+		get_connector_control_name(mixer, term, is_input, kctl->id.name,
+					   sizeof(kctl->id.name));
 	kctl->private_free = snd_usb_mixer_elem_free;
 	snd_usb_mixer_add_control(&cval->head, kctl);
 }
@@ -2109,8 +2127,9 @@ static int parse_audio_input_terminal(struct mixer_build *state, int unitid,
 	check_input_term(state, term_id, &iterm);
 
 	/* Check for jack detection. */
-	if (uac_v2v3_control_is_readable(bmctls, control))
-		build_connector_control(state->mixer, &iterm, true);
+	if ((iterm.type & 0xff00) != 0x0100 &&
+	    uac_v2v3_control_is_readable(bmctls, control))
+		build_connector_control(state->mixer, state->map, &iterm, true);
 
 	return 0;
 }
@@ -3071,13 +3090,13 @@ static int snd_usb_mixer_controls_badd(struct usb_mixer_interface *mixer,
 		memset(&iterm, 0, sizeof(iterm));
 		iterm.id = UAC3_BADD_IT_ID4;
 		iterm.type = UAC_BIDIR_TERMINAL_HEADSET;
-		build_connector_control(mixer, &iterm, true);
+		build_connector_control(mixer, map->map, &iterm, true);
 
 		/* Output Term - Insertion control */
 		memset(&oterm, 0, sizeof(oterm));
 		oterm.id = UAC3_BADD_OT_ID3;
 		oterm.type = UAC_BIDIR_TERMINAL_HEADSET;
-		build_connector_control(mixer, &oterm, false);
+		build_connector_control(mixer, map->map, &oterm, false);
 	}
 
 	return 0;
@@ -3106,7 +3125,8 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 		if (map->id == state.chip->usb_id) {
 			state.map = map->map;
 			state.selector_map = map->selector_map;
-			mixer->ignore_ctl_error = map->ignore_ctl_error;
+			mixer->connector_map = map->connector_map;
+			mixer->ignore_ctl_error |= map->ignore_ctl_error;
 			break;
 		}
 	}
@@ -3149,10 +3169,11 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 			if (err < 0 && err != -EINVAL)
 				return err;
 
-			if (uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls),
+			if ((state.oterm.type & 0xff00) != 0x0100 &&
+			    uac_v2v3_control_is_readable(le16_to_cpu(desc->bmControls),
 							 UAC2_TE_CONNECTOR)) {
-				build_connector_control(state.mixer, &state.oterm,
-							false);
+				build_connector_control(state.mixer, state.map,
+							&state.oterm, false);
 			}
 		} else {  /* UAC_VERSION_3 */
 			struct uac3_output_terminal_descriptor *desc = p;
@@ -3174,10 +3195,11 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 			if (err < 0 && err != -EINVAL)
 				return err;
 
-			if (uac_v2v3_control_is_readable(le32_to_cpu(desc->bmControls),
+			if ((state.oterm.type & 0xff00) != 0x0100 &&
+			    uac_v2v3_control_is_readable(le32_to_cpu(desc->bmControls),
 							 UAC3_TE_INSERTION)) {
-				build_connector_control(state.mixer, &state.oterm,
-							false);
+				build_connector_control(state.mixer, state.map,
+							&state.oterm, false);
 			}
 		}
 	}
@@ -3185,10 +3207,32 @@ static int snd_usb_mixer_controls(struct usb_mixer_interface *mixer)
 	return 0;
 }
 
+static int delegate_notify(struct usb_mixer_interface *mixer, int unitid,
+			   u8 *control, u8 *channel)
+{
+	const struct usbmix_connector_map *map = mixer->connector_map;
+
+	if (!map)
+		return unitid;
+
+	for (; map->id; map++) {
+		if (map->id == unitid) {
+			if (control && map->control)
+				*control = map->control;
+			if (channel && map->channel)
+				*channel = map->channel;
+			return map->delegated_id;
+		}
+	}
+	return unitid;
+}
+
 void snd_usb_mixer_notify_id(struct usb_mixer_interface *mixer, int unitid)
 {
 	struct usb_mixer_elem_list *list;
 
+	unitid = delegate_notify(mixer, unitid, NULL, NULL);
+
 	for_each_mixer_elem(list, mixer, unitid) {
 		struct usb_mixer_elem_info *info =
 			mixer_elem_list_to_info(list);
@@ -3258,6 +3302,8 @@ static void snd_usb_mixer_interrupt_v2(struct usb_mixer_interface *mixer,
 		return;
 	}
 
+	unitid = delegate_notify(mixer, unitid, &control, &channel);
+
 	for_each_mixer_elem(list, mixer, unitid)
 		count++;
 
diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index 65d6d08c96f5..41ec9dc4139b 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -6,6 +6,13 @@
 
 struct media_mixer_ctl;
 
+struct usbmix_connector_map {
+	u8 id;
+	u8 delegated_id;
+	u8 control;
+	u8 channel;
+};
+
 struct usb_mixer_interface {
 	struct snd_usb_audio *chip;
 	struct usb_host_interface *hostif;
@@ -18,6 +25,9 @@ struct usb_mixer_interface {
 	/* the usb audio specification version this interface complies to */
 	int protocol;
 
+	/* optional connector delegation map */
+	const struct usbmix_connector_map *connector_map;
+
 	/* Sound Blaster remote control stuff */
 	const struct rc_config *rc_cfg;
 	u32 rc_code;
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 72b575c34860..9af7aa93f6fa 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -27,6 +27,7 @@ struct usbmix_ctl_map {
 	u32 id;
 	const struct usbmix_name_map *map;
 	const struct usbmix_selector_map *selector_map;
+	const struct usbmix_connector_map *connector_map;
 	int ignore_ctl_error;
 };
 
@@ -360,13 +361,57 @@ static const struct usbmix_name_map corsair_virtuoso_map[] = {
 };
 
 /* Some mobos shipped with a dummy HD-audio show the invalid GET_MIN/GET_MAX
- * response for Input Gain Pad (id=19, control=12).  Skip it.
+ * response for Input Gain Pad (id=19, control=12) and the connector status
+ * for SPDIF terminal (id=18).  Skip them.
  */
 static const struct usbmix_name_map asus_rog_map[] = {
+	{ 18, NULL }, /* OT, connector control */
 	{ 19, NULL, 12 }, /* FU, Input Gain Pad */
 	{}
 };
 
+/* TRX40 mobos with Realtek ALC1220-VB */
+static const struct usbmix_name_map trx40_mobo_map[] = {
+	{ 18, NULL }, /* OT, IEC958 - broken response, disabled */
+	{ 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */
+	{ 16, "Speaker" },		/* OT */
+	{ 22, "Speaker Playback" },	/* FU */
+	{ 7, "Line" },			/* IT */
+	{ 19, "Line Capture" },		/* FU */
+	{ 17, "Front Headphone" },	/* OT */
+	{ 23, "Front Headphone Playback" },	/* FU */
+	{ 8, "Mic" },			/* IT */
+	{ 20, "Mic Capture" },		/* FU */
+	{ 9, "Front Mic" },		/* IT */
+	{ 21, "Front Mic Capture" },	/* FU */
+	{ 24, "IEC958 Playback" },	/* FU */
+	{}
+};
+
+static const struct usbmix_connector_map trx40_mobo_connector_map[] = {
+	{ 10, 16 },	/* (Back) Speaker */
+	{ 11, 17 },	/* Front Headphone */
+	{ 13, 7 },	/* Line */
+	{ 14, 8 },	/* Mic */
+	{ 15, 9 },	/* Front Mic */
+	{}
+};
+
+/* Rear panel + front mic on Gigabyte TRX40 Aorus Master with ALC1220-VB */
+static const struct usbmix_name_map aorus_master_alc1220vb_map[] = {
+	{ 17, NULL },			/* OT, IEC958?, disabled */
+	{ 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */
+	{ 16, "Line Out" },		/* OT */
+	{ 22, "Line Out Playback" },	/* FU */
+	{ 7, "Line" },			/* IT */
+	{ 19, "Line Capture" },		/* FU */
+	{ 8, "Mic" },			/* IT */
+	{ 20, "Mic Capture" },		/* FU */
+	{ 9, "Front Mic" },		/* IT */
+	{ 21, "Front Mic Capture" },	/* FU */
+	{}
+};
+
 /*
  * Control map entries
  */
@@ -496,9 +541,14 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.id = USB_ID(0x1b1c, 0x0a42),
 		.map = corsair_virtuoso_map,
 	},
+	{	/* Gigabyte TRX40 Aorus Master (rear panel + front mic) */
+		.id = USB_ID(0x0414, 0xa001),
+		.map = aorus_master_alc1220vb_map,
+	},
 	{	/* Gigabyte TRX40 Aorus Pro WiFi */
 		.id = USB_ID(0x0414, 0xa002),
-		.map = asus_rog_map,
+		.map = trx40_mobo_map,
+		.connector_map = trx40_mobo_connector_map,
 	},
 	{	/* ASUS ROG Zenith II */
 		.id = USB_ID(0x0b05, 0x1916),
@@ -510,11 +560,18 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = {
 	},
 	{	/* MSI TRX40 Creator */
 		.id = USB_ID(0x0db0, 0x0d64),
-		.map = asus_rog_map,
+		.map = trx40_mobo_map,
+		.connector_map = trx40_mobo_connector_map,
 	},
 	{	/* MSI TRX40 */
 		.id = USB_ID(0x0db0, 0x543d),
-		.map = asus_rog_map,
+		.map = trx40_mobo_map,
+		.connector_map = trx40_mobo_connector_map,
+	},
+	{	/* Asrock TRX40 Creator */
+		.id = USB_ID(0x26ce, 0x0a01),
+		.map = trx40_mobo_map,
+		.connector_map = trx40_mobo_connector_map,
 	},
 	{ 0 } /* terminator */
 };
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 02b036b2aefb..a5f65a9a0254 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -1509,11 +1509,15 @@ static int snd_microii_spdif_default_get(struct snd_kcontrol *kcontrol,
 
 	/* use known values for that card: interface#1 altsetting#1 */
 	iface = usb_ifnum_to_if(chip->dev, 1);
-	if (!iface || iface->num_altsetting < 2)
-		return -EINVAL;
+	if (!iface || iface->num_altsetting < 2) {
+		err = -EINVAL;
+		goto end;
+	}
 	alts = &iface->altsetting[1];
-	if (get_iface_desc(alts)->bNumEndpoints < 1)
-		return -EINVAL;
+	if (get_iface_desc(alts)->bNumEndpoints < 1) {
+		err = -EINVAL;
+		goto end;
+	}
 	ep = get_endpoint(alts, 0)->bEndpointAddress;
 
 	err = snd_usb_ctl_msg(chip->dev,
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index e009d584e7d0..eb89902a83be 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2756,90 +2756,6 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 		.type = QUIRK_MIDI_NOVATION
 	}
 },
-{
-	/*
-	 * Focusrite Scarlett Solo 2nd generation
-	 * Reports that playback should use Synch: Synchronous
-	 * while still providing a feedback endpoint. Synchronous causes
-	 * snapping on some sample rates.
-	 * Force it to use Synch: Asynchronous.
-	 */
-	USB_DEVICE(0x1235, 0x8205),
-	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
-		.ifnum = QUIRK_ANY_INTERFACE,
-		.type = QUIRK_COMPOSITE,
-		.data = (const struct snd_usb_audio_quirk[]) {
-			{
-				.ifnum = 1,
-				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
-				.data = & (const struct audioformat) {
-					.formats = SNDRV_PCM_FMTBIT_S32_LE,
-					.channels = 2,
-					.iface = 1,
-					.altsetting = 1,
-					.altset_idx = 1,
-					.attributes = 0,
-					.endpoint = 0x01,
-					.ep_attr = USB_ENDPOINT_XFER_ISOC |
-						   USB_ENDPOINT_SYNC_ASYNC,
-					.protocol = UAC_VERSION_2,
-					.rates = SNDRV_PCM_RATE_44100 |
-						 SNDRV_PCM_RATE_48000 |
-						 SNDRV_PCM_RATE_88200 |
-						 SNDRV_PCM_RATE_96000 |
-						 SNDRV_PCM_RATE_176400 |
-						 SNDRV_PCM_RATE_192000,
-					.rate_min = 44100,
-					.rate_max = 192000,
-					.nr_rates = 6,
-					.rate_table = (unsigned int[]) {
-						44100, 48000, 88200,
-						96000, 176400, 192000
-					},
-					.clock = 41
-				}
-			},
-			{
-				.ifnum = 2,
-				.type = QUIRK_AUDIO_FIXED_ENDPOINT,
-				.data = & (const struct audioformat) {
-					.formats = SNDRV_PCM_FMTBIT_S32_LE,
-					.channels = 2,
-					.iface = 2,
-					.altsetting = 1,
-					.altset_idx = 1,
-					.attributes = 0,
-					.endpoint = 0x82,
-					.ep_attr = USB_ENDPOINT_XFER_ISOC |
-						   USB_ENDPOINT_SYNC_ASYNC |
-						   USB_ENDPOINT_USAGE_IMPLICIT_FB,
-					.protocol = UAC_VERSION_2,
-					.rates = SNDRV_PCM_RATE_44100 |
-						 SNDRV_PCM_RATE_48000 |
-						 SNDRV_PCM_RATE_88200 |
-						 SNDRV_PCM_RATE_96000 |
-						 SNDRV_PCM_RATE_176400 |
-						 SNDRV_PCM_RATE_192000,
-					.rate_min = 44100,
-					.rate_max = 192000,
-					.nr_rates = 6,
-					.rate_table = (unsigned int[]) {
-						44100, 48000, 88200,
-						96000, 176400, 192000
-					},
-					.clock = 41
-				}
-			},
-			{
-				.ifnum = 3,
-				.type = QUIRK_IGNORE_INTERFACE
-			},
-			{
-				.ifnum = -1
-			}
-		}
-	}
-},
 
 /* Access Music devices */
 {
@@ -3635,4 +3551,44 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 	}
 },
 
+#define ALC1220_VB_DESKTOP(vend, prod) { \
+	USB_DEVICE(vend, prod),	\
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { \
+		.vendor_name = "Realtek", \
+		.product_name = "ALC1220-VB-DT", \
+		.profile_name = "Realtek-ALC1220-VB-Desktop", \
+		.ifnum = QUIRK_NO_INTERFACE \
+	} \
+}
+ALC1220_VB_DESKTOP(0x0414, 0xa002), /* Gigabyte TRX40 Aorus Pro WiFi */
+ALC1220_VB_DESKTOP(0x0db0, 0x0d64), /* MSI TRX40 Creator */
+ALC1220_VB_DESKTOP(0x0db0, 0x543d), /* MSI TRX40 */
+ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */
+#undef ALC1220_VB_DESKTOP
+
+/* Two entries for Gigabyte TRX40 Aorus Master:
+ * TRX40 Aorus Master has two USB-audio devices, one for the front headphone
+ * with ESS SABRE9218 DAC chip, while another for the rest I/O (the rear
+ * panel and the front mic) with Realtek ALC1220-VB.
+ * Here we provide two distinct names for making UCM profiles easier.
+ */
+{
+	USB_DEVICE(0x0414, 0xa000),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.vendor_name = "Gigabyte",
+		.product_name = "Aorus Master Front Headphone",
+		.profile_name = "Gigabyte-Aorus-Master-Front-Headphone",
+		.ifnum = QUIRK_NO_INTERFACE
+	}
+},
+{
+	USB_DEVICE(0x0414, 0xa001),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.vendor_name = "Gigabyte",
+		.product_name = "Aorus Master Main Audio",
+		.profile_name = "Gigabyte-Aorus-Master-Main-Audio",
+		.ifnum = QUIRK_NO_INTERFACE
+	}
+},
+
 #undef USB_DEVICE_VENDOR_SPEC
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index a8ece1701068..d8a765be5dfe 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1636,13 +1636,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	    && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		msleep(20);
 
-	/* Zoom R16/24, Logitech H650e, Jabra 550a needs a tiny delay here,
-	 * otherwise requests like get/set frequency return as failed despite
-	 * actually succeeding.
+	/* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny
+	 * delay here, otherwise requests like get/set frequency return as
+	 * failed despite actually succeeding.
 	 */
 	if ((chip->usb_id == USB_ID(0x1686, 0x00dd) ||
 	     chip->usb_id == USB_ID(0x046d, 0x0a46) ||
-	     chip->usb_id == USB_ID(0x0b0e, 0x0349)) &&
+	     chip->usb_id == USB_ID(0x0b0e, 0x0349) ||
+	     chip->usb_id == USB_ID(0x0951, 0x16ad)) &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		usleep_range(1000, 2000);
 }
@@ -1687,7 +1688,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 
 	case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */
 	case USB_ID(0x10cb, 0x0103): /* The Bit Opus #3; with fp->dsd_raw */
-	case USB_ID(0x16b0, 0x06b2): /* NuPrime DAC-10 */
+	case USB_ID(0x16d0, 0x06b2): /* NuPrime DAC-10 */
 	case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */
 	case USB_ID(0x16d0, 0x0733): /* Furutech ADL Stratos */
 	case USB_ID(0x16d0, 0x09db): /* NuPrime Audio DAC-9 */
@@ -1806,6 +1807,20 @@ void snd_usb_audioformat_attributes_quirk(struct snd_usb_audio *chip,
 		 */
 		fp->attributes &= ~UAC_EP_CS_ATTR_FILL_MAX;
 		break;
+	case USB_ID(0x1235, 0x8200):  /* Focusrite Scarlett 2i4 2nd gen */
+	case USB_ID(0x1235, 0x8202):  /* Focusrite Scarlett 2i2 2nd gen */
+	case USB_ID(0x1235, 0x8205):  /* Focusrite Scarlett Solo 2nd gen */
+		/*
+		 * Reports that playback should use Synch: Synchronous
+		 * while still providing a feedback endpoint.
+		 * Synchronous causes snapping on some sample rates.
+		 * Force it to use Synch: Asynchronous.
+		 */
+		if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
+			fp->ep_attr &= ~USB_ENDPOINT_SYNCTYPE;
+			fp->ep_attr |= USB_ENDPOINT_SYNC_ASYNC;
+		}
+		break;
 	}
 }
 
diff --git a/sound/usb/usx2y/usbusx2yaudio.c b/sound/usb/usx2y/usbusx2yaudio.c
index 37d290fe9d43..ecaf41265dcd 100644
--- a/sound/usb/usx2y/usbusx2yaudio.c
+++ b/sound/usb/usx2y/usbusx2yaudio.c
@@ -681,6 +681,8 @@ static int usX2Y_rate_set(struct usX2Ydev *usX2Y, int rate)
 			us->submitted =	2*NOOF_SETRATE_URBS;
 			for (i = 0; i < NOOF_SETRATE_URBS; ++i) {
 				struct urb *urb = us->urb[i];
+				if (!urb)
+					continue;
 				if (urb->status) {
 					if (!err)
 						err = -ENODEV;
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index f3327cb56edf..db189945e9b0 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -217,7 +217,7 @@
 #define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 #define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -285,6 +285,7 @@
 #define X86_FEATURE_CQM_MBM_LOCAL	(11*32+ 3) /* LLC Local MBM monitoring */
 #define X86_FEATURE_FENCE_SWAPGS_USER	(11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
 #define X86_FEATURE_FENCE_SWAPGS_KERNEL	(11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
+#define X86_FEATURE_SPLIT_LOCK_DETECT	(11*32+ 6) /* #AC for split lock */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -299,6 +300,7 @@
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_AMD_STIBP_ALWAYS_ON	(13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */
+#define X86_FEATURE_AMD_PPIN		(13*32+23) /* Protected Processor Inventory Number */
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
@@ -367,6 +369,7 @@
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_CORE_CAPABILITIES	(18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
 /*
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index d5e517d1c3dd..12c9684d59ba 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -41,6 +41,10 @@
 
 /* Intel MSRs. Some also available on other CPUs */
 
+#define MSR_TEST_CTRL				0x00000033
+#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT	29
+#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT		BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT)
+
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
 #define SPEC_CTRL_IBRS			BIT(0)	   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP_SHIFT		1	   /* Single Thread Indirect Branch Predictor (STIBP) bit */
@@ -70,6 +74,11 @@
  */
 #define MSR_IA32_UMWAIT_CONTROL_TIME_MASK	(~0x03U)
 
+/* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */
+#define MSR_IA32_CORE_CAPS			  0x000000cf
+#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT  5
+#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT	  BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT)
+
 #define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
 #define NHM_C1_AUTO_DEMOTE		(1UL << 26)
diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h
index 6e060907c163..d25534940bde 100644
--- a/tools/arch/x86/include/asm/orc_types.h
+++ b/tools/arch/x86/include/asm/orc_types.h
@@ -58,8 +58,7 @@
 #define ORC_TYPE_CALL			0
 #define ORC_TYPE_REGS			1
 #define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_SAVE		3
-#define UNWIND_HINT_TYPE_RESTORE	4
+#define UNWIND_HINT_TYPE_RET_OFFSET	3
 
 #ifndef __ASSEMBLY__
 /*
diff --git a/tools/arch/x86/include/uapi/asm/unistd.h b/tools/arch/x86/include/uapi/asm/unistd.h
index 196fdd02b8b1..30d7d04d72d6 100644
--- a/tools/arch/x86/include/uapi/asm/unistd.h
+++ b/tools/arch/x86/include/uapi/asm/unistd.h
@@ -3,7 +3,7 @@
 #define _UAPI_ASM_X86_UNISTD_H
 
 /* x32 syscall flag bit */
-#define __X32_SYSCALL_BIT	0x40000000UL
+#define __X32_SYSCALL_BIT	0x40000000
 
 #ifndef __KERNEL__
 # ifdef __i386__
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 16b9a420e6fd..0efaf45f7367 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -314,6 +314,7 @@ int apply_xbc(const char *path, const char *xbc_path)
 	ret = delete_xbc(path);
 	if (ret < 0) {
 		pr_err("Failed to delete previous boot config: %d\n", ret);
+		free(data);
 		return ret;
 	}
 
@@ -321,24 +322,27 @@ int apply_xbc(const char *path, const char *xbc_path)
 	fd = open(path, O_RDWR | O_APPEND);
 	if (fd < 0) {
 		pr_err("Failed to open %s: %d\n", path, fd);
+		free(data);
 		return fd;
 	}
 	/* TODO: Ensure the @path is initramfs/initrd image */
 	ret = write(fd, data, size + 8);
 	if (ret < 0) {
 		pr_err("Failed to apply a boot config: %d\n", ret);
-		return ret;
+		goto out;
 	}
 	/* Write a magic word of the bootconfig */
 	ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
 	if (ret < 0) {
 		pr_err("Failed to apply a boot config magic: %d\n", ret);
-		return ret;
+		goto out;
 	}
+	ret = 0;
+out:
 	close(fd);
 	free(data);
 
-	return 0;
+	return ret;
 }
 
 int usage(void)
diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c
index 2a7befbd11ad..e17738479edc 100644
--- a/tools/bpf/bpftool/struct_ops.c
+++ b/tools/bpf/bpftool/struct_ops.c
@@ -479,6 +479,7 @@ static int do_unregister(int argc, char **argv)
 
 static int do_register(int argc, char **argv)
 {
+	struct bpf_object_load_attr load_attr = {};
 	const struct bpf_map_def *def;
 	struct bpf_map_info info = {};
 	__u32 info_len = sizeof(info);
@@ -499,7 +500,12 @@ static int do_register(int argc, char **argv)
 
 	set_max_rlimit();
 
-	if (bpf_object__load(obj)) {
+	load_attr.obj = obj;
+	if (verifier_logs)
+		/* log_level1 + log_level2 + stats, but not stable UAPI */
+		load_attr.log_level = 1 + 2 + 4;
+
+	if (bpf_object__load_xattr(&load_attr)) {
 		bpf_object__close(obj);
 		return -1;
 	}
@@ -591,6 +597,8 @@ int do_struct_ops(int argc, char **argv)
 
 	err = cmd_select(cmds, argc, argv, do_help);
 
-	btf__free(btf_vmlinux);
+	if (!IS_ERR(btf_vmlinux))
+		btf__free(btf_vmlinux);
+
 	return err;
 }
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index 39edd68afa8e..8a6f82e56a24 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -8,7 +8,7 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL)
 LIBBPF_SRC := $(abspath ../../lib/bpf)
 BPFOBJ := $(OUTPUT)/libbpf.a
 BPF_INCLUDE := $(OUTPUT)
-INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib)
+INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../lib)
 CFLAGS := -g -Wall
 
 # Try to detect best kernel BTF source
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 3e0c019ef297..3abd4316cd4f 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -98,7 +98,8 @@ FEATURE_TESTS_EXTRA :=                  \
          llvm                           \
          llvm-version                   \
          clang                          \
-         libbpf
+         libbpf                         \
+         libpfm4
 
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
 
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 92012381393a..84f845b9627d 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -69,7 +69,8 @@ FILES=                                          \
          test-libaio.bin			\
          test-libzstd.bin			\
          test-clang-bpf-global-var.bin		\
-         test-file-handle.bin
+         test-file-handle.bin			\
+         test-libpfm4.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -331,6 +332,9 @@ $(OUTPUT)test-clang-bpf-global-var.bin:
 $(OUTPUT)test-file-handle.bin:
 	$(BUILD)
 
+$(OUTPUT)test-libpfm4.bin:
+	$(BUILD) -lpfm
+
 ###############################
 
 clean:
diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c
index 2b0e02c38870..1547bc2c0950 100644
--- a/tools/build/feature/test-libopencsd.c
+++ b/tools/build/feature/test-libopencsd.c
@@ -4,9 +4,9 @@
 /*
  * Check OpenCSD library version is sufficient to provide required features
  */
-#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0))
+#define OCSD_MIN_VER ((0 << 16) | (14 << 8) | (0))
 #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
-#error "OpenCSD >= 0.11.0 is required"
+#error "OpenCSD >= 0.14.0 is required"
 #endif
 
 int main(void)
diff --git a/tools/build/feature/test-libpfm4.c b/tools/build/feature/test-libpfm4.c
new file mode 100644
index 000000000000..af49b259459e
--- /dev/null
+++ b/tools/build/feature/test-libpfm4.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/types.h>
+#include <perfmon/pfmlib.h>
+
+int main(void)
+{
+	pfm_initialize();
+	return 0;
+}
diff --git a/tools/build/feature/test-sync-compare-and-swap.c b/tools/build/feature/test-sync-compare-and-swap.c
index 1e38d1930a97..3bc6b0768a53 100644
--- a/tools/build/feature/test-sync-compare-and-swap.c
+++ b/tools/build/feature/test-sync-compare-and-swap.c
@@ -7,7 +7,7 @@ int main(int argc, char *argv[])
 {
 	uint64_t old, new = argc;
 
-	argv = argv;
+	(void)argv;
 	do {
 		old = __sync_val_compare_and_swap(&x, 0, 0);
 	} while (!__sync_bool_compare_and_swap(&x, old, new));
diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py
index 7427a5ee761b..9d8e9613008a 100644
--- a/tools/cgroup/iocost_monitor.py
+++ b/tools/cgroup/iocost_monitor.py
@@ -159,7 +159,12 @@ class IocgStat:
         else:
             self.inflight_pct = 0
 
-        self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000
+        # vdebt used to be an atomic64_t and is now u64, support both
+        try:
+            self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000
+        except:
+            self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000
+
         self.use_delay = blkg.use_delay.counter.value_()
         self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000
 
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 669d69441a62..4671fbf28842 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -3,9 +3,9 @@
 #define __LINUX_BITS_H
 
 #include <linux/const.h>
+#include <vdso/bits.h>
 #include <asm/bitsperlong.h>
 
-#define BIT(nr)			(UL(1) << (nr))
 #define BIT_ULL(nr)		(ULL(1) << (nr))
 #define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
@@ -18,12 +18,30 @@
  * position @h. For example
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
-#define GENMASK(h, l) \
+#if !defined(__ASSEMBLY__) && \
+	(!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000)
+#include <linux/build_bug.h>
+#define GENMASK_INPUT_CHECK(h, l) \
+	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
+		__builtin_constant_p((l) > (h)), (l) > (h), 0)))
+#else
+/*
+ * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
+ * disable the input check if that is the case.
+ */
+#define GENMASK_INPUT_CHECK(h, l) 0
+#endif
+
+#define __GENMASK(h, l) \
 	(((~UL(0)) - (UL(1) << (l)) + 1) & \
 	 (~UL(0) >> (BITS_PER_LONG - 1 - (h))))
+#define GENMASK(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
 
-#define GENMASK_ULL(h, l) \
+#define __GENMASK_ULL(h, l) \
 	(((~ULL(0)) - (ULL(1) << (l)) + 1) & \
 	 (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
+#define GENMASK_ULL(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
 
 #endif	/* __LINUX_BITS_H */
diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h
new file mode 100644
index 000000000000..cc7070c7439b
--- /dev/null
+++ b/tools/include/linux/build_bug.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BUILD_BUG_H
+#define _LINUX_BUILD_BUG_H
+
+#include <linux/compiler.h>
+
+#ifdef __CHECKER__
+#define BUILD_BUG_ON_ZERO(e) (0)
+#else /* __CHECKER__ */
+/*
+ * Force a compilation error if condition is true, but also produce a
+ * result (of value 0 and type int), so the expression can be used
+ * e.g. in a structure initializer (or where-ever else comma expressions
+ * aren't permitted).
+ */
+#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); })))
+#endif /* __CHECKER__ */
+
+/* Force a compilation error if a constant expression is not a power of 2 */
+#define __BUILD_BUG_ON_NOT_POWER_OF_2(n)	\
+	BUILD_BUG_ON(((n) & ((n) - 1)) != 0)
+#define BUILD_BUG_ON_NOT_POWER_OF_2(n)			\
+	BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0))
+
+/*
+ * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the
+ * expression but avoids the generation of any code, even if that expression
+ * has side-effects.
+ */
+#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e))))
+
+/**
+ * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied
+ *		      error message.
+ * @condition: the condition which the compiler should know is false.
+ *
+ * See BUILD_BUG_ON for description.
+ */
+#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
+
+/**
+ * BUILD_BUG_ON - break compile if a condition is true.
+ * @condition: the condition which the compiler should know is false.
+ *
+ * If you have some code which relies on certain constants being equal, or
+ * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to
+ * detect if someone changes it.
+ */
+#define BUILD_BUG_ON(condition) \
+	BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition)
+
+/**
+ * BUILD_BUG - break compile if used.
+ *
+ * If you have some code that you expect the compiler to eliminate at
+ * build time, you should use BUILD_BUG to detect if it is
+ * unexpectedly used.
+ */
+#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed")
+
+/**
+ * static_assert - check integer constant expression at build time
+ *
+ * static_assert() is a wrapper for the C11 _Static_assert, with a
+ * little macro magic to make the message optional (defaulting to the
+ * stringification of the tested expression).
+ *
+ * Contrary to BUILD_BUG_ON(), static_assert() can be used at global
+ * scope, but requires the expression to be an integer constant
+ * expression (i.e., it is not enough that __builtin_constant_p() is
+ * true for expr).
+ *
+ * Also note that BUILD_BUG_ON() fails the build if the condition is
+ * true, while static_assert() fails the build if the expression is
+ * false.
+ */
+#ifndef static_assert
+#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
+#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
+#endif // static_assert
+
+#endif	/* _LINUX_BUILD_BUG_H */
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 1827c2f973f9..180f7714a5f1 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -10,6 +10,32 @@
 # define __compiletime_error(message)
 #endif
 
+#ifdef __OPTIMIZE__
+# define __compiletime_assert(condition, msg, prefix, suffix)		\
+	do {								\
+		extern void prefix ## suffix(void) __compiletime_error(msg); \
+		if (!(condition))					\
+			prefix ## suffix();				\
+	} while (0)
+#else
+# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0)
+#endif
+
+#define _compiletime_assert(condition, msg, prefix, suffix) \
+	__compiletime_assert(condition, msg, prefix, suffix)
+
+/**
+ * compiletime_assert - break build and emit msg if condition is false
+ * @condition: a compile-time constant condition to check
+ * @msg:       a message to emit if condition is false
+ *
+ * In tradition of POSIX assert, this macro will break the build if the
+ * supplied condition is *false*, emitting the supplied error message if the
+ * compiler has support to do so.
+ */
+#define compiletime_assert(condition, msg) \
+	_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
+
 /* Optimization barrier */
 /* The "volatile" is due to gcc bugs */
 #define barrier() __asm__ __volatile__("": : :"memory")
diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h
index 7b55a55f5911..81b8aae5a855 100644
--- a/tools/include/linux/const.h
+++ b/tools/include/linux/const.h
@@ -1,9 +1,6 @@
 #ifndef _LINUX_CONST_H
 #define _LINUX_CONST_H
 
-#include <uapi/linux/const.h>
-
-#define UL(x)		(_UL(x))
-#define ULL(x)		(_ULL(x))
+#include <vdso/const.h>
 
 #endif /* _LINUX_CONST_H */
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index cba226948a0c..a7e54a08fb54 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -5,6 +5,7 @@
 #include <stdarg.h>
 #include <stddef.h>
 #include <assert.h>
+#include <linux/build_bug.h>
 #include <linux/compiler.h>
 #include <endian.h>
 #include <byteswap.h>
@@ -35,9 +36,6 @@
 	(type *)((char *)__mptr - offsetof(type, member)); })
 #endif
 
-#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
-#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
-
 #ifndef max
 #define max(x, y) ({				\
 	typeof(x) _max1 = (x);			\
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 868bf7996c0f..808b48a93330 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -948,6 +948,8 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_TRANSFER	DRM_IOWR(0xCC, struct drm_syncobj_transfer)
 #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL	DRM_IOWR(0xCD, struct drm_syncobj_timeline_array)
 
+#define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 829c0a48577f..2813e579b480 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -1619,6 +1619,27 @@ struct drm_i915_gem_context_param {
  * By default, new contexts allow persistence.
  */
 #define I915_CONTEXT_PARAM_PERSISTENCE	0xb
+
+/*
+ * I915_CONTEXT_PARAM_RINGSIZE:
+ *
+ * Sets the size of the CS ringbuffer to use for logical ring contexts. This
+ * applies a limit of how many batches can be queued to HW before the caller
+ * is blocked due to lack of space for more commands.
+ *
+ * Only reliably possible to be set prior to first use, i.e. during
+ * construction. At any later point, the current execution must be flushed as
+ * the ring can only be changed while the context is idle. Note, the ringsize
+ * can be specified as a constructor property, see
+ * I915_CONTEXT_CREATE_EXT_SETPARAM, but can also be set later if required.
+ *
+ * Only applies to the current set of engine and lost when those engines
+ * are replaced by a new mapping (see I915_CONTEXT_PARAM_ENGINES).
+ *
+ * Must be between 4 - 512 KiB, in intervals of page size [4 KiB].
+ * Default is 16 KiB.
+ */
+#define I915_CONTEXT_PARAM_RINGSIZE	0xc
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2e29a671d67e..7bbf1b65be10 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1642,7 +1642,7 @@ union bpf_attr {
  * 		ifindex, but doesn't require a map to do so.
  * 	Return
  * 		**XDP_REDIRECT** on success, or the value of the two lower bits
- * 		of the **flags* argument on error.
+ * 		of the *flags* argument on error.
  *
  * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
  * 	Description
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 0d8a6f47711c..a10e3cdc2839 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -163,6 +163,7 @@ struct fscrypt_get_key_status_arg {
 #define FS_IOC_REMOVE_ENCRYPTION_KEY		_IOWR('f', 24, struct fscrypt_remove_key_arg)
 #define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS	_IOWR('f', 25, struct fscrypt_remove_key_arg)
 #define FS_IOC_GET_ENCRYPTION_KEY_STATUS	_IOWR('f', 26, struct fscrypt_get_key_status_arg)
+#define FS_IOC_GET_ENCRYPTION_NONCE		_IOR('f', 27, __u8[16])
 
 /**********************************************************************/
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index e5f32fcec68f..fdd632c833b4 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -474,12 +474,17 @@ struct kvm_s390_mem_op {
 	__u32 size;		/* amount of bytes */
 	__u32 op;		/* type of operation */
 	__u64 buf;		/* buffer in userspace */
-	__u8 ar;		/* the access register number */
-	__u8 reserved[31];	/* should be set to 0 */
+	union {
+		__u8 ar;	/* the access register number */
+		__u32 sida_offset; /* offset into the sida */
+		__u8 reserved[32]; /* should be set to 0 */
+	};
 };
 /* types for kvm_s390_mem_op->op */
 #define KVM_S390_MEMOP_LOGICAL_READ	0
 #define KVM_S390_MEMOP_LOGICAL_WRITE	1
+#define KVM_S390_MEMOP_SIDA_READ	2
+#define KVM_S390_MEMOP_SIDA_WRITE	3
 /* flags for kvm_s390_mem_op->flags */
 #define KVM_S390_MEMOP_F_CHECK_ONLY		(1ULL << 0)
 #define KVM_S390_MEMOP_F_INJECT_EXCEPTION	(1ULL << 1)
@@ -1010,6 +1015,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_NISV_TO_USER 177
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
 #define KVM_CAP_S390_VCPU_RESETS 179
+#define KVM_CAP_S390_PROTECTED 180
+#define KVM_CAP_PPC_SECURE_GUEST 181
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1478,6 +1485,39 @@ struct kvm_enc_region {
 #define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
 #define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
 
+struct kvm_s390_pv_sec_parm {
+	__u64 origin;
+	__u64 length;
+};
+
+struct kvm_s390_pv_unp {
+	__u64 addr;
+	__u64 size;
+	__u64 tweak;
+};
+
+enum pv_cmd_id {
+	KVM_PV_ENABLE,
+	KVM_PV_DISABLE,
+	KVM_PV_SET_SEC_PARMS,
+	KVM_PV_UNPACK,
+	KVM_PV_VERIFY,
+	KVM_PV_PREP_RESET,
+	KVM_PV_UNSHARE_ALL,
+};
+
+struct kvm_pv_cmd {
+	__u32 cmd;	/* Command to be executed */
+	__u16 rc;	/* Ultravisor return code */
+	__u16 rrc;	/* Ultravisor return reason code */
+	__u64 data;	/* Data or address */
+	__u32 flags;    /* flags for future extensions. Must be 0 for now */
+	__u32 reserved[3];
+};
+
+/* Available with KVM_CAP_S390_PROTECTED */
+#define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1628,4 +1668,7 @@ struct kvm_hyperv_eventfd {
 #define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
 #define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
 
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index fc1a64c3447b..923cc162609c 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -5,8 +5,9 @@
 #include <asm/mman.h>
 #include <asm-generic/hugetlb_encode.h>
 
-#define MREMAP_MAYMOVE	1
-#define MREMAP_FIXED	2
+#define MREMAP_MAYMOVE		1
+#define MREMAP_FIXED		2
+#define MREMAP_DONTUNMAP	4
 
 #define OVERCOMMIT_GUESS		0
 #define OVERCOMMIT_ALWAYS		1
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 2e3bc22c6f20..3bac0a8ceab2 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -35,6 +35,7 @@
 
 /* Flags for the clone3() syscall. */
 #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
 
 /*
  * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
@@ -81,6 +82,8 @@
  * @set_tid_size: This defines the size of the array referenced
  *                in @set_tid. This cannot be larger than the
  *                kernel's limit of nested PID namespaces.
+ * @cgroup:       If CLONE_INTO_CGROUP is specified set this to
+ *                a file descriptor for the cgroup.
  *
  * The structure is versioned by size and thus extensible.
  * New struct members must go at the end of the struct and
@@ -97,11 +100,13 @@ struct clone_args {
 	__aligned_u64 tls;
 	__aligned_u64 set_tid;
 	__aligned_u64 set_tid_size;
+	__aligned_u64 cgroup;
 };
 #endif
 
 #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
 #define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
+#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */
 
 /*
  * Scheduling policies
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 40d028eed645..9fe72e4b1373 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -116,4 +116,28 @@
 #define VHOST_VSOCK_SET_GUEST_CID	_IOW(VHOST_VIRTIO, 0x60, __u64)
 #define VHOST_VSOCK_SET_RUNNING		_IOW(VHOST_VIRTIO, 0x61, int)
 
+/* VHOST_VDPA specific defines */
+
+/* Get the device id. The device ids follow the same definition of
+ * the device id defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_DEVICE_ID	_IOR(VHOST_VIRTIO, 0x70, __u32)
+/* Get and set the status. The status bits follow the same definition
+ * of the device status defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_STATUS		_IOR(VHOST_VIRTIO, 0x71, __u8)
+#define VHOST_VDPA_SET_STATUS		_IOW(VHOST_VIRTIO, 0x72, __u8)
+/* Get and set the device config. The device config follows the same
+ * definition of the device config defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_CONFIG		_IOR(VHOST_VIRTIO, 0x73, \
+					     struct vhost_vdpa_config)
+#define VHOST_VDPA_SET_CONFIG		_IOW(VHOST_VIRTIO, 0x74, \
+					     struct vhost_vdpa_config)
+/* Enable/disable the ring. */
+#define VHOST_VDPA_SET_VRING_ENABLE	_IOW(VHOST_VIRTIO, 0x75, \
+					     struct vhost_vring_state)
+/* Get the max ring size. */
+#define VHOST_VDPA_GET_VRING_NUM	_IOR(VHOST_VIRTIO, 0x76, __u16)
+
 #endif
diff --git a/tools/include/vdso/bits.h b/tools/include/vdso/bits.h
new file mode 100644
index 000000000000..6d005a1f5d94
--- /dev/null
+++ b/tools/include/vdso/bits.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_BITS_H
+#define __VDSO_BITS_H
+
+#include <vdso/const.h>
+
+#define BIT(nr)			(UL(1) << (nr))
+
+#endif	/* __VDSO_BITS_H */
diff --git a/tools/include/vdso/const.h b/tools/include/vdso/const.h
new file mode 100644
index 000000000000..94b385ad438d
--- /dev/null
+++ b/tools/include/vdso/const.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_CONST_H
+#define __VDSO_CONST_H
+
+#include <uapi/linux/const.h>
+
+#define UL(x)		(_UL(x))
+#define ULL(x)		(_ULL(x))
+
+#endif /* __VDSO_CONST_H */
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 027b18f7ed8c..82f53d81a7a7 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -90,6 +90,7 @@ struct fs {
 	const char * const	*mounts;
 	char			 path[PATH_MAX];
 	bool			 found;
+	bool			 checked;
 	long			 magic;
 };
 
@@ -111,31 +112,37 @@ static struct fs fs__entries[] = {
 		.name	= "sysfs",
 		.mounts	= sysfs__fs_known_mountpoints,
 		.magic	= SYSFS_MAGIC,
+		.checked = false,
 	},
 	[FS__PROCFS] = {
 		.name	= "proc",
 		.mounts	= procfs__known_mountpoints,
 		.magic	= PROC_SUPER_MAGIC,
+		.checked = false,
 	},
 	[FS__DEBUGFS] = {
 		.name	= "debugfs",
 		.mounts	= debugfs__known_mountpoints,
 		.magic	= DEBUGFS_MAGIC,
+		.checked = false,
 	},
 	[FS__TRACEFS] = {
 		.name	= "tracefs",
 		.mounts	= tracefs__known_mountpoints,
 		.magic	= TRACEFS_MAGIC,
+		.checked = false,
 	},
 	[FS__HUGETLBFS] = {
 		.name	= "hugetlbfs",
 		.mounts = hugetlbfs__known_mountpoints,
 		.magic	= HUGETLBFS_MAGIC,
+		.checked = false,
 	},
 	[FS__BPF_FS] = {
 		.name	= "bpf",
 		.mounts = bpf_fs__known_mountpoints,
 		.magic	= BPF_FS_MAGIC,
+		.checked = false,
 	},
 };
 
@@ -158,6 +165,7 @@ static bool fs__read_mounts(struct fs *fs)
 	}
 
 	fclose(fp);
+	fs->checked = true;
 	return fs->found = found;
 }
 
@@ -220,6 +228,7 @@ static bool fs__env_override(struct fs *fs)
 		return false;
 
 	fs->found = true;
+	fs->checked = true;
 	strncpy(fs->path, override_path, sizeof(fs->path) - 1);
 	fs->path[sizeof(fs->path) - 1] = '\0';
 	return true;
@@ -246,6 +255,14 @@ static const char *fs__mountpoint(int idx)
 	if (fs->found)
 		return (const char *)fs->path;
 
+	/* the mount point was already checked for the mount point
+	 * but and did not exist, so return NULL to avoid scanning again.
+	 * This makes the found and not found paths cost equivalent
+	 * in case of multiple calls.
+	 */
+	if (fs->checked)
+		return NULL;
+
 	return fs__get_mountpoint(fs);
 }
 
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index 936edb95e1f3..aa222ca30311 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -18,6 +18,18 @@
 	const char *name##__mount(void);	\
 	bool name##__configured(void);		\
 
+/*
+ * The xxxx__mountpoint() entry points find the first match mount point for each
+ * filesystems listed below, where xxxx is the filesystem type.
+ *
+ * The interface is as follows:
+ *
+ * - If a mount point is found on first call, it is cached and used for all
+ *   subsequent calls.
+ *
+ * - If a mount point is not found, NULL is returned on first call and all
+ *   subsequent calls.
+ */
 FS(sysfs)
 FS(procfs)
 FS(debugfs)
diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
new file mode 100644
index 000000000000..777c20f6b604
--- /dev/null
+++ b/tools/lib/api/io.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Lightweight buffered reading library.
+ *
+ * Copyright 2019 Google LLC.
+ */
+#ifndef __API_IO__
+#define __API_IO__
+
+#include <stdlib.h>
+#include <unistd.h>
+
+struct io {
+	/* File descriptor being read/ */
+	int fd;
+	/* Size of the read buffer. */
+	unsigned int buf_len;
+	/* Pointer to storage for buffering read. */
+	char *buf;
+	/* End of the storage. */
+	char *end;
+	/* Currently accessed data pointer. */
+	char *data;
+	/* Set true on when the end of file on read error. */
+	bool eof;
+};
+
+static inline void io__init(struct io *io, int fd,
+			    char *buf, unsigned int buf_len)
+{
+	io->fd = fd;
+	io->buf_len = buf_len;
+	io->buf = buf;
+	io->end = buf;
+	io->data = buf;
+	io->eof = false;
+}
+
+/* Reads one character from the "io" file with similar semantics to fgetc. */
+static inline int io__get_char(struct io *io)
+{
+	char *ptr = io->data;
+
+	if (io->eof)
+		return -1;
+
+	if (ptr == io->end) {
+		ssize_t n = read(io->fd, io->buf, io->buf_len);
+
+		if (n <= 0) {
+			io->eof = true;
+			return -1;
+		}
+		ptr = &io->buf[0];
+		io->end = &io->buf[n];
+	}
+	io->data = ptr + 1;
+	return *ptr;
+}
+
+/* Read a hexadecimal value with no 0x prefix into the out argument hex. If the
+ * first character isn't hexadecimal returns -2, io->eof returns -1, otherwise
+ * returns the character after the hexadecimal value which may be -1 for eof.
+ * If the read value is larger than a u64 the high-order bits will be dropped.
+ */
+static inline int io__get_hex(struct io *io, __u64 *hex)
+{
+	bool first_read = true;
+
+	*hex = 0;
+	while (true) {
+		int ch = io__get_char(io);
+
+		if (ch < 0)
+			return ch;
+		if (ch >= '0' && ch <= '9')
+			*hex = (*hex << 4) | (ch - '0');
+		else if (ch >= 'a' && ch <= 'f')
+			*hex = (*hex << 4) | (ch - 'a' + 10);
+		else if (ch >= 'A' && ch <= 'F')
+			*hex = (*hex << 4) | (ch - 'A' + 10);
+		else if (first_read)
+			return -2;
+		else
+			return ch;
+		first_read = false;
+	}
+}
+
+/* Read a positive decimal value with out argument dec. If the first character
+ * isn't a decimal returns -2, io->eof returns -1, otherwise returns the
+ * character after the decimal value which may be -1 for eof. If the read value
+ * is larger than a u64 the high-order bits will be dropped.
+ */
+static inline int io__get_dec(struct io *io, __u64 *dec)
+{
+	bool first_read = true;
+
+	*dec = 0;
+	while (true) {
+		int ch = io__get_char(io);
+
+		if (ch < 0)
+			return ch;
+		if (ch >= '0' && ch <= '9')
+			*dec = (*dec * 10) + ch - '0';
+		else if (first_read)
+			return -2;
+		else
+			return ch;
+		first_read = false;
+	}
+}
+
+#endif /* __API_IO__ */
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index f3f3c3fb98cb..48a9c7c69ef1 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -148,11 +148,11 @@ struct pt_regs;
 #define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
 #define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
 #define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), grps[14])
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14])
 #define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
 #define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
 #define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), pdw.addr)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr)
 
 #elif defined(bpf_target_arm)
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ff9174282a8c..8f480e29a6b0 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -178,6 +178,8 @@ struct bpf_capabilities {
 	__u32 array_mmap:1;
 	/* BTF_FUNC_GLOBAL is supported */
 	__u32 btf_func_global:1;
+	/* kernel support for expected_attach_type in BPF_PROG_LOAD */
+	__u32 exp_attach_type:1;
 };
 
 enum reloc_type {
@@ -194,6 +196,22 @@ struct reloc_desc {
 	int sym_off;
 };
 
+struct bpf_sec_def;
+
+typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec,
+					struct bpf_program *prog);
+
+struct bpf_sec_def {
+	const char *sec;
+	size_t len;
+	enum bpf_prog_type prog_type;
+	enum bpf_attach_type expected_attach_type;
+	bool is_exp_attach_type_optional;
+	bool is_attachable;
+	bool is_attach_btf;
+	attach_fn_t attach_fn;
+};
+
 /*
  * bpf_prog should be a better name but it has been used in
  * linux/filter.h.
@@ -204,6 +222,7 @@ struct bpf_program {
 	char *name;
 	int prog_ifindex;
 	char *section_name;
+	const struct bpf_sec_def *sec_def;
 	/* section_name with / replaced by _; makes recursive pinning
 	 * in bpf_object__pin_programs easier
 	 */
@@ -3316,6 +3335,37 @@ static int bpf_object__probe_array_mmap(struct bpf_object *obj)
 }
 
 static int
+bpf_object__probe_exp_attach_type(struct bpf_object *obj)
+{
+	struct bpf_load_program_attr attr;
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int fd;
+
+	memset(&attr, 0, sizeof(attr));
+	/* use any valid combination of program type and (optional)
+	 * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
+	 * to see if kernel supports expected_attach_type field for
+	 * BPF_PROG_LOAD command
+	 */
+	attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
+	attr.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE;
+	attr.insns = insns;
+	attr.insns_cnt = ARRAY_SIZE(insns);
+	attr.license = "GPL";
+
+	fd = bpf_load_program_xattr(&attr, NULL, 0);
+	if (fd >= 0) {
+		obj->caps.exp_attach_type = 1;
+		close(fd);
+		return 1;
+	}
+	return 0;
+}
+
+static int
 bpf_object__probe_caps(struct bpf_object *obj)
 {
 	int (*probe_fn[])(struct bpf_object *obj) = {
@@ -3325,6 +3375,7 @@ bpf_object__probe_caps(struct bpf_object *obj)
 		bpf_object__probe_btf_func_global,
 		bpf_object__probe_btf_datasec,
 		bpf_object__probe_array_mmap,
+		bpf_object__probe_exp_attach_type,
 	};
 	int i, ret;
 
@@ -4861,7 +4912,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 
 	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
 	load_attr.prog_type = prog->type;
-	load_attr.expected_attach_type = prog->expected_attach_type;
+	/* old kernels might not support specifying expected_attach_type */
+	if (!prog->caps->exp_attach_type && prog->sec_def &&
+	    prog->sec_def->is_exp_attach_type_optional)
+		load_attr.expected_attach_type = 0;
+	else
+		load_attr.expected_attach_type = prog->expected_attach_type;
 	if (prog->caps->name)
 		load_attr.name = prog->name;
 	load_attr.insns = insns;
@@ -5062,6 +5118,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 	return 0;
 }
 
+static const struct bpf_sec_def *find_sec_def(const char *sec_name);
+
 static struct bpf_object *
 __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		   const struct bpf_object_open_opts *opts)
@@ -5117,24 +5175,17 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	bpf_object__elf_finish(obj);
 
 	bpf_object__for_each_program(prog, obj) {
-		enum bpf_prog_type prog_type;
-		enum bpf_attach_type attach_type;
-
-		if (prog->type != BPF_PROG_TYPE_UNSPEC)
-			continue;
-
-		err = libbpf_prog_type_by_name(prog->section_name, &prog_type,
-					       &attach_type);
-		if (err == -ESRCH)
+		prog->sec_def = find_sec_def(prog->section_name);
+		if (!prog->sec_def)
 			/* couldn't guess, but user might manually specify */
 			continue;
-		if (err)
-			goto out;
 
-		bpf_program__set_type(prog, prog_type);
-		bpf_program__set_expected_attach_type(prog, attach_type);
-		if (prog_type == BPF_PROG_TYPE_TRACING ||
-		    prog_type == BPF_PROG_TYPE_EXT)
+		bpf_program__set_type(prog, prog->sec_def->prog_type);
+		bpf_program__set_expected_attach_type(prog,
+				prog->sec_def->expected_attach_type);
+
+		if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING ||
+		    prog->sec_def->prog_type == BPF_PROG_TYPE_EXT)
 			prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
 	}
 
@@ -6223,23 +6274,32 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	prog->expected_attach_type = type;
 }
 
-#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, btf, atype) \
-	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, btf, atype }
+#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional,	    \
+			  attachable, attach_btf)			    \
+	{								    \
+		.sec = string,						    \
+		.len = sizeof(string) - 1,				    \
+		.prog_type = ptype,					    \
+		.expected_attach_type = eatype,				    \
+		.is_exp_attach_type_optional = eatype_optional,		    \
+		.is_attachable = attachable,				    \
+		.is_attach_btf = attach_btf,				    \
+	}
 
 /* Programs that can NOT be attached. */
 #define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0)
 
 /* Programs that can be attached. */
 #define BPF_APROG_SEC(string, ptype, atype) \
-	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, 0, atype)
+	BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0)
 
 /* Programs that must specify expected attach type at load time. */
 #define BPF_EAPROG_SEC(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, 0, eatype)
+	BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0)
 
 /* Programs that use BTF to identify attach point */
 #define BPF_PROG_BTF(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, 0, 1, 0)
+	BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1)
 
 /* Programs that can be attached but attach type can't be identified by section
  * name. Kept for backward compatibility.
@@ -6253,11 +6313,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	__VA_ARGS__							    \
 }
 
-struct bpf_sec_def;
-
-typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec,
-					struct bpf_program *prog);
-
 static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
 				      struct bpf_program *prog);
 static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
@@ -6269,17 +6324,6 @@ static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
 static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
 				   struct bpf_program *prog);
 
-struct bpf_sec_def {
-	const char *sec;
-	size_t len;
-	enum bpf_prog_type prog_type;
-	enum bpf_attach_type expected_attach_type;
-	bool is_attachable;
-	bool is_attach_btf;
-	enum bpf_attach_type attach_type;
-	attach_fn_t attach_fn;
-};
-
 static const struct bpf_sec_def section_defs[] = {
 	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
 	BPF_PROG_SEC("sk_reuseport",		BPF_PROG_TYPE_SK_REUSEPORT),
@@ -6713,7 +6757,7 @@ int libbpf_attach_type_by_name(const char *name,
 			continue;
 		if (!section_defs[i].is_attachable)
 			return -EINVAL;
-		*attach_type = section_defs[i].attach_type;
+		*attach_type = section_defs[i].expected_attach_type;
 		return 0;
 	}
 	pr_debug("failed to guess attach type based on ELF section name '%s'\n", name);
@@ -7542,7 +7586,6 @@ static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
 struct bpf_link *
 bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
 {
-	const struct bpf_sec_def *sec_def;
 	enum bpf_attach_type attach_type;
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
@@ -7561,11 +7604,6 @@ bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
 	link->detach = &bpf_link__detach_fd;
 
 	attach_type = bpf_program__get_expected_attach_type(prog);
-	if (!attach_type) {
-		sec_def = find_sec_def(bpf_program__title(prog, false));
-		if (sec_def)
-			attach_type = sec_def->attach_type;
-	}
 	link_fd = bpf_link_create(prog_fd, cgroup_fd, attach_type, NULL);
 	if (link_fd < 0) {
 		link_fd = -errno;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 44df1d3e7287..f1dacecb1619 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -458,7 +458,7 @@ struct xdp_link_info {
 
 struct bpf_xdp_set_link_opts {
 	size_t sz;
-	__u32 old_fd;
+	int old_fd;
 };
 #define bpf_xdp_set_link_opts__last_field old_fd
 
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 18b5319025e1..312f887570b2 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -142,7 +142,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
 		struct ifinfomsg ifinfo;
 		char             attrbuf[64];
 	} req;
-	__u32 nl_pid;
+	__u32 nl_pid = 0;
 
 	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0)
@@ -288,7 +288,7 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 {
 	struct xdp_id_md xdp_id = {};
 	int sock, ret;
-	__u32 nl_pid;
+	__u32 nl_pid = 0;
 	__u32 mask;
 
 	if (flags & ~XDP_FLAGS_MASK || !info_size)
@@ -321,7 +321,9 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 
 static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags)
 {
-	if (info->attach_mode != XDP_ATTACHED_MULTI)
+	flags &= XDP_FLAGS_MODES;
+
+	if (info->attach_mode != XDP_ATTACHED_MULTI && !flags)
 		return info->prog_id;
 	if (flags & XDP_FLAGS_DRV_MODE)
 		return info->drv_prog_id;
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index f93f4e703e4c..ca0215047c32 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -247,7 +247,7 @@ out:
 
 int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
 {
-	if (idx < cpus->nr)
+	if (cpus && idx < cpus->nr)
 		return cpus->map[idx];
 
 	return -1;
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 5b9f2ca50591..6a875a0f01bb 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -11,10 +11,8 @@
 #include <internal/mmap.h>
 #include <internal/cpumap.h>
 #include <internal/threadmap.h>
-#include <internal/xyarray.h>
 #include <internal/lib.h>
 #include <linux/zalloc.h>
-#include <sys/ioctl.h>
 #include <stdlib.h>
 #include <errno.h>
 #include <unistd.h>
@@ -125,8 +123,10 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
 	perf_cpu_map__put(evlist->cpus);
+	perf_cpu_map__put(evlist->all_cpus);
 	perf_thread_map__put(evlist->threads);
 	evlist->cpus = NULL;
+	evlist->all_cpus = NULL;
 	evlist->threads = NULL;
 	fdarray__exit(&evlist->pollfd);
 }
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index af9def589863..d2414144eb8c 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -151,6 +151,8 @@ struct option {
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
 #define OPT_CALLBACK(s, l, v, a, h, f) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) }
+#define OPT_CALLBACK_SET(s, l, v, os, a, h, f) \
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .set = check_vtype(os, bool *)}
 #define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
 #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
index 1a7a9f877095..e335ac2b9e19 100644
--- a/tools/lib/symbol/kallsyms.c
+++ b/tools/lib/symbol/kallsyms.c
@@ -1,7 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "symbol/kallsyms.h"
+#include "api/io.h"
 #include <stdio.h>
-#include <stdlib.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 
 u8 kallsyms2elf_type(char type)
 {
@@ -15,74 +17,62 @@ bool kallsyms__is_function(char symbol_type)
 	return symbol_type == 'T' || symbol_type == 'W';
 }
 
-/*
- * While we find nice hex chars, build a long_val.
- * Return number of chars processed.
- */
-int hex2u64(const char *ptr, u64 *long_val)
+static void read_to_eol(struct io *io)
 {
-	char *p;
+	int ch;
 
-	*long_val = strtoull(ptr, &p, 16);
-
-	return p - ptr;
+	for (;;) {
+		ch = io__get_char(io);
+		if (ch < 0 || ch == '\n')
+			return;
+	}
 }
 
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start))
 {
-	char *line = NULL;
-	size_t n;
-	int err = -1;
-	FILE *file = fopen(filename, "r");
-
-	if (file == NULL)
-		goto out_failure;
-
-	err = 0;
+	struct io io;
+	char bf[BUFSIZ];
+	int err;
 
-	while (!feof(file)) {
-		u64 start;
-		int line_len, len;
-		char symbol_type;
-		char *symbol_name;
+	io.fd = open(filename, O_RDONLY, 0);
 
-		line_len = getline(&line, &n, file);
-		if (line_len < 0 || !line)
-			break;
+	if (io.fd < 0)
+		return -1;
 
-		line[--line_len] = '\0'; /* \n */
+	io__init(&io, io.fd, bf, sizeof(bf));
 
-		len = hex2u64(line, &start);
+	err = 0;
+	while (!io.eof) {
+		__u64 start;
+		int ch;
+		size_t i;
+		char symbol_type;
+		char symbol_name[KSYM_NAME_LEN + 1];
 
-		/* Skip the line if we failed to parse the address. */
-		if (!len)
+		if (io__get_hex(&io, &start) != ' ') {
+			read_to_eol(&io);
 			continue;
-
-		len++;
-		if (len + 2 >= line_len)
+		}
+		symbol_type = io__get_char(&io);
+		if (io__get_char(&io) != ' ') {
+			read_to_eol(&io);
 			continue;
-
-		symbol_type = line[len];
-		len += 2;
-		symbol_name = line + len;
-		len = line_len - len;
-
-		if (len >= KSYM_NAME_LEN) {
-			err = -1;
-			break;
 		}
+		for (i = 0; i < sizeof(symbol_name); i++) {
+			ch = io__get_char(&io);
+			if (ch < 0 || ch == '\n')
+				break;
+			symbol_name[i]  = ch;
+		}
+		symbol_name[i]  = '\0';
 
 		err = process_symbol(arg, symbol_name, symbol_type, start);
 		if (err)
 			break;
 	}
 
-	free(line);
-	fclose(file);
+	close(io.fd);
 	return err;
-
-out_failure:
-	return -1;
 }
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
index bd988f7b18d4..72ab9870454b 100644
--- a/tools/lib/symbol/kallsyms.h
+++ b/tools/lib/symbol/kallsyms.h
@@ -18,8 +18,6 @@ static inline u8 kallsyms2elf_binding(char type)
 	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
 }
 
-int hex2u64(const char *ptr, u64 *long_val);
-
 u8 kallsyms2elf_type(char type);
 
 bool kallsyms__is_function(char symbol_type);
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index b887e7437d67..27f3b07fdae8 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -438,7 +438,7 @@ void *kbuffer_translate_data(int swap, void *data, unsigned int *size)
 	case KBUFFER_TYPE_TIME_EXTEND:
 	case KBUFFER_TYPE_TIME_STAMP:
 		return NULL;
-	};
+	}
 
 	*size = length;
 
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 20eed719542e..c271aeeb227d 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1958,7 +1958,8 @@ static char *op_to_str(struct tep_event_filter *filter, struct tep_filter_arg *a
 				default:
 					break;
 				}
-				asprintf(&str, val ? "TRUE" : "FALSE");
+				if (asprintf(&str, val ? "TRUE" : "FALSE") < 0)
+					str = NULL;
 				break;
 			}
 		}
@@ -1976,7 +1977,8 @@ static char *op_to_str(struct tep_event_filter *filter, struct tep_filter_arg *a
 			break;
 		}
 
-		asprintf(&str, "(%s) %s (%s)", left, op, right);
+		if (asprintf(&str, "(%s) %s (%s)", left, op, right) < 0)
+			str = NULL;
 		break;
 
 	case TEP_FILTER_OP_NOT:
@@ -1992,10 +1994,12 @@ static char *op_to_str(struct tep_event_filter *filter, struct tep_filter_arg *a
 			right_val = 0;
 		if (right_val >= 0) {
 			/* just return the opposite */
-			asprintf(&str, right_val ? "FALSE" : "TRUE");
+			if (asprintf(&str, right_val ? "FALSE" : "TRUE") < 0)
+				str = NULL;
 			break;
 		}
-		asprintf(&str, "%s(%s)", op, right);
+		if (asprintf(&str, "%s(%s)", op, right) < 0)
+			str = NULL;
 		break;
 
 	default:
@@ -2011,7 +2015,8 @@ static char *val_to_str(struct tep_event_filter *filter, struct tep_filter_arg *
 {
 	char *str = NULL;
 
-	asprintf(&str, "%lld", arg->value.val);
+	if (asprintf(&str, "%lld", arg->value.val) < 0)
+		str = NULL;
 
 	return str;
 }
@@ -2069,7 +2074,8 @@ static char *exp_to_str(struct tep_event_filter *filter, struct tep_filter_arg *
 		break;
 	}
 
-	asprintf(&str, "%s %s %s", lstr, op, rstr);
+	if (asprintf(&str, "%s %s %s", lstr, op, rstr) < 0)
+		str = NULL;
 out:
 	free(lstr);
 	free(rstr);
@@ -2113,7 +2119,8 @@ static char *num_to_str(struct tep_event_filter *filter, struct tep_filter_arg *
 		if (!op)
 			op = "<=";
 
-		asprintf(&str, "%s %s %s", lstr, op, rstr);
+		if (asprintf(&str, "%s %s %s", lstr, op, rstr) < 0)
+			str = NULL;
 		break;
 
 	default:
@@ -2148,8 +2155,9 @@ static char *str_to_str(struct tep_event_filter *filter, struct tep_filter_arg *
 		if (!op)
 			op = "!~";
 
-		asprintf(&str, "%s %s \"%s\"",
-			 arg->str.field->name, op, arg->str.val);
+		if (asprintf(&str, "%s %s \"%s\"",
+			 arg->str.field->name, op, arg->str.val) < 0)
+			str = NULL;
 		break;
 
 	default:
@@ -2165,7 +2173,8 @@ static char *arg_to_str(struct tep_event_filter *filter, struct tep_filter_arg *
 
 	switch (arg->type) {
 	case TEP_FILTER_ARG_BOOLEAN:
-		asprintf(&str, arg->boolean.value ? "TRUE" : "FALSE");
+		if (asprintf(&str, arg->boolean.value ? "TRUE" : "FALSE") < 0)
+			str = NULL;
 		return str;
 
 	case TEP_FILTER_ARG_OP:
diff --git a/tools/objtool/Build b/tools/objtool/Build
index 66f44f5cd2a6..b7222d5cc7bc 100644
--- a/tools/objtool/Build
+++ b/tools/objtool/Build
@@ -1,11 +1,16 @@
 objtool-y += arch/$(SRCARCH)/
+
+objtool-y += weak.o
+
+objtool-$(SUBCMD_CHECK) += check.o
+objtool-$(SUBCMD_CHECK) += special.o
+objtool-$(SUBCMD_ORC) += check.o
+objtool-$(SUBCMD_ORC) += orc_gen.o
+objtool-$(SUBCMD_ORC) += orc_dump.o
+
 objtool-y += builtin-check.o
 objtool-y += builtin-orc.o
-objtool-y += check.o
-objtool-y += orc_gen.o
-objtool-y += orc_dump.o
 objtool-y += elf.o
-objtool-y += special.o
 objtool-y += objtool.o
 
 objtool-y += libstring.o
diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt
index de094670050b..0542e46c7552 100644
--- a/tools/objtool/Documentation/stack-validation.txt
+++ b/tools/objtool/Documentation/stack-validation.txt
@@ -289,6 +289,47 @@ they mean, and suggestions for how to fix them.
       might be corrupt due to a gcc bug.  For more details, see:
       https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646
 
+9. file.o: warning: objtool: funcA() call to funcB() with UACCESS enabled
+
+   This means that an unexpected call to a non-whitelisted function exists
+   outside of arch-specific guards.
+   X86: SMAP (stac/clac): __uaccess_begin()/__uaccess_end()
+   ARM: PAN: uaccess_enable()/uaccess_disable()
+
+   These functions should be called to denote a minimal critical section around
+   access to __user variables. See also: https://lwn.net/Articles/517475/
+
+   The intention of the warning is to prevent calls to funcB() from eventually
+   calling schedule(), potentially leaking the AC flags state, and not
+   restoring them correctly.
+
+   It also helps verify that there are no unexpected calls to funcB() which may
+   access user space pages with protections against doing so disabled.
+
+   To fix, either:
+   1) remove explicit calls to funcB() from funcA().
+   2) add the correct guards before and after calls to low level functions like
+      __get_user_size()/__put_user_size().
+   3) add funcB to uaccess_safe_builtin whitelist in tools/objtool/check.c, if
+      funcB obviously does not call schedule(), and is marked notrace (since
+      function tracing inserts additional calls, which is not obvious from the
+      sources).
+
+10. file.o: warning: func()+0x5c: alternative modifies stack
+
+    This means that an alternative includes instructions that modify the
+    stack. The problem is that there is only one ORC unwind table, this means
+    that the ORC unwind entries must be valid for each of the alternatives.
+    The easiest way to enforce this is to ensure alternatives do not contain
+    any ORC entries, which in turn implies the above constraint.
+
+11. file.o: warning: unannotated intra-function call
+
+   This warning means that a direct call is done to a destination which
+   is not at the beginning of a function. If this is a legit call, you
+   can remove this warning by putting the ANNOTATE_INTRA_FUNCTION_CALL
+   directive right before the call.
+
 
 If the error doesn't seem to make sense, it could be a bug in objtool.
 Feel free to ask the objtool maintainer for help.
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index f591c4d1b6fe..7770edcda3a0 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -35,7 +35,8 @@ all: $(OBJTOOL)
 
 INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
-	    -I$(srctree)/tools/arch/$(SRCARCH)/include
+	    -I$(srctree)/tools/arch/$(SRCARCH)/include	\
+	    -I$(srctree)/tools/objtool/arch/$(SRCARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
 CFLAGS   := -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
 LDFLAGS  += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
@@ -45,14 +46,24 @@ elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E -
 CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED)
 
 AWK = awk
+
+SUBCMD_CHECK := n
+SUBCMD_ORC := n
+
+ifeq ($(SRCARCH),x86)
+	SUBCMD_CHECK := y
+	SUBCMD_ORC := y
+endif
+
+export SUBCMD_CHECK SUBCMD_ORC
 export srctree OUTPUT CFLAGS SRCARCH AWK
 include $(srctree)/tools/build/Makefile.include
 
 $(OBJTOOL_IN): fixdep FORCE
+	@$(CONFIG_SHELL) ./sync-check.sh
 	@$(MAKE) $(build)=objtool
 
 $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
-	@$(CONFIG_SHELL) ./sync-check.sh
 	$(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
 
 
diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h
index ced3765c4f44..eda15a5a285e 100644
--- a/tools/objtool/arch.h
+++ b/tools/objtool/arch.h
@@ -8,9 +8,11 @@
 
 #include <stdbool.h>
 #include <linux/list.h>
-#include "elf.h"
+#include "objtool.h"
 #include "cfi.h"
 
+#include <asm/orc_types.h>
+
 enum insn_type {
 	INSN_JUMP_CONDITIONAL,
 	INSN_JUMP_UNCONDITIONAL,
@@ -20,7 +22,6 @@ enum insn_type {
 	INSN_CALL_DYNAMIC,
 	INSN_RETURN,
 	INSN_CONTEXT_SWITCH,
-	INSN_STACK,
 	INSN_BUG,
 	INSN_NOP,
 	INSN_STAC,
@@ -64,15 +65,23 @@ struct op_src {
 struct stack_op {
 	struct op_dest dest;
 	struct op_src src;
+	struct list_head list;
 };
 
-void arch_initial_func_cfi_state(struct cfi_state *state);
+struct instruction;
+
+void arch_initial_func_cfi_state(struct cfi_init_state *state);
 
-int arch_decode_instruction(struct elf *elf, struct section *sec,
+int arch_decode_instruction(const struct elf *elf, const struct section *sec,
 			    unsigned long offset, unsigned int maxlen,
 			    unsigned int *len, enum insn_type *type,
-			    unsigned long *immediate, struct stack_op *op);
+			    unsigned long *immediate,
+			    struct list_head *ops_list);
 
 bool arch_callee_saved_reg(unsigned char reg);
 
+unsigned long arch_jump_destination(struct instruction *insn);
+
+unsigned long arch_dest_rela_offset(int addend);
+
 #endif /* _ARCH_H */
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index a62e032863a8..4b504fc90bbb 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -11,6 +11,7 @@
 #include "../../../arch/x86/lib/inat.c"
 #include "../../../arch/x86/lib/insn.c"
 
+#include "../../check.h"
 #include "../../elf.h"
 #include "../../arch.h"
 #include "../../warn.h"
@@ -26,7 +27,7 @@ static unsigned char op_to_cfi_reg[][2] = {
 	{CFI_DI, CFI_R15},
 };
 
-static int is_x86_64(struct elf *elf)
+static int is_x86_64(const struct elf *elf)
 {
 	switch (elf->ehdr.e_machine) {
 	case EM_X86_64:
@@ -66,16 +67,34 @@ bool arch_callee_saved_reg(unsigned char reg)
 	}
 }
 
-int arch_decode_instruction(struct elf *elf, struct section *sec,
+unsigned long arch_dest_rela_offset(int addend)
+{
+	return addend + 4;
+}
+
+unsigned long arch_jump_destination(struct instruction *insn)
+{
+	return insn->offset + insn->len + insn->immediate;
+}
+
+#define ADD_OP(op) \
+	if (!(op = calloc(1, sizeof(*op)))) \
+		return -1; \
+	else for (list_add_tail(&op->list, ops_list); op; op = NULL)
+
+int arch_decode_instruction(const struct elf *elf, const struct section *sec,
 			    unsigned long offset, unsigned int maxlen,
 			    unsigned int *len, enum insn_type *type,
-			    unsigned long *immediate, struct stack_op *op)
+			    unsigned long *immediate,
+			    struct list_head *ops_list)
 {
 	struct insn insn;
 	int x86_64, sign;
 	unsigned char op1, op2, rex = 0, rex_b = 0, rex_r = 0, rex_w = 0,
 		      rex_x = 0, modrm = 0, modrm_mod = 0, modrm_rm = 0,
 		      modrm_reg = 0, sib = 0;
+	struct stack_op *op = NULL;
+	struct symbol *sym;
 
 	x86_64 = is_x86_64(elf);
 	if (x86_64 == -1)
@@ -85,7 +104,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 	insn_get_length(&insn);
 
 	if (!insn_complete(&insn)) {
-		WARN_FUNC("can't decode instruction", sec, offset);
+		WARN("can't decode instruction at %s:0x%lx", sec->name, offset);
 		return -1;
 	}
 
@@ -123,40 +142,44 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		if (rex_w && !rex_b && modrm_mod == 3 && modrm_rm == 4) {
 
 			/* add/sub reg, %rsp */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_ADD;
-			op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_SP;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_ADD;
+				op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = CFI_SP;
+			}
 		}
 		break;
 
 	case 0x50 ... 0x57:
 
 		/* push reg */
-		*type = INSN_STACK;
-		op->src.type = OP_SRC_REG;
-		op->src.reg = op_to_cfi_reg[op1 & 0x7][rex_b];
-		op->dest.type = OP_DEST_PUSH;
+		ADD_OP(op) {
+			op->src.type = OP_SRC_REG;
+			op->src.reg = op_to_cfi_reg[op1 & 0x7][rex_b];
+			op->dest.type = OP_DEST_PUSH;
+		}
 
 		break;
 
 	case 0x58 ... 0x5f:
 
 		/* pop reg */
-		*type = INSN_STACK;
-		op->src.type = OP_SRC_POP;
-		op->dest.type = OP_DEST_REG;
-		op->dest.reg = op_to_cfi_reg[op1 & 0x7][rex_b];
+		ADD_OP(op) {
+			op->src.type = OP_SRC_POP;
+			op->dest.type = OP_DEST_REG;
+			op->dest.reg = op_to_cfi_reg[op1 & 0x7][rex_b];
+		}
 
 		break;
 
 	case 0x68:
 	case 0x6a:
 		/* push immediate */
-		*type = INSN_STACK;
-		op->src.type = OP_SRC_CONST;
-		op->dest.type = OP_DEST_PUSH;
+		ADD_OP(op) {
+			op->src.type = OP_SRC_CONST;
+			op->dest.type = OP_DEST_PUSH;
+		}
 		break;
 
 	case 0x70 ... 0x7f:
@@ -170,12 +193,13 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 
 		if (modrm == 0xe4) {
 			/* and imm, %rsp */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_AND;
-			op->src.reg = CFI_SP;
-			op->src.offset = insn.immediate.value;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_SP;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_AND;
+				op->src.reg = CFI_SP;
+				op->src.offset = insn.immediate.value;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = CFI_SP;
+			}
 			break;
 		}
 
@@ -187,34 +211,37 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 			break;
 
 		/* add/sub imm, %rsp */
-		*type = INSN_STACK;
-		op->src.type = OP_SRC_ADD;
-		op->src.reg = CFI_SP;
-		op->src.offset = insn.immediate.value * sign;
-		op->dest.type = OP_DEST_REG;
-		op->dest.reg = CFI_SP;
+		ADD_OP(op) {
+			op->src.type = OP_SRC_ADD;
+			op->src.reg = CFI_SP;
+			op->src.offset = insn.immediate.value * sign;
+			op->dest.type = OP_DEST_REG;
+			op->dest.reg = CFI_SP;
+		}
 		break;
 
 	case 0x89:
 		if (rex_w && !rex_r && modrm_mod == 3 && modrm_reg == 4) {
 
 			/* mov %rsp, reg */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_REG;
-			op->src.reg = CFI_SP;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b];
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG;
+				op->src.reg = CFI_SP;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b];
+			}
 			break;
 		}
 
 		if (rex_w && !rex_b && modrm_mod == 3 && modrm_rm == 4) {
 
 			/* mov reg, %rsp */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_REG;
-			op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_SP;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG;
+				op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = CFI_SP;
+			}
 			break;
 		}
 
@@ -224,22 +251,24 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		    (modrm_mod == 1 || modrm_mod == 2) && modrm_rm == 5) {
 
 			/* mov reg, disp(%rbp) */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_REG;
-			op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
-			op->dest.type = OP_DEST_REG_INDIRECT;
-			op->dest.reg = CFI_BP;
-			op->dest.offset = insn.displacement.value;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG;
+				op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
+				op->dest.type = OP_DEST_REG_INDIRECT;
+				op->dest.reg = CFI_BP;
+				op->dest.offset = insn.displacement.value;
+			}
 
 		} else if (rex_w && !rex_b && modrm_rm == 4 && sib == 0x24) {
 
 			/* mov reg, disp(%rsp) */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_REG;
-			op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
-			op->dest.type = OP_DEST_REG_INDIRECT;
-			op->dest.reg = CFI_SP;
-			op->dest.offset = insn.displacement.value;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG;
+				op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
+				op->dest.type = OP_DEST_REG_INDIRECT;
+				op->dest.reg = CFI_SP;
+				op->dest.offset = insn.displacement.value;
+			}
 		}
 
 		break;
@@ -248,23 +277,25 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		if (rex_w && !rex_b && modrm_mod == 1 && modrm_rm == 5) {
 
 			/* mov disp(%rbp), reg */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_REG_INDIRECT;
-			op->src.reg = CFI_BP;
-			op->src.offset = insn.displacement.value;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG_INDIRECT;
+				op->src.reg = CFI_BP;
+				op->src.offset = insn.displacement.value;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
+			}
 
 		} else if (rex_w && !rex_b && sib == 0x24 &&
 			   modrm_mod != 3 && modrm_rm == 4) {
 
 			/* mov disp(%rsp), reg */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_REG_INDIRECT;
-			op->src.reg = CFI_SP;
-			op->src.offset = insn.displacement.value;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG_INDIRECT;
+				op->src.reg = CFI_SP;
+				op->src.offset = insn.displacement.value;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
+			}
 		}
 
 		break;
@@ -272,28 +303,30 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 	case 0x8d:
 		if (sib == 0x24 && rex_w && !rex_b && !rex_x) {
 
-			*type = INSN_STACK;
-			if (!insn.displacement.value) {
-				/* lea (%rsp), reg */
-				op->src.type = OP_SRC_REG;
-			} else {
-				/* lea disp(%rsp), reg */
-				op->src.type = OP_SRC_ADD;
-				op->src.offset = insn.displacement.value;
+			ADD_OP(op) {
+				if (!insn.displacement.value) {
+					/* lea (%rsp), reg */
+					op->src.type = OP_SRC_REG;
+				} else {
+					/* lea disp(%rsp), reg */
+					op->src.type = OP_SRC_ADD;
+					op->src.offset = insn.displacement.value;
+				}
+				op->src.reg = CFI_SP;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
 			}
-			op->src.reg = CFI_SP;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
 
 		} else if (rex == 0x48 && modrm == 0x65) {
 
 			/* lea disp(%rbp), %rsp */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_ADD;
-			op->src.reg = CFI_BP;
-			op->src.offset = insn.displacement.value;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_SP;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_ADD;
+				op->src.reg = CFI_BP;
+				op->src.offset = insn.displacement.value;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = CFI_SP;
+			}
 
 		} else if (rex == 0x49 && modrm == 0x62 &&
 			   insn.displacement.value == -8) {
@@ -304,12 +337,13 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 			 * Restoring rsp back to its original value after a
 			 * stack realignment.
 			 */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_ADD;
-			op->src.reg = CFI_R10;
-			op->src.offset = -8;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_SP;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_ADD;
+				op->src.reg = CFI_R10;
+				op->src.offset = -8;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = CFI_SP;
+			}
 
 		} else if (rex == 0x49 && modrm == 0x65 &&
 			   insn.displacement.value == -16) {
@@ -320,21 +354,23 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 			 * Restoring rsp back to its original value after a
 			 * stack realignment.
 			 */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_ADD;
-			op->src.reg = CFI_R13;
-			op->src.offset = -16;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_SP;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_ADD;
+				op->src.reg = CFI_R13;
+				op->src.offset = -16;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = CFI_SP;
+			}
 		}
 
 		break;
 
 	case 0x8f:
 		/* pop to mem */
-		*type = INSN_STACK;
-		op->src.type = OP_SRC_POP;
-		op->dest.type = OP_DEST_MEM;
+		ADD_OP(op) {
+			op->src.type = OP_SRC_POP;
+			op->dest.type = OP_DEST_MEM;
+		}
 		break;
 
 	case 0x90:
@@ -343,16 +379,18 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 
 	case 0x9c:
 		/* pushf */
-		*type = INSN_STACK;
-		op->src.type = OP_SRC_CONST;
-		op->dest.type = OP_DEST_PUSHF;
+		ADD_OP(op) {
+			op->src.type = OP_SRC_CONST;
+			op->dest.type = OP_DEST_PUSHF;
+		}
 		break;
 
 	case 0x9d:
 		/* popf */
-		*type = INSN_STACK;
-		op->src.type = OP_SRC_POPF;
-		op->dest.type = OP_DEST_MEM;
+		ADD_OP(op) {
+			op->src.type = OP_SRC_POPF;
+			op->dest.type = OP_DEST_MEM;
+		}
 		break;
 
 	case 0x0f:
@@ -387,16 +425,18 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		} else if (op2 == 0xa0 || op2 == 0xa8) {
 
 			/* push fs/gs */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_CONST;
-			op->dest.type = OP_DEST_PUSH;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_CONST;
+				op->dest.type = OP_DEST_PUSH;
+			}
 
 		} else if (op2 == 0xa1 || op2 == 0xa9) {
 
 			/* pop fs/gs */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_POP;
-			op->dest.type = OP_DEST_MEM;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_POP;
+				op->dest.type = OP_DEST_MEM;
+			}
 		}
 
 		break;
@@ -409,8 +449,8 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		 * mov bp, sp
 		 * pop bp
 		 */
-		*type = INSN_STACK;
-		op->dest.type = OP_DEST_LEAVE;
+		ADD_OP(op)
+			op->dest.type = OP_DEST_LEAVE;
 
 		break;
 
@@ -429,14 +469,41 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		*type = INSN_RETURN;
 		break;
 
+	case 0xcf: /* iret */
+		/*
+		 * Handle sync_core(), which has an IRET to self.
+		 * All other IRET are in STT_NONE entry code.
+		 */
+		sym = find_symbol_containing(sec, offset);
+		if (sym && sym->type == STT_FUNC) {
+			ADD_OP(op) {
+				/* add $40, %rsp */
+				op->src.type = OP_SRC_ADD;
+				op->src.reg = CFI_SP;
+				op->src.offset = 5*8;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = CFI_SP;
+			}
+			break;
+		}
+
+		/* fallthrough */
+
 	case 0xca: /* retf */
 	case 0xcb: /* retf */
-	case 0xcf: /* iret */
 		*type = INSN_CONTEXT_SWITCH;
 		break;
 
 	case 0xe8:
 		*type = INSN_CALL;
+		/*
+		 * For the impact on the stack, a CALL behaves like
+		 * a PUSH of an immediate value (the return address).
+		 */
+		ADD_OP(op) {
+			op->src.type = OP_SRC_CONST;
+			op->dest.type = OP_DEST_PUSH;
+		}
 		break;
 
 	case 0xfc:
@@ -464,9 +531,10 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		else if (modrm_reg == 6) {
 
 			/* push from mem */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_CONST;
-			op->dest.type = OP_DEST_PUSH;
+			ADD_OP(op) {
+				op->src.type = OP_SRC_CONST;
+				op->dest.type = OP_DEST_PUSH;
+			}
 		}
 
 		break;
@@ -480,7 +548,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 	return 0;
 }
 
-void arch_initial_func_cfi_state(struct cfi_state *state)
+void arch_initial_func_cfi_state(struct cfi_init_state *state)
 {
 	int i;
 
diff --git a/tools/objtool/arch/x86/include/cfi_regs.h b/tools/objtool/arch/x86/include/cfi_regs.h
new file mode 100644
index 000000000000..79bc517efba8
--- /dev/null
+++ b/tools/objtool/arch/x86/include/cfi_regs.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _OBJTOOL_CFI_REGS_H
+#define _OBJTOOL_CFI_REGS_H
+
+#define CFI_AX			0
+#define CFI_DX			1
+#define CFI_CX			2
+#define CFI_BX			3
+#define CFI_SI			4
+#define CFI_DI			5
+#define CFI_BP			6
+#define CFI_SP			7
+#define CFI_R8			8
+#define CFI_R9			9
+#define CFI_R10			10
+#define CFI_R11			11
+#define CFI_R12			12
+#define CFI_R13			13
+#define CFI_R14			14
+#define CFI_R15			15
+#define CFI_RA			16
+#define CFI_NUM_REGS		17
+
+#endif /* _OBJTOOL_CFI_REGS_H */
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 10fbe75ab43d..7a44174967b5 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -14,10 +14,11 @@
  */
 
 #include <subcmd/parse-options.h>
+#include <string.h>
 #include "builtin.h"
-#include "check.h"
+#include "objtool.h"
 
-bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats;
+bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux;
 
 static const char * const check_usage[] = {
 	"objtool check [<options>] file.o",
@@ -32,12 +33,14 @@ const struct option check_options[] = {
 	OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"),
 	OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"),
 	OPT_BOOLEAN('s', "stats", &stats, "print statistics"),
+	OPT_BOOLEAN('d', "duplicate", &validate_dup, "duplicate validation for vmlinux.o"),
+	OPT_BOOLEAN('l', "vmlinux", &vmlinux, "vmlinux.o validation"),
 	OPT_END(),
 };
 
 int cmd_check(int argc, const char **argv)
 {
-	const char *objname;
+	const char *objname, *s;
 
 	argc = parse_options(argc, argv, check_options, check_usage, 0);
 
@@ -46,5 +49,9 @@ int cmd_check(int argc, const char **argv)
 
 	objname = argv[0];
 
+	s = strstr(objname, "vmlinux.o");
+	if (s && !s[9])
+		vmlinux = true;
+
 	return check(objname, false);
 }
diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c
index 5f7cc6157edd..b1dfe2007962 100644
--- a/tools/objtool/builtin-orc.c
+++ b/tools/objtool/builtin-orc.c
@@ -14,8 +14,7 @@
 
 #include <string.h>
 #include "builtin.h"
-#include "check.h"
-
+#include "objtool.h"
 
 static const char *orc_usage[] = {
 	"objtool orc generate [<options>] file.o",
diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h
index 0b907902ee79..85c979caa367 100644
--- a/tools/objtool/builtin.h
+++ b/tools/objtool/builtin.h
@@ -8,7 +8,7 @@
 #include <subcmd/parse-options.h>
 
 extern const struct option check_options[];
-extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats;
+extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux;
 
 extern int cmd_check(int argc, const char **argv);
 extern int cmd_orc(int argc, const char **argv);
diff --git a/tools/objtool/cfi.h b/tools/objtool/cfi.h
index 4427bf8ed686..c7c59c6a44ee 100644
--- a/tools/objtool/cfi.h
+++ b/tools/objtool/cfi.h
@@ -6,38 +6,33 @@
 #ifndef _OBJTOOL_CFI_H
 #define _OBJTOOL_CFI_H
 
+#include "cfi_regs.h"
+
 #define CFI_UNDEFINED		-1
 #define CFI_CFA			-2
 #define CFI_SP_INDIRECT		-3
 #define CFI_BP_INDIRECT		-4
 
-#define CFI_AX			0
-#define CFI_DX			1
-#define CFI_CX			2
-#define CFI_BX			3
-#define CFI_SI			4
-#define CFI_DI			5
-#define CFI_BP			6
-#define CFI_SP			7
-#define CFI_R8			8
-#define CFI_R9			9
-#define CFI_R10			10
-#define CFI_R11			11
-#define CFI_R12			12
-#define CFI_R13			13
-#define CFI_R14			14
-#define CFI_R15			15
-#define CFI_RA			16
-#define CFI_NUM_REGS		17
-
 struct cfi_reg {
 	int base;
 	int offset;
 };
 
-struct cfi_state {
+struct cfi_init_state {
+	struct cfi_reg regs[CFI_NUM_REGS];
 	struct cfi_reg cfa;
+};
+
+struct cfi_state {
 	struct cfi_reg regs[CFI_NUM_REGS];
+	struct cfi_reg vals[CFI_NUM_REGS];
+	struct cfi_reg cfa;
+	int stack_size;
+	int drap_reg, drap_offset;
+	unsigned char type;
+	bool bp_scratch;
+	bool drap;
+	bool end;
 };
 
 #endif /* _OBJTOOL_CFI_H */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 8dd01f986fbb..63d65a702900 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -7,10 +7,10 @@
 #include <stdlib.h>
 
 #include "builtin.h"
+#include "cfi.h"
+#include "arch.h"
 #include "check.h"
-#include "elf.h"
 #include "special.h"
-#include "arch.h"
 #include "warn.h"
 
 #include <linux/hashtable.h>
@@ -27,16 +27,17 @@ struct alternative {
 };
 
 const char *objname;
-struct cfi_state initial_func_cfi;
+struct cfi_init_state initial_func_cfi;
 
 struct instruction *find_insn(struct objtool_file *file,
 			      struct section *sec, unsigned long offset)
 {
 	struct instruction *insn;
 
-	hash_for_each_possible(file->insn_hash, insn, hash, offset)
+	hash_for_each_possible(file->insn_hash, insn, hash, sec_offset_hash(sec, offset)) {
 		if (insn->sec == sec && insn->offset == offset)
 			return insn;
+	}
 
 	return NULL;
 }
@@ -72,6 +73,17 @@ static struct instruction *next_insn_same_func(struct objtool_file *file,
 	return find_insn(file, func->cfunc->sec, func->cfunc->offset);
 }
 
+static struct instruction *prev_insn_same_sym(struct objtool_file *file,
+					       struct instruction *insn)
+{
+	struct instruction *prev = list_prev_entry(insn, list);
+
+	if (&prev->list != &file->insn_list && prev->func == insn->func)
+		return prev;
+
+	return NULL;
+}
+
 #define func_for_each_insn(file, func, insn)				\
 	for (insn = find_insn(file, func->sec, func->offset);		\
 	     insn;							\
@@ -215,18 +227,31 @@ static bool dead_end_function(struct objtool_file *file, struct symbol *func)
 	return __dead_end_function(file, func, 0);
 }
 
-static void clear_insn_state(struct insn_state *state)
+static void init_cfi_state(struct cfi_state *cfi)
 {
 	int i;
 
-	memset(state, 0, sizeof(*state));
-	state->cfa.base = CFI_UNDEFINED;
 	for (i = 0; i < CFI_NUM_REGS; i++) {
-		state->regs[i].base = CFI_UNDEFINED;
-		state->vals[i].base = CFI_UNDEFINED;
+		cfi->regs[i].base = CFI_UNDEFINED;
+		cfi->vals[i].base = CFI_UNDEFINED;
 	}
-	state->drap_reg = CFI_UNDEFINED;
-	state->drap_offset = -1;
+	cfi->cfa.base = CFI_UNDEFINED;
+	cfi->drap_reg = CFI_UNDEFINED;
+	cfi->drap_offset = -1;
+}
+
+static void init_insn_state(struct insn_state *state, struct section *sec)
+{
+	memset(state, 0, sizeof(*state));
+	init_cfi_state(&state->cfi);
+
+	/*
+	 * We need the full vmlinux for noinstr validation, otherwise we can
+	 * not correctly determine insn->call_dest->sec (external symbols do
+	 * not have a section).
+	 */
+	if (vmlinux && sec)
+		state->noinstr = sec->noinstr;
 }
 
 /*
@@ -252,6 +277,10 @@ static int decode_instructions(struct objtool_file *file)
 		    strncmp(sec->name, ".discard.", 9))
 			sec->text = true;
 
+		if (!strcmp(sec->name, ".noinstr.text") ||
+		    !strcmp(sec->name, ".entry.text"))
+			sec->noinstr = true;
+
 		for (offset = 0; offset < sec->len; offset += insn->len) {
 			insn = malloc(sizeof(*insn));
 			if (!insn) {
@@ -260,7 +289,8 @@ static int decode_instructions(struct objtool_file *file)
 			}
 			memset(insn, 0, sizeof(*insn));
 			INIT_LIST_HEAD(&insn->alts);
-			clear_insn_state(&insn->state);
+			INIT_LIST_HEAD(&insn->stack_ops);
+			init_cfi_state(&insn->cfi);
 
 			insn->sec = sec;
 			insn->offset = offset;
@@ -269,11 +299,11 @@ static int decode_instructions(struct objtool_file *file)
 						      sec->len - offset,
 						      &insn->len, &insn->type,
 						      &insn->immediate,
-						      &insn->stack_op);
+						      &insn->stack_ops);
 			if (ret)
 				goto err;
 
-			hash_add(file->insn_hash, &insn->hash, insn->offset);
+			hash_add(file->insn_hash, &insn->hash, sec_offset_hash(sec, insn->offset));
 			list_add_tail(&insn->list, &file->insn_list);
 			nr_insns++;
 		}
@@ -303,6 +333,19 @@ err:
 	return ret;
 }
 
+static struct instruction *find_last_insn(struct objtool_file *file,
+					  struct section *sec)
+{
+	struct instruction *insn = NULL;
+	unsigned int offset;
+	unsigned int end = (sec->len > 10) ? sec->len - 10 : 0;
+
+	for (offset = sec->len - 1; offset >= end && !insn; offset--)
+		insn = find_insn(file, sec, offset);
+
+	return insn;
+}
+
 /*
  * Mark "ud2" instructions and manually annotated dead ends.
  */
@@ -311,7 +354,6 @@ static int add_dead_ends(struct objtool_file *file)
 	struct section *sec;
 	struct rela *rela;
 	struct instruction *insn;
-	bool found;
 
 	/*
 	 * By default, "ud2" is a dead end unless otherwise annotated, because
@@ -337,15 +379,8 @@ static int add_dead_ends(struct objtool_file *file)
 		if (insn)
 			insn = list_prev_entry(insn, list);
 		else if (rela->addend == rela->sym->sec->len) {
-			found = false;
-			list_for_each_entry_reverse(insn, &file->insn_list, list) {
-				if (insn->sec == rela->sym->sec) {
-					found = true;
-					break;
-				}
-			}
-
-			if (!found) {
+			insn = find_last_insn(file, rela->sym->sec);
+			if (!insn) {
 				WARN("can't find unreachable insn at %s+0x%x",
 				     rela->sym->sec->name, rela->addend);
 				return -1;
@@ -379,15 +414,8 @@ reachable:
 		if (insn)
 			insn = list_prev_entry(insn, list);
 		else if (rela->addend == rela->sym->sec->len) {
-			found = false;
-			list_for_each_entry_reverse(insn, &file->insn_list, list) {
-				if (insn->sec == rela->sym->sec) {
-					found = true;
-					break;
-				}
-			}
-
-			if (!found) {
+			insn = find_last_insn(file, rela->sym->sec);
+			if (!insn) {
 				WARN("can't find reachable insn at %s+0x%x",
 				     rela->sym->sec->name, rela->addend);
 				return -1;
@@ -479,6 +507,7 @@ static const char *uaccess_safe_builtin[] = {
 	"__asan_report_store16_noabort",
 	/* KCOV */
 	"write_comp_data",
+	"check_kcov_mode",
 	"__sanitizer_cov_trace_pc",
 	"__sanitizer_cov_trace_const_cmp1",
 	"__sanitizer_cov_trace_const_cmp2",
@@ -574,13 +603,14 @@ static int add_jump_destinations(struct objtool_file *file)
 					       insn->offset, insn->len);
 		if (!rela) {
 			dest_sec = insn->sec;
-			dest_off = insn->offset + insn->len + insn->immediate;
+			dest_off = arch_jump_destination(insn);
 		} else if (rela->sym->type == STT_SECTION) {
 			dest_sec = rela->sym->sec;
-			dest_off = rela->addend + 4;
+			dest_off = arch_dest_rela_offset(rela->addend);
 		} else if (rela->sym->sec->idx) {
 			dest_sec = rela->sym->sec;
-			dest_off = rela->sym->sym.st_value + rela->addend + 4;
+			dest_off = rela->sym->sym.st_value +
+				   arch_dest_rela_offset(rela->addend);
 		} else if (strstr(rela->sym->name, "_indirect_thunk_")) {
 			/*
 			 * Retpoline jumps are really dynamic jumps in
@@ -654,6 +684,16 @@ static int add_jump_destinations(struct objtool_file *file)
 	return 0;
 }
 
+static void remove_insn_ops(struct instruction *insn)
+{
+	struct stack_op *op, *tmp;
+
+	list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) {
+		list_del(&op->list);
+		free(op);
+	}
+}
+
 /*
  * Find the destination instructions for all calls.
  */
@@ -670,7 +710,7 @@ static int add_call_destinations(struct objtool_file *file)
 		rela = find_rela_by_dest_range(file->elf, insn->sec,
 					       insn->offset, insn->len);
 		if (!rela) {
-			dest_off = insn->offset + insn->len + insn->immediate;
+			dest_off = arch_jump_destination(insn);
 			insn->call_dest = find_func_by_offset(insn->sec, dest_off);
 			if (!insn->call_dest)
 				insn->call_dest = find_symbol_by_offset(insn->sec, dest_off);
@@ -679,10 +719,7 @@ static int add_call_destinations(struct objtool_file *file)
 				continue;
 
 			if (!insn->call_dest) {
-				WARN_FUNC("unsupported intra-function call",
-					  insn->sec, insn->offset);
-				if (retpoline)
-					WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE.");
+				WARN_FUNC("unannotated intra-function call", insn->sec, insn->offset);
 				return -1;
 			}
 
@@ -693,17 +730,27 @@ static int add_call_destinations(struct objtool_file *file)
 			}
 
 		} else if (rela->sym->type == STT_SECTION) {
+			dest_off = arch_dest_rela_offset(rela->addend);
 			insn->call_dest = find_func_by_offset(rela->sym->sec,
-							      rela->addend+4);
+							      dest_off);
 			if (!insn->call_dest) {
-				WARN_FUNC("can't find call dest symbol at %s+0x%x",
+				WARN_FUNC("can't find call dest symbol at %s+0x%lx",
 					  insn->sec, insn->offset,
 					  rela->sym->sec->name,
-					  rela->addend + 4);
+					  dest_off);
 				return -1;
 			}
 		} else
 			insn->call_dest = rela->sym;
+
+		/*
+		 * Whatever stack impact regular CALLs have, should be undone
+		 * by the RETURN of the called function.
+		 *
+		 * Annotated intra-function calls retain the stack_ops but
+		 * are converted to JUMP, see read_intra_function_calls().
+		 */
+		remove_insn_ops(insn);
 	}
 
 	return 0;
@@ -731,7 +778,9 @@ static int handle_group_alt(struct objtool_file *file,
 			    struct instruction *orig_insn,
 			    struct instruction **new_insn)
 {
+	static unsigned int alt_group_next_index = 1;
 	struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump = NULL;
+	unsigned int alt_group = alt_group_next_index++;
 	unsigned long dest_off;
 
 	last_orig_insn = NULL;
@@ -740,7 +789,7 @@ static int handle_group_alt(struct objtool_file *file,
 		if (insn->offset >= special_alt->orig_off + special_alt->orig_len)
 			break;
 
-		insn->alt_group = true;
+		insn->alt_group = alt_group;
 		last_orig_insn = insn;
 	}
 
@@ -752,7 +801,8 @@ static int handle_group_alt(struct objtool_file *file,
 		}
 		memset(fake_jump, 0, sizeof(*fake_jump));
 		INIT_LIST_HEAD(&fake_jump->alts);
-		clear_insn_state(&fake_jump->state);
+		INIT_LIST_HEAD(&fake_jump->stack_ops);
+		init_cfi_state(&fake_jump->cfi);
 
 		fake_jump->sec = special_alt->new_sec;
 		fake_jump->offset = FAKE_JUMP_OFFSET;
@@ -773,6 +823,7 @@ static int handle_group_alt(struct objtool_file *file,
 	}
 
 	last_new_insn = NULL;
+	alt_group = alt_group_next_index++;
 	insn = *new_insn;
 	sec_for_each_insn_from(file, insn) {
 		if (insn->offset >= special_alt->new_off + special_alt->new_len)
@@ -782,6 +833,7 @@ static int handle_group_alt(struct objtool_file *file,
 
 		insn->ignore = orig_insn->ignore_alts;
 		insn->func = orig_insn->func;
+		insn->alt_group = alt_group;
 
 		/*
 		 * Since alternative replacement code is copy/pasted by the
@@ -810,7 +862,7 @@ static int handle_group_alt(struct objtool_file *file,
 		if (!insn->immediate)
 			continue;
 
-		dest_off = insn->offset + insn->len + insn->immediate;
+		dest_off = arch_jump_destination(insn);
 		if (dest_off == special_alt->new_off + special_alt->new_len) {
 			if (!fake_jump) {
 				WARN("%s: alternative jump to end of section",
@@ -905,6 +957,12 @@ static int add_special_section_alts(struct objtool_file *file)
 		}
 
 		if (special_alt->group) {
+			if (!special_alt->orig_len) {
+				WARN_FUNC("empty alternative entry",
+					  orig_insn->sec, orig_insn->offset);
+				continue;
+			}
+
 			ret = handle_group_alt(file, special_alt, orig_insn,
 					       &new_insn);
 			if (ret)
@@ -1050,11 +1108,8 @@ static struct rela *find_jump_table(struct objtool_file *file,
 	 * it.
 	 */
 	for (;
-	     &insn->list != &file->insn_list &&
-	     insn->sec == func->sec &&
-	     insn->offset >= func->offset;
-
-	     insn = insn->first_jump_src ?: list_prev_entry(insn, list)) {
+	     insn && insn->func && insn->func->pfunc == func;
+	     insn = insn->first_jump_src ?: prev_insn_same_sym(file, insn)) {
 
 		if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC)
 			break;
@@ -1245,15 +1300,10 @@ static int read_unwind_hints(struct objtool_file *file)
 			return -1;
 		}
 
-		cfa = &insn->state.cfa;
-
-		if (hint->type == UNWIND_HINT_TYPE_SAVE) {
-			insn->save = true;
-			continue;
+		cfa = &insn->cfi.cfa;
 
-		} else if (hint->type == UNWIND_HINT_TYPE_RESTORE) {
-			insn->restore = true;
-			insn->hint = true;
+		if (hint->type == UNWIND_HINT_TYPE_RET_OFFSET) {
+			insn->ret_offset = hint->sp_offset;
 			continue;
 		}
 
@@ -1291,8 +1341,8 @@ static int read_unwind_hints(struct objtool_file *file)
 		}
 
 		cfa->offset = hint->sp_offset;
-		insn->state.type = hint->type;
-		insn->state.end = hint->end;
+		insn->cfi.type = hint->type;
+		insn->cfi.end = hint->end;
 	}
 
 	return 0;
@@ -1333,6 +1383,104 @@ static int read_retpoline_hints(struct objtool_file *file)
 	return 0;
 }
 
+static int read_instr_hints(struct objtool_file *file)
+{
+	struct section *sec;
+	struct instruction *insn;
+	struct rela *rela;
+
+	sec = find_section_by_name(file->elf, ".rela.discard.instr_end");
+	if (!sec)
+		return 0;
+
+	list_for_each_entry(rela, &sec->rela_list, list) {
+		if (rela->sym->type != STT_SECTION) {
+			WARN("unexpected relocation symbol type in %s", sec->name);
+			return -1;
+		}
+
+		insn = find_insn(file, rela->sym->sec, rela->addend);
+		if (!insn) {
+			WARN("bad .discard.instr_end entry");
+			return -1;
+		}
+
+		insn->instr--;
+	}
+
+	sec = find_section_by_name(file->elf, ".rela.discard.instr_begin");
+	if (!sec)
+		return 0;
+
+	list_for_each_entry(rela, &sec->rela_list, list) {
+		if (rela->sym->type != STT_SECTION) {
+			WARN("unexpected relocation symbol type in %s", sec->name);
+			return -1;
+		}
+
+		insn = find_insn(file, rela->sym->sec, rela->addend);
+		if (!insn) {
+			WARN("bad .discard.instr_begin entry");
+			return -1;
+		}
+
+		insn->instr++;
+	}
+
+	return 0;
+}
+
+static int read_intra_function_calls(struct objtool_file *file)
+{
+	struct instruction *insn;
+	struct section *sec;
+	struct rela *rela;
+
+	sec = find_section_by_name(file->elf, ".rela.discard.intra_function_calls");
+	if (!sec)
+		return 0;
+
+	list_for_each_entry(rela, &sec->rela_list, list) {
+		unsigned long dest_off;
+
+		if (rela->sym->type != STT_SECTION) {
+			WARN("unexpected relocation symbol type in %s",
+			     sec->name);
+			return -1;
+		}
+
+		insn = find_insn(file, rela->sym->sec, rela->addend);
+		if (!insn) {
+			WARN("bad .discard.intra_function_call entry");
+			return -1;
+		}
+
+		if (insn->type != INSN_CALL) {
+			WARN_FUNC("intra_function_call not a direct call",
+				  insn->sec, insn->offset);
+			return -1;
+		}
+
+		/*
+		 * Treat intra-function CALLs as JMPs, but with a stack_op.
+		 * See add_call_destinations(), which strips stack_ops from
+		 * normal CALLs.
+		 */
+		insn->type = INSN_JUMP_UNCONDITIONAL;
+
+		dest_off = insn->offset + insn->len + insn->immediate;
+		insn->jump_dest = find_insn(file, insn->sec, dest_off);
+		if (!insn->jump_dest) {
+			WARN_FUNC("can't find call dest at %s+0x%lx",
+				  insn->sec, insn->offset,
+				  insn->sec->name, dest_off);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
 static void mark_rodata(struct objtool_file *file)
 {
 	struct section *sec;
@@ -1349,8 +1497,8 @@ static void mark_rodata(struct objtool_file *file)
 	 * .rodata.str1.* sections are ignored; they don't contain jump tables.
 	 */
 	for_each_sec(file, sec) {
-		if ((!strncmp(sec->name, ".rodata", 7) && !strstr(sec->name, ".str1.")) ||
-		    !strcmp(sec->name, C_JUMP_TABLE_SECTION)) {
+		if (!strncmp(sec->name, ".rodata", 7) &&
+		    !strstr(sec->name, ".str1.")) {
 			sec->rodata = true;
 			found = true;
 		}
@@ -1388,6 +1536,10 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
+	ret = read_intra_function_calls(file);
+	if (ret)
+		return ret;
+
 	ret = add_call_destinations(file);
 	if (ret)
 		return ret;
@@ -1404,12 +1556,16 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
+	ret = read_instr_hints(file);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
 static bool is_fentry_call(struct instruction *insn)
 {
-	if (insn->type == INSN_CALL &&
+	if (insn->type == INSN_CALL && insn->call_dest &&
 	    insn->call_dest->type == STT_NOTYPE &&
 	    !strcmp(insn->call_dest->name, "__fentry__"))
 		return true;
@@ -1417,42 +1573,59 @@ static bool is_fentry_call(struct instruction *insn)
 	return false;
 }
 
-static bool has_modified_stack_frame(struct insn_state *state)
+static bool has_modified_stack_frame(struct instruction *insn, struct insn_state *state)
 {
+	u8 ret_offset = insn->ret_offset;
+	struct cfi_state *cfi = &state->cfi;
 	int i;
 
-	if (state->cfa.base != initial_func_cfi.cfa.base ||
-	    state->cfa.offset != initial_func_cfi.cfa.offset ||
-	    state->stack_size != initial_func_cfi.cfa.offset ||
-	    state->drap)
+	if (cfi->cfa.base != initial_func_cfi.cfa.base || cfi->drap)
+		return true;
+
+	if (cfi->cfa.offset != initial_func_cfi.cfa.offset + ret_offset)
 		return true;
 
-	for (i = 0; i < CFI_NUM_REGS; i++)
-		if (state->regs[i].base != initial_func_cfi.regs[i].base ||
-		    state->regs[i].offset != initial_func_cfi.regs[i].offset)
+	if (cfi->stack_size != initial_func_cfi.cfa.offset + ret_offset)
+		return true;
+
+	/*
+	 * If there is a ret offset hint then don't check registers
+	 * because a callee-saved register might have been pushed on
+	 * the stack.
+	 */
+	if (ret_offset)
+		return false;
+
+	for (i = 0; i < CFI_NUM_REGS; i++) {
+		if (cfi->regs[i].base != initial_func_cfi.regs[i].base ||
+		    cfi->regs[i].offset != initial_func_cfi.regs[i].offset)
 			return true;
+	}
 
 	return false;
 }
 
 static bool has_valid_stack_frame(struct insn_state *state)
 {
-	if (state->cfa.base == CFI_BP && state->regs[CFI_BP].base == CFI_CFA &&
-	    state->regs[CFI_BP].offset == -16)
+	struct cfi_state *cfi = &state->cfi;
+
+	if (cfi->cfa.base == CFI_BP && cfi->regs[CFI_BP].base == CFI_CFA &&
+	    cfi->regs[CFI_BP].offset == -16)
 		return true;
 
-	if (state->drap && state->regs[CFI_BP].base == CFI_BP)
+	if (cfi->drap && cfi->regs[CFI_BP].base == CFI_BP)
 		return true;
 
 	return false;
 }
 
-static int update_insn_state_regs(struct instruction *insn, struct insn_state *state)
+static int update_cfi_state_regs(struct instruction *insn,
+				  struct cfi_state *cfi,
+				  struct stack_op *op)
 {
-	struct cfi_reg *cfa = &state->cfa;
-	struct stack_op *op = &insn->stack_op;
+	struct cfi_reg *cfa = &cfi->cfa;
 
-	if (cfa->base != CFI_SP)
+	if (cfa->base != CFI_SP && cfa->base != CFI_SP_INDIRECT)
 		return 0;
 
 	/* push */
@@ -1471,20 +1644,19 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s
 	return 0;
 }
 
-static void save_reg(struct insn_state *state, unsigned char reg, int base,
-		     int offset)
+static void save_reg(struct cfi_state *cfi, unsigned char reg, int base, int offset)
 {
 	if (arch_callee_saved_reg(reg) &&
-	    state->regs[reg].base == CFI_UNDEFINED) {
-		state->regs[reg].base = base;
-		state->regs[reg].offset = offset;
+	    cfi->regs[reg].base == CFI_UNDEFINED) {
+		cfi->regs[reg].base = base;
+		cfi->regs[reg].offset = offset;
 	}
 }
 
-static void restore_reg(struct insn_state *state, unsigned char reg)
+static void restore_reg(struct cfi_state *cfi, unsigned char reg)
 {
-	state->regs[reg].base = CFI_UNDEFINED;
-	state->regs[reg].offset = 0;
+	cfi->regs[reg].base = initial_func_cfi.regs[reg].base;
+	cfi->regs[reg].offset = initial_func_cfi.regs[reg].offset;
 }
 
 /*
@@ -1540,11 +1712,11 @@ static void restore_reg(struct insn_state *state, unsigned char reg)
  *   41 5d			pop    %r13
  *   c3				retq
  */
-static int update_insn_state(struct instruction *insn, struct insn_state *state)
+static int update_cfi_state(struct instruction *insn, struct cfi_state *cfi,
+			     struct stack_op *op)
 {
-	struct stack_op *op = &insn->stack_op;
-	struct cfi_reg *cfa = &state->cfa;
-	struct cfi_reg *regs = state->regs;
+	struct cfi_reg *cfa = &cfi->cfa;
+	struct cfi_reg *regs = cfi->regs;
 
 	/* stack operations don't make sense with an undefined CFA */
 	if (cfa->base == CFI_UNDEFINED) {
@@ -1555,8 +1727,8 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 		return 0;
 	}
 
-	if (state->type == ORC_TYPE_REGS || state->type == ORC_TYPE_REGS_IRET)
-		return update_insn_state_regs(insn, state);
+	if (cfi->type == ORC_TYPE_REGS || cfi->type == ORC_TYPE_REGS_IRET)
+		return update_cfi_state_regs(insn, cfi, op);
 
 	switch (op->dest.type) {
 
@@ -1571,16 +1743,16 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 
 				/* mov %rsp, %rbp */
 				cfa->base = op->dest.reg;
-				state->bp_scratch = false;
+				cfi->bp_scratch = false;
 			}
 
 			else if (op->src.reg == CFI_SP &&
-				 op->dest.reg == CFI_BP && state->drap) {
+				 op->dest.reg == CFI_BP && cfi->drap) {
 
 				/* drap: mov %rsp, %rbp */
 				regs[CFI_BP].base = CFI_BP;
-				regs[CFI_BP].offset = -state->stack_size;
-				state->bp_scratch = false;
+				regs[CFI_BP].offset = -cfi->stack_size;
+				cfi->bp_scratch = false;
 			}
 
 			else if (op->src.reg == CFI_SP && cfa->base == CFI_SP) {
@@ -1595,8 +1767,8 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 				 *   ...
 				 *   mov    %rax, %rsp
 				 */
-				state->vals[op->dest.reg].base = CFI_CFA;
-				state->vals[op->dest.reg].offset = -state->stack_size;
+				cfi->vals[op->dest.reg].base = CFI_CFA;
+				cfi->vals[op->dest.reg].offset = -cfi->stack_size;
 			}
 
 			else if (op->src.reg == CFI_BP && op->dest.reg == CFI_SP &&
@@ -1607,14 +1779,14 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 				 *
 				 * Restore the original stack pointer (Clang).
 				 */
-				state->stack_size = -state->regs[CFI_BP].offset;
+				cfi->stack_size = -cfi->regs[CFI_BP].offset;
 			}
 
 			else if (op->dest.reg == cfa->base) {
 
 				/* mov %reg, %rsp */
 				if (cfa->base == CFI_SP &&
-				    state->vals[op->src.reg].base == CFI_CFA) {
+				    cfi->vals[op->src.reg].base == CFI_CFA) {
 
 					/*
 					 * This is needed for the rare case
@@ -1624,8 +1796,8 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 					 *   ...
 					 *   mov    %rcx, %rsp
 					 */
-					cfa->offset = -state->vals[op->src.reg].offset;
-					state->stack_size = cfa->offset;
+					cfa->offset = -cfi->vals[op->src.reg].offset;
+					cfi->stack_size = cfa->offset;
 
 				} else {
 					cfa->base = CFI_UNDEFINED;
@@ -1639,7 +1811,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 			if (op->dest.reg == CFI_SP && op->src.reg == CFI_SP) {
 
 				/* add imm, %rsp */
-				state->stack_size -= op->src.offset;
+				cfi->stack_size -= op->src.offset;
 				if (cfa->base == CFI_SP)
 					cfa->offset -= op->src.offset;
 				break;
@@ -1648,14 +1820,14 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 			if (op->dest.reg == CFI_SP && op->src.reg == CFI_BP) {
 
 				/* lea disp(%rbp), %rsp */
-				state->stack_size = -(op->src.offset + regs[CFI_BP].offset);
+				cfi->stack_size = -(op->src.offset + regs[CFI_BP].offset);
 				break;
 			}
 
 			if (op->src.reg == CFI_SP && cfa->base == CFI_SP) {
 
 				/* drap: lea disp(%rsp), %drap */
-				state->drap_reg = op->dest.reg;
+				cfi->drap_reg = op->dest.reg;
 
 				/*
 				 * lea disp(%rsp), %reg
@@ -1667,25 +1839,25 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 				 *   ...
 				 *   mov    %rcx, %rsp
 				 */
-				state->vals[op->dest.reg].base = CFI_CFA;
-				state->vals[op->dest.reg].offset = \
-					-state->stack_size + op->src.offset;
+				cfi->vals[op->dest.reg].base = CFI_CFA;
+				cfi->vals[op->dest.reg].offset = \
+					-cfi->stack_size + op->src.offset;
 
 				break;
 			}
 
-			if (state->drap && op->dest.reg == CFI_SP &&
-			    op->src.reg == state->drap_reg) {
+			if (cfi->drap && op->dest.reg == CFI_SP &&
+			    op->src.reg == cfi->drap_reg) {
 
 				 /* drap: lea disp(%drap), %rsp */
 				cfa->base = CFI_SP;
-				cfa->offset = state->stack_size = -op->src.offset;
-				state->drap_reg = CFI_UNDEFINED;
-				state->drap = false;
+				cfa->offset = cfi->stack_size = -op->src.offset;
+				cfi->drap_reg = CFI_UNDEFINED;
+				cfi->drap = false;
 				break;
 			}
 
-			if (op->dest.reg == state->cfa.base) {
+			if (op->dest.reg == cfi->cfa.base) {
 				WARN_FUNC("unsupported stack register modification",
 					  insn->sec, insn->offset);
 				return -1;
@@ -1695,18 +1867,18 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 
 		case OP_SRC_AND:
 			if (op->dest.reg != CFI_SP ||
-			    (state->drap_reg != CFI_UNDEFINED && cfa->base != CFI_SP) ||
-			    (state->drap_reg == CFI_UNDEFINED && cfa->base != CFI_BP)) {
+			    (cfi->drap_reg != CFI_UNDEFINED && cfa->base != CFI_SP) ||
+			    (cfi->drap_reg == CFI_UNDEFINED && cfa->base != CFI_BP)) {
 				WARN_FUNC("unsupported stack pointer realignment",
 					  insn->sec, insn->offset);
 				return -1;
 			}
 
-			if (state->drap_reg != CFI_UNDEFINED) {
+			if (cfi->drap_reg != CFI_UNDEFINED) {
 				/* drap: and imm, %rsp */
-				cfa->base = state->drap_reg;
-				cfa->offset = state->stack_size = 0;
-				state->drap = true;
+				cfa->base = cfi->drap_reg;
+				cfa->offset = cfi->stack_size = 0;
+				cfi->drap = true;
 			}
 
 			/*
@@ -1718,57 +1890,55 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 
 		case OP_SRC_POP:
 		case OP_SRC_POPF:
-			if (!state->drap && op->dest.type == OP_DEST_REG &&
-			    op->dest.reg == cfa->base) {
+			if (!cfi->drap && op->dest.reg == cfa->base) {
 
 				/* pop %rbp */
 				cfa->base = CFI_SP;
 			}
 
-			if (state->drap && cfa->base == CFI_BP_INDIRECT &&
-			    op->dest.type == OP_DEST_REG &&
-			    op->dest.reg == state->drap_reg &&
-			    state->drap_offset == -state->stack_size) {
+			if (cfi->drap && cfa->base == CFI_BP_INDIRECT &&
+			    op->dest.reg == cfi->drap_reg &&
+			    cfi->drap_offset == -cfi->stack_size) {
 
 				/* drap: pop %drap */
-				cfa->base = state->drap_reg;
+				cfa->base = cfi->drap_reg;
 				cfa->offset = 0;
-				state->drap_offset = -1;
+				cfi->drap_offset = -1;
 
-			} else if (regs[op->dest.reg].offset == -state->stack_size) {
+			} else if (regs[op->dest.reg].offset == -cfi->stack_size) {
 
 				/* pop %reg */
-				restore_reg(state, op->dest.reg);
+				restore_reg(cfi, op->dest.reg);
 			}
 
-			state->stack_size -= 8;
+			cfi->stack_size -= 8;
 			if (cfa->base == CFI_SP)
 				cfa->offset -= 8;
 
 			break;
 
 		case OP_SRC_REG_INDIRECT:
-			if (state->drap && op->src.reg == CFI_BP &&
-			    op->src.offset == state->drap_offset) {
+			if (cfi->drap && op->src.reg == CFI_BP &&
+			    op->src.offset == cfi->drap_offset) {
 
 				/* drap: mov disp(%rbp), %drap */
-				cfa->base = state->drap_reg;
+				cfa->base = cfi->drap_reg;
 				cfa->offset = 0;
-				state->drap_offset = -1;
+				cfi->drap_offset = -1;
 			}
 
-			if (state->drap && op->src.reg == CFI_BP &&
+			if (cfi->drap && op->src.reg == CFI_BP &&
 			    op->src.offset == regs[op->dest.reg].offset) {
 
 				/* drap: mov disp(%rbp), %reg */
-				restore_reg(state, op->dest.reg);
+				restore_reg(cfi, op->dest.reg);
 
 			} else if (op->src.reg == cfa->base &&
 			    op->src.offset == regs[op->dest.reg].offset + cfa->offset) {
 
 				/* mov disp(%rbp), %reg */
 				/* mov disp(%rsp), %reg */
-				restore_reg(state, op->dest.reg);
+				restore_reg(cfi, op->dest.reg);
 			}
 
 			break;
@@ -1783,78 +1953,78 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 
 	case OP_DEST_PUSH:
 	case OP_DEST_PUSHF:
-		state->stack_size += 8;
+		cfi->stack_size += 8;
 		if (cfa->base == CFI_SP)
 			cfa->offset += 8;
 
 		if (op->src.type != OP_SRC_REG)
 			break;
 
-		if (state->drap) {
-			if (op->src.reg == cfa->base && op->src.reg == state->drap_reg) {
+		if (cfi->drap) {
+			if (op->src.reg == cfa->base && op->src.reg == cfi->drap_reg) {
 
 				/* drap: push %drap */
 				cfa->base = CFI_BP_INDIRECT;
-				cfa->offset = -state->stack_size;
+				cfa->offset = -cfi->stack_size;
 
 				/* save drap so we know when to restore it */
-				state->drap_offset = -state->stack_size;
+				cfi->drap_offset = -cfi->stack_size;
 
-			} else if (op->src.reg == CFI_BP && cfa->base == state->drap_reg) {
+			} else if (op->src.reg == CFI_BP && cfa->base == cfi->drap_reg) {
 
 				/* drap: push %rbp */
-				state->stack_size = 0;
+				cfi->stack_size = 0;
 
 			} else if (regs[op->src.reg].base == CFI_UNDEFINED) {
 
 				/* drap: push %reg */
-				save_reg(state, op->src.reg, CFI_BP, -state->stack_size);
+				save_reg(cfi, op->src.reg, CFI_BP, -cfi->stack_size);
 			}
 
 		} else {
 
 			/* push %reg */
-			save_reg(state, op->src.reg, CFI_CFA, -state->stack_size);
+			save_reg(cfi, op->src.reg, CFI_CFA, -cfi->stack_size);
 		}
 
 		/* detect when asm code uses rbp as a scratch register */
 		if (!no_fp && insn->func && op->src.reg == CFI_BP &&
 		    cfa->base != CFI_BP)
-			state->bp_scratch = true;
+			cfi->bp_scratch = true;
 		break;
 
 	case OP_DEST_REG_INDIRECT:
 
-		if (state->drap) {
-			if (op->src.reg == cfa->base && op->src.reg == state->drap_reg) {
+		if (cfi->drap) {
+			if (op->src.reg == cfa->base && op->src.reg == cfi->drap_reg) {
 
 				/* drap: mov %drap, disp(%rbp) */
 				cfa->base = CFI_BP_INDIRECT;
 				cfa->offset = op->dest.offset;
 
 				/* save drap offset so we know when to restore it */
-				state->drap_offset = op->dest.offset;
+				cfi->drap_offset = op->dest.offset;
 			}
 
 			else if (regs[op->src.reg].base == CFI_UNDEFINED) {
 
 				/* drap: mov reg, disp(%rbp) */
-				save_reg(state, op->src.reg, CFI_BP, op->dest.offset);
+				save_reg(cfi, op->src.reg, CFI_BP, op->dest.offset);
 			}
 
 		} else if (op->dest.reg == cfa->base) {
 
 			/* mov reg, disp(%rbp) */
 			/* mov reg, disp(%rsp) */
-			save_reg(state, op->src.reg, CFI_CFA,
-				 op->dest.offset - state->cfa.offset);
+			save_reg(cfi, op->src.reg, CFI_CFA,
+				 op->dest.offset - cfi->cfa.offset);
 		}
 
 		break;
 
 	case OP_DEST_LEAVE:
-		if ((!state->drap && cfa->base != CFI_BP) ||
-		    (state->drap && cfa->base != state->drap_reg)) {
+		if ((!cfi->drap && cfa->base != CFI_BP) ||
+		    (cfi->drap && cfa->base != cfi->drap_reg)) {
 			WARN_FUNC("leave instruction with modified stack frame",
 				  insn->sec, insn->offset);
 			return -1;
@@ -1862,10 +2032,10 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 
 		/* leave (mov %rbp, %rsp; pop %rbp) */
 
-		state->stack_size = -state->regs[CFI_BP].offset - 8;
-		restore_reg(state, CFI_BP);
+		cfi->stack_size = -cfi->regs[CFI_BP].offset - 8;
+		restore_reg(cfi, CFI_BP);
 
-		if (!state->drap) {
+		if (!cfi->drap) {
 			cfa->base = CFI_SP;
 			cfa->offset -= 8;
 		}
@@ -1880,7 +2050,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 		}
 
 		/* pop mem */
-		state->stack_size -= 8;
+		cfi->stack_size -= 8;
 		if (cfa->base == CFI_SP)
 			cfa->offset -= 8;
 
@@ -1895,41 +2065,86 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 	return 0;
 }
 
-static bool insn_state_match(struct instruction *insn, struct insn_state *state)
+static int handle_insn_ops(struct instruction *insn, struct insn_state *state)
 {
-	struct insn_state *state1 = &insn->state, *state2 = state;
+	struct stack_op *op;
+
+	list_for_each_entry(op, &insn->stack_ops, list) {
+		struct cfi_state old_cfi = state->cfi;
+		int res;
+
+		res = update_cfi_state(insn, &state->cfi, op);
+		if (res)
+			return res;
+
+		if (insn->alt_group && memcmp(&state->cfi, &old_cfi, sizeof(struct cfi_state))) {
+			WARN_FUNC("alternative modifies stack", insn->sec, insn->offset);
+			return -1;
+		}
+
+		if (op->dest.type == OP_DEST_PUSHF) {
+			if (!state->uaccess_stack) {
+				state->uaccess_stack = 1;
+			} else if (state->uaccess_stack >> 31) {
+				WARN_FUNC("PUSHF stack exhausted",
+					  insn->sec, insn->offset);
+				return 1;
+			}
+			state->uaccess_stack <<= 1;
+			state->uaccess_stack  |= state->uaccess;
+		}
+
+		if (op->src.type == OP_SRC_POPF) {
+			if (state->uaccess_stack) {
+				state->uaccess = state->uaccess_stack & 1;
+				state->uaccess_stack >>= 1;
+				if (state->uaccess_stack == 1)
+					state->uaccess_stack = 0;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2)
+{
+	struct cfi_state *cfi1 = &insn->cfi;
 	int i;
 
-	if (memcmp(&state1->cfa, &state2->cfa, sizeof(state1->cfa))) {
+	if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) {
+
 		WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d",
 			  insn->sec, insn->offset,
-			  state1->cfa.base, state1->cfa.offset,
-			  state2->cfa.base, state2->cfa.offset);
+			  cfi1->cfa.base, cfi1->cfa.offset,
+			  cfi2->cfa.base, cfi2->cfa.offset);
 
-	} else if (memcmp(&state1->regs, &state2->regs, sizeof(state1->regs))) {
+	} else if (memcmp(&cfi1->regs, &cfi2->regs, sizeof(cfi1->regs))) {
 		for (i = 0; i < CFI_NUM_REGS; i++) {
-			if (!memcmp(&state1->regs[i], &state2->regs[i],
+			if (!memcmp(&cfi1->regs[i], &cfi2->regs[i],
 				    sizeof(struct cfi_reg)))
 				continue;
 
 			WARN_FUNC("stack state mismatch: reg1[%d]=%d%+d reg2[%d]=%d%+d",
 				  insn->sec, insn->offset,
-				  i, state1->regs[i].base, state1->regs[i].offset,
-				  i, state2->regs[i].base, state2->regs[i].offset);
+				  i, cfi1->regs[i].base, cfi1->regs[i].offset,
+				  i, cfi2->regs[i].base, cfi2->regs[i].offset);
 			break;
 		}
 
-	} else if (state1->type != state2->type) {
+	} else if (cfi1->type != cfi2->type) {
+
 		WARN_FUNC("stack state mismatch: type1=%d type2=%d",
-			  insn->sec, insn->offset, state1->type, state2->type);
+			  insn->sec, insn->offset, cfi1->type, cfi2->type);
+
+	} else if (cfi1->drap != cfi2->drap ||
+		   (cfi1->drap && cfi1->drap_reg != cfi2->drap_reg) ||
+		   (cfi1->drap && cfi1->drap_offset != cfi2->drap_offset)) {
 
-	} else if (state1->drap != state2->drap ||
-		 (state1->drap && state1->drap_reg != state2->drap_reg) ||
-		 (state1->drap && state1->drap_offset != state2->drap_offset)) {
 		WARN_FUNC("stack state mismatch: drap1=%d(%d,%d) drap2=%d(%d,%d)",
 			  insn->sec, insn->offset,
-			  state1->drap, state1->drap_reg, state1->drap_offset,
-			  state2->drap, state2->drap_reg, state2->drap_offset);
+			  cfi1->drap, cfi1->drap_reg, cfi1->drap_offset,
+			  cfi2->drap, cfi2->drap_reg, cfi2->drap_offset);
 
 	} else
 		return true;
@@ -1955,6 +2170,13 @@ static inline const char *call_dest_name(struct instruction *insn)
 
 static int validate_call(struct instruction *insn, struct insn_state *state)
 {
+	if (state->noinstr && state->instr <= 0 &&
+	    (!insn->call_dest || !insn->call_dest->sec->noinstr)) {
+		WARN_FUNC("call to %s() leaves .noinstr.text section",
+				insn->sec, insn->offset, call_dest_name(insn));
+		return 1;
+	}
+
 	if (state->uaccess && !func_uaccess_safe(insn->call_dest)) {
 		WARN_FUNC("call to %s() with UACCESS enabled",
 				insn->sec, insn->offset, call_dest_name(insn));
@@ -1972,7 +2194,7 @@ static int validate_call(struct instruction *insn, struct insn_state *state)
 
 static int validate_sibling_call(struct instruction *insn, struct insn_state *state)
 {
-	if (has_modified_stack_frame(state)) {
+	if (has_modified_stack_frame(insn, state)) {
 		WARN_FUNC("sibling call from callable instruction with modified stack frame",
 				insn->sec, insn->offset);
 		return 1;
@@ -1983,6 +2205,12 @@ static int validate_sibling_call(struct instruction *insn, struct insn_state *st
 
 static int validate_return(struct symbol *func, struct instruction *insn, struct insn_state *state)
 {
+	if (state->noinstr && state->instr > 0) {
+		WARN_FUNC("return with instrumentation enabled",
+			  insn->sec, insn->offset);
+		return 1;
+	}
+
 	if (state->uaccess && !func_uaccess_safe(func)) {
 		WARN_FUNC("return with UACCESS enabled",
 			  insn->sec, insn->offset);
@@ -2001,15 +2229,15 @@ static int validate_return(struct symbol *func, struct instruction *insn, struct
 		return 1;
 	}
 
-	if (func && has_modified_stack_frame(state)) {
+	if (func && has_modified_stack_frame(insn, state)) {
 		WARN_FUNC("return with modified stack frame",
 			  insn->sec, insn->offset);
 		return 1;
 	}
 
-	if (state->bp_scratch) {
-		WARN("%s uses BP as a scratch register",
-		     func->name);
+	if (state->cfi.bp_scratch) {
+		WARN_FUNC("BP used as a scratch register",
+			  insn->sec, insn->offset);
 		return 1;
 	}
 
@@ -2017,29 +2245,46 @@ static int validate_return(struct symbol *func, struct instruction *insn, struct
 }
 
 /*
+ * Alternatives should not contain any ORC entries, this in turn means they
+ * should not contain any CFI ops, which implies all instructions should have
+ * the same same CFI state.
+ *
+ * It is possible to constuct alternatives that have unreachable holes that go
+ * unreported (because they're NOPs), such holes would result in CFI_UNDEFINED
+ * states which then results in ORC entries, which we just said we didn't want.
+ *
+ * Avoid them by copying the CFI entry of the first instruction into the whole
+ * alternative.
+ */
+static void fill_alternative_cfi(struct objtool_file *file, struct instruction *insn)
+{
+	struct instruction *first_insn = insn;
+	int alt_group = insn->alt_group;
+
+	sec_for_each_insn_continue(file, insn) {
+		if (insn->alt_group != alt_group)
+			break;
+		insn->cfi = first_insn->cfi;
+	}
+}
+
+/*
  * Follow the branch starting at the given instruction, and recursively follow
  * any other branches (jumps).  Meanwhile, track the frame pointer state at
  * each instruction and validate all the rules described in
  * tools/objtool/Documentation/stack-validation.txt.
  */
 static int validate_branch(struct objtool_file *file, struct symbol *func,
-			   struct instruction *first, struct insn_state state)
+			   struct instruction *insn, struct insn_state state)
 {
 	struct alternative *alt;
-	struct instruction *insn, *next_insn;
+	struct instruction *next_insn;
 	struct section *sec;
 	u8 visited;
 	int ret;
 
-	insn = first;
 	sec = insn->sec;
 
-	if (insn->alt_group && list_empty(&insn->alts)) {
-		WARN_FUNC("don't know how to handle branch to middle of alternative instruction group",
-			  sec, insn->offset);
-		return 1;
-	}
-
 	while (1) {
 		next_insn = next_insn_same_sec(file, insn);
 
@@ -2057,59 +2302,24 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 
 		visited = 1 << state.uaccess;
 		if (insn->visited) {
-			if (!insn->hint && !insn_state_match(insn, &state))
+			if (!insn->hint && !insn_cfi_match(insn, &state.cfi))
 				return 1;
 
 			if (insn->visited & visited)
 				return 0;
 		}
 
-		if (insn->hint) {
-			if (insn->restore) {
-				struct instruction *save_insn, *i;
-
-				i = insn;
-				save_insn = NULL;
-				sym_for_each_insn_continue_reverse(file, func, i) {
-					if (i->save) {
-						save_insn = i;
-						break;
-					}
-				}
-
-				if (!save_insn) {
-					WARN_FUNC("no corresponding CFI save for CFI restore",
-						  sec, insn->offset);
-					return 1;
-				}
-
-				if (!save_insn->visited) {
-					/*
-					 * Oops, no state to copy yet.
-					 * Hopefully we can reach this
-					 * instruction from another branch
-					 * after the save insn has been
-					 * visited.
-					 */
-					if (insn == first)
-						return 0;
-
-					WARN_FUNC("objtool isn't smart enough to handle this CFI save/restore combo",
-						  sec, insn->offset);
-					return 1;
-				}
+		if (state.noinstr)
+			state.instr += insn->instr;
 
-				insn->state = save_insn->state;
-			}
-
-			state = insn->state;
-
-		} else
-			insn->state = state;
+		if (insn->hint)
+			state.cfi = insn->cfi;
+		else
+			insn->cfi = state.cfi;
 
 		insn->visited |= visited;
 
-		if (!insn->ignore_alts) {
+		if (!insn->ignore_alts && !list_empty(&insn->alts)) {
 			bool skip_orig = false;
 
 			list_for_each_entry(alt, &insn->alts, list) {
@@ -2124,10 +2334,16 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 				}
 			}
 
+			if (insn->alt_group)
+				fill_alternative_cfi(file, insn);
+
 			if (skip_orig)
 				return 0;
 		}
 
+		if (handle_insn_ops(insn, &state))
+			return 1;
+
 		switch (insn->type) {
 
 		case INSN_RETURN:
@@ -2194,32 +2410,6 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			}
 			return 0;
 
-		case INSN_STACK:
-			if (update_insn_state(insn, &state))
-				return 1;
-
-			if (insn->stack_op.dest.type == OP_DEST_PUSHF) {
-				if (!state.uaccess_stack) {
-					state.uaccess_stack = 1;
-				} else if (state.uaccess_stack >> 31) {
-					WARN_FUNC("PUSHF stack exhausted", sec, insn->offset);
-					return 1;
-				}
-				state.uaccess_stack <<= 1;
-				state.uaccess_stack  |= state.uaccess;
-			}
-
-			if (insn->stack_op.src.type == OP_SRC_POPF) {
-				if (state.uaccess_stack) {
-					state.uaccess = state.uaccess_stack & 1;
-					state.uaccess_stack >>= 1;
-					if (state.uaccess_stack == 1)
-						state.uaccess_stack = 0;
-				}
-			}
-
-			break;
-
 		case INSN_STAC:
 			if (state.uaccess) {
 				WARN_FUNC("recursive UACCESS enable", sec, insn->offset);
@@ -2265,7 +2455,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			return 0;
 
 		if (!next_insn) {
-			if (state.cfa.base == CFI_UNDEFINED)
+			if (state.cfi.cfa.base == CFI_UNDEFINED)
 				return 0;
 			WARN("%s: unexpected end of section", sec->name);
 			return 1;
@@ -2277,24 +2467,34 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 	return 0;
 }
 
-static int validate_unwind_hints(struct objtool_file *file)
+static int validate_unwind_hints(struct objtool_file *file, struct section *sec)
 {
 	struct instruction *insn;
-	int ret, warnings = 0;
 	struct insn_state state;
+	int ret, warnings = 0;
 
 	if (!file->hints)
 		return 0;
 
-	clear_insn_state(&state);
+	init_insn_state(&state, sec);
 
-	for_each_insn(file, insn) {
+	if (sec) {
+		insn = find_insn(file, sec, 0);
+		if (!insn)
+			return 0;
+	} else {
+		insn = list_first_entry(&file->insn_list, typeof(*insn), list);
+	}
+
+	while (&insn->list != &file->insn_list && (!sec || insn->sec == sec)) {
 		if (insn->hint && !insn->visited) {
 			ret = validate_branch(file, insn->func, insn, state);
 			if (ret && backtrace)
 				BT_FUNC("<=== (hint)", insn);
 			warnings += ret;
 		}
+
+		insn = list_next_entry(insn, list);
 	}
 
 	return warnings;
@@ -2364,14 +2564,27 @@ static bool ignore_unreachable_insn(struct instruction *insn)
 	    !strcmp(insn->sec->name, ".altinstr_aux"))
 		return true;
 
+	if (!insn->func)
+		return false;
+
+	/*
+	 * CONFIG_UBSAN_TRAP inserts a UD2 when it sees
+	 * __builtin_unreachable().  The BUG() macro has an unreachable() after
+	 * the UD2, which causes GCC's undefined trap logic to emit another UD2
+	 * (or occasionally a JMP to UD2).
+	 */
+	if (list_prev_entry(insn, list)->dead_end &&
+	    (insn->type == INSN_BUG ||
+	     (insn->type == INSN_JUMP_UNCONDITIONAL &&
+	      insn->jump_dest && insn->jump_dest->type == INSN_BUG)))
+		return true;
+
 	/*
 	 * Check if this (or a subsequent) instruction is related to
 	 * CONFIG_UBSAN or CONFIG_KASAN.
 	 *
 	 * End the search at 5 instructions to avoid going into the weeds.
 	 */
-	if (!insn->func)
-		return false;
 	for (i = 0; i < 5; i++) {
 
 		if (is_kasan_insn(insn) || is_ubsan_insn(insn))
@@ -2396,43 +2609,69 @@ static bool ignore_unreachable_insn(struct instruction *insn)
 	return false;
 }
 
-static int validate_section(struct objtool_file *file, struct section *sec)
+static int validate_symbol(struct objtool_file *file, struct section *sec,
+			   struct symbol *sym, struct insn_state *state)
 {
-	struct symbol *func;
 	struct instruction *insn;
-	struct insn_state state;
-	int ret, warnings = 0;
+	int ret;
+
+	if (!sym->len) {
+		WARN("%s() is missing an ELF size annotation", sym->name);
+		return 1;
+	}
+
+	if (sym->pfunc != sym || sym->alias != sym)
+		return 0;
+
+	insn = find_insn(file, sec, sym->offset);
+	if (!insn || insn->ignore || insn->visited)
+		return 0;
 
-	clear_insn_state(&state);
+	state->uaccess = sym->uaccess_safe;
 
-	state.cfa = initial_func_cfi.cfa;
-	memcpy(&state.regs, &initial_func_cfi.regs,
-	       CFI_NUM_REGS * sizeof(struct cfi_reg));
-	state.stack_size = initial_func_cfi.cfa.offset;
+	ret = validate_branch(file, insn->func, insn, *state);
+	if (ret && backtrace)
+		BT_FUNC("<=== (sym)", insn);
+	return ret;
+}
+
+static int validate_section(struct objtool_file *file, struct section *sec)
+{
+	struct insn_state state;
+	struct symbol *func;
+	int warnings = 0;
 
 	list_for_each_entry(func, &sec->symbol_list, list) {
 		if (func->type != STT_FUNC)
 			continue;
 
-		if (!func->len) {
-			WARN("%s() is missing an ELF size annotation",
-			     func->name);
-			warnings++;
-		}
+		init_insn_state(&state, sec);
+		state.cfi.cfa = initial_func_cfi.cfa;
+		memcpy(&state.cfi.regs, &initial_func_cfi.regs,
+		       CFI_NUM_REGS * sizeof(struct cfi_reg));
+		state.cfi.stack_size = initial_func_cfi.cfa.offset;
 
-		if (func->pfunc != func || func->alias != func)
-			continue;
+		warnings += validate_symbol(file, sec, func, &state);
+	}
 
-		insn = find_insn(file, sec, func->offset);
-		if (!insn || insn->ignore || insn->visited)
-			continue;
+	return warnings;
+}
+
+static int validate_vmlinux_functions(struct objtool_file *file)
+{
+	struct section *sec;
+	int warnings = 0;
 
-		state.uaccess = func->uaccess_safe;
+	sec = find_section_by_name(file->elf, ".noinstr.text");
+	if (sec) {
+		warnings += validate_section(file, sec);
+		warnings += validate_unwind_hints(file, sec);
+	}
 
-		ret = validate_branch(file, func, insn, state);
-		if (ret && backtrace)
-			BT_FUNC("<=== (func)", insn);
-		warnings += ret;
+	sec = find_section_by_name(file->elf, ".entry.text");
+	if (sec) {
+		warnings += validate_section(file, sec);
+		warnings += validate_unwind_hints(file, sec);
 	}
 
 	return warnings;
@@ -2443,8 +2682,12 @@ static int validate_functions(struct objtool_file *file)
 	struct section *sec;
 	int warnings = 0;
 
-	for_each_sec(file, sec)
+	for_each_sec(file, sec) {
+		if (!(sec->sh.sh_flags & SHF_EXECINSTR))
+			continue;
+
 		warnings += validate_section(file, sec);
+	}
 
 	return warnings;
 }
@@ -2475,7 +2718,7 @@ int check(const char *_objname, bool orc)
 
 	objname = _objname;
 
-	file.elf = elf_read(objname, orc ? O_RDWR : O_RDONLY);
+	file.elf = elf_open_read(objname, orc ? O_RDWR : O_RDONLY);
 	if (!file.elf)
 		return 1;
 
@@ -2495,6 +2738,15 @@ int check(const char *_objname, bool orc)
 	if (list_empty(&file.insn_list))
 		goto out;
 
+	if (vmlinux && !validate_dup) {
+		ret = validate_vmlinux_functions(&file);
+		if (ret < 0)
+			goto out;
+
+		warnings += ret;
+		goto out;
+	}
+
 	if (retpoline) {
 		ret = validate_retpoline(&file);
 		if (ret < 0)
@@ -2507,7 +2759,7 @@ int check(const char *_objname, bool orc)
 		goto out;
 	warnings += ret;
 
-	ret = validate_unwind_hints(&file);
+	ret = validate_unwind_hints(&file, NULL);
 	if (ret < 0)
 		goto out;
 	warnings += ret;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index f0ce8ffe7135..906b5210f7ca 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -7,22 +7,16 @@
 #define _CHECK_H
 
 #include <stdbool.h>
-#include "elf.h"
 #include "cfi.h"
 #include "arch.h"
-#include "orc.h"
-#include <linux/hashtable.h>
 
 struct insn_state {
-	struct cfi_reg cfa;
-	struct cfi_reg regs[CFI_NUM_REGS];
-	int stack_size;
-	unsigned char type;
-	bool bp_scratch;
-	bool drap, end, uaccess, df;
+	struct cfi_state cfi;
 	unsigned int uaccess_stack;
-	int drap_reg, drap_offset;
-	struct cfi_reg vals[CFI_NUM_REGS];
+	bool uaccess;
+	bool df;
+	bool noinstr;
+	s8 instr;
 };
 
 struct instruction {
@@ -33,29 +27,24 @@ struct instruction {
 	unsigned int len;
 	enum insn_type type;
 	unsigned long immediate;
-	bool alt_group, dead_end, ignore, hint, save, restore, ignore_alts;
+	bool dead_end, ignore, ignore_alts;
+	bool hint;
 	bool retpoline_safe;
+	s8 instr;
 	u8 visited;
+	u8 ret_offset;
+	int alt_group;
 	struct symbol *call_dest;
 	struct instruction *jump_dest;
 	struct instruction *first_jump_src;
 	struct rela *jump_table;
 	struct list_head alts;
 	struct symbol *func;
-	struct stack_op stack_op;
-	struct insn_state state;
+	struct list_head stack_ops;
+	struct cfi_state cfi;
 	struct orc_entry orc;
 };
 
-struct objtool_file {
-	struct elf *elf;
-	struct list_head insn_list;
-	DECLARE_HASHTABLE(insn_hash, 20);
-	bool ignore_unreachables, c_file, hints, rodata;
-};
-
-int check(const char *objname, bool orc);
-
 struct instruction *find_insn(struct objtool_file *file,
 			      struct section *sec, unsigned long offset);
 
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 09ddc8f1def3..84225679f96d 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -27,6 +27,22 @@ static inline u32 str_hash(const char *str)
 	return jhash(str, strlen(str), 0);
 }
 
+static inline int elf_hash_bits(void)
+{
+	return vmlinux ? ELF_HASH_BITS : 16;
+}
+
+#define elf_hash_add(hashtable, node, key) \
+	hlist_add_head(node, &hashtable[hash_min(key, elf_hash_bits())])
+
+static void elf_hash_init(struct hlist_head *table)
+{
+	__hash_init(table, 1U << elf_hash_bits());
+}
+
+#define elf_hash_for_each_possible(name, obj, member, key)			\
+	hlist_for_each_entry(obj, &name[hash_min(key, elf_hash_bits())], member)
+
 static void rb_add(struct rb_root *tree, struct rb_node *node,
 		   int (*cmp)(struct rb_node *, const struct rb_node *))
 {
@@ -45,7 +61,7 @@ static void rb_add(struct rb_root *tree, struct rb_node *node,
 	rb_insert_color(node, tree);
 }
 
-static struct rb_node *rb_find_first(struct rb_root *tree, const void *key,
+static struct rb_node *rb_find_first(const struct rb_root *tree, const void *key,
 			       int (*cmp)(const void *key, const struct rb_node *))
 {
 	struct rb_node *node = tree->rb_node;
@@ -105,17 +121,17 @@ static int symbol_by_offset(const void *key, const struct rb_node *node)
 
 	if (*o < s->offset)
 		return -1;
-	if (*o > s->offset + s->len)
+	if (*o >= s->offset + s->len)
 		return 1;
 
 	return 0;
 }
 
-struct section *find_section_by_name(struct elf *elf, const char *name)
+struct section *find_section_by_name(const struct elf *elf, const char *name)
 {
 	struct section *sec;
 
-	hash_for_each_possible(elf->section_name_hash, sec, name_hash, str_hash(name))
+	elf_hash_for_each_possible(elf->section_name_hash, sec, name_hash, str_hash(name))
 		if (!strcmp(sec->name, name))
 			return sec;
 
@@ -127,7 +143,7 @@ static struct section *find_section_by_index(struct elf *elf,
 {
 	struct section *sec;
 
-	hash_for_each_possible(elf->section_hash, sec, hash, idx)
+	elf_hash_for_each_possible(elf->section_hash, sec, hash, idx)
 		if (sec->idx == idx)
 			return sec;
 
@@ -138,7 +154,7 @@ static struct symbol *find_symbol_by_index(struct elf *elf, unsigned int idx)
 {
 	struct symbol *sym;
 
-	hash_for_each_possible(elf->symbol_hash, sym, hash, idx)
+	elf_hash_for_each_possible(elf->symbol_hash, sym, hash, idx)
 		if (sym->idx == idx)
 			return sym;
 
@@ -173,7 +189,7 @@ struct symbol *find_func_by_offset(struct section *sec, unsigned long offset)
 	return NULL;
 }
 
-struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
+struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset)
 {
 	struct rb_node *node;
 
@@ -201,18 +217,18 @@ struct symbol *find_func_containing(struct section *sec, unsigned long offset)
 	return NULL;
 }
 
-struct symbol *find_symbol_by_name(struct elf *elf, const char *name)
+struct symbol *find_symbol_by_name(const struct elf *elf, const char *name)
 {
 	struct symbol *sym;
 
-	hash_for_each_possible(elf->symbol_name_hash, sym, name_hash, str_hash(name))
+	elf_hash_for_each_possible(elf->symbol_name_hash, sym, name_hash, str_hash(name))
 		if (!strcmp(sym->name, name))
 			return sym;
 
 	return NULL;
 }
 
-struct rela *find_rela_by_dest_range(struct elf *elf, struct section *sec,
+struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec,
 				     unsigned long offset, unsigned int len)
 {
 	struct rela *rela, *r = NULL;
@@ -224,7 +240,7 @@ struct rela *find_rela_by_dest_range(struct elf *elf, struct section *sec,
 	sec = sec->rela;
 
 	for_offset_range(o, offset, offset + len) {
-		hash_for_each_possible(elf->rela_hash, rela, hash,
+		elf_hash_for_each_possible(elf->rela_hash, rela, hash,
 				       sec_offset_hash(sec, o)) {
 			if (rela->sec != sec)
 				continue;
@@ -241,7 +257,7 @@ struct rela *find_rela_by_dest_range(struct elf *elf, struct section *sec,
 	return NULL;
 }
 
-struct rela *find_rela_by_dest(struct elf *elf, struct section *sec, unsigned long offset)
+struct rela *find_rela_by_dest(const struct elf *elf, struct section *sec, unsigned long offset)
 {
 	return find_rela_by_dest_range(elf, sec, offset, 1);
 }
@@ -309,8 +325,8 @@ static int read_sections(struct elf *elf)
 		sec->len = sec->sh.sh_size;
 
 		list_add_tail(&sec->list, &elf->sections);
-		hash_add(elf->section_hash, &sec->hash, sec->idx);
-		hash_add(elf->section_name_hash, &sec->name_hash, str_hash(sec->name));
+		elf_hash_add(elf->section_hash, &sec->hash, sec->idx);
+		elf_hash_add(elf->section_name_hash, &sec->name_hash, str_hash(sec->name));
 	}
 
 	if (stats)
@@ -327,12 +343,14 @@ static int read_sections(struct elf *elf)
 
 static int read_symbols(struct elf *elf)
 {
-	struct section *symtab, *sec;
+	struct section *symtab, *symtab_shndx, *sec;
 	struct symbol *sym, *pfunc;
 	struct list_head *entry;
 	struct rb_node *pnode;
 	int symbols_nr, i;
 	char *coldstr;
+	Elf_Data *shndx_data = NULL;
+	Elf32_Word shndx;
 
 	symtab = find_section_by_name(elf, ".symtab");
 	if (!symtab) {
@@ -340,6 +358,10 @@ static int read_symbols(struct elf *elf)
 		return -1;
 	}
 
+	symtab_shndx = find_section_by_name(elf, ".symtab_shndx");
+	if (symtab_shndx)
+		shndx_data = symtab_shndx->data;
+
 	symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize;
 
 	for (i = 0; i < symbols_nr; i++) {
@@ -353,8 +375,9 @@ static int read_symbols(struct elf *elf)
 
 		sym->idx = i;
 
-		if (!gelf_getsym(symtab->data, i, &sym->sym)) {
-			WARN_ELF("gelf_getsym");
+		if (!gelf_getsymshndx(symtab->data, shndx_data, i, &sym->sym,
+				      &shndx)) {
+			WARN_ELF("gelf_getsymshndx");
 			goto err;
 		}
 
@@ -368,10 +391,13 @@ static int read_symbols(struct elf *elf)
 		sym->type = GELF_ST_TYPE(sym->sym.st_info);
 		sym->bind = GELF_ST_BIND(sym->sym.st_info);
 
-		if (sym->sym.st_shndx > SHN_UNDEF &&
-		    sym->sym.st_shndx < SHN_LORESERVE) {
-			sym->sec = find_section_by_index(elf,
-							 sym->sym.st_shndx);
+		if ((sym->sym.st_shndx > SHN_UNDEF &&
+		     sym->sym.st_shndx < SHN_LORESERVE) ||
+		    (shndx_data && sym->sym.st_shndx == SHN_XINDEX)) {
+			if (sym->sym.st_shndx != SHN_XINDEX)
+				shndx = sym->sym.st_shndx;
+
+			sym->sec = find_section_by_index(elf, shndx);
 			if (!sym->sec) {
 				WARN("couldn't find section for symbol %s",
 				     sym->name);
@@ -394,8 +420,8 @@ static int read_symbols(struct elf *elf)
 		else
 			entry = &sym->sec->symbol_list;
 		list_add(&sym->list, entry);
-		hash_add(elf->symbol_hash, &sym->hash, sym->idx);
-		hash_add(elf->symbol_name_hash, &sym->name_hash, str_hash(sym->name));
+		elf_hash_add(elf->symbol_hash, &sym->hash, sym->idx);
+		elf_hash_add(elf->symbol_name_hash, &sym->name_hash, str_hash(sym->name));
 	}
 
 	if (stats)
@@ -456,6 +482,14 @@ err:
 	return -1;
 }
 
+void elf_add_rela(struct elf *elf, struct rela *rela)
+{
+	struct section *sec = rela->sec;
+
+	list_add_tail(&rela->list, &sec->rela_list);
+	elf_hash_add(elf->rela_hash, &rela->hash, rela_hash(rela));
+}
+
 static int read_relas(struct elf *elf)
 {
 	struct section *sec;
@@ -503,8 +537,7 @@ static int read_relas(struct elf *elf)
 				return -1;
 			}
 
-			list_add_tail(&rela->list, &sec->rela_list);
-			hash_add(elf->rela_hash, &rela->hash, rela_hash(rela));
+			elf_add_rela(elf, rela);
 			nr_rela++;
 		}
 		max_rela = max(max_rela, nr_rela);
@@ -519,7 +552,7 @@ static int read_relas(struct elf *elf)
 	return 0;
 }
 
-struct elf *elf_read(const char *name, int flags)
+struct elf *elf_open_read(const char *name, int flags)
 {
 	struct elf *elf;
 	Elf_Cmd cmd;
@@ -531,15 +564,16 @@ struct elf *elf_read(const char *name, int flags)
 		perror("malloc");
 		return NULL;
 	}
-	memset(elf, 0, sizeof(*elf));
+	memset(elf, 0, offsetof(struct elf, sections));
 
-	hash_init(elf->symbol_hash);
-	hash_init(elf->symbol_name_hash);
-	hash_init(elf->section_hash);
-	hash_init(elf->section_name_hash);
-	hash_init(elf->rela_hash);
 	INIT_LIST_HEAD(&elf->sections);
 
+	elf_hash_init(elf->symbol_hash);
+	elf_hash_init(elf->symbol_name_hash);
+	elf_hash_init(elf->section_hash);
+	elf_hash_init(elf->section_name_hash);
+	elf_hash_init(elf->rela_hash);
+
 	elf->fd = open(name, flags);
 	if (elf->fd == -1) {
 		fprintf(stderr, "objtool: Can't open '%s': %s\n",
@@ -676,8 +710,8 @@ struct section *elf_create_section(struct elf *elf, const char *name,
 	shstrtab->changed = true;
 
 	list_add_tail(&sec->list, &elf->sections);
-	hash_add(elf->section_hash, &sec->hash, sec->idx);
-	hash_add(elf->section_name_hash, &sec->name_hash, str_hash(sec->name));
+	elf_hash_add(elf->section_hash, &sec->hash, sec->idx);
+	elf_hash_add(elf->section_name_hash, &sec->name_hash, str_hash(sec->name));
 
 	return sec;
 }
@@ -745,7 +779,7 @@ int elf_rebuild_rela_section(struct section *sec)
 	return 0;
 }
 
-int elf_write(struct elf *elf)
+int elf_write(const struct elf *elf)
 {
 	struct section *sec;
 	Elf_Scn *s;
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index ebbb10c61e24..f4fe1d6ea392 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -39,7 +39,7 @@ struct section {
 	char *name;
 	int idx;
 	unsigned int len;
-	bool changed, text, rodata;
+	bool changed, text, rodata, noinstr;
 };
 
 struct symbol {
@@ -70,26 +70,29 @@ struct rela {
 	bool jump_table_start;
 };
 
+#define ELF_HASH_BITS	20
+
 struct elf {
 	Elf *elf;
 	GElf_Ehdr ehdr;
 	int fd;
 	char *name;
 	struct list_head sections;
-	DECLARE_HASHTABLE(symbol_hash, 20);
-	DECLARE_HASHTABLE(symbol_name_hash, 20);
-	DECLARE_HASHTABLE(section_hash, 16);
-	DECLARE_HASHTABLE(section_name_hash, 16);
-	DECLARE_HASHTABLE(rela_hash, 20);
+	DECLARE_HASHTABLE(symbol_hash, ELF_HASH_BITS);
+	DECLARE_HASHTABLE(symbol_name_hash, ELF_HASH_BITS);
+	DECLARE_HASHTABLE(section_hash, ELF_HASH_BITS);
+	DECLARE_HASHTABLE(section_name_hash, ELF_HASH_BITS);
+	DECLARE_HASHTABLE(rela_hash, ELF_HASH_BITS);
 };
 
 #define OFFSET_STRIDE_BITS	4
 #define OFFSET_STRIDE		(1UL << OFFSET_STRIDE_BITS)
 #define OFFSET_STRIDE_MASK	(~(OFFSET_STRIDE - 1))
 
-#define for_offset_range(_offset, _start, _end)		\
-	for (_offset = ((_start) & OFFSET_STRIDE_MASK);	\
-	     _offset <= ((_end) & OFFSET_STRIDE_MASK);	\
+#define for_offset_range(_offset, _start, _end)			\
+	for (_offset = ((_start) & OFFSET_STRIDE_MASK);		\
+	     _offset >= ((_start) & OFFSET_STRIDE_MASK) &&	\
+	     _offset <= ((_end) & OFFSET_STRIDE_MASK);		\
 	     _offset += OFFSET_STRIDE)
 
 static inline u32 sec_offset_hash(struct section *sec, unsigned long offset)
@@ -99,7 +102,7 @@ static inline u32 sec_offset_hash(struct section *sec, unsigned long offset)
 	offset &= OFFSET_STRIDE_MASK;
 
 	ol = offset;
-	oh = offset >> 32;
+	oh = (offset >> 16) >> 16;
 
 	__jhash_mix(ol, oh, idx);
 
@@ -111,22 +114,23 @@ static inline u32 rela_hash(struct rela *rela)
 	return sec_offset_hash(rela->sec, rela->offset);
 }
 
-struct elf *elf_read(const char *name, int flags);
-struct section *find_section_by_name(struct elf *elf, const char *name);
+struct elf *elf_open_read(const char *name, int flags);
+struct section *elf_create_section(struct elf *elf, const char *name, size_t entsize, int nr);
+struct section *elf_create_rela_section(struct elf *elf, struct section *base);
+void elf_add_rela(struct elf *elf, struct rela *rela);
+int elf_write(const struct elf *elf);
+void elf_close(struct elf *elf);
+
+struct section *find_section_by_name(const struct elf *elf, const char *name);
 struct symbol *find_func_by_offset(struct section *sec, unsigned long offset);
 struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
-struct symbol *find_symbol_by_name(struct elf *elf, const char *name);
-struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
-struct rela *find_rela_by_dest(struct elf *elf, struct section *sec, unsigned long offset);
-struct rela *find_rela_by_dest_range(struct elf *elf, struct section *sec,
+struct symbol *find_symbol_by_name(const struct elf *elf, const char *name);
+struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset);
+struct rela *find_rela_by_dest(const struct elf *elf, struct section *sec, unsigned long offset);
+struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec,
 				     unsigned long offset, unsigned int len);
 struct symbol *find_func_containing(struct section *sec, unsigned long offset);
-struct section *elf_create_section(struct elf *elf, const char *name, size_t
-				   entsize, int nr);
-struct section *elf_create_rela_section(struct elf *elf, struct section *base);
 int elf_rebuild_rela_section(struct section *sec);
-int elf_write(struct elf *elf);
-void elf_close(struct elf *elf);
 
 #define for_each_sec(file, sec)						\
 	list_for_each_entry(sec, &file->elf->sections, list)
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index 0b3528f05053..58fdda510653 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -58,7 +58,9 @@ static void cmd_usage(void)
 
 	printf("\n");
 
-	exit(129);
+	if (!help)
+		exit(129);
+	exit(0);
 }
 
 static void handle_options(int *argc, const char ***argv)
diff --git a/tools/objtool/objtool.h b/tools/objtool/objtool.h
new file mode 100644
index 000000000000..528028a66816
--- /dev/null
+++ b/tools/objtool/objtool.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2020 Matt Helsley <mhelsley@vmware.com>
+ */
+
+#ifndef _OBJTOOL_H
+#define _OBJTOOL_H
+
+#include <stdbool.h>
+#include <linux/list.h>
+#include <linux/hashtable.h>
+
+#include "elf.h"
+
+struct objtool_file {
+	struct elf *elf;
+	struct list_head insn_list;
+	DECLARE_HASHTABLE(insn_hash, 20);
+	bool ignore_unreachables, c_file, hints, rodata;
+};
+
+int check(const char *objname, bool orc);
+int orc_dump(const char *objname);
+int create_orc(struct objtool_file *file);
+int create_orc_sections(struct objtool_file *file);
+
+#endif /* _OBJTOOL_H */
diff --git a/tools/objtool/orc.h b/tools/objtool/orc.h
deleted file mode 100644
index ee2832221e62..000000000000
--- a/tools/objtool/orc.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
- */
-
-#ifndef _ORC_H
-#define _ORC_H
-
-#include <asm/orc_types.h>
-
-struct objtool_file;
-
-int create_orc(struct objtool_file *file);
-int create_orc_sections(struct objtool_file *file);
-
-int orc_dump(const char *objname);
-
-#endif /* _ORC_H */
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index 13ccf775a83a..fca46e006fc2 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -4,7 +4,8 @@
  */
 
 #include <unistd.h>
-#include "orc.h"
+#include <asm/orc_types.h>
+#include "objtool.h"
 #include "warn.h"
 
 static const char *reg_name(unsigned int reg)
@@ -66,7 +67,7 @@ int orc_dump(const char *_objname)
 	char *name;
 	size_t nr_sections;
 	Elf64_Addr orc_ip_addr = 0;
-	size_t shstrtab_idx;
+	size_t shstrtab_idx, strtab_idx = 0;
 	Elf *elf;
 	Elf_Scn *scn;
 	GElf_Shdr sh;
@@ -127,6 +128,8 @@ int orc_dump(const char *_objname)
 
 		if (!strcmp(name, ".symtab")) {
 			symtab = data;
+		} else if (!strcmp(name, ".strtab")) {
+			strtab_idx = i;
 		} else if (!strcmp(name, ".orc_unwind")) {
 			orc = data->d_buf;
 			orc_size = sh.sh_size;
@@ -138,7 +141,7 @@ int orc_dump(const char *_objname)
 		}
 	}
 
-	if (!symtab || !orc || !orc_ip)
+	if (!symtab || !strtab_idx || !orc || !orc_ip)
 		return 0;
 
 	if (orc_size % sizeof(*orc) != 0) {
@@ -159,21 +162,29 @@ int orc_dump(const char *_objname)
 				return -1;
 			}
 
-			scn = elf_getscn(elf, sym.st_shndx);
-			if (!scn) {
-				WARN_ELF("elf_getscn");
-				return -1;
-			}
-
-			if (!gelf_getshdr(scn, &sh)) {
-				WARN_ELF("gelf_getshdr");
-				return -1;
-			}
-
-			name = elf_strptr(elf, shstrtab_idx, sh.sh_name);
-			if (!name || !*name) {
-				WARN_ELF("elf_strptr");
-				return -1;
+			if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) {
+				scn = elf_getscn(elf, sym.st_shndx);
+				if (!scn) {
+					WARN_ELF("elf_getscn");
+					return -1;
+				}
+
+				if (!gelf_getshdr(scn, &sh)) {
+					WARN_ELF("gelf_getshdr");
+					return -1;
+				}
+
+				name = elf_strptr(elf, shstrtab_idx, sh.sh_name);
+				if (!name) {
+					WARN_ELF("elf_strptr");
+					return -1;
+				}
+			} else {
+				name = elf_strptr(elf, strtab_idx, sym.st_name);
+				if (!name) {
+					WARN_ELF("elf_strptr");
+					return -1;
+				}
 			}
 
 			printf("%s+%llx:", name, (unsigned long long)rela.r_addend);
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 41e4a2754da4..c9549988121a 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -6,7 +6,6 @@
 #include <stdlib.h>
 #include <string.h>
 
-#include "orc.h"
 #include "check.h"
 #include "warn.h"
 
@@ -16,10 +15,10 @@ int create_orc(struct objtool_file *file)
 
 	for_each_insn(file, insn) {
 		struct orc_entry *orc = &insn->orc;
-		struct cfi_reg *cfa = &insn->state.cfa;
-		struct cfi_reg *bp = &insn->state.regs[CFI_BP];
+		struct cfi_reg *cfa = &insn->cfi.cfa;
+		struct cfi_reg *bp = &insn->cfi.regs[CFI_BP];
 
-		orc->end = insn->state.end;
+		orc->end = insn->cfi.end;
 
 		if (cfa->base == CFI_UNDEFINED) {
 			orc->sp_reg = ORC_REG_UNDEFINED;
@@ -75,7 +74,7 @@ int create_orc(struct objtool_file *file)
 
 		orc->sp_offset = cfa->offset;
 		orc->bp_offset = bp->offset;
-		orc->type = insn->state.type;
+		orc->type = insn->cfi.type;
 	}
 
 	return 0;
@@ -88,11 +87,6 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti
 	struct orc_entry *orc;
 	struct rela *rela;
 
-	if (!insn_sec->sym) {
-		WARN("missing symbol for section %s", insn_sec->name);
-		return -1;
-	}
-
 	/* populate ORC data */
 	orc = (struct orc_entry *)u_sec->data->d_buf + idx;
 	memcpy(orc, o, sizeof(*orc));
@@ -105,14 +99,37 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti
 	}
 	memset(rela, 0, sizeof(*rela));
 
-	rela->sym = insn_sec->sym;
-	rela->addend = insn_off;
+	if (insn_sec->sym) {
+		rela->sym = insn_sec->sym;
+		rela->addend = insn_off;
+	} else {
+		/*
+		 * The Clang assembler doesn't produce section symbols, so we
+		 * have to reference the function symbol instead:
+		 */
+		rela->sym = find_symbol_containing(insn_sec, insn_off);
+		if (!rela->sym) {
+			/*
+			 * Hack alert.  This happens when we need to reference
+			 * the NOP pad insn immediately after the function.
+			 */
+			rela->sym = find_symbol_containing(insn_sec,
+							   insn_off - 1);
+		}
+		if (!rela->sym) {
+			WARN("missing symbol for insn at offset 0x%lx\n",
+			     insn_off);
+			return -1;
+		}
+
+		rela->addend = insn_off - rela->sym->offset;
+	}
+
 	rela->type = R_X86_64_PC32;
 	rela->offset = idx * sizeof(int);
 	rela->sec = ip_relasec;
 
-	list_add_tail(&rela->list, &ip_relasec->rela_list);
-	hash_add(elf->rela_hash, &rela->hash, rela_hash(rela));
+	elf_add_rela(elf, rela);
 
 	return 0;
 }
diff --git a/tools/objtool/weak.c b/tools/objtool/weak.c
new file mode 100644
index 000000000000..942ea5e8ac36
--- /dev/null
+++ b/tools/objtool/weak.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2020 Matt Helsley <mhelsley@vmware.com>
+ * Weak definitions necessary to compile objtool without
+ * some subcommands (e.g. check, orc).
+ */
+
+#include <stdbool.h>
+#include <errno.h>
+#include "objtool.h"
+
+#define __weak __attribute__((weak))
+
+#define UNSUPPORTED(name)						\
+({									\
+	fprintf(stderr, "error: objtool: " name " not implemented\n");	\
+	return ENOSYS;							\
+})
+
+const char __weak *objname;
+
+int __weak check(const char *_objname, bool orc)
+{
+	UNSUPPORTED("check subcommand");
+}
+
+int __weak orc_dump(const char *_objname)
+{
+	UNSUPPORTED("orc");
+}
+
+int __weak create_orc(struct objtool_file *file)
+{
+	UNSUPPORTED("orc");
+}
+
+int __weak create_orc_sections(struct objtool_file *file)
+{
+	UNSUPPORTED("orc");
+}
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 31824d5269cc..6e54979c2124 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -48,7 +48,7 @@ man5dir=$(mandir)/man5
 man7dir=$(mandir)/man7
 
 ASCIIDOC=asciidoc
-ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf
+ASCIIDOC_EXTRA += --unsafe -f asciidoc.conf
 ASCIIDOC_HTML = xhtml11
 MANPAGE_XSL = manpage-normal.xsl
 XMLTO_EXTRA =
@@ -59,7 +59,7 @@ HTML_REF = origin/html
 
 ifdef USE_ASCIIDOCTOR
 ASCIIDOC = asciidoctor
-ASCIIDOC_EXTRA = -a compat-mode
+ASCIIDOC_EXTRA += -a compat-mode
 ASCIIDOC_EXTRA += -I. -rasciidoctor-extensions
 ASCIIDOC_EXTRA += -a mansource="perf" -a manmanual="perf Manual"
 ASCIIDOC_HTML = xhtml5
diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index 82ff7dad40c2..271484754fee 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -10,7 +10,9 @@
 		e	synthesize error events
 		d	create a debug log
 		g	synthesize a call chain (use with i or x)
+		G	synthesize a call chain on existing event records
 		l	synthesize last branch entries (use with i or x)
+		L	synthesize last branch entries on existing event records
 		s       skip initial number of events
 
 	The default is all events i.e. the same as --itrace=ibxwpe,
@@ -31,6 +33,10 @@
 	Also the number of last branch entries (default 64, max. 1024) for
 	instructions or transactions events can be specified.
 
+	Similar to options g and l, size may also be specified for options G and L.
+	On x86, note that G and L work poorly when data has been recorded with
+	large PEBS. Refer linkperf:perf-intel-pt[1] man page for details.
+
 	It is also possible to skip events generated (instructions, branches, transactions,
 	ptwrite, power) at the beginning. This is useful to ignore initialization code.
 
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index 0921a3c67381..bad16512c48d 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -61,6 +61,9 @@ SUBSYSTEM
 'epoll'::
 	Eventpoll (epoll) stressing benchmarks.
 
+'internals'::
+	Benchmark internal perf functionality.
+
 'all'::
 	All benchmark subsystems.
 
@@ -214,6 +217,11 @@ Suite for evaluating concurrent epoll_wait calls.
 *ctl*::
 Suite for evaluating multiple epoll_ctl calls.
 
+SUITES FOR 'internals'
+~~~~~~~~~~~~~~~~~~~~~~
+*synthesize*::
+Suite for evaluating perf's event synthesis performance.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index e6150f21267d..2133eb320cb0 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -111,6 +111,17 @@ REPORT OPTIONS
 --display::
 	Switch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default.
 
+--stitch-lbr::
+	Show callgraph with stitched LBRs, which may have more complete
+	callgraph. The perf.data file must have been obtained using
+	perf c2c record --call-graph lbr.
+	Disabled by default. In common cases with call stack overflows,
+	it can recreate better call stacks than the default lbr call stack
+	output. But this approach is not full proof. There can be cases
+	where it creates incorrect call stacks from incorrect matches.
+	The known limitations include exception handing such as
+	setjmp/longjmp will have calls/returns not match.
+
 C2C RECORD
 ----------
 The perf c2c record command setup options related to HITM cacheline analysis
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 456fdcbf26ac..eb8b7d42591a 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -69,22 +69,22 @@ And profiled with 'perf report' e.g.
 To also trace kernel space presents a problem, namely kernel self-modifying
 code.  A fairly good kernel image is available in /proc/kcore but to get an
 accurate image a copy of /proc/kcore needs to be made under the same conditions
-as the data capture.  A script perf-with-kcore can do that, but beware that the
-script makes use of 'sudo' to copy /proc/kcore.  If you have perf installed
-locally from the source tree you can do:
+as the data capture. 'perf record' can make a copy of /proc/kcore if the option
+--kcore is used, but access to /proc/kcore is restricted e.g.
 
-	~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
+	sudo perf record -o pt_ls --kcore -e intel_pt// -- ls
 
-which will create a directory named 'pt_ls' and put the perf.data file and
-copies of /proc/kcore, /proc/kallsyms and /proc/modules into it.  Then to use
-'perf report' becomes:
+which will create a directory named 'pt_ls' and put the perf.data file (named
+simply 'data') and copies of /proc/kcore, /proc/kallsyms and /proc/modules into
+it.  The other tools understand the directory format, so to use 'perf report'
+becomes:
 
-	~/libexec/perf-core/perf-with-kcore report pt_ls
+	sudo perf report -i pt_ls
 
 Because samples are synthesized after-the-fact, the sampling period can be
 selected for reporting. e.g. sample every microsecond
 
-	~/libexec/perf-core/perf-with-kcore report pt_ls --itrace=i1usge
+	sudo perf report pt_ls --itrace=i1usge
 
 See the sections below for more information about the --itrace option.
 
@@ -821,7 +821,9 @@ The letters are:
 	e	synthesize tracing error events
 	d	create a debug log
 	g	synthesize a call chain (use with i or x)
+	G	synthesize a call chain on existing event records
 	l	synthesize last branch entries (use with i or x)
+	L	synthesize last branch entries on existing event records
 	s	skip initial number of events
 
 "Instructions" events look like they were recorded by "perf record -e
@@ -912,6 +914,39 @@ transactions events can be specified. e.g.
 Note that last branch entries are cleared for each sample, so there is no overlap
 from one sample to the next.
 
+The G and L options are designed in particular for sample mode, and work much
+like g and l but add call chain and branch stack to the other selected events
+instead of synthesized events. For example, to record branch-misses events for
+'ls' and then add a call chain derived from the Intel PT trace:
+
+	perf record --aux-sample -e '{intel_pt//u,branch-misses:u}' -- ls
+	perf report --itrace=Ge
+
+Although in fact G is a default for perf report, so that is the same as just:
+
+	perf report
+
+One caveat with the G and L options is that they work poorly with "Large PEBS".
+Large PEBS means PEBS records will be accumulated by hardware and the written
+into the event buffer in one go.  That reduces interrupts, but can give very
+late timestamps.  Because the Intel PT trace is synchronized by timestamps,
+the PEBS events do not match the trace.  Currently, Large PEBS is used only in
+certain circumstances:
+	- hardware supports it
+	- PEBS is used
+	- event period is specified, instead of frequency
+	- the sample type is limited to the following flags:
+		PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR |
+		PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID |
+		PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER |
+		PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR |
+		PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER |
+		PERF_SAMPLE_PERIOD (and sometimes) | PERF_SAMPLE_TIME
+Because Intel PT sample mode uses a different sample type to the list above,
+Large PEBS is not used with Intel PT sample mode. To avoid Large PEBS in other
+cases, avoid specifying the event period i.e. avoid the 'perf record' -c option,
+--count option, or 'period' config term.
+
 To disable trace decoding entirely, use the option --no-itrace.
 
 It is also possible to skip events generated (instructions, branches, transactions)
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 6345db33c533..376a50b3452d 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -115,6 +115,11 @@ raw encoding of 0x1A8 can be used:
  perf stat -e r1a8 -a sleep 1
  perf record -e r1a8 ...
 
+It's also possible to use pmu syntax:
+
+ perf record -e r1a8 -a sleep 1
+ perf record -e cpu/r1a8/ ...
+
 You should refer to the processor specific documentation for getting these
 details. Some of them are referenced in the SEE ALSO section below.
 
@@ -258,6 +263,9 @@ Normally all events in an event group sample, but with :S only
 the first event (the leader) samples, and it only reads the values of the
 other events in the group.
 
+However, in the case AUX area events (e.g. Intel PT or CoreSight), the AUX
+area event must be the leader, so then the second event samples, not the first.
+
 OPTIONS
 -------
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index b3f3b3f1c161..561ef55743e2 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -556,6 +556,19 @@ overhead. You can still switch them on with:
 
   --switch-output --no-no-buildid  --no-no-buildid-cache
 
+--switch-output-event::
+Events that will cause the switch of the perf.data file, auto-selecting
+--switch-output=signal, the results are similar as internally the side band
+thread will also send a SIGUSR2 to the main one.
+
+Uses the same syntax as --event, it will just not be recorded, serving only to
+switch the perf.data file as soon as the --switch-output event is processed by
+a separate sideband thread.
+
+This sideband thread is also used to other purposes, like processing the
+PERF_RECORD_BPF_EVENT records as they happen, asking the kernel for extra BPF
+information, etc.
+
 --switch-max-files=N::
 
 When rotating perf.data with --switch-output, only keep N files.
@@ -596,6 +609,10 @@ Make a copy of /proc/kcore and place it into a directory with the perf data file
 Limit the sample data max size, <size> is expected to be a number with
 appended unit character - B/K/M/G
 
+--num-thread-synthesize::
+	The number of threads to run when synthesizing events for existing processes.
+	By default, the number of threads equals 1.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index f569b9ea4002..d068103690cc 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -488,6 +488,17 @@ include::itrace.txt[]
 	This option extends the perf report to show reference callgraphs,
 	which collected by reference event, in no callgraph event.
 
+--stitch-lbr::
+	Show callgraph with stitched LBRs, which may have more complete
+	callgraph. The perf.data file must have been obtained using
+	perf record --call-graph lbr.
+	Disabled by default. In common cases with call stack overflows,
+	it can recreate better call stacks than the default lbr call stack
+	output. But this approach is not full proof. There can be cases
+	where it creates incorrect call stacks from incorrect matches.
+	The known limitations include exception handing such as
+	setjmp/longjmp will have calls/returns not match.
+
 --socket-filter::
 	Only report the samples on the processor socket that match with this filter
 
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 963487e82edc..372dfd110e6d 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -440,6 +440,17 @@ include::itrace.txt[]
 --show-on-off-events::
 	Show the --switch-on/off events too.
 
+--stitch-lbr::
+	Show callgraph with stitched LBRs, which may have more complete
+	callgraph. The perf.data file must have been obtained using
+	perf record --call-graph lbr.
+	Disabled by default. In common cases with call stack overflows,
+	it can recreate better call stacks than the default lbr call stack
+	output. But this approach is not full proof. There can be cases
+	where it creates incorrect call stacks from incorrect matches.
+	The known limitations include exception handing such as
+	setjmp/longjmp will have calls/returns not match.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4d56586b2fb9..3fb5028aef08 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -176,6 +176,8 @@ Print count deltas every N milliseconds (minimum: 1ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
+If the metric exists, it is calculated by the counts generated in this interval and the metric is printed after #.
+
 --interval-count times::
 Print count deltas for fixed number of times.
 This option should be used together with "-I" option.
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 487737a725e9..20227dabc208 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -319,6 +319,15 @@ Default is to monitor all CPUS.
 	go straight to the histogram browser, just like 'perf top' with no events
 	explicitely specified does.
 
+--stitch-lbr::
+	Show callgraph with stitched LBRs, which may have more complete
+	callgraph. The option must be used with --call-graph lbr recording.
+	Disabled by default. In common cases with call stack overflows,
+	it can recreate better call stacks than the default lbr call stack
+	output. But this approach is not full proof. There can be cases
+	where it creates incorrect call stacks from incorrect matches.
+	The known limitations include exception handing such as
+	setjmp/longjmp will have calls/returns not match.
 
 INTERACTIVE PROMPTING KEYS
 --------------------------
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index b0152e1095c5..b6472e463284 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -373,6 +373,22 @@ struct {
 Indicates that trace contains records of PERF_RECORD_COMPRESSED type
 that have perf_events records in compressed form.
 
+	HEADER_CPU_PMU_CAPS = 28,
+
+	A list of cpu PMU capabilities. The format of data is as below.
+
+struct {
+	u32 nr_cpu_pmu_caps;
+	{
+		char	name[];
+		char	value[];
+	} [nr_cpu_pmu_caps]
+};
+
+
+Example:
+ cpu pmu capabilities: branches=32, max_precise=3, pmu_name=icelake
+
 	other bits are reserved and should ignored for now
 	HEADER_FEAT_BITS	= 256,
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index d15a311408f1..94a495594e99 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -188,7 +188,7 @@ AWK     = awk
 # non-config cases
 config := 1
 
-NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf
+NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help
 
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
@@ -832,7 +832,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
 
 # 'make doc' should call 'make -C Documentation all'
 $(DOC_TARGETS):
-	$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all)
+	$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all) ASCIIDOC_EXTRA=$(ASCIIDOC_EXTRA)
 
 TAG_FOLDERS= . ../lib ../include
 TAG_FILES= ../../include/uapi/linux/perf_event.h
@@ -959,7 +959,7 @@ install-python_ext:
 
 # 'make install-doc' should call 'make -C Documentation install'
 $(INSTALL_DOC_TARGETS):
-	$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=)
+	$(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=) ASCIIDOC_EXTRA=$(ASCIIDOC_EXTRA)
 
 ### Cleaning rules
 
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 941f814820b8..97aa02c4491d 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -23,6 +23,7 @@
 #include "../../util/event.h"
 #include "../../util/evlist.h"
 #include "../../util/evsel.h"
+#include "../../util/perf_api_probe.h"
 #include "../../util/evsel_config.h"
 #include "../../util/pmu.h"
 #include "../../util/cs-etm.h"
@@ -232,7 +233,7 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu,
 		ret = perf_pmu__scan_file(pmu, path, "%x", &hash);
 		if (ret != 1) {
 			pr_err("failed to set sink \"%s\" on event %s with %d (%s)\n",
-			       sink, perf_evsel__name(evsel), errno,
+			       sink, evsel__name(evsel), errno,
 			       str_error_r(errno, msg, sizeof(msg)));
 			return ret;
 		}
@@ -401,7 +402,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	 * when a context switch happened.
 	 */
 	if (!perf_cpu_map__empty(cpus)) {
-		perf_evsel__set_sample_bit(cs_etm_evsel, CPU);
+		evsel__set_sample_bit(cs_etm_evsel, CPU);
 
 		err = cs_etm_set_option(itr, cs_etm_evsel,
 					ETM_OPT_CTXTID | ETM_OPT_TS);
@@ -425,7 +426,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 
 		/* In per-cpu case, always need the time of mmap events etc */
 		if (!perf_cpu_map__empty(cpus))
-			perf_evsel__set_sample_bit(tracking_evsel, TIME);
+			evsel__set_sample_bit(tracking_evsel, TIME);
 	}
 
 out:
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 27653be24447..e3593063b3d1 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -120,9 +120,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 */
 	perf_evlist__to_front(evlist, arm_spe_evsel);
 
-	perf_evsel__set_sample_bit(arm_spe_evsel, CPU);
-	perf_evsel__set_sample_bit(arm_spe_evsel, TIME);
-	perf_evsel__set_sample_bit(arm_spe_evsel, TID);
+	evsel__set_sample_bit(arm_spe_evsel, CPU);
+	evsel__set_sample_bit(arm_spe_evsel, TIME);
+	evsel__set_sample_bit(arm_spe_evsel, TID);
 
 	/* Add dummy event to keep tracking */
 	err = parse_events(evlist, "dummy:u", NULL);
@@ -134,9 +134,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 
 	tracking_evsel->core.attr.freq = 0;
 	tracking_evsel->core.attr.sample_period = 1;
-	perf_evsel__set_sample_bit(tracking_evsel, TIME);
-	perf_evsel__set_sample_bit(tracking_evsel, CPU);
-	perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
+	evsel__set_sample_bit(tracking_evsel, TIME);
+	evsel__set_sample_bit(tracking_evsel, CPU);
+	evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
 
 	return 0;
 }
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 3b4cdfc5efd6..d4870074f14c 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -7,6 +7,8 @@
 #include <string.h>
 #include <linux/stringify.h>
 #include "header.h"
+#include "metricgroup.h"
+#include <api/fs/fs.h>
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \
@@ -44,3 +46,9 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 
 	return bufp;
 }
+
+int arch_get_runtimeparam(void)
+{
+	int count;
+	return sysfs__read_int("/devices/hv_24x7/interface/sockets", &count) < 0 ? 1 : count;
+}
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
index 16807269317c..eed9e5a42935 100644
--- a/tools/perf/arch/powerpc/util/kvm-stat.c
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -39,7 +39,7 @@ static void hcall_event_get_key(struct evsel *evsel,
 				struct event_key *key)
 {
 	key->info = 0;
-	key->key = perf_evsel__intval(evsel, sample, "req");
+	key->key = evsel__intval(evsel, sample, "req");
 }
 
 static const char *get_hcall_exit_reason(u64 exit_code)
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index 0fd4e9f49ed0..34da89ced29a 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -30,7 +30,7 @@ static void event_icpt_insn_get_key(struct evsel *evsel,
 {
 	unsigned long insn;
 
-	insn = perf_evsel__intval(evsel, sample, "instruction");
+	insn = evsel__intval(evsel, sample, "instruction");
 	key->key = icpt_insn_decoder(insn);
 	key->exit_reasons = sie_icpt_insn_codes;
 }
@@ -39,7 +39,7 @@ static void event_sigp_get_key(struct evsel *evsel,
 			       struct perf_sample *sample,
 			       struct event_key *key)
 {
-	key->key = perf_evsel__intval(evsel, sample, "order_code");
+	key->key = evsel__intval(evsel, sample, "order_code");
 	key->exit_reasons = sie_sigp_order_codes;
 }
 
@@ -47,7 +47,7 @@ static void event_diag_get_key(struct evsel *evsel,
 			       struct perf_sample *sample,
 			       struct event_key *key)
 {
-	key->key = perf_evsel__intval(evsel, sample, "code");
+	key->key = evsel__intval(evsel, sample, "code");
 	key->exit_reasons = sie_diagnose_codes;
 }
 
@@ -55,7 +55,7 @@ static void event_icpt_prog_get_key(struct evsel *evsel,
 				    struct perf_sample *sample,
 				    struct event_key *key)
 {
-	key->key = perf_evsel__intval(evsel, sample, "code");
+	key->key = evsel__intval(evsel, sample, "code");
 	key->exit_reasons = sie_icpt_prog_codes;
 }
 
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 44d510bc9b78..37b844f839bc 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -8,357 +8,357 @@
 #
 # The abi is "common", "64" or "x32" for this file.
 #
-0	common	read			__x64_sys_read
-1	common	write			__x64_sys_write
-2	common	open			__x64_sys_open
-3	common	close			__x64_sys_close
-4	common	stat			__x64_sys_newstat
-5	common	fstat			__x64_sys_newfstat
-6	common	lstat			__x64_sys_newlstat
-7	common	poll			__x64_sys_poll
-8	common	lseek			__x64_sys_lseek
-9	common	mmap			__x64_sys_mmap
-10	common	mprotect		__x64_sys_mprotect
-11	common	munmap			__x64_sys_munmap
-12	common	brk			__x64_sys_brk
-13	64	rt_sigaction		__x64_sys_rt_sigaction
-14	common	rt_sigprocmask		__x64_sys_rt_sigprocmask
-15	64	rt_sigreturn		__x64_sys_rt_sigreturn/ptregs
-16	64	ioctl			__x64_sys_ioctl
-17	common	pread64			__x64_sys_pread64
-18	common	pwrite64		__x64_sys_pwrite64
-19	64	readv			__x64_sys_readv
-20	64	writev			__x64_sys_writev
-21	common	access			__x64_sys_access
-22	common	pipe			__x64_sys_pipe
-23	common	select			__x64_sys_select
-24	common	sched_yield		__x64_sys_sched_yield
-25	common	mremap			__x64_sys_mremap
-26	common	msync			__x64_sys_msync
-27	common	mincore			__x64_sys_mincore
-28	common	madvise			__x64_sys_madvise
-29	common	shmget			__x64_sys_shmget
-30	common	shmat			__x64_sys_shmat
-31	common	shmctl			__x64_sys_shmctl
-32	common	dup			__x64_sys_dup
-33	common	dup2			__x64_sys_dup2
-34	common	pause			__x64_sys_pause
-35	common	nanosleep		__x64_sys_nanosleep
-36	common	getitimer		__x64_sys_getitimer
-37	common	alarm			__x64_sys_alarm
-38	common	setitimer		__x64_sys_setitimer
-39	common	getpid			__x64_sys_getpid
-40	common	sendfile		__x64_sys_sendfile64
-41	common	socket			__x64_sys_socket
-42	common	connect			__x64_sys_connect
-43	common	accept			__x64_sys_accept
-44	common	sendto			__x64_sys_sendto
-45	64	recvfrom		__x64_sys_recvfrom
-46	64	sendmsg			__x64_sys_sendmsg
-47	64	recvmsg			__x64_sys_recvmsg
-48	common	shutdown		__x64_sys_shutdown
-49	common	bind			__x64_sys_bind
-50	common	listen			__x64_sys_listen
-51	common	getsockname		__x64_sys_getsockname
-52	common	getpeername		__x64_sys_getpeername
-53	common	socketpair		__x64_sys_socketpair
-54	64	setsockopt		__x64_sys_setsockopt
-55	64	getsockopt		__x64_sys_getsockopt
-56	common	clone			__x64_sys_clone/ptregs
-57	common	fork			__x64_sys_fork/ptregs
-58	common	vfork			__x64_sys_vfork/ptregs
-59	64	execve			__x64_sys_execve/ptregs
-60	common	exit			__x64_sys_exit
-61	common	wait4			__x64_sys_wait4
-62	common	kill			__x64_sys_kill
-63	common	uname			__x64_sys_newuname
-64	common	semget			__x64_sys_semget
-65	common	semop			__x64_sys_semop
-66	common	semctl			__x64_sys_semctl
-67	common	shmdt			__x64_sys_shmdt
-68	common	msgget			__x64_sys_msgget
-69	common	msgsnd			__x64_sys_msgsnd
-70	common	msgrcv			__x64_sys_msgrcv
-71	common	msgctl			__x64_sys_msgctl
-72	common	fcntl			__x64_sys_fcntl
-73	common	flock			__x64_sys_flock
-74	common	fsync			__x64_sys_fsync
-75	common	fdatasync		__x64_sys_fdatasync
-76	common	truncate		__x64_sys_truncate
-77	common	ftruncate		__x64_sys_ftruncate
-78	common	getdents		__x64_sys_getdents
-79	common	getcwd			__x64_sys_getcwd
-80	common	chdir			__x64_sys_chdir
-81	common	fchdir			__x64_sys_fchdir
-82	common	rename			__x64_sys_rename
-83	common	mkdir			__x64_sys_mkdir
-84	common	rmdir			__x64_sys_rmdir
-85	common	creat			__x64_sys_creat
-86	common	link			__x64_sys_link
-87	common	unlink			__x64_sys_unlink
-88	common	symlink			__x64_sys_symlink
-89	common	readlink		__x64_sys_readlink
-90	common	chmod			__x64_sys_chmod
-91	common	fchmod			__x64_sys_fchmod
-92	common	chown			__x64_sys_chown
-93	common	fchown			__x64_sys_fchown
-94	common	lchown			__x64_sys_lchown
-95	common	umask			__x64_sys_umask
-96	common	gettimeofday		__x64_sys_gettimeofday
-97	common	getrlimit		__x64_sys_getrlimit
-98	common	getrusage		__x64_sys_getrusage
-99	common	sysinfo			__x64_sys_sysinfo
-100	common	times			__x64_sys_times
-101	64	ptrace			__x64_sys_ptrace
-102	common	getuid			__x64_sys_getuid
-103	common	syslog			__x64_sys_syslog
-104	common	getgid			__x64_sys_getgid
-105	common	setuid			__x64_sys_setuid
-106	common	setgid			__x64_sys_setgid
-107	common	geteuid			__x64_sys_geteuid
-108	common	getegid			__x64_sys_getegid
-109	common	setpgid			__x64_sys_setpgid
-110	common	getppid			__x64_sys_getppid
-111	common	getpgrp			__x64_sys_getpgrp
-112	common	setsid			__x64_sys_setsid
-113	common	setreuid		__x64_sys_setreuid
-114	common	setregid		__x64_sys_setregid
-115	common	getgroups		__x64_sys_getgroups
-116	common	setgroups		__x64_sys_setgroups
-117	common	setresuid		__x64_sys_setresuid
-118	common	getresuid		__x64_sys_getresuid
-119	common	setresgid		__x64_sys_setresgid
-120	common	getresgid		__x64_sys_getresgid
-121	common	getpgid			__x64_sys_getpgid
-122	common	setfsuid		__x64_sys_setfsuid
-123	common	setfsgid		__x64_sys_setfsgid
-124	common	getsid			__x64_sys_getsid
-125	common	capget			__x64_sys_capget
-126	common	capset			__x64_sys_capset
-127	64	rt_sigpending		__x64_sys_rt_sigpending
-128	64	rt_sigtimedwait		__x64_sys_rt_sigtimedwait
-129	64	rt_sigqueueinfo		__x64_sys_rt_sigqueueinfo
-130	common	rt_sigsuspend		__x64_sys_rt_sigsuspend
-131	64	sigaltstack		__x64_sys_sigaltstack
-132	common	utime			__x64_sys_utime
-133	common	mknod			__x64_sys_mknod
+0	common	read			sys_read
+1	common	write			sys_write
+2	common	open			sys_open
+3	common	close			sys_close
+4	common	stat			sys_newstat
+5	common	fstat			sys_newfstat
+6	common	lstat			sys_newlstat
+7	common	poll			sys_poll
+8	common	lseek			sys_lseek
+9	common	mmap			sys_mmap
+10	common	mprotect		sys_mprotect
+11	common	munmap			sys_munmap
+12	common	brk			sys_brk
+13	64	rt_sigaction		sys_rt_sigaction
+14	common	rt_sigprocmask		sys_rt_sigprocmask
+15	64	rt_sigreturn		sys_rt_sigreturn
+16	64	ioctl			sys_ioctl
+17	common	pread64			sys_pread64
+18	common	pwrite64		sys_pwrite64
+19	64	readv			sys_readv
+20	64	writev			sys_writev
+21	common	access			sys_access
+22	common	pipe			sys_pipe
+23	common	select			sys_select
+24	common	sched_yield		sys_sched_yield
+25	common	mremap			sys_mremap
+26	common	msync			sys_msync
+27	common	mincore			sys_mincore
+28	common	madvise			sys_madvise
+29	common	shmget			sys_shmget
+30	common	shmat			sys_shmat
+31	common	shmctl			sys_shmctl
+32	common	dup			sys_dup
+33	common	dup2			sys_dup2
+34	common	pause			sys_pause
+35	common	nanosleep		sys_nanosleep
+36	common	getitimer		sys_getitimer
+37	common	alarm			sys_alarm
+38	common	setitimer		sys_setitimer
+39	common	getpid			sys_getpid
+40	common	sendfile		sys_sendfile64
+41	common	socket			sys_socket
+42	common	connect			sys_connect
+43	common	accept			sys_accept
+44	common	sendto			sys_sendto
+45	64	recvfrom		sys_recvfrom
+46	64	sendmsg			sys_sendmsg
+47	64	recvmsg			sys_recvmsg
+48	common	shutdown		sys_shutdown
+49	common	bind			sys_bind
+50	common	listen			sys_listen
+51	common	getsockname		sys_getsockname
+52	common	getpeername		sys_getpeername
+53	common	socketpair		sys_socketpair
+54	64	setsockopt		sys_setsockopt
+55	64	getsockopt		sys_getsockopt
+56	common	clone			sys_clone
+57	common	fork			sys_fork
+58	common	vfork			sys_vfork
+59	64	execve			sys_execve
+60	common	exit			sys_exit
+61	common	wait4			sys_wait4
+62	common	kill			sys_kill
+63	common	uname			sys_newuname
+64	common	semget			sys_semget
+65	common	semop			sys_semop
+66	common	semctl			sys_semctl
+67	common	shmdt			sys_shmdt
+68	common	msgget			sys_msgget
+69	common	msgsnd			sys_msgsnd
+70	common	msgrcv			sys_msgrcv
+71	common	msgctl			sys_msgctl
+72	common	fcntl			sys_fcntl
+73	common	flock			sys_flock
+74	common	fsync			sys_fsync
+75	common	fdatasync		sys_fdatasync
+76	common	truncate		sys_truncate
+77	common	ftruncate		sys_ftruncate
+78	common	getdents		sys_getdents
+79	common	getcwd			sys_getcwd
+80	common	chdir			sys_chdir
+81	common	fchdir			sys_fchdir
+82	common	rename			sys_rename
+83	common	mkdir			sys_mkdir
+84	common	rmdir			sys_rmdir
+85	common	creat			sys_creat
+86	common	link			sys_link
+87	common	unlink			sys_unlink
+88	common	symlink			sys_symlink
+89	common	readlink		sys_readlink
+90	common	chmod			sys_chmod
+91	common	fchmod			sys_fchmod
+92	common	chown			sys_chown
+93	common	fchown			sys_fchown
+94	common	lchown			sys_lchown
+95	common	umask			sys_umask
+96	common	gettimeofday		sys_gettimeofday
+97	common	getrlimit		sys_getrlimit
+98	common	getrusage		sys_getrusage
+99	common	sysinfo			sys_sysinfo
+100	common	times			sys_times
+101	64	ptrace			sys_ptrace
+102	common	getuid			sys_getuid
+103	common	syslog			sys_syslog
+104	common	getgid			sys_getgid
+105	common	setuid			sys_setuid
+106	common	setgid			sys_setgid
+107	common	geteuid			sys_geteuid
+108	common	getegid			sys_getegid
+109	common	setpgid			sys_setpgid
+110	common	getppid			sys_getppid
+111	common	getpgrp			sys_getpgrp
+112	common	setsid			sys_setsid
+113	common	setreuid		sys_setreuid
+114	common	setregid		sys_setregid
+115	common	getgroups		sys_getgroups
+116	common	setgroups		sys_setgroups
+117	common	setresuid		sys_setresuid
+118	common	getresuid		sys_getresuid
+119	common	setresgid		sys_setresgid
+120	common	getresgid		sys_getresgid
+121	common	getpgid			sys_getpgid
+122	common	setfsuid		sys_setfsuid
+123	common	setfsgid		sys_setfsgid
+124	common	getsid			sys_getsid
+125	common	capget			sys_capget
+126	common	capset			sys_capset
+127	64	rt_sigpending		sys_rt_sigpending
+128	64	rt_sigtimedwait		sys_rt_sigtimedwait
+129	64	rt_sigqueueinfo		sys_rt_sigqueueinfo
+130	common	rt_sigsuspend		sys_rt_sigsuspend
+131	64	sigaltstack		sys_sigaltstack
+132	common	utime			sys_utime
+133	common	mknod			sys_mknod
 134	64	uselib
-135	common	personality		__x64_sys_personality
-136	common	ustat			__x64_sys_ustat
-137	common	statfs			__x64_sys_statfs
-138	common	fstatfs			__x64_sys_fstatfs
-139	common	sysfs			__x64_sys_sysfs
-140	common	getpriority		__x64_sys_getpriority
-141	common	setpriority		__x64_sys_setpriority
-142	common	sched_setparam		__x64_sys_sched_setparam
-143	common	sched_getparam		__x64_sys_sched_getparam
-144	common	sched_setscheduler	__x64_sys_sched_setscheduler
-145	common	sched_getscheduler	__x64_sys_sched_getscheduler
-146	common	sched_get_priority_max	__x64_sys_sched_get_priority_max
-147	common	sched_get_priority_min	__x64_sys_sched_get_priority_min
-148	common	sched_rr_get_interval	__x64_sys_sched_rr_get_interval
-149	common	mlock			__x64_sys_mlock
-150	common	munlock			__x64_sys_munlock
-151	common	mlockall		__x64_sys_mlockall
-152	common	munlockall		__x64_sys_munlockall
-153	common	vhangup			__x64_sys_vhangup
-154	common	modify_ldt		__x64_sys_modify_ldt
-155	common	pivot_root		__x64_sys_pivot_root
-156	64	_sysctl			__x64_sys_sysctl
-157	common	prctl			__x64_sys_prctl
-158	common	arch_prctl		__x64_sys_arch_prctl
-159	common	adjtimex		__x64_sys_adjtimex
-160	common	setrlimit		__x64_sys_setrlimit
-161	common	chroot			__x64_sys_chroot
-162	common	sync			__x64_sys_sync
-163	common	acct			__x64_sys_acct
-164	common	settimeofday		__x64_sys_settimeofday
-165	common	mount			__x64_sys_mount
-166	common	umount2			__x64_sys_umount
-167	common	swapon			__x64_sys_swapon
-168	common	swapoff			__x64_sys_swapoff
-169	common	reboot			__x64_sys_reboot
-170	common	sethostname		__x64_sys_sethostname
-171	common	setdomainname		__x64_sys_setdomainname
-172	common	iopl			__x64_sys_iopl/ptregs
-173	common	ioperm			__x64_sys_ioperm
+135	common	personality		sys_personality
+136	common	ustat			sys_ustat
+137	common	statfs			sys_statfs
+138	common	fstatfs			sys_fstatfs
+139	common	sysfs			sys_sysfs
+140	common	getpriority		sys_getpriority
+141	common	setpriority		sys_setpriority
+142	common	sched_setparam		sys_sched_setparam
+143	common	sched_getparam		sys_sched_getparam
+144	common	sched_setscheduler	sys_sched_setscheduler
+145	common	sched_getscheduler	sys_sched_getscheduler
+146	common	sched_get_priority_max	sys_sched_get_priority_max
+147	common	sched_get_priority_min	sys_sched_get_priority_min
+148	common	sched_rr_get_interval	sys_sched_rr_get_interval
+149	common	mlock			sys_mlock
+150	common	munlock			sys_munlock
+151	common	mlockall		sys_mlockall
+152	common	munlockall		sys_munlockall
+153	common	vhangup			sys_vhangup
+154	common	modify_ldt		sys_modify_ldt
+155	common	pivot_root		sys_pivot_root
+156	64	_sysctl			sys_sysctl
+157	common	prctl			sys_prctl
+158	common	arch_prctl		sys_arch_prctl
+159	common	adjtimex		sys_adjtimex
+160	common	setrlimit		sys_setrlimit
+161	common	chroot			sys_chroot
+162	common	sync			sys_sync
+163	common	acct			sys_acct
+164	common	settimeofday		sys_settimeofday
+165	common	mount			sys_mount
+166	common	umount2			sys_umount
+167	common	swapon			sys_swapon
+168	common	swapoff			sys_swapoff
+169	common	reboot			sys_reboot
+170	common	sethostname		sys_sethostname
+171	common	setdomainname		sys_setdomainname
+172	common	iopl			sys_iopl
+173	common	ioperm			sys_ioperm
 174	64	create_module
-175	common	init_module		__x64_sys_init_module
-176	common	delete_module		__x64_sys_delete_module
+175	common	init_module		sys_init_module
+176	common	delete_module		sys_delete_module
 177	64	get_kernel_syms
 178	64	query_module
-179	common	quotactl		__x64_sys_quotactl
+179	common	quotactl		sys_quotactl
 180	64	nfsservctl
 181	common	getpmsg
 182	common	putpmsg
 183	common	afs_syscall
 184	common	tuxcall
 185	common	security
-186	common	gettid			__x64_sys_gettid
-187	common	readahead		__x64_sys_readahead
-188	common	setxattr		__x64_sys_setxattr
-189	common	lsetxattr		__x64_sys_lsetxattr
-190	common	fsetxattr		__x64_sys_fsetxattr
-191	common	getxattr		__x64_sys_getxattr
-192	common	lgetxattr		__x64_sys_lgetxattr
-193	common	fgetxattr		__x64_sys_fgetxattr
-194	common	listxattr		__x64_sys_listxattr
-195	common	llistxattr		__x64_sys_llistxattr
-196	common	flistxattr		__x64_sys_flistxattr
-197	common	removexattr		__x64_sys_removexattr
-198	common	lremovexattr		__x64_sys_lremovexattr
-199	common	fremovexattr		__x64_sys_fremovexattr
-200	common	tkill			__x64_sys_tkill
-201	common	time			__x64_sys_time
-202	common	futex			__x64_sys_futex
-203	common	sched_setaffinity	__x64_sys_sched_setaffinity
-204	common	sched_getaffinity	__x64_sys_sched_getaffinity
+186	common	gettid			sys_gettid
+187	common	readahead		sys_readahead
+188	common	setxattr		sys_setxattr
+189	common	lsetxattr		sys_lsetxattr
+190	common	fsetxattr		sys_fsetxattr
+191	common	getxattr		sys_getxattr
+192	common	lgetxattr		sys_lgetxattr
+193	common	fgetxattr		sys_fgetxattr
+194	common	listxattr		sys_listxattr
+195	common	llistxattr		sys_llistxattr
+196	common	flistxattr		sys_flistxattr
+197	common	removexattr		sys_removexattr
+198	common	lremovexattr		sys_lremovexattr
+199	common	fremovexattr		sys_fremovexattr
+200	common	tkill			sys_tkill
+201	common	time			sys_time
+202	common	futex			sys_futex
+203	common	sched_setaffinity	sys_sched_setaffinity
+204	common	sched_getaffinity	sys_sched_getaffinity
 205	64	set_thread_area
-206	64	io_setup		__x64_sys_io_setup
-207	common	io_destroy		__x64_sys_io_destroy
-208	common	io_getevents		__x64_sys_io_getevents
-209	64	io_submit		__x64_sys_io_submit
-210	common	io_cancel		__x64_sys_io_cancel
+206	64	io_setup		sys_io_setup
+207	common	io_destroy		sys_io_destroy
+208	common	io_getevents		sys_io_getevents
+209	64	io_submit		sys_io_submit
+210	common	io_cancel		sys_io_cancel
 211	64	get_thread_area
-212	common	lookup_dcookie		__x64_sys_lookup_dcookie
-213	common	epoll_create		__x64_sys_epoll_create
+212	common	lookup_dcookie		sys_lookup_dcookie
+213	common	epoll_create		sys_epoll_create
 214	64	epoll_ctl_old
 215	64	epoll_wait_old
-216	common	remap_file_pages	__x64_sys_remap_file_pages
-217	common	getdents64		__x64_sys_getdents64
-218	common	set_tid_address		__x64_sys_set_tid_address
-219	common	restart_syscall		__x64_sys_restart_syscall
-220	common	semtimedop		__x64_sys_semtimedop
-221	common	fadvise64		__x64_sys_fadvise64
-222	64	timer_create		__x64_sys_timer_create
-223	common	timer_settime		__x64_sys_timer_settime
-224	common	timer_gettime		__x64_sys_timer_gettime
-225	common	timer_getoverrun	__x64_sys_timer_getoverrun
-226	common	timer_delete		__x64_sys_timer_delete
-227	common	clock_settime		__x64_sys_clock_settime
-228	common	clock_gettime		__x64_sys_clock_gettime
-229	common	clock_getres		__x64_sys_clock_getres
-230	common	clock_nanosleep		__x64_sys_clock_nanosleep
-231	common	exit_group		__x64_sys_exit_group
-232	common	epoll_wait		__x64_sys_epoll_wait
-233	common	epoll_ctl		__x64_sys_epoll_ctl
-234	common	tgkill			__x64_sys_tgkill
-235	common	utimes			__x64_sys_utimes
+216	common	remap_file_pages	sys_remap_file_pages
+217	common	getdents64		sys_getdents64
+218	common	set_tid_address		sys_set_tid_address
+219	common	restart_syscall		sys_restart_syscall
+220	common	semtimedop		sys_semtimedop
+221	common	fadvise64		sys_fadvise64
+222	64	timer_create		sys_timer_create
+223	common	timer_settime		sys_timer_settime
+224	common	timer_gettime		sys_timer_gettime
+225	common	timer_getoverrun	sys_timer_getoverrun
+226	common	timer_delete		sys_timer_delete
+227	common	clock_settime		sys_clock_settime
+228	common	clock_gettime		sys_clock_gettime
+229	common	clock_getres		sys_clock_getres
+230	common	clock_nanosleep		sys_clock_nanosleep
+231	common	exit_group		sys_exit_group
+232	common	epoll_wait		sys_epoll_wait
+233	common	epoll_ctl		sys_epoll_ctl
+234	common	tgkill			sys_tgkill
+235	common	utimes			sys_utimes
 236	64	vserver
-237	common	mbind			__x64_sys_mbind
-238	common	set_mempolicy		__x64_sys_set_mempolicy
-239	common	get_mempolicy		__x64_sys_get_mempolicy
-240	common	mq_open			__x64_sys_mq_open
-241	common	mq_unlink		__x64_sys_mq_unlink
-242	common	mq_timedsend		__x64_sys_mq_timedsend
-243	common	mq_timedreceive		__x64_sys_mq_timedreceive
-244	64	mq_notify		__x64_sys_mq_notify
-245	common	mq_getsetattr		__x64_sys_mq_getsetattr
-246	64	kexec_load		__x64_sys_kexec_load
-247	64	waitid			__x64_sys_waitid
-248	common	add_key			__x64_sys_add_key
-249	common	request_key		__x64_sys_request_key
-250	common	keyctl			__x64_sys_keyctl
-251	common	ioprio_set		__x64_sys_ioprio_set
-252	common	ioprio_get		__x64_sys_ioprio_get
-253	common	inotify_init		__x64_sys_inotify_init
-254	common	inotify_add_watch	__x64_sys_inotify_add_watch
-255	common	inotify_rm_watch	__x64_sys_inotify_rm_watch
-256	common	migrate_pages		__x64_sys_migrate_pages
-257	common	openat			__x64_sys_openat
-258	common	mkdirat			__x64_sys_mkdirat
-259	common	mknodat			__x64_sys_mknodat
-260	common	fchownat		__x64_sys_fchownat
-261	common	futimesat		__x64_sys_futimesat
-262	common	newfstatat		__x64_sys_newfstatat
-263	common	unlinkat		__x64_sys_unlinkat
-264	common	renameat		__x64_sys_renameat
-265	common	linkat			__x64_sys_linkat
-266	common	symlinkat		__x64_sys_symlinkat
-267	common	readlinkat		__x64_sys_readlinkat
-268	common	fchmodat		__x64_sys_fchmodat
-269	common	faccessat		__x64_sys_faccessat
-270	common	pselect6		__x64_sys_pselect6
-271	common	ppoll			__x64_sys_ppoll
-272	common	unshare			__x64_sys_unshare
-273	64	set_robust_list		__x64_sys_set_robust_list
-274	64	get_robust_list		__x64_sys_get_robust_list
-275	common	splice			__x64_sys_splice
-276	common	tee			__x64_sys_tee
-277	common	sync_file_range		__x64_sys_sync_file_range
-278	64	vmsplice		__x64_sys_vmsplice
-279	64	move_pages		__x64_sys_move_pages
-280	common	utimensat		__x64_sys_utimensat
-281	common	epoll_pwait		__x64_sys_epoll_pwait
-282	common	signalfd		__x64_sys_signalfd
-283	common	timerfd_create		__x64_sys_timerfd_create
-284	common	eventfd			__x64_sys_eventfd
-285	common	fallocate		__x64_sys_fallocate
-286	common	timerfd_settime		__x64_sys_timerfd_settime
-287	common	timerfd_gettime		__x64_sys_timerfd_gettime
-288	common	accept4			__x64_sys_accept4
-289	common	signalfd4		__x64_sys_signalfd4
-290	common	eventfd2		__x64_sys_eventfd2
-291	common	epoll_create1		__x64_sys_epoll_create1
-292	common	dup3			__x64_sys_dup3
-293	common	pipe2			__x64_sys_pipe2
-294	common	inotify_init1		__x64_sys_inotify_init1
-295	64	preadv			__x64_sys_preadv
-296	64	pwritev			__x64_sys_pwritev
-297	64	rt_tgsigqueueinfo	__x64_sys_rt_tgsigqueueinfo
-298	common	perf_event_open		__x64_sys_perf_event_open
-299	64	recvmmsg		__x64_sys_recvmmsg
-300	common	fanotify_init		__x64_sys_fanotify_init
-301	common	fanotify_mark		__x64_sys_fanotify_mark
-302	common	prlimit64		__x64_sys_prlimit64
-303	common	name_to_handle_at	__x64_sys_name_to_handle_at
-304	common	open_by_handle_at	__x64_sys_open_by_handle_at
-305	common	clock_adjtime		__x64_sys_clock_adjtime
-306	common	syncfs			__x64_sys_syncfs
-307	64	sendmmsg		__x64_sys_sendmmsg
-308	common	setns			__x64_sys_setns
-309	common	getcpu			__x64_sys_getcpu
-310	64	process_vm_readv	__x64_sys_process_vm_readv
-311	64	process_vm_writev	__x64_sys_process_vm_writev
-312	common	kcmp			__x64_sys_kcmp
-313	common	finit_module		__x64_sys_finit_module
-314	common	sched_setattr		__x64_sys_sched_setattr
-315	common	sched_getattr		__x64_sys_sched_getattr
-316	common	renameat2		__x64_sys_renameat2
-317	common	seccomp			__x64_sys_seccomp
-318	common	getrandom		__x64_sys_getrandom
-319	common	memfd_create		__x64_sys_memfd_create
-320	common	kexec_file_load		__x64_sys_kexec_file_load
-321	common	bpf			__x64_sys_bpf
-322	64	execveat		__x64_sys_execveat/ptregs
-323	common	userfaultfd		__x64_sys_userfaultfd
-324	common	membarrier		__x64_sys_membarrier
-325	common	mlock2			__x64_sys_mlock2
-326	common	copy_file_range		__x64_sys_copy_file_range
-327	64	preadv2			__x64_sys_preadv2
-328	64	pwritev2		__x64_sys_pwritev2
-329	common	pkey_mprotect		__x64_sys_pkey_mprotect
-330	common	pkey_alloc		__x64_sys_pkey_alloc
-331	common	pkey_free		__x64_sys_pkey_free
-332	common	statx			__x64_sys_statx
-333	common	io_pgetevents		__x64_sys_io_pgetevents
-334	common	rseq			__x64_sys_rseq
+237	common	mbind			sys_mbind
+238	common	set_mempolicy		sys_set_mempolicy
+239	common	get_mempolicy		sys_get_mempolicy
+240	common	mq_open			sys_mq_open
+241	common	mq_unlink		sys_mq_unlink
+242	common	mq_timedsend		sys_mq_timedsend
+243	common	mq_timedreceive		sys_mq_timedreceive
+244	64	mq_notify		sys_mq_notify
+245	common	mq_getsetattr		sys_mq_getsetattr
+246	64	kexec_load		sys_kexec_load
+247	64	waitid			sys_waitid
+248	common	add_key			sys_add_key
+249	common	request_key		sys_request_key
+250	common	keyctl			sys_keyctl
+251	common	ioprio_set		sys_ioprio_set
+252	common	ioprio_get		sys_ioprio_get
+253	common	inotify_init		sys_inotify_init
+254	common	inotify_add_watch	sys_inotify_add_watch
+255	common	inotify_rm_watch	sys_inotify_rm_watch
+256	common	migrate_pages		sys_migrate_pages
+257	common	openat			sys_openat
+258	common	mkdirat			sys_mkdirat
+259	common	mknodat			sys_mknodat
+260	common	fchownat		sys_fchownat
+261	common	futimesat		sys_futimesat
+262	common	newfstatat		sys_newfstatat
+263	common	unlinkat		sys_unlinkat
+264	common	renameat		sys_renameat
+265	common	linkat			sys_linkat
+266	common	symlinkat		sys_symlinkat
+267	common	readlinkat		sys_readlinkat
+268	common	fchmodat		sys_fchmodat
+269	common	faccessat		sys_faccessat
+270	common	pselect6		sys_pselect6
+271	common	ppoll			sys_ppoll
+272	common	unshare			sys_unshare
+273	64	set_robust_list		sys_set_robust_list
+274	64	get_robust_list		sys_get_robust_list
+275	common	splice			sys_splice
+276	common	tee			sys_tee
+277	common	sync_file_range		sys_sync_file_range
+278	64	vmsplice		sys_vmsplice
+279	64	move_pages		sys_move_pages
+280	common	utimensat		sys_utimensat
+281	common	epoll_pwait		sys_epoll_pwait
+282	common	signalfd		sys_signalfd
+283	common	timerfd_create		sys_timerfd_create
+284	common	eventfd			sys_eventfd
+285	common	fallocate		sys_fallocate
+286	common	timerfd_settime		sys_timerfd_settime
+287	common	timerfd_gettime		sys_timerfd_gettime
+288	common	accept4			sys_accept4
+289	common	signalfd4		sys_signalfd4
+290	common	eventfd2		sys_eventfd2
+291	common	epoll_create1		sys_epoll_create1
+292	common	dup3			sys_dup3
+293	common	pipe2			sys_pipe2
+294	common	inotify_init1		sys_inotify_init1
+295	64	preadv			sys_preadv
+296	64	pwritev			sys_pwritev
+297	64	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo
+298	common	perf_event_open		sys_perf_event_open
+299	64	recvmmsg		sys_recvmmsg
+300	common	fanotify_init		sys_fanotify_init
+301	common	fanotify_mark		sys_fanotify_mark
+302	common	prlimit64		sys_prlimit64
+303	common	name_to_handle_at	sys_name_to_handle_at
+304	common	open_by_handle_at	sys_open_by_handle_at
+305	common	clock_adjtime		sys_clock_adjtime
+306	common	syncfs			sys_syncfs
+307	64	sendmmsg		sys_sendmmsg
+308	common	setns			sys_setns
+309	common	getcpu			sys_getcpu
+310	64	process_vm_readv	sys_process_vm_readv
+311	64	process_vm_writev	sys_process_vm_writev
+312	common	kcmp			sys_kcmp
+313	common	finit_module		sys_finit_module
+314	common	sched_setattr		sys_sched_setattr
+315	common	sched_getattr		sys_sched_getattr
+316	common	renameat2		sys_renameat2
+317	common	seccomp			sys_seccomp
+318	common	getrandom		sys_getrandom
+319	common	memfd_create		sys_memfd_create
+320	common	kexec_file_load		sys_kexec_file_load
+321	common	bpf			sys_bpf
+322	64	execveat		sys_execveat
+323	common	userfaultfd		sys_userfaultfd
+324	common	membarrier		sys_membarrier
+325	common	mlock2			sys_mlock2
+326	common	copy_file_range		sys_copy_file_range
+327	64	preadv2			sys_preadv2
+328	64	pwritev2		sys_pwritev2
+329	common	pkey_mprotect		sys_pkey_mprotect
+330	common	pkey_alloc		sys_pkey_alloc
+331	common	pkey_free		sys_pkey_free
+332	common	statx			sys_statx
+333	common	io_pgetevents		sys_io_pgetevents
+334	common	rseq			sys_rseq
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
-424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal
-425	common	io_uring_setup		__x64_sys_io_uring_setup
-426	common	io_uring_enter		__x64_sys_io_uring_enter
-427	common	io_uring_register	__x64_sys_io_uring_register
-428	common	open_tree		__x64_sys_open_tree
-429	common	move_mount		__x64_sys_move_mount
-430	common	fsopen			__x64_sys_fsopen
-431	common	fsconfig		__x64_sys_fsconfig
-432	common	fsmount			__x64_sys_fsmount
-433	common	fspick			__x64_sys_fspick
-434	common	pidfd_open		__x64_sys_pidfd_open
-435	common	clone3			__x64_sys_clone3/ptregs
-437	common	openat2			__x64_sys_openat2
-438	common	pidfd_getfd		__x64_sys_pidfd_getfd
+424	common	pidfd_send_signal	sys_pidfd_send_signal
+425	common	io_uring_setup		sys_io_uring_setup
+426	common	io_uring_enter		sys_io_uring_enter
+427	common	io_uring_register	sys_io_uring_register
+428	common	open_tree		sys_open_tree
+429	common	move_mount		sys_move_mount
+430	common	fsopen			sys_fsopen
+431	common	fsconfig		sys_fsconfig
+432	common	fsmount			sys_fsmount
+433	common	fspick			sys_fspick
+434	common	pidfd_open		sys_pidfd_open
+435	common	clone3			sys_clone3
+437	common	openat2			sys_openat2
+438	common	pidfd_getfd		sys_pidfd_getfd
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
@@ -366,39 +366,39 @@
 # on-the-fly for compat_sys_*() compatibility system calls if X86_X32
 # is defined.
 #
-512	x32	rt_sigaction		__x32_compat_sys_rt_sigaction
-513	x32	rt_sigreturn		sys32_x32_rt_sigreturn
-514	x32	ioctl			__x32_compat_sys_ioctl
-515	x32	readv			__x32_compat_sys_readv
-516	x32	writev			__x32_compat_sys_writev
-517	x32	recvfrom		__x32_compat_sys_recvfrom
-518	x32	sendmsg			__x32_compat_sys_sendmsg
-519	x32	recvmsg			__x32_compat_sys_recvmsg
-520	x32	execve			__x32_compat_sys_execve/ptregs
-521	x32	ptrace			__x32_compat_sys_ptrace
-522	x32	rt_sigpending		__x32_compat_sys_rt_sigpending
-523	x32	rt_sigtimedwait		__x32_compat_sys_rt_sigtimedwait_time64
-524	x32	rt_sigqueueinfo		__x32_compat_sys_rt_sigqueueinfo
-525	x32	sigaltstack		__x32_compat_sys_sigaltstack
-526	x32	timer_create		__x32_compat_sys_timer_create
-527	x32	mq_notify		__x32_compat_sys_mq_notify
-528	x32	kexec_load		__x32_compat_sys_kexec_load
-529	x32	waitid			__x32_compat_sys_waitid
-530	x32	set_robust_list		__x32_compat_sys_set_robust_list
-531	x32	get_robust_list		__x32_compat_sys_get_robust_list
-532	x32	vmsplice		__x32_compat_sys_vmsplice
-533	x32	move_pages		__x32_compat_sys_move_pages
-534	x32	preadv			__x32_compat_sys_preadv64
-535	x32	pwritev			__x32_compat_sys_pwritev64
-536	x32	rt_tgsigqueueinfo	__x32_compat_sys_rt_tgsigqueueinfo
-537	x32	recvmmsg		__x32_compat_sys_recvmmsg_time64
-538	x32	sendmmsg		__x32_compat_sys_sendmmsg
-539	x32	process_vm_readv	__x32_compat_sys_process_vm_readv
-540	x32	process_vm_writev	__x32_compat_sys_process_vm_writev
-541	x32	setsockopt		__x32_compat_sys_setsockopt
-542	x32	getsockopt		__x32_compat_sys_getsockopt
-543	x32	io_setup		__x32_compat_sys_io_setup
-544	x32	io_submit		__x32_compat_sys_io_submit
-545	x32	execveat		__x32_compat_sys_execveat/ptregs
-546	x32	preadv2			__x32_compat_sys_preadv64v2
-547	x32	pwritev2		__x32_compat_sys_pwritev64v2
+512	x32	rt_sigaction		compat_sys_rt_sigaction
+513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
+514	x32	ioctl			compat_sys_ioctl
+515	x32	readv			compat_sys_readv
+516	x32	writev			compat_sys_writev
+517	x32	recvfrom		compat_sys_recvfrom
+518	x32	sendmsg			compat_sys_sendmsg
+519	x32	recvmsg			compat_sys_recvmsg
+520	x32	execve			compat_sys_execve
+521	x32	ptrace			compat_sys_ptrace
+522	x32	rt_sigpending		compat_sys_rt_sigpending
+523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait_time64
+524	x32	rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
+525	x32	sigaltstack		compat_sys_sigaltstack
+526	x32	timer_create		compat_sys_timer_create
+527	x32	mq_notify		compat_sys_mq_notify
+528	x32	kexec_load		compat_sys_kexec_load
+529	x32	waitid			compat_sys_waitid
+530	x32	set_robust_list		compat_sys_set_robust_list
+531	x32	get_robust_list		compat_sys_get_robust_list
+532	x32	vmsplice		compat_sys_vmsplice
+533	x32	move_pages		compat_sys_move_pages
+534	x32	preadv			compat_sys_preadv64
+535	x32	pwritev			compat_sys_pwritev64
+536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
+537	x32	recvmmsg		compat_sys_recvmmsg_time64
+538	x32	sendmmsg		compat_sys_sendmmsg
+539	x32	process_vm_readv	compat_sys_process_vm_readv
+540	x32	process_vm_writev	compat_sys_process_vm_writev
+541	x32	setsockopt		compat_sys_setsockopt
+542	x32	getsockopt		compat_sys_getsockopt
+543	x32	io_setup		compat_sys_io_setup
+544	x32	io_submit		compat_sys_io_submit
+545	x32	execveat		compat_sys_execveat
+546	x32	preadv2			compat_sys_preadv64v2
+547	x32	pwritev2		compat_sys_pwritev64v2
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 909ead08a6f6..026d32ed078e 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -130,13 +130,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 				goto next_event;
 
 			if (strcmp(event->comm.comm, comm1) == 0) {
-				CHECK__(perf_evsel__parse_sample(evsel, event,
-								 &sample));
+				CHECK__(evsel__parse_sample(evsel, event, &sample));
 				comm1_time = sample.time;
 			}
 			if (strcmp(event->comm.comm, comm2) == 0) {
-				CHECK__(perf_evsel__parse_sample(evsel, event,
-								 &sample));
+				CHECK__(evsel__parse_sample(evsel, event, &sample));
 				comm2_time = sample.time;
 			}
 next_event:
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 09f93800bffd..0dc09b5809c1 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -224,7 +224,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 		 * AUX event.
 		 */
 		if (!perf_cpu_map__empty(cpus))
-			perf_evsel__set_sample_bit(intel_bts_evsel, CPU);
+			evsel__set_sample_bit(intel_bts_evsel, CPU);
 	}
 
 	/* Add dummy event to keep tracking */
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 1643aed8c4c8..3f7c20cc7b79 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -25,6 +25,7 @@
 #include "../../../util/pmu.h"
 #include "../../../util/debug.h"
 #include "../../../util/auxtrace.h"
+#include "../../../util/perf_api_probe.h"
 #include "../../../util/record.h"
 #include "../../../util/target.h"
 #include "../../../util/tsc.h"
@@ -420,8 +421,8 @@ static int intel_pt_track_switches(struct evlist *evlist)
 
 	evsel = evlist__last(evlist);
 
-	perf_evsel__set_sample_bit(evsel, CPU);
-	perf_evsel__set_sample_bit(evsel, TIME);
+	evsel__set_sample_bit(evsel, CPU);
+	evsel__set_sample_bit(evsel, TIME);
 
 	evsel->core.system_wide = true;
 	evsel->no_aux_samples = true;
@@ -801,10 +802,10 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 				switch_evsel->no_aux_samples = true;
 				switch_evsel->immediate = true;
 
-				perf_evsel__set_sample_bit(switch_evsel, TID);
-				perf_evsel__set_sample_bit(switch_evsel, TIME);
-				perf_evsel__set_sample_bit(switch_evsel, CPU);
-				perf_evsel__reset_sample_bit(switch_evsel, BRANCH_STACK);
+				evsel__set_sample_bit(switch_evsel, TID);
+				evsel__set_sample_bit(switch_evsel, TIME);
+				evsel__set_sample_bit(switch_evsel, CPU);
+				evsel__reset_sample_bit(switch_evsel, BRANCH_STACK);
 
 				opts->record_switch_events = false;
 				ptr->have_sched_switch = 3;
@@ -838,7 +839,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		 * AUX event.
 		 */
 		if (!perf_cpu_map__empty(cpus))
-			perf_evsel__set_sample_bit(intel_pt_evsel, CPU);
+			evsel__set_sample_bit(intel_pt_evsel, CPU);
 	}
 
 	/* Add dummy event to keep tracking */
@@ -862,11 +863,11 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 
 		/* In per-cpu case, always need the time of mmap events etc */
 		if (!perf_cpu_map__empty(cpus)) {
-			perf_evsel__set_sample_bit(tracking_evsel, TIME);
+			evsel__set_sample_bit(tracking_evsel, TIME);
 			/* And the CPU for switch events */
-			perf_evsel__set_sample_bit(tracking_evsel, CPU);
+			evsel__set_sample_bit(tracking_evsel, CPU);
 		}
-		perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
+		evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
 	}
 
 	/*
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index c0775c39227f..072920475b65 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -31,8 +31,8 @@ const char *kvm_exit_trace = "kvm:kvm_exit";
 static void mmio_event_get_key(struct evsel *evsel, struct perf_sample *sample,
 			       struct event_key *key)
 {
-	key->key  = perf_evsel__intval(evsel, sample, "gpa");
-	key->info = perf_evsel__intval(evsel, sample, "type");
+	key->key  = evsel__intval(evsel, sample, "gpa");
+	key->info = evsel__intval(evsel, sample, "type");
 }
 
 #define KVM_TRACE_MMIO_READ_UNSATISFIED 0
@@ -48,7 +48,7 @@ static bool mmio_event_begin(struct evsel *evsel,
 
 	/* MMIO write begin event in kernel. */
 	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
-	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
+	    evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
 		mmio_event_get_key(evsel, sample, key);
 		return true;
 	}
@@ -65,7 +65,7 @@ static bool mmio_event_end(struct evsel *evsel, struct perf_sample *sample,
 
 	/* MMIO read end event in kernel.*/
 	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
-	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
+	    evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
 		mmio_event_get_key(evsel, sample, key);
 		return true;
 	}
@@ -94,8 +94,8 @@ static void ioport_event_get_key(struct evsel *evsel,
 				 struct perf_sample *sample,
 				 struct event_key *key)
 {
-	key->key  = perf_evsel__intval(evsel, sample, "port");
-	key->info = perf_evsel__intval(evsel, sample, "rw");
+	key->key  = evsel__intval(evsel, sample, "port");
+	key->info = evsel__intval(evsel, sample, "rw");
 }
 
 static bool ioport_event_begin(struct evsel *evsel,
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index e4e321b6f883..768e408757a0 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -6,9 +6,10 @@ perf-y += futex-wake.o
 perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 perf-y += futex-lock-pi.o
-
 perf-y += epoll-wait.o
 perf-y += epoll-ctl.o
+perf-y += synthesize.o
+perf-y += kallsyms-parse.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 4aa6de1aa67d..61cae4966cae 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -41,9 +41,10 @@ int bench_futex_wake_parallel(int argc, const char **argv);
 int bench_futex_requeue(int argc, const char **argv);
 /* pi futexes */
 int bench_futex_lock_pi(int argc, const char **argv);
-
 int bench_epoll_wait(int argc, const char **argv);
 int bench_epoll_ctl(int argc, const char **argv);
+int bench_synthesize(int argc, const char **argv);
+int bench_kallsyms_parse(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index f938c585d512..cf797362675b 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -519,7 +519,8 @@ int bench_epoll_wait(int argc, const char **argv)
 		qsort(worker, nthreads, sizeof(struct worker), cmpworker);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
+		unsigned long t = bench__runtime.tv_sec > 0 ?
+			worker[i].ops / bench__runtime.tv_sec : 0;
 
 		update_stats(&throughput_stats, t);
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 65eebe06c04d..915bf3da7ce2 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -205,7 +205,8 @@ int bench_futex_hash(int argc, const char **argv)
 	pthread_mutex_destroy(&thread_lock);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
+		unsigned long t = bench__runtime.tv_sec > 0 ?
+			worker[i].ops / bench__runtime.tv_sec : 0;
 		update_stats(&throughput_stats, t);
 		if (!silent) {
 			if (nfutexes == 1)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 89fd8f325f38..bb25d8beb3b8 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -211,7 +211,8 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	pthread_mutex_destroy(&thread_lock);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
+		unsigned long t = bench__runtime.tv_sec > 0 ?
+			worker[i].ops / bench__runtime.tv_sec : 0;
 
 		update_stats(&throughput_stats, t);
 		if (!silent)
diff --git a/tools/perf/bench/kallsyms-parse.c b/tools/perf/bench/kallsyms-parse.c
new file mode 100644
index 000000000000..2b0d0f980ae9
--- /dev/null
+++ b/tools/perf/bench/kallsyms-parse.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Benchmark of /proc/kallsyms parsing.
+ *
+ * Copyright 2020 Google LLC.
+ */
+#include <stdlib.h>
+#include "bench.h"
+#include "../util/stat.h"
+#include <linux/time64.h>
+#include <subcmd/parse-options.h>
+#include <symbol/kallsyms.h>
+
+static unsigned int iterations = 100;
+
+static const struct option options[] = {
+	OPT_UINTEGER('i', "iterations", &iterations,
+		"Number of iterations used to compute average"),
+	OPT_END()
+};
+
+static const char *const bench_usage[] = {
+	"perf bench internals kallsyms-parse <options>",
+	NULL
+};
+
+static int bench_process_symbol(void *arg __maybe_unused,
+				const char *name __maybe_unused,
+				char type __maybe_unused,
+				u64 start __maybe_unused)
+{
+	return 0;
+}
+
+static int do_kallsyms_parse(void)
+{
+	struct timeval start, end, diff;
+	u64 runtime_us;
+	unsigned int i;
+	double time_average, time_stddev;
+	int err;
+	struct stats time_stats;
+
+	init_stats(&time_stats);
+
+	for (i = 0; i < iterations; i++) {
+		gettimeofday(&start, NULL);
+		err = kallsyms__parse("/proc/kallsyms", NULL,
+				bench_process_symbol);
+		if (err)
+			return err;
+
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &diff);
+		runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec;
+		update_stats(&time_stats, runtime_us);
+	}
+
+	time_average = avg_stats(&time_stats) / USEC_PER_MSEC;
+	time_stddev = stddev_stats(&time_stats) / USEC_PER_MSEC;
+	printf("  Average kallsyms__parse took: %.3f ms (+- %.3f ms)\n",
+		time_average, time_stddev);
+	return 0;
+}
+
+int bench_kallsyms_parse(int argc, const char **argv)
+{
+	argc = parse_options(argc, argv, options, bench_usage, 0);
+	if (argc) {
+		usage_with_options(bench_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	return do_kallsyms_parse();
+}
diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c
new file mode 100644
index 000000000000..8d624aea1c5e
--- /dev/null
+++ b/tools/perf/bench/synthesize.c
@@ -0,0 +1,262 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Benchmark synthesis of perf events such as at the start of a 'perf
+ * record'. Synthesis is done on the current process and the 'dummy' event
+ * handlers are invoked that support dump_trace but otherwise do nothing.
+ *
+ * Copyright 2019 Google LLC.
+ */
+#include <stdio.h>
+#include "bench.h"
+#include "../util/debug.h"
+#include "../util/session.h"
+#include "../util/stat.h"
+#include "../util/synthetic-events.h"
+#include "../util/target.h"
+#include "../util/thread_map.h"
+#include "../util/tool.h"
+#include "../util/util.h"
+#include <linux/atomic.h>
+#include <linux/err.h>
+#include <linux/time64.h>
+#include <subcmd/parse-options.h>
+
+static unsigned int min_threads = 1;
+static unsigned int max_threads = UINT_MAX;
+static unsigned int single_iterations = 10000;
+static unsigned int multi_iterations = 10;
+static bool run_st;
+static bool run_mt;
+
+static const struct option options[] = {
+	OPT_BOOLEAN('s', "st", &run_st, "Run single threaded benchmark"),
+	OPT_BOOLEAN('t', "mt", &run_mt, "Run multi-threaded benchmark"),
+	OPT_UINTEGER('m', "min-threads", &min_threads,
+		"Minimum number of threads in multithreaded bench"),
+	OPT_UINTEGER('M', "max-threads", &max_threads,
+		"Maximum number of threads in multithreaded bench"),
+	OPT_UINTEGER('i', "single-iterations", &single_iterations,
+		"Number of iterations used to compute single-threaded average"),
+	OPT_UINTEGER('I', "multi-iterations", &multi_iterations,
+		"Number of iterations used to compute multi-threaded average"),
+	OPT_END()
+};
+
+static const char *const bench_usage[] = {
+	"perf bench internals synthesize <options>",
+	NULL
+};
+
+static atomic_t event_count;
+
+static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event __maybe_unused,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine __maybe_unused)
+{
+	atomic_inc(&event_count);
+	return 0;
+}
+
+static int do_run_single_threaded(struct perf_session *session,
+				struct perf_thread_map *threads,
+				struct target *target, bool data_mmap)
+{
+	const unsigned int nr_threads_synthesize = 1;
+	struct timeval start, end, diff;
+	u64 runtime_us;
+	unsigned int i;
+	double time_average, time_stddev, event_average, event_stddev;
+	int err;
+	struct stats time_stats, event_stats;
+
+	init_stats(&time_stats);
+	init_stats(&event_stats);
+
+	for (i = 0; i < single_iterations; i++) {
+		atomic_set(&event_count, 0);
+		gettimeofday(&start, NULL);
+		err = __machine__synthesize_threads(&session->machines.host,
+						NULL,
+						target, threads,
+						process_synthesized_event,
+						data_mmap,
+						nr_threads_synthesize);
+		if (err)
+			return err;
+
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &diff);
+		runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec;
+		update_stats(&time_stats, runtime_us);
+		update_stats(&event_stats, atomic_read(&event_count));
+	}
+
+	time_average = avg_stats(&time_stats);
+	time_stddev = stddev_stats(&time_stats);
+	printf("  Average %ssynthesis took: %.3f usec (+- %.3f usec)\n",
+		data_mmap ? "data " : "", time_average, time_stddev);
+
+	event_average = avg_stats(&event_stats);
+	event_stddev = stddev_stats(&event_stats);
+	printf("  Average num. events: %.3f (+- %.3f)\n",
+		event_average, event_stddev);
+
+	printf("  Average time per event %.3f usec\n",
+		time_average / event_average);
+	return 0;
+}
+
+static int run_single_threaded(void)
+{
+	struct perf_session *session;
+	struct target target = {
+		.pid = "self",
+	};
+	struct perf_thread_map *threads;
+	int err;
+
+	perf_set_singlethreaded();
+	session = perf_session__new(NULL, false, NULL);
+	if (IS_ERR(session)) {
+		pr_err("Session creation failed.\n");
+		return PTR_ERR(session);
+	}
+	threads = thread_map__new_by_pid(getpid());
+	if (!threads) {
+		pr_err("Thread map creation failed.\n");
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	puts(
+"Computing performance of single threaded perf event synthesis by\n"
+"synthesizing events on the perf process itself:");
+
+	err = do_run_single_threaded(session, threads, &target, false);
+	if (err)
+		goto err_out;
+
+	err = do_run_single_threaded(session, threads, &target, true);
+
+err_out:
+	if (threads)
+		perf_thread_map__put(threads);
+
+	perf_session__delete(session);
+	return err;
+}
+
+static int do_run_multi_threaded(struct target *target,
+				unsigned int nr_threads_synthesize)
+{
+	struct timeval start, end, diff;
+	u64 runtime_us;
+	unsigned int i;
+	double time_average, time_stddev, event_average, event_stddev;
+	int err;
+	struct stats time_stats, event_stats;
+	struct perf_session *session;
+
+	init_stats(&time_stats);
+	init_stats(&event_stats);
+	for (i = 0; i < multi_iterations; i++) {
+		session = perf_session__new(NULL, false, NULL);
+		if (!session)
+			return -ENOMEM;
+
+		atomic_set(&event_count, 0);
+		gettimeofday(&start, NULL);
+		err = __machine__synthesize_threads(&session->machines.host,
+						NULL,
+						target, NULL,
+						process_synthesized_event,
+						false,
+						nr_threads_synthesize);
+		if (err) {
+			perf_session__delete(session);
+			return err;
+		}
+
+		gettimeofday(&end, NULL);
+		timersub(&end, &start, &diff);
+		runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec;
+		update_stats(&time_stats, runtime_us);
+		update_stats(&event_stats, atomic_read(&event_count));
+		perf_session__delete(session);
+	}
+
+	time_average = avg_stats(&time_stats);
+	time_stddev = stddev_stats(&time_stats);
+	printf("    Average synthesis took: %.3f usec (+- %.3f usec)\n",
+		time_average, time_stddev);
+
+	event_average = avg_stats(&event_stats);
+	event_stddev = stddev_stats(&event_stats);
+	printf("    Average num. events: %.3f (+- %.3f)\n",
+		event_average, event_stddev);
+
+	printf("    Average time per event %.3f usec\n",
+		time_average / event_average);
+	return 0;
+}
+
+static int run_multi_threaded(void)
+{
+	struct target target = {
+		.cpu_list = "0"
+	};
+	unsigned int nr_threads_synthesize;
+	int err;
+
+	if (max_threads == UINT_MAX)
+		max_threads = sysconf(_SC_NPROCESSORS_ONLN);
+
+	puts(
+"Computing performance of multi threaded perf event synthesis by\n"
+"synthesizing events on CPU 0:");
+
+	for (nr_threads_synthesize = min_threads;
+	     nr_threads_synthesize <= max_threads;
+	     nr_threads_synthesize++) {
+		if (nr_threads_synthesize == 1)
+			perf_set_singlethreaded();
+		else
+			perf_set_multithreaded();
+
+		printf("  Number of synthesis threads: %u\n",
+			nr_threads_synthesize);
+
+		err = do_run_multi_threaded(&target, nr_threads_synthesize);
+		if (err)
+			return err;
+	}
+	perf_set_singlethreaded();
+	return 0;
+}
+
+int bench_synthesize(int argc, const char **argv)
+{
+	int err = 0;
+
+	argc = parse_options(argc, argv, options, bench_usage, 0);
+	if (argc) {
+		usage_with_options(bench_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	/*
+	 * If neither single threaded or multi-threaded are specified, default
+	 * to running just single threaded.
+	 */
+	if (!run_st && !run_mt)
+		run_st = true;
+
+	if (run_st)
+		err = run_single_threaded();
+
+	if (!err && run_mt)
+		err = run_multi_threaded();
+
+	return err;
+}
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 6c0a0412502e..d3e5a84f87a2 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -212,11 +212,9 @@ static bool has_annotation(struct perf_annotate *ann)
 	return ui__has_annotation() || ann->use_stdio2;
 }
 
-static int perf_evsel__add_sample(struct evsel *evsel,
-				  struct perf_sample *sample,
-				  struct addr_location *al,
-				  struct perf_annotate *ann,
-				  struct machine *machine)
+static int evsel__add_sample(struct evsel *evsel, struct perf_sample *sample,
+			     struct addr_location *al, struct perf_annotate *ann,
+			     struct machine *machine)
 {
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
@@ -278,7 +276,7 @@ static int process_sample_event(struct perf_tool *tool,
 		goto out_put;
 
 	if (!al.filtered &&
-	    perf_evsel__add_sample(evsel, sample, &al, ann, machine)) {
+	    evsel__add_sample(evsel, sample, &al, ann, machine)) {
 		pr_warning("problem incrementing symbol count, "
 			   "skipping event\n");
 		ret = -1;
@@ -433,11 +431,10 @@ static int __cmd_annotate(struct perf_annotate *ann)
 			total_nr_samples += nr_samples;
 			hists__collapse_resort(hists, NULL);
 			/* Don't sort callchain */
-			perf_evsel__reset_sample_bit(pos, CALLCHAIN);
+			evsel__reset_sample_bit(pos, CALLCHAIN);
 			perf_evsel__output_resort(pos, NULL);
 
-			if (symbol_conf.event_group &&
-			    !perf_evsel__is_group_leader(pos))
+			if (symbol_conf.event_group && !evsel__is_group_leader(pos))
 				continue;
 
 			hists__find_annotations(hists, pos, ann);
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index c06fe21c8613..083273209c88 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -76,6 +76,12 @@ static struct bench epoll_benchmarks[] = {
 };
 #endif // HAVE_EVENTFD
 
+static struct bench internals_benchmarks[] = {
+	{ "synthesize", "Benchmark perf event synthesis",	bench_synthesize	},
+	{ "kallsyms-parse", "Benchmark kallsyms parsing",	bench_kallsyms_parse	},
+	{ NULL,		NULL,					NULL			}
+};
+
 struct collection {
 	const char	*name;
 	const char	*summary;
@@ -92,6 +98,7 @@ static struct collection collections[] = {
 #ifdef HAVE_EVENTFD
 	{"epoll",       "Epoll stressing benchmarks",                   epoll_benchmarks        },
 #endif
+	{ "internals",	"Perf-internals benchmarks",			internals_benchmarks	},
 	{ "all",	"All benchmarks",				NULL			},
 	{ NULL,		NULL,						NULL			}
 };
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 246ac0b4d54f..1baf4cae086f 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -95,6 +95,7 @@ struct perf_c2c {
 	bool			 use_stdio;
 	bool			 stats_only;
 	bool			 symbol_full;
+	bool			 stitch_lbr;
 
 	/* HITM shared clines stats */
 	struct c2c_stats	hitm_stats;
@@ -273,6 +274,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
+	if (c2c.stitch_lbr)
+		al.thread->lbr_stitch_enable = true;
+
 	ret = sample__resolve_callchain(sample, &callchain_cursor, NULL,
 					evsel, &al, sysctl_perf_event_max_stack);
 	if (ret)
@@ -1705,7 +1709,7 @@ static struct c2c_dimension *get_dimension(const char *name)
 
 		if (!strcmp(dim->name, name))
 			return dim;
-	};
+	}
 
 	return NULL;
 }
@@ -1921,7 +1925,7 @@ static bool he__display(struct hist_entry *he, struct c2c_stats *stats)
 		FILTER_HITM(tot_hitm);
 	default:
 		break;
-	};
+	}
 
 #undef FILTER_HITM
 
@@ -2255,8 +2259,7 @@ static void print_c2c_info(FILE *out, struct perf_session *session)
 	fprintf(out, "=================================================\n");
 
 	evlist__for_each_entry(evlist, evsel) {
-		fprintf(out, "%-36s: %s\n", first ? "  Events" : "",
-			perf_evsel__name(evsel));
+		fprintf(out, "%-36s: %s\n", first ? "  Events" : "", evsel__name(evsel));
 		first = false;
 	}
 	fprintf(out, "  Cachelines sort on                : %s HITMs\n",
@@ -2601,6 +2604,12 @@ static int setup_callchain(struct evlist *evlist)
 		}
 	}
 
+	if (c2c.stitch_lbr && (mode != CALLCHAIN_LBR)) {
+		ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
+			    "Please apply --call-graph lbr when recording.\n");
+		c2c.stitch_lbr = false;
+	}
+
 	callchain_param.record_mode = mode;
 	callchain_param.min_percent = 0;
 	return 0;
@@ -2752,6 +2761,8 @@ static int perf_c2c__report(int argc, const char **argv)
 	OPT_STRING('c', "coalesce", &coalesce, "coalesce fields",
 		   "coalesce fields: pid,tid,iaddr,dso"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
+	OPT_BOOLEAN(0, "stitch-lbr", &c2c.stitch_lbr,
+		    "Enable LBR callgraph stitching approach"),
 	OPT_PARENT(c2c_options),
 	OPT_END()
 	};
@@ -2947,7 +2958,7 @@ static int perf_c2c__record(int argc, const char **argv)
 
 		rec_argv[i++] = "-e";
 		rec_argv[i++] = perf_mem_events__name(j);
-	};
+	}
 
 	if (all_user)
 		rec_argv[i++] = "--all-user";
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index c94a002f295e..f8c9bdd8269a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -467,7 +467,7 @@ static struct evsel *evsel_match(struct evsel *evsel,
 	struct evsel *e;
 
 	evlist__for_each_entry(evlist, e) {
-		if (perf_evsel__match2(evsel, e))
+		if (evsel__match2(evsel, e))
 			return e;
 	}
 
@@ -981,7 +981,7 @@ static void data_process(void)
 
 		if (!quiet) {
 			fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
-				perf_evsel__name(evsel_base));
+				evsel__name(evsel_base));
 		}
 
 		first = false;
@@ -990,7 +990,7 @@ static void data_process(void)
 			data__fprintf();
 
 		/* Don't sort callchain for perf diff */
-		perf_evsel__reset_sample_bit(evsel_base, CALLCHAIN);
+		evsel__reset_sample_bit(evsel_base, CALLCHAIN);
 
 		hists__process(hists_base);
 	}
@@ -1562,7 +1562,7 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
 
 	default:
 		BUG_ON(1);
-	};
+	}
 }
 
 static void
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index d5adc417a4ca..55eda54240fb 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -284,10 +284,11 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 		.events = POLLIN,
 	};
 
-	if (!perf_cap__capable(CAP_SYS_ADMIN)) {
+	if (!(perf_cap__capable(CAP_PERFMON) ||
+	      perf_cap__capable(CAP_SYS_ADMIN))) {
 		pr_err("ftrace only works for %s!\n",
 #ifdef HAVE_LIBCAP_SUPPORT
-		"users with the SYS_ADMIN capability"
+		"users with the CAP_PERFMON or CAP_SYS_ADMIN capability"
 #else
 		"root"
 #endif
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 7e124a7b8bfd..53932db97a79 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -536,7 +536,7 @@ static int perf_inject__sched_stat(struct perf_tool *tool,
 	union perf_event *event_sw;
 	struct perf_sample sample_sw;
 	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
-	u32 pid = perf_evsel__intval(evsel, sample, "pid");
+	u32 pid = evsel__intval(evsel, sample, "pid");
 
 	list_for_each_entry(ent, &inject->samples, node) {
 		if (pid == ent->tid)
@@ -546,7 +546,7 @@ static int perf_inject__sched_stat(struct perf_tool *tool,
 	return 0;
 found:
 	event_sw = &ent->event[0];
-	perf_evsel__parse_sample(evsel, event_sw, &sample_sw);
+	evsel__parse_sample(evsel, event_sw, &sample_sw);
 
 	sample_sw.period = sample->period;
 	sample_sw.time	 = sample->time;
@@ -561,11 +561,10 @@ static void sig_handler(int sig __maybe_unused)
 	session_done = 1;
 }
 
-static int perf_evsel__check_stype(struct evsel *evsel,
-				   u64 sample_type, const char *sample_msg)
+static int evsel__check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
-	const char *name = perf_evsel__name(evsel);
+	const char *name = evsel__name(evsel);
 
 	if (!(attr->sample_type & sample_type)) {
 		pr_err("Samples for %s event do not have %s attribute set.",
@@ -622,10 +621,10 @@ static int __cmd_inject(struct perf_inject *inject)
 		struct evsel *evsel;
 
 		evlist__for_each_entry(session->evlist, evsel) {
-			const char *name = perf_evsel__name(evsel);
+			const char *name = evsel__name(evsel);
 
 			if (!strcmp(name, "sched:sched_switch")) {
-				if (perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID"))
+				if (evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID"))
 					return -EINVAL;
 
 				evsel->handler = perf_inject__sched_switch;
@@ -684,14 +683,14 @@ static int __cmd_inject(struct perf_inject *inject)
 
 			perf_header__clear_feat(&session->header,
 						HEADER_AUXTRACE);
-			if (inject->itrace_synth_opts.last_branch)
+			if (inject->itrace_synth_opts.last_branch ||
+			    inject->itrace_synth_opts.add_last_branch)
 				perf_header__set_feat(&session->header,
 						      HEADER_BRANCH_STACK);
 			evsel = perf_evlist__id2evsel_strict(session->evlist,
 							     inject->aux_id);
 			if (evsel) {
-				pr_debug("Deleting %s\n",
-					 perf_evsel__name(evsel));
+				pr_debug("Deleting %s\n", evsel__name(evsel));
 				evlist__remove(session->evlist, evsel);
 				evsel__delete(evsel);
 			}
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 003c85f5f56c..38a5ab683ebc 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -169,13 +169,12 @@ static int insert_caller_stat(unsigned long call_site,
 	return 0;
 }
 
-static int perf_evsel__process_alloc_event(struct evsel *evsel,
-					   struct perf_sample *sample)
+static int evsel__process_alloc_event(struct evsel *evsel, struct perf_sample *sample)
 {
-	unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr"),
-		      call_site = perf_evsel__intval(evsel, sample, "call_site");
-	int bytes_req = perf_evsel__intval(evsel, sample, "bytes_req"),
-	    bytes_alloc = perf_evsel__intval(evsel, sample, "bytes_alloc");
+	unsigned long ptr = evsel__intval(evsel, sample, "ptr"),
+		      call_site = evsel__intval(evsel, sample, "call_site");
+	int bytes_req = evsel__intval(evsel, sample, "bytes_req"),
+	    bytes_alloc = evsel__intval(evsel, sample, "bytes_alloc");
 
 	if (insert_alloc_stat(call_site, ptr, bytes_req, bytes_alloc, sample->cpu) ||
 	    insert_caller_stat(call_site, bytes_req, bytes_alloc))
@@ -188,14 +187,13 @@ static int perf_evsel__process_alloc_event(struct evsel *evsel,
 	return 0;
 }
 
-static int perf_evsel__process_alloc_node_event(struct evsel *evsel,
-						struct perf_sample *sample)
+static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_sample *sample)
 {
-	int ret = perf_evsel__process_alloc_event(evsel, sample);
+	int ret = evsel__process_alloc_event(evsel, sample);
 
 	if (!ret) {
 		int node1 = cpu__get_node(sample->cpu),
-		    node2 = perf_evsel__intval(evsel, sample, "node");
+		    node2 = evsel__intval(evsel, sample, "node");
 
 		if (node1 != node2)
 			nr_cross_allocs++;
@@ -232,10 +230,9 @@ static struct alloc_stat *search_alloc_stat(unsigned long ptr,
 	return NULL;
 }
 
-static int perf_evsel__process_free_event(struct evsel *evsel,
-					  struct perf_sample *sample)
+static int evsel__process_free_event(struct evsel *evsel, struct perf_sample *sample)
 {
-	unsigned long ptr = perf_evsel__intval(evsel, sample, "ptr");
+	unsigned long ptr = evsel__intval(evsel, sample, "ptr");
 	struct alloc_stat *s_alloc, *s_caller;
 
 	s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp);
@@ -784,13 +781,12 @@ static int parse_gfp_flags(struct evsel *evsel, struct perf_sample *sample,
 	return 0;
 }
 
-static int perf_evsel__process_page_alloc_event(struct evsel *evsel,
-						struct perf_sample *sample)
+static int evsel__process_page_alloc_event(struct evsel *evsel, struct perf_sample *sample)
 {
 	u64 page;
-	unsigned int order = perf_evsel__intval(evsel, sample, "order");
-	unsigned int gfp_flags = perf_evsel__intval(evsel, sample, "gfp_flags");
-	unsigned int migrate_type = perf_evsel__intval(evsel, sample,
+	unsigned int order = evsel__intval(evsel, sample, "order");
+	unsigned int gfp_flags = evsel__intval(evsel, sample, "gfp_flags");
+	unsigned int migrate_type = evsel__intval(evsel, sample,
 						       "migratetype");
 	u64 bytes = kmem_page_size << order;
 	u64 callsite;
@@ -802,9 +798,9 @@ static int perf_evsel__process_page_alloc_event(struct evsel *evsel,
 	};
 
 	if (use_pfn)
-		page = perf_evsel__intval(evsel, sample, "pfn");
+		page = evsel__intval(evsel, sample, "pfn");
 	else
-		page = perf_evsel__intval(evsel, sample, "page");
+		page = evsel__intval(evsel, sample, "page");
 
 	nr_page_allocs++;
 	total_page_alloc_bytes += bytes;
@@ -857,11 +853,10 @@ static int perf_evsel__process_page_alloc_event(struct evsel *evsel,
 	return 0;
 }
 
-static int perf_evsel__process_page_free_event(struct evsel *evsel,
-						struct perf_sample *sample)
+static int evsel__process_page_free_event(struct evsel *evsel, struct perf_sample *sample)
 {
 	u64 page;
-	unsigned int order = perf_evsel__intval(evsel, sample, "order");
+	unsigned int order = evsel__intval(evsel, sample, "order");
 	u64 bytes = kmem_page_size << order;
 	struct page_stat *pstat;
 	struct page_stat this = {
@@ -869,9 +864,9 @@ static int perf_evsel__process_page_free_event(struct evsel *evsel,
 	};
 
 	if (use_pfn)
-		page = perf_evsel__intval(evsel, sample, "pfn");
+		page = evsel__intval(evsel, sample, "pfn");
 	else
-		page = perf_evsel__intval(evsel, sample, "page");
+		page = evsel__intval(evsel, sample, "page");
 
 	nr_page_frees++;
 	total_page_free_bytes += bytes;
@@ -1371,15 +1366,15 @@ static int __cmd_kmem(struct perf_session *session)
 	struct evsel *evsel;
 	const struct evsel_str_handler kmem_tracepoints[] = {
 		/* slab allocator */
-		{ "kmem:kmalloc",		perf_evsel__process_alloc_event, },
-    		{ "kmem:kmem_cache_alloc",	perf_evsel__process_alloc_event, },
-		{ "kmem:kmalloc_node",		perf_evsel__process_alloc_node_event, },
-    		{ "kmem:kmem_cache_alloc_node", perf_evsel__process_alloc_node_event, },
-		{ "kmem:kfree",			perf_evsel__process_free_event, },
-    		{ "kmem:kmem_cache_free",	perf_evsel__process_free_event, },
+		{ "kmem:kmalloc",		evsel__process_alloc_event, },
+		{ "kmem:kmem_cache_alloc",	evsel__process_alloc_event, },
+		{ "kmem:kmalloc_node",		evsel__process_alloc_node_event, },
+		{ "kmem:kmem_cache_alloc_node", evsel__process_alloc_node_event, },
+		{ "kmem:kfree",			evsel__process_free_event, },
+		{ "kmem:kmem_cache_free",	evsel__process_free_event, },
 		/* page allocator */
-		{ "kmem:mm_page_alloc",		perf_evsel__process_page_alloc_event, },
-		{ "kmem:mm_page_free",		perf_evsel__process_page_free_event, },
+		{ "kmem:mm_page_alloc",		evsel__process_page_alloc_event, },
+		{ "kmem:mm_page_free",		evsel__process_page_free_event, },
 	};
 
 	if (!perf_session__has_traces(session, "kmem record"))
@@ -1391,8 +1386,8 @@ static int __cmd_kmem(struct perf_session *session)
 	}
 
 	evlist__for_each_entry(session->evlist, evsel) {
-		if (!strcmp(perf_evsel__name(evsel), "kmem:mm_page_alloc") &&
-		    perf_evsel__field(evsel, "pfn")) {
+		if (!strcmp(evsel__name(evsel), "kmem:mm_page_alloc") &&
+		    evsel__field(evsel, "pfn")) {
 			use_pfn = true;
 			break;
 		}
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 577af4f3297a..95a77058023e 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -69,7 +69,7 @@ void exit_event_get_key(struct evsel *evsel,
 			struct event_key *key)
 {
 	key->info = 0;
-	key->key = perf_evsel__intval(evsel, sample, kvm_exit_reason);
+	key->key  = evsel__intval(evsel, sample, kvm_exit_reason);
 }
 
 bool kvm_exit_event(struct evsel *evsel)
@@ -416,8 +416,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 			return NULL;
 		}
 
-		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample,
-							  vcpu_id_str);
+		vcpu_record->vcpu_id = evsel__intval(evsel, sample, vcpu_id_str);
 		thread__set_priv(thread, vcpu_record);
 	}
 
@@ -1033,16 +1032,16 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 		struct perf_event_attr *attr = &pos->core.attr;
 
 		/* make sure these *are* set */
-		perf_evsel__set_sample_bit(pos, TID);
-		perf_evsel__set_sample_bit(pos, TIME);
-		perf_evsel__set_sample_bit(pos, CPU);
-		perf_evsel__set_sample_bit(pos, RAW);
+		evsel__set_sample_bit(pos, TID);
+		evsel__set_sample_bit(pos, TIME);
+		evsel__set_sample_bit(pos, CPU);
+		evsel__set_sample_bit(pos, RAW);
 		/* make sure these are *not*; want as small a sample as possible */
-		perf_evsel__reset_sample_bit(pos, PERIOD);
-		perf_evsel__reset_sample_bit(pos, IP);
-		perf_evsel__reset_sample_bit(pos, CALLCHAIN);
-		perf_evsel__reset_sample_bit(pos, ADDR);
-		perf_evsel__reset_sample_bit(pos, READ);
+		evsel__reset_sample_bit(pos, PERIOD);
+		evsel__reset_sample_bit(pos, IP);
+		evsel__reset_sample_bit(pos, CALLCHAIN);
+		evsel__reset_sample_bit(pos, ADDR);
+		evsel__reset_sample_bit(pos, READ);
 		attr->mmap = 0;
 		attr->comm = 0;
 		attr->task = 0;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 474dfd59d7eb..f0a1dbacb46c 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -48,7 +48,7 @@ struct lock_stat {
 	struct rb_node		rb;		/* used for sorting */
 
 	/*
-	 * FIXME: perf_evsel__intval() returns u64,
+	 * FIXME: evsel__intval() returns u64,
 	 * so address of lockdep_map should be dealed as 64bit.
 	 * Is there more better solution?
 	 */
@@ -404,9 +404,9 @@ static int report_lock_acquire_event(struct evsel *evsel,
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
-	const char *name = perf_evsel__strval(evsel, sample, "name");
-	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
-	int flag = perf_evsel__intval(evsel, sample, "flag");
+	const char *name = evsel__strval(evsel, sample, "name");
+	u64 tmp	 = evsel__intval(evsel, sample, "lockdep_addr");
+	int flag = evsel__intval(evsel, sample, "flag");
 
 	memcpy(&addr, &tmp, sizeof(void *));
 
@@ -477,8 +477,8 @@ static int report_lock_acquired_event(struct evsel *evsel,
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
 	u64 contended_term;
-	const char *name = perf_evsel__strval(evsel, sample, "name");
-	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
+	const char *name = evsel__strval(evsel, sample, "name");
+	u64 tmp = evsel__intval(evsel, sample, "lockdep_addr");
 
 	memcpy(&addr, &tmp, sizeof(void *));
 
@@ -539,8 +539,8 @@ static int report_lock_contended_event(struct evsel *evsel,
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
-	const char *name = perf_evsel__strval(evsel, sample, "name");
-	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
+	const char *name = evsel__strval(evsel, sample, "name");
+	u64 tmp = evsel__intval(evsel, sample, "lockdep_addr");
 
 	memcpy(&addr, &tmp, sizeof(void *));
 
@@ -594,8 +594,8 @@ static int report_lock_release_event(struct evsel *evsel,
 	struct lock_stat *ls;
 	struct thread_stat *ts;
 	struct lock_seq_stat *seq;
-	const char *name = perf_evsel__strval(evsel, sample, "name");
-	u64 tmp = perf_evsel__intval(evsel, sample, "lockdep_addr");
+	const char *name = evsel__strval(evsel, sample, "name");
+	u64 tmp = evsel__intval(evsel, sample, "lockdep_addr");
 
 	memcpy(&addr, &tmp, sizeof(void *));
 
@@ -657,32 +657,28 @@ static struct trace_lock_handler report_lock_ops  = {
 
 static struct trace_lock_handler *trace_handler;
 
-static int perf_evsel__process_lock_acquire(struct evsel *evsel,
-					     struct perf_sample *sample)
+static int evsel__process_lock_acquire(struct evsel *evsel, struct perf_sample *sample)
 {
 	if (trace_handler->acquire_event)
 		return trace_handler->acquire_event(evsel, sample);
 	return 0;
 }
 
-static int perf_evsel__process_lock_acquired(struct evsel *evsel,
-					      struct perf_sample *sample)
+static int evsel__process_lock_acquired(struct evsel *evsel, struct perf_sample *sample)
 {
 	if (trace_handler->acquired_event)
 		return trace_handler->acquired_event(evsel, sample);
 	return 0;
 }
 
-static int perf_evsel__process_lock_contended(struct evsel *evsel,
-					      struct perf_sample *sample)
+static int evsel__process_lock_contended(struct evsel *evsel, struct perf_sample *sample)
 {
 	if (trace_handler->contended_event)
 		return trace_handler->contended_event(evsel, sample);
 	return 0;
 }
 
-static int perf_evsel__process_lock_release(struct evsel *evsel,
-					    struct perf_sample *sample)
+static int evsel__process_lock_release(struct evsel *evsel, struct perf_sample *sample)
 {
 	if (trace_handler->release_event)
 		return trace_handler->release_event(evsel, sample);
@@ -775,7 +771,7 @@ static void dump_threads(void)
 		pr_info("%10d: %s\n", st->tid, thread__comm_str(t));
 		node = rb_next(node);
 		thread__put(t);
-	};
+	}
 }
 
 static void dump_map(void)
@@ -849,10 +845,10 @@ static void sort_result(void)
 }
 
 static const struct evsel_str_handler lock_tracepoints[] = {
-	{ "lock:lock_acquire",	 perf_evsel__process_lock_acquire,   }, /* CONFIG_LOCKDEP */
-	{ "lock:lock_acquired",	 perf_evsel__process_lock_acquired,  }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
-	{ "lock:lock_contended", perf_evsel__process_lock_contended, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
-	{ "lock:lock_release",	 perf_evsel__process_lock_release,   }, /* CONFIG_LOCKDEP */
+	{ "lock:lock_acquire",	 evsel__process_lock_acquire,   }, /* CONFIG_LOCKDEP */
+	{ "lock:lock_acquired",	 evsel__process_lock_acquired,  }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+	{ "lock:lock_contended", evsel__process_lock_contended, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+	{ "lock:lock_release",	 evsel__process_lock_release,   }, /* CONFIG_LOCKDEP */
 };
 
 static bool force;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index a13f5817d6fc..68a7eb84561a 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -123,7 +123,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
 		rec_argv[i++] = "-e";
 		rec_argv[i++] = perf_mem_events__name(j);
-	};
+	}
 
 	if (all_user)
 		rec_argv[i++] = "--all-user";
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 1ab349abe904..e4efdbf1a81e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -34,6 +34,7 @@
 #include "util/tsc.h"
 #include "util/parse-branch-options.h"
 #include "util/parse-regs-options.h"
+#include "util/perf_api_probe.h"
 #include "util/llvm-utils.h"
 #include "util/bpf-loader.h"
 #include "util/trigger.h"
@@ -43,6 +44,7 @@
 #include "util/time-utils.h"
 #include "util/units.h"
 #include "util/bpf-event.h"
+#include "util/util.h"
 #include "asm/bug.h"
 #include "perf.h"
 
@@ -50,6 +52,7 @@
 #include <inttypes.h>
 #include <locale.h>
 #include <poll.h>
+#include <pthread.h>
 #include <unistd.h>
 #include <sched.h>
 #include <signal.h>
@@ -84,7 +87,10 @@ struct record {
 	struct auxtrace_record	*itr;
 	struct evlist	*evlist;
 	struct perf_session	*session;
+	struct evlist		*sb_evlist;
+	pthread_t		thread_id;
 	int			realtime_prio;
+	bool			switch_output_event_set;
 	bool			no_buildid;
 	bool			no_buildid_set;
 	bool			no_buildid_cache;
@@ -503,6 +509,20 @@ static int process_synthesized_event(struct perf_tool *tool,
 	return record__write(rec, NULL, event, event->header.size);
 }
 
+static int process_locked_synthesized_event(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine __maybe_unused)
+{
+	static pthread_mutex_t synth_lock = PTHREAD_MUTEX_INITIALIZER;
+	int ret;
+
+	pthread_mutex_lock(&synth_lock);
+	ret = process_synthesized_event(tool, event, sample, machine);
+	pthread_mutex_unlock(&synth_lock);
+	return ret;
+}
+
 static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 {
 	struct record *rec = to;
@@ -825,7 +845,7 @@ static int record__open(struct record *rec)
 	evlist__for_each_entry(evlist, pos) {
 try_again:
 		if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) {
-			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
+			if (evsel__fallback(pos, errno, msg, sizeof(msg))) {
 				if (verbose > 0)
 					ui__warning("%s\n", msg);
 				goto try_again;
@@ -837,8 +857,7 @@ try_again:
 				goto try_again;
 			}
 			rc = -errno;
-			perf_evsel__open_strerror(pos, &opts->target,
-						  errno, msg, sizeof(msg));
+			evsel__open_strerror(pos, &opts->target, errno, msg, sizeof(msg));
 			ui__error("%s\n", msg);
 			goto out;
 		}
@@ -859,7 +878,7 @@ try_again:
 
 	if (perf_evlist__apply_filters(evlist, &pos)) {
 		pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n",
-			pos->filter, perf_evsel__name(pos), errno,
+			pos->filter, evsel__name(pos), errno,
 			str_error_r(errno, msg, sizeof(msg)));
 		rc = -1;
 		goto out;
@@ -1288,6 +1307,7 @@ static int record__synthesize(struct record *rec, bool tail)
 	struct perf_tool *tool = &rec->tool;
 	int fd = perf_data__fd(data);
 	int err = 0;
+	event_op f = process_synthesized_event;
 
 	if (rec->opts.tail_synthesize != tail)
 		return 0;
@@ -1402,13 +1422,67 @@ static int record__synthesize(struct record *rec, bool tail)
 	if (err < 0)
 		pr_warning("Couldn't synthesize cgroup events.\n");
 
+	if (rec->opts.nr_threads_synthesize > 1) {
+		perf_set_multithreaded();
+		f = process_locked_synthesized_event;
+	}
+
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads,
-					    process_synthesized_event, opts->sample_address,
-					    1);
+					    f, opts->sample_address,
+					    rec->opts.nr_threads_synthesize);
+
+	if (rec->opts.nr_threads_synthesize > 1)
+		perf_set_singlethreaded();
+
 out:
 	return err;
 }
 
+static int record__process_signal_event(union perf_event *event __maybe_unused, void *data)
+{
+	struct record *rec = data;
+	pthread_kill(rec->thread_id, SIGUSR2);
+	return 0;
+}
+
+static int record__setup_sb_evlist(struct record *rec)
+{
+	struct record_opts *opts = &rec->opts;
+
+	if (rec->sb_evlist != NULL) {
+		/*
+		 * We get here if --switch-output-event populated the
+		 * sb_evlist, so associate a callback that will send a SIGUSR2
+		 * to the main thread.
+		 */
+		evlist__set_cb(rec->sb_evlist, record__process_signal_event, rec);
+		rec->thread_id = pthread_self();
+	}
+
+	if (!opts->no_bpf_event) {
+		if (rec->sb_evlist == NULL) {
+			rec->sb_evlist = evlist__new();
+
+			if (rec->sb_evlist == NULL) {
+				pr_err("Couldn't create side band evlist.\n.");
+				return -1;
+			}
+		}
+
+		if (evlist__add_bpf_sb_event(rec->sb_evlist, &rec->session->header.env)) {
+			pr_err("Couldn't ask for PERF_RECORD_BPF_EVENT side band events.\n.");
+			return -1;
+		}
+	}
+
+	if (perf_evlist__start_sb_thread(rec->sb_evlist, &rec->opts.target)) {
+		pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
+		opts->no_bpf_event = true;
+	}
+
+	return 0;
+}
+
 static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
 	int err;
@@ -1420,7 +1494,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	struct perf_data *data = &rec->data;
 	struct perf_session *session;
 	bool disabled = false, draining = false;
-	struct evlist *sb_evlist = NULL;
 	int fd;
 	float ratio = 0;
 
@@ -1546,21 +1619,17 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			goto out_child;
 	}
 
+	err = -1;
 	if (!rec->no_buildid
 	    && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
 		pr_err("Couldn't generate buildids. "
 		       "Use --no-buildid to profile anyway.\n");
-		err = -1;
 		goto out_child;
 	}
 
-	if (!opts->no_bpf_event)
-		bpf_event__add_sb_event(&sb_evlist, &session->header.env);
-
-	if (perf_evlist__start_sb_thread(sb_evlist, &rec->opts.target)) {
-		pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
-		opts->no_bpf_event = true;
-	}
+	err = record__setup_sb_evlist(rec);
+	if (err)
+		goto out_child;
 
 	err = record__synthesize(rec, false);
 	if (err < 0)
@@ -1831,7 +1900,7 @@ out_delete_session:
 	perf_session__delete(session);
 
 	if (!opts->no_bpf_event)
-		perf_evlist__stop_sb_thread(sb_evlist);
+		perf_evlist__stop_sb_thread(rec->sb_evlist);
 	return status;
 }
 
@@ -2142,10 +2211,19 @@ static int switch_output_setup(struct record *rec)
 	};
 	unsigned long val;
 
+	/*
+	 * If we're using --switch-output-events, then we imply its 
+	 * --switch-output=signal, as we'll send a SIGUSR2 from the side band
+	 *  thread to its parent.
+	 */
+	if (rec->switch_output_event_set)
+		goto do_signal;
+
 	if (!s->set)
 		return 0;
 
 	if (!strcmp(s->str, "signal")) {
+do_signal:
 		s->signal = true;
 		pr_debug("switch-output with SIGUSR2 signal\n");
 		goto enabled;
@@ -2232,6 +2310,7 @@ static struct record record = {
 			.default_per_cpu = true,
 		},
 		.mmap_flush          = MMAP_FLUSH_DEFAULT,
+		.nr_threads_synthesize = 1,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -2402,6 +2481,9 @@ static struct option __record_options[] = {
 			  &record.switch_output.set, "signal or size[BKMG] or time[smhd]",
 			  "Switch output when receiving SIGUSR2 (signal) or cross a size or time threshold",
 			  "signal"),
+	OPT_CALLBACK_SET(0, "switch-output-event", &record.sb_evlist, &record.switch_output_event_set, "switch output event",
+			 "switch output event selector. use 'perf list' to list available events",
+			 parse_events_option_new_evlist),
 	OPT_INTEGER(0, "switch-max-files", &record.switch_output.num_files,
 		   "Limit number of switch output generated files"),
 	OPT_BOOLEAN(0, "dry-run", &dry_run,
@@ -2421,6 +2503,9 @@ static struct option __record_options[] = {
 #endif
 	OPT_CALLBACK(0, "max-size", &record.output_max_size,
 		     "size", "Limit the maximum size of the output file", parse_output_max_size),
+	OPT_UINTEGER(0, "num-thread-synthesize",
+		     &record.opts.nr_threads_synthesize,
+		     "number of threads to run for event synthesis"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 26d8fc27e427..ba63390246c2 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -84,6 +84,7 @@ struct report {
 	bool			header_only;
 	bool			nonany_branch_mode;
 	bool			group_set;
+	bool			stitch_lbr;
 	int			max_stack;
 	struct perf_read_values	show_threads_values;
 	struct annotation_options annotation_opts;
@@ -267,6 +268,9 @@ static int process_sample_event(struct perf_tool *tool,
 		return -1;
 	}
 
+	if (rep->stitch_lbr)
+		al.thread->lbr_stitch_enable = true;
+
 	if (symbol_conf.hide_unresolved && al.sym == NULL)
 		goto out_put;
 
@@ -317,7 +321,7 @@ static int process_read_event(struct perf_tool *tool,
 	struct report *rep = container_of(tool, struct report, tool);
 
 	if (rep->show_threads) {
-		const char *name = perf_evsel__name(evsel);
+		const char *name = evsel__name(evsel);
 		int err = perf_read_values_add_value(&rep->show_threads_values,
 					   event->read.pid, event->read.tid,
 					   evsel->idx,
@@ -339,12 +343,14 @@ static int report__setup_sample_type(struct report *rep)
 	bool is_pipe = perf_data__is_pipe(session->data);
 
 	if (session->itrace_synth_opts->callchain ||
+	    session->itrace_synth_opts->add_callchain ||
 	    (!is_pipe &&
 	     perf_header__has_feat(&session->header, HEADER_AUXTRACE) &&
 	     !session->itrace_synth_opts->set))
 		sample_type |= PERF_SAMPLE_CALLCHAIN;
 
-	if (session->itrace_synth_opts->last_branch)
+	if (session->itrace_synth_opts->last_branch ||
+	    session->itrace_synth_opts->add_last_branch)
 		sample_type |= PERF_SAMPLE_BRANCH_STACK;
 
 	if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
@@ -407,6 +413,12 @@ static int report__setup_sample_type(struct report *rep)
 			callchain_param.record_mode = CALLCHAIN_FP;
 	}
 
+	if (rep->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
+		ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
+			    "Please apply --call-graph lbr when recording.\n");
+		rep->stitch_lbr = false;
+	}
+
 	/* ??? handle more cases than just ANY? */
 	if (!(perf_evlist__combined_branch_type(session->evlist) &
 				PERF_SAMPLE_BRANCH_ANY))
@@ -447,10 +459,10 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 		nr_events = hists->stats.total_non_filtered_period;
 	}
 
-	if (perf_evsel__is_group_event(evsel)) {
+	if (evsel__is_group_event(evsel)) {
 		struct evsel *pos;
 
-		perf_evsel__group_desc(evsel, buf, size);
+		evsel__group_desc(evsel, buf, size);
 		evname = buf;
 
 		for_each_group_member(pos, evsel) {
@@ -525,10 +537,9 @@ static int perf_evlist__tty_browse_hists(struct evlist *evlist,
 
 	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
-		const char *evname = perf_evsel__name(pos);
+		const char *evname = evsel__name(pos);
 
-		if (symbol_conf.event_group &&
-		    !perf_evsel__is_group_leader(pos))
+		if (symbol_conf.event_group && !evsel__is_group_leader(pos))
 			continue;
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
@@ -670,8 +681,7 @@ static int report__collapse_hists(struct report *rep)
 			break;
 
 		/* Non-group events are considered as leader */
-		if (symbol_conf.event_group &&
-		    !perf_evsel__is_group_leader(pos)) {
+		if (symbol_conf.event_group && !evsel__is_group_leader(pos)) {
 			struct hists *leader_hists = evsel__hists(pos->leader);
 
 			hists__match(leader_hists, hists);
@@ -1257,6 +1267,8 @@ int cmd_report(int argc, const char **argv)
 			"Show full source file name path for source lines"),
 	OPT_BOOLEAN(0, "show-ref-call-graph", &symbol_conf.show_ref_callgraph,
 		    "Show callgraph from reference event"),
+	OPT_BOOLEAN(0, "stitch-lbr", &report.stitch_lbr,
+		    "Enable LBR callgraph stitching approach"),
 	OPT_INTEGER(0, "socket-filter", &report.socket_filter,
 		    "only show processor socket that match with this filter"),
 	OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
@@ -1332,7 +1344,7 @@ int cmd_report(int argc, const char **argv)
 	if (symbol_conf.cumulate_callchain && !callchain_param.order_set)
 		callchain_param.order = ORDER_CALLER;
 
-	if (itrace_synth_opts.callchain &&
+	if ((itrace_synth_opts.callchain || itrace_synth_opts.add_callchain) &&
 	    (int)itrace_synth_opts.callchain_sz > report.max_stack)
 		report.max_stack = itrace_synth_opts.callchain_sz;
 
@@ -1380,7 +1392,7 @@ repeat:
 		goto error;
 	}
 
-	if (itrace_synth_opts.last_branch)
+	if (itrace_synth_opts.last_branch || itrace_synth_opts.add_last_branch)
 		has_br_stack = true;
 
 	if (has_br_stack && branch_call_mode)
@@ -1400,7 +1412,7 @@ repeat:
 	}
 	if (branch_call_mode) {
 		callchain_param.key = CCKEY_ADDRESS;
-		callchain_param.branch_callstack = 1;
+		callchain_param.branch_callstack = true;
 		symbol_conf.use_callchain = true;
 		callchain_register_param(&callchain_param);
 		if (sort_order == NULL)
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 82fcc2c15fe4..459e4229945e 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -811,8 +811,8 @@ replay_wakeup_event(struct perf_sched *sched,
 		    struct evsel *evsel, struct perf_sample *sample,
 		    struct machine *machine __maybe_unused)
 {
-	const char *comm = perf_evsel__strval(evsel, sample, "comm");
-	const u32 pid	 = perf_evsel__intval(evsel, sample, "pid");
+	const char *comm = evsel__strval(evsel, sample, "comm");
+	const u32 pid	 = evsel__intval(evsel, sample, "pid");
 	struct task_desc *waker, *wakee;
 
 	if (verbose > 0) {
@@ -833,11 +833,11 @@ static int replay_switch_event(struct perf_sched *sched,
 			       struct perf_sample *sample,
 			       struct machine *machine __maybe_unused)
 {
-	const char *prev_comm  = perf_evsel__strval(evsel, sample, "prev_comm"),
-		   *next_comm  = perf_evsel__strval(evsel, sample, "next_comm");
-	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
-		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
-	const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
+	const char *prev_comm  = evsel__strval(evsel, sample, "prev_comm"),
+		   *next_comm  = evsel__strval(evsel, sample, "next_comm");
+	const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"),
+		  next_pid = evsel__intval(evsel, sample, "next_pid");
+	const u64 prev_state = evsel__intval(evsel, sample, "prev_state");
 	struct task_desc *prev, __maybe_unused *next;
 	u64 timestamp0, timestamp = sample->time;
 	int cpu = sample->cpu;
@@ -1106,9 +1106,9 @@ static int latency_switch_event(struct perf_sched *sched,
 				struct perf_sample *sample,
 				struct machine *machine)
 {
-	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
-		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
-	const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
+	const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"),
+		  next_pid = evsel__intval(evsel, sample, "next_pid");
+	const u64 prev_state = evsel__intval(evsel, sample, "prev_state");
 	struct work_atoms *out_events, *in_events;
 	struct thread *sched_out, *sched_in;
 	u64 timestamp0, timestamp = sample->time;
@@ -1176,8 +1176,8 @@ static int latency_runtime_event(struct perf_sched *sched,
 				 struct perf_sample *sample,
 				 struct machine *machine)
 {
-	const u32 pid	   = perf_evsel__intval(evsel, sample, "pid");
-	const u64 runtime  = perf_evsel__intval(evsel, sample, "runtime");
+	const u32 pid	   = evsel__intval(evsel, sample, "pid");
+	const u64 runtime  = evsel__intval(evsel, sample, "runtime");
 	struct thread *thread = machine__findnew_thread(machine, -1, pid);
 	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 	u64 timestamp = sample->time;
@@ -1211,7 +1211,7 @@ static int latency_wakeup_event(struct perf_sched *sched,
 				struct perf_sample *sample,
 				struct machine *machine)
 {
-	const u32 pid	  = perf_evsel__intval(evsel, sample, "pid");
+	const u32 pid	  = evsel__intval(evsel, sample, "pid");
 	struct work_atoms *atoms;
 	struct work_atom *atom;
 	struct thread *wakee;
@@ -1272,7 +1272,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 				      struct perf_sample *sample,
 				      struct machine *machine)
 {
-	const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+	const u32 pid = evsel__intval(evsel, sample, "pid");
 	u64 timestamp = sample->time;
 	struct work_atoms *atoms;
 	struct work_atom *atom;
@@ -1526,7 +1526,7 @@ map__findnew_thread(struct perf_sched *sched, struct machine *machine, pid_t pid
 static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 			    struct perf_sample *sample, struct machine *machine)
 {
-	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	const u32 next_pid = evsel__intval(evsel, sample, "next_pid");
 	struct thread *sched_in;
 	struct thread_runtime *tr;
 	int new_shortname;
@@ -1670,8 +1670,8 @@ static int process_sched_switch_event(struct perf_tool *tool,
 {
 	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 	int this_cpu = sample->cpu, err = 0;
-	u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
-	    next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"),
+	    next_pid = evsel__intval(evsel, sample, "next_pid");
 
 	if (sched->curr_pid[this_cpu] != (u32)-1) {
 		/*
@@ -1848,7 +1848,7 @@ static inline void print_sched_time(unsigned long long nsecs, int width)
  * returns runtime data for event, allocating memory for it the
  * first time it is used.
  */
-static struct evsel_runtime *perf_evsel__get_runtime(struct evsel *evsel)
+static struct evsel_runtime *evsel__get_runtime(struct evsel *evsel)
 {
 	struct evsel_runtime *r = evsel->priv;
 
@@ -1863,10 +1863,9 @@ static struct evsel_runtime *perf_evsel__get_runtime(struct evsel *evsel)
 /*
  * save last time event was seen per cpu
  */
-static void perf_evsel__save_time(struct evsel *evsel,
-				  u64 timestamp, u32 cpu)
+static void evsel__save_time(struct evsel *evsel, u64 timestamp, u32 cpu)
 {
-	struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
+	struct evsel_runtime *r = evsel__get_runtime(evsel);
 
 	if (r == NULL)
 		return;
@@ -1890,9 +1889,9 @@ static void perf_evsel__save_time(struct evsel *evsel,
 }
 
 /* returns last time this event was seen on the given cpu */
-static u64 perf_evsel__get_time(struct evsel *evsel, u32 cpu)
+static u64 evsel__get_time(struct evsel *evsel, u32 cpu)
 {
-	struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
+	struct evsel_runtime *r = evsel__get_runtime(evsel);
 
 	if ((r == NULL) || (r->last_time == NULL) || (cpu >= r->ncpu))
 		return 0;
@@ -2004,8 +2003,8 @@ static void timehist_print_sample(struct perf_sched *sched,
 				  u64 t, int state)
 {
 	struct thread_runtime *tr = thread__priv(thread);
-	const char *next_comm = perf_evsel__strval(evsel, sample, "next_comm");
-	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	const char *next_comm = evsel__strval(evsel, sample, "next_comm");
+	const u32 next_pid = evsel__intval(evsel, sample, "next_pid");
 	u32 max_cpus = sched->max_cpu + 1;
 	char tstr[64];
 	char nstr[30];
@@ -2136,8 +2135,8 @@ static bool is_idle_sample(struct perf_sample *sample,
 			   struct evsel *evsel)
 {
 	/* pid 0 == swapper == idle task */
-	if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0)
-		return perf_evsel__intval(evsel, sample, "prev_pid") == 0;
+	if (strcmp(evsel__name(evsel), "sched:sched_switch") == 0)
+		return evsel__intval(evsel, sample, "prev_pid") == 0;
 
 	return sample->pid == 0;
 }
@@ -2334,7 +2333,7 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 			itr->last_thread = thread;
 
 			/* copy task callchain when entering to idle */
-			if (perf_evsel__intval(evsel, sample, "next_pid") == 0)
+			if (evsel__intval(evsel, sample, "next_pid") == 0)
 				save_idle_callchain(sched, itr, sample);
 		}
 	}
@@ -2355,10 +2354,10 @@ static bool timehist_skip_sample(struct perf_sched *sched,
 	}
 
 	if (sched->idle_hist) {
-		if (strcmp(perf_evsel__name(evsel), "sched:sched_switch"))
+		if (strcmp(evsel__name(evsel), "sched:sched_switch"))
 			rc = true;
-		else if (perf_evsel__intval(evsel, sample, "prev_pid") != 0 &&
-			 perf_evsel__intval(evsel, sample, "next_pid") != 0)
+		else if (evsel__intval(evsel, sample, "prev_pid") != 0 &&
+			 evsel__intval(evsel, sample, "next_pid") != 0)
 			rc = true;
 	}
 
@@ -2409,7 +2408,7 @@ static int timehist_sched_wakeup_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct thread_runtime *tr = NULL;
 	/* want pid of awakened task not pid in sample */
-	const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+	const u32 pid = evsel__intval(evsel, sample, "pid");
 
 	thread = machine__findnew_thread(machine, 0, pid);
 	if (thread == NULL)
@@ -2445,8 +2444,8 @@ static void timehist_print_migration_event(struct perf_sched *sched,
 		return;
 
 	max_cpus = sched->max_cpu + 1;
-	ocpu = perf_evsel__intval(evsel, sample, "orig_cpu");
-	dcpu = perf_evsel__intval(evsel, sample, "dest_cpu");
+	ocpu = evsel__intval(evsel, sample, "orig_cpu");
+	dcpu = evsel__intval(evsel, sample, "dest_cpu");
 
 	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
 	if (thread == NULL)
@@ -2493,7 +2492,7 @@ static int timehist_migrate_task_event(struct perf_tool *tool,
 	struct thread *thread;
 	struct thread_runtime *tr = NULL;
 	/* want pid of migrated task not pid in sample */
-	const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+	const u32 pid = evsel__intval(evsel, sample, "pid");
 
 	thread = machine__findnew_thread(machine, 0, pid);
 	if (thread == NULL)
@@ -2524,8 +2523,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	struct thread_runtime *tr = NULL;
 	u64 tprev, t = sample->time;
 	int rc = 0;
-	int state = perf_evsel__intval(evsel, sample, "prev_state");
-
+	int state = evsel__intval(evsel, sample, "prev_state");
 
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_err("problem processing %d event. skipping it\n",
@@ -2549,7 +2547,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 		goto out;
 	}
 
-	tprev = perf_evsel__get_time(evsel, sample->cpu);
+	tprev = evsel__get_time(evsel, sample->cpu);
 
 	/*
 	 * If start time given:
@@ -2632,7 +2630,7 @@ out:
 		tr->ready_to_run = 0;
 	}
 
-	perf_evsel__save_time(evsel, sample->time, sample->cpu);
+	evsel__save_time(evsel, sample->time, sample->cpu);
 
 	return rc;
 }
@@ -2942,7 +2940,7 @@ static int timehist_check_attr(struct perf_sched *sched,
 	struct evsel_runtime *er;
 
 	list_for_each_entry(evsel, &evlist->core.entries, core.node) {
-		er = perf_evsel__get_runtime(evsel);
+		er = evsel__get_runtime(evsel);
 		if (er == NULL) {
 			pr_err("Failed to allocate memory for evsel runtime data\n");
 			return -1;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 1f57a7ecdf3d..56d7bcd12671 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -273,7 +273,7 @@ static struct evsel_script *perf_evsel_script__new(struct evsel *evsel,
 	struct evsel_script *es = zalloc(sizeof(*es));
 
 	if (es != NULL) {
-		if (asprintf(&es->filename, "%s.%s.dump", data->file.path, perf_evsel__name(evsel)) < 0)
+		if (asprintf(&es->filename, "%s.%s.dump", data->file.path, evsel__name(evsel)) < 0)
 			goto out_free;
 		es->fp = fopen(es->filename, "w");
 		if (es->fp == NULL)
@@ -351,10 +351,8 @@ static const char *output_field2str(enum perf_output_field field)
 
 #define PRINT_FIELD(x)  (output[output_type(attr->type)].fields & PERF_OUTPUT_##x)
 
-static int perf_evsel__do_check_stype(struct evsel *evsel,
-				      u64 sample_type, const char *sample_msg,
-				      enum perf_output_field field,
-				      bool allow_user_set)
+static int evsel__do_check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg,
+				 enum perf_output_field field, bool allow_user_set)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 	int type = output_type(attr->type);
@@ -366,7 +364,7 @@ static int perf_evsel__do_check_stype(struct evsel *evsel,
 	if (output[type].user_set_fields & field) {
 		if (allow_user_set)
 			return 0;
-		evname = perf_evsel__name(evsel);
+		evname = evsel__name(evsel);
 		pr_err("Samples for '%s' event do not have %s attribute set. "
 		       "Cannot print '%s' field.\n",
 		       evname, sample_msg, output_field2str(field));
@@ -375,7 +373,7 @@ static int perf_evsel__do_check_stype(struct evsel *evsel,
 
 	/* user did not ask for it explicitly so remove from the default list */
 	output[type].fields &= ~field;
-	evname = perf_evsel__name(evsel);
+	evname = evsel__name(evsel);
 	pr_debug("Samples for '%s' event do not have %s attribute set. "
 		 "Skipping '%s' field.\n",
 		 evname, sample_msg, output_field2str(field));
@@ -383,16 +381,13 @@ static int perf_evsel__do_check_stype(struct evsel *evsel,
 	return 0;
 }
 
-static int perf_evsel__check_stype(struct evsel *evsel,
-				   u64 sample_type, const char *sample_msg,
-				   enum perf_output_field field)
+static int evsel__check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg,
+			      enum perf_output_field field)
 {
-	return perf_evsel__do_check_stype(evsel, sample_type, sample_msg, field,
-					  false);
+	return evsel__do_check_stype(evsel, sample_type, sample_msg, field, false);
 }
 
-static int perf_evsel__check_attr(struct evsel *evsel,
-				  struct perf_session *session)
+static int perf_evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 	bool allow_user_set;
@@ -404,32 +399,28 @@ static int perf_evsel__check_attr(struct evsel *evsel,
 					       HEADER_AUXTRACE);
 
 	if (PRINT_FIELD(TRACE) &&
-		!perf_session__has_traces(session, "record -R"))
+	    !perf_session__has_traces(session, "record -R"))
 		return -EINVAL;
 
 	if (PRINT_FIELD(IP)) {
-		if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
-					    PERF_OUTPUT_IP))
+		if (evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP", PERF_OUTPUT_IP))
 			return -EINVAL;
 	}
 
 	if (PRINT_FIELD(ADDR) &&
-		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
-					   PERF_OUTPUT_ADDR, allow_user_set))
+	    evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR", PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(DATA_SRC) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC",
-					PERF_OUTPUT_DATA_SRC))
+	    evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC))
 		return -EINVAL;
 
 	if (PRINT_FIELD(WEIGHT) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT",
-					PERF_OUTPUT_WEIGHT))
+	    evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", PERF_OUTPUT_WEIGHT))
 		return -EINVAL;
 
 	if (PRINT_FIELD(SYM) &&
-		!(evsel->core.attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
+	    !(evsel->core.attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
 		pr_err("Display of symbols requested but neither sample IP nor "
 			   "sample address\navailable. Hence, no addresses to convert "
 		       "to symbols.\n");
@@ -441,7 +432,7 @@ static int perf_evsel__check_attr(struct evsel *evsel,
 		return -EINVAL;
 	}
 	if (PRINT_FIELD(DSO) &&
-		!(evsel->core.attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
+	    !(evsel->core.attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
 		pr_err("Display of DSO requested but no address to convert.\n");
 		return -EINVAL;
 	}
@@ -458,33 +449,27 @@ static int perf_evsel__check_attr(struct evsel *evsel,
 		return -EINVAL;
 	}
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
-					PERF_OUTPUT_TID|PERF_OUTPUT_PID))
+	    evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID", PERF_OUTPUT_TID|PERF_OUTPUT_PID))
 		return -EINVAL;
 
 	if (PRINT_FIELD(TIME) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_TIME, "TIME",
-					PERF_OUTPUT_TIME))
+	    evsel__check_stype(evsel, PERF_SAMPLE_TIME, "TIME", PERF_OUTPUT_TIME))
 		return -EINVAL;
 
 	if (PRINT_FIELD(CPU) &&
-		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
-					   PERF_OUTPUT_CPU, allow_user_set))
+	    evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU", PERF_OUTPUT_CPU, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(IREGS) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS",
-					PERF_OUTPUT_IREGS))
+	    evsel__check_stype(evsel, PERF_SAMPLE_REGS_INTR, "IREGS", PERF_OUTPUT_IREGS))
 		return -EINVAL;
 
 	if (PRINT_FIELD(UREGS) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS",
-					PERF_OUTPUT_UREGS))
+	    evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS", PERF_OUTPUT_UREGS))
 		return -EINVAL;
 
 	if (PRINT_FIELD(PHYS_ADDR) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
-					PERF_OUTPUT_PHYS_ADDR))
+	    evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR))
 		return -EINVAL;
 
 	return 0;
@@ -604,8 +589,6 @@ static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask,
 		printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
 	}
 
-	fprintf(fp, "\n");
-
 	return printed;
 }
 
@@ -1697,6 +1680,7 @@ struct perf_script {
 	bool			show_cgroup_events;
 	bool			allocated;
 	bool			per_event_dump;
+	bool			stitch_lbr;
 	struct evswitch		evswitch;
 	struct perf_cpu_map	*cpus;
 	struct perf_thread_map *threads;
@@ -1713,7 +1697,7 @@ static int perf_evlist__max_name_len(struct evlist *evlist)
 	int max = 0;
 
 	evlist__for_each_entry(evlist, evsel) {
-		int len = strlen(perf_evsel__name(evsel));
+		int len = strlen(evsel__name(evsel));
 
 		max = MAX(len, max);
 	}
@@ -1887,7 +1871,7 @@ static void process_event(struct perf_script *script,
 		fprintf(fp, "%10" PRIu64 " ", sample->period);
 
 	if (PRINT_FIELD(EVNAME)) {
-		const char *evname = perf_evsel__name(evsel);
+		const char *evname = evsel__name(evsel);
 
 		if (!script->name_width)
 			script->name_width = perf_evlist__max_name_len(script->session->evlist);
@@ -1923,6 +1907,9 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(IP)) {
 		struct callchain_cursor *cursor = NULL;
 
+		if (script->stitch_lbr)
+			al->thread->lbr_stitch_enable = true;
+
 		if (symbol_conf.use_callchain && sample->callchain &&
 		    thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
 					      sample, NULL, NULL, scripting_max_stack) == 0)
@@ -1946,7 +1933,7 @@ static void process_event(struct perf_script *script,
 	else if (PRINT_FIELD(BRSTACKOFF))
 		perf_sample__fprintf_brstackoff(sample, thread, attr, fp);
 
-	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
+	if (evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		perf_sample__fprintf_bpf_output(sample, fp);
 	perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
 
@@ -1975,7 +1962,7 @@ static struct scripting_ops	*scripting_ops;
 static void __process_stat(struct evsel *counter, u64 tstamp)
 {
 	int nthreads = perf_thread_map__nr(counter->core.threads);
-	int ncpus = perf_evsel__nr_cpus(counter);
+	int ncpus = evsel__nr_cpus(counter);
 	int cpu, thread;
 	static int header_printed;
 
@@ -2001,7 +1988,7 @@ static void __process_stat(struct evsel *counter, u64 tstamp)
 				counts->ena,
 				counts->run,
 				tstamp,
-				perf_evsel__name(counter));
+				evsel__name(counter));
 		}
 	}
 }
@@ -2040,7 +2027,7 @@ static int cleanup_scripting(void)
 
 static bool filter_cpu(struct perf_sample *sample)
 {
-	if (cpu_list)
+	if (cpu_list && sample->cpu != (u32)-1)
 		return !test_bit(sample->cpu, cpu_bitmap);
 	return false;
 }
@@ -2138,41 +2125,59 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	return err;
 }
 
-static int process_comm_event(struct perf_tool *tool,
-			      union perf_event *event,
-			      struct perf_sample *sample,
-			      struct machine *machine)
+static int print_event_with_time(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_sample *sample,
+				 struct machine *machine,
+				 pid_t pid, pid_t tid, u64 timestamp)
 {
-	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
 	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-	int ret = -1;
+	struct thread *thread = NULL;
 
-	thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid);
-	if (thread == NULL) {
-		pr_debug("problem processing COMM event, skipping it.\n");
-		return -1;
+	if (evsel && !evsel->core.attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = timestamp;
+		sample->pid = pid;
+		sample->tid = tid;
 	}
 
-	if (perf_event__process_comm(tool, event, sample, machine) < 0)
-		goto out;
+	if (filter_cpu(sample))
+		return 0;
 
-	if (!evsel->core.attr.sample_id_all) {
-		sample->cpu = 0;
-		sample->time = 0;
-		sample->tid = event->comm.tid;
-		sample->pid = event->comm.pid;
-	}
-	if (!filter_cpu(sample)) {
+	if (tid != -1)
+		thread = machine__findnew_thread(machine, pid, tid);
+
+	if (thread && evsel) {
 		perf_sample__fprintf_start(sample, thread, evsel,
-				   PERF_RECORD_COMM, stdout);
-		perf_event__fprintf(event, stdout);
+					   event->header.type, stdout);
 	}
-	ret = 0;
-out:
+
+	perf_event__fprintf(event, stdout);
+
 	thread__put(thread);
-	return ret;
+
+	return 0;
+}
+
+static int print_event(struct perf_tool *tool, union perf_event *event,
+		       struct perf_sample *sample, struct machine *machine,
+		       pid_t pid, pid_t tid)
+{
+	return print_event_with_time(tool, event, sample, machine, pid, tid, 0);
+}
+
+static int process_comm_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	if (perf_event__process_comm(tool, event, sample, machine) < 0)
+		return -1;
+
+	return print_event(tool, event, sample, machine, event->comm.pid,
+			   event->comm.tid);
 }
 
 static int process_namespaces_event(struct perf_tool *tool,
@@ -2180,37 +2185,11 @@ static int process_namespaces_event(struct perf_tool *tool,
 				    struct perf_sample *sample,
 				    struct machine *machine)
 {
-	struct thread *thread;
-	struct perf_script *script = container_of(tool, struct perf_script, tool);
-	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-	int ret = -1;
-
-	thread = machine__findnew_thread(machine, event->namespaces.pid,
-					 event->namespaces.tid);
-	if (thread == NULL) {
-		pr_debug("problem processing NAMESPACES event, skipping it.\n");
-		return -1;
-	}
-
 	if (perf_event__process_namespaces(tool, event, sample, machine) < 0)
-		goto out;
+		return -1;
 
-	if (!evsel->core.attr.sample_id_all) {
-		sample->cpu = 0;
-		sample->time = 0;
-		sample->tid = event->namespaces.tid;
-		sample->pid = event->namespaces.pid;
-	}
-	if (!filter_cpu(sample)) {
-		perf_sample__fprintf_start(sample, thread, evsel,
-					   PERF_RECORD_NAMESPACES, stdout);
-		perf_event__fprintf(event, stdout);
-	}
-	ret = 0;
-out:
-	thread__put(thread);
-	return ret;
+	return print_event(tool, event, sample, machine, event->namespaces.pid,
+			   event->namespaces.tid);
 }
 
 static int process_cgroup_event(struct perf_tool *tool,
@@ -2218,34 +2197,11 @@ static int process_cgroup_event(struct perf_tool *tool,
 				struct perf_sample *sample,
 				struct machine *machine)
 {
-	struct thread *thread;
-	struct perf_script *script = container_of(tool, struct perf_script, tool);
-	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-	int ret = -1;
-
-	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
-	if (thread == NULL) {
-		pr_debug("problem processing CGROUP event, skipping it.\n");
-		return -1;
-	}
-
 	if (perf_event__process_cgroup(tool, event, sample, machine) < 0)
-		goto out;
+		return -1;
 
-	if (!evsel->core.attr.sample_id_all) {
-		sample->cpu = 0;
-		sample->time = 0;
-	}
-	if (!filter_cpu(sample)) {
-		perf_sample__fprintf_start(sample, thread, evsel,
-					   PERF_RECORD_CGROUP, stdout);
-		perf_event__fprintf(event, stdout);
-	}
-	ret = 0;
-out:
-	thread__put(thread);
-	return ret;
+	return print_event(tool, event, sample, machine, sample->pid,
+			    sample->tid);
 }
 
 static int process_fork_event(struct perf_tool *tool,
@@ -2253,69 +2209,24 @@ static int process_fork_event(struct perf_tool *tool,
 			      struct perf_sample *sample,
 			      struct machine *machine)
 {
-	struct thread *thread;
-	struct perf_script *script = container_of(tool, struct perf_script, tool);
-	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-
 	if (perf_event__process_fork(tool, event, sample, machine) < 0)
 		return -1;
 
-	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
-	if (thread == NULL) {
-		pr_debug("problem processing FORK event, skipping it.\n");
-		return -1;
-	}
-
-	if (!evsel->core.attr.sample_id_all) {
-		sample->cpu = 0;
-		sample->time = event->fork.time;
-		sample->tid = event->fork.tid;
-		sample->pid = event->fork.pid;
-	}
-	if (!filter_cpu(sample)) {
-		perf_sample__fprintf_start(sample, thread, evsel,
-					   PERF_RECORD_FORK, stdout);
-		perf_event__fprintf(event, stdout);
-	}
-	thread__put(thread);
-
-	return 0;
+	return print_event_with_time(tool, event, sample, machine,
+				     event->fork.pid, event->fork.tid,
+				     event->fork.time);
 }
 static int process_exit_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample,
 			      struct machine *machine)
 {
-	int err = 0;
-	struct thread *thread;
-	struct perf_script *script = container_of(tool, struct perf_script, tool);
-	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-
-	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
-	if (thread == NULL) {
-		pr_debug("problem processing EXIT event, skipping it.\n");
+	/* Print before 'exit' deletes anything */
+	if (print_event_with_time(tool, event, sample, machine, event->fork.pid,
+				  event->fork.tid, event->fork.time))
 		return -1;
-	}
-
-	if (!evsel->core.attr.sample_id_all) {
-		sample->cpu = 0;
-		sample->time = 0;
-		sample->tid = event->fork.tid;
-		sample->pid = event->fork.pid;
-	}
-	if (!filter_cpu(sample)) {
-		perf_sample__fprintf_start(sample, thread, evsel,
-					   PERF_RECORD_EXIT, stdout);
-		perf_event__fprintf(event, stdout);
-	}
-
-	if (perf_event__process_exit(tool, event, sample, machine) < 0)
-		err = -1;
 
-	thread__put(thread);
-	return err;
+	return perf_event__process_exit(tool, event, sample, machine);
 }
 
 static int process_mmap_event(struct perf_tool *tool,
@@ -2323,33 +2234,11 @@ static int process_mmap_event(struct perf_tool *tool,
 			      struct perf_sample *sample,
 			      struct machine *machine)
 {
-	struct thread *thread;
-	struct perf_script *script = container_of(tool, struct perf_script, tool);
-	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-
 	if (perf_event__process_mmap(tool, event, sample, machine) < 0)
 		return -1;
 
-	thread = machine__findnew_thread(machine, event->mmap.pid, event->mmap.tid);
-	if (thread == NULL) {
-		pr_debug("problem processing MMAP event, skipping it.\n");
-		return -1;
-	}
-
-	if (!evsel->core.attr.sample_id_all) {
-		sample->cpu = 0;
-		sample->time = 0;
-		sample->tid = event->mmap.tid;
-		sample->pid = event->mmap.pid;
-	}
-	if (!filter_cpu(sample)) {
-		perf_sample__fprintf_start(sample, thread, evsel,
-					   PERF_RECORD_MMAP, stdout);
-		perf_event__fprintf(event, stdout);
-	}
-	thread__put(thread);
-	return 0;
+	return print_event(tool, event, sample, machine, event->mmap.pid,
+			   event->mmap.tid);
 }
 
 static int process_mmap2_event(struct perf_tool *tool,
@@ -2357,33 +2246,11 @@ static int process_mmap2_event(struct perf_tool *tool,
 			      struct perf_sample *sample,
 			      struct machine *machine)
 {
-	struct thread *thread;
-	struct perf_script *script = container_of(tool, struct perf_script, tool);
-	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-
 	if (perf_event__process_mmap2(tool, event, sample, machine) < 0)
 		return -1;
 
-	thread = machine__findnew_thread(machine, event->mmap2.pid, event->mmap2.tid);
-	if (thread == NULL) {
-		pr_debug("problem processing MMAP2 event, skipping it.\n");
-		return -1;
-	}
-
-	if (!evsel->core.attr.sample_id_all) {
-		sample->cpu = 0;
-		sample->time = 0;
-		sample->tid = event->mmap2.tid;
-		sample->pid = event->mmap2.pid;
-	}
-	if (!filter_cpu(sample)) {
-		perf_sample__fprintf_start(sample, thread, evsel,
-					   PERF_RECORD_MMAP2, stdout);
-		perf_event__fprintf(event, stdout);
-	}
-	thread__put(thread);
-	return 0;
+	return print_event(tool, event, sample, machine, event->mmap2.pid,
+			   event->mmap2.tid);
 }
 
 static int process_switch_event(struct perf_tool *tool,
@@ -2391,10 +2258,7 @@ static int process_switch_event(struct perf_tool *tool,
 				struct perf_sample *sample,
 				struct machine *machine)
 {
-	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
-	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
 
 	if (perf_event__process_switch(tool, event, sample, machine) < 0)
 		return -1;
@@ -2405,20 +2269,8 @@ static int process_switch_event(struct perf_tool *tool,
 	if (!script->show_switch_events)
 		return 0;
 
-	thread = machine__findnew_thread(machine, sample->pid,
-					 sample->tid);
-	if (thread == NULL) {
-		pr_debug("problem processing SWITCH event, skipping it.\n");
-		return -1;
-	}
-
-	if (!filter_cpu(sample)) {
-		perf_sample__fprintf_start(sample, thread, evsel,
-					   PERF_RECORD_SWITCH, stdout);
-		perf_event__fprintf(event, stdout);
-	}
-	thread__put(thread);
-	return 0;
+	return print_event(tool, event, sample, machine, sample->pid,
+			   sample->tid);
 }
 
 static int
@@ -2427,23 +2279,8 @@ process_lost_event(struct perf_tool *tool,
 		   struct perf_sample *sample,
 		   struct machine *machine)
 {
-	struct perf_script *script = container_of(tool, struct perf_script, tool);
-	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-	struct thread *thread;
-
-	thread = machine__findnew_thread(machine, sample->pid,
-					 sample->tid);
-	if (thread == NULL)
-		return -1;
-
-	if (!filter_cpu(sample)) {
-		perf_sample__fprintf_start(sample, thread, evsel,
-					   PERF_RECORD_LOST, stdout);
-		perf_event__fprintf(event, stdout);
-	}
-	thread__put(thread);
-	return 0;
+	return print_event(tool, event, sample, machine, sample->pid,
+			   sample->tid);
 }
 
 static int
@@ -2462,33 +2299,11 @@ process_bpf_events(struct perf_tool *tool __maybe_unused,
 		   struct perf_sample *sample,
 		   struct machine *machine)
 {
-	struct thread *thread;
-	struct perf_script *script = container_of(tool, struct perf_script, tool);
-	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
-
 	if (machine__process_ksymbol(machine, event, sample) < 0)
 		return -1;
 
-	if (!evsel->core.attr.sample_id_all) {
-		perf_event__fprintf(event, stdout);
-		return 0;
-	}
-
-	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
-	if (thread == NULL) {
-		pr_debug("problem processing MMAP event, skipping it.\n");
-		return -1;
-	}
-
-	if (!filter_cpu(sample)) {
-		perf_sample__fprintf_start(sample, thread, evsel,
-					   event->header.type, stdout);
-		perf_event__fprintf(event, stdout);
-	}
-
-	thread__put(thread);
-	return 0;
+	return print_event(tool, event, sample, machine, sample->pid,
+			   sample->tid);
 }
 
 static void sig_handler(int sig __maybe_unused)
@@ -3145,7 +2960,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
 
 			match = 0;
 			evlist__for_each_entry(session->evlist, pos) {
-				if (!strcmp(perf_evsel__name(pos), evname)) {
+				if (!strcmp(evsel__name(pos), evname)) {
 					match = 1;
 					break;
 				}
@@ -3342,6 +3157,12 @@ static void script__setup_sample_type(struct perf_script *script)
 		else
 			callchain_param.record_mode = CALLCHAIN_FP;
 	}
+
+	if (script->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
+		pr_warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
+			   "Please apply --call-graph lbr when recording.\n");
+		script->stitch_lbr = false;
+	}
 }
 
 static int process_stat_round_event(struct perf_session *session,
@@ -3653,6 +3474,8 @@ int cmd_script(int argc, const char **argv)
 		   "file", "file saving guest os /proc/kallsyms"),
 	OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
 		   "file", "file saving guest os /proc/modules"),
+	OPT_BOOLEAN('\0', "stitch-lbr", &script.stitch_lbr,
+		    "Enable LBR callgraph stitching approach"),
 	OPTS_EVSWITCH(&script.evswitch),
 	OPT_END()
 	};
@@ -3709,7 +3532,7 @@ int cmd_script(int argc, const char **argv)
 		return -1;
 	}
 
-	if (itrace_synth_opts.callchain &&
+	if ((itrace_synth_opts.callchain || itrace_synth_opts.add_callchain) &&
 	    itrace_synth_opts.callchain_sz > scripting_max_stack)
 		scripting_max_stack = itrace_synth_opts.callchain_sz;
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ec053dc1e35c..e0c1ad23c768 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -238,9 +238,8 @@ static int write_stat_round_event(u64 tm, u64 type)
 
 #define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y)
 
-static int
-perf_evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread,
-			     struct perf_counts_values *count)
+static int evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread,
+				   struct perf_counts_values *count)
 {
 	struct perf_sample_id *sid = SID(counter, cpu, thread);
 
@@ -259,7 +258,7 @@ static int read_single_counter(struct evsel *counter, int cpu,
 		count->val = val;
 		return 0;
 	}
-	return perf_evsel__read_counter(counter, cpu, thread);
+	return evsel__read_counter(counter, cpu, thread);
 }
 
 /*
@@ -284,7 +283,7 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
 
 		/*
 		 * The leader's group read loads data into its group members
-		 * (via perf_evsel__read_counter()) and sets their count->loaded.
+		 * (via evsel__read_counter()) and sets their count->loaded.
 		 */
 		if (!perf_counts__is_loaded(counter->counts, cpu, thread) &&
 		    read_single_counter(counter, cpu, thread, rs)) {
@@ -297,7 +296,7 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
 		perf_counts__set_loaded(counter->counts, cpu, thread, false);
 
 		if (STAT_RECORD) {
-			if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
+			if (evsel__write_stat_event(counter, cpu, thread, count)) {
 				pr_err("failed to write stat event\n");
 				return -1;
 			}
@@ -306,7 +305,7 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
 		if (verbose > 1) {
 			fprintf(stat_config.output,
 				"%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
-					perf_evsel__name(counter),
+					evsel__name(counter),
 					cpu,
 					count->val, count->ena, count->run);
 		}
@@ -359,6 +358,7 @@ static void process_interval(void)
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
 
+	perf_stat__reset_shadow_per_stat(&rt_stat);
 	read_counters(&rs);
 
 	if (STAT_RECORD) {
@@ -409,7 +409,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
-static bool perf_evsel__should_store_id(struct evsel *counter)
+static bool evsel__should_store_id(struct evsel *counter)
 {
 	return STAT_RECORD || counter->core.attr.read_format & PERF_FORMAT_ID;
 }
@@ -454,7 +454,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 	    errno == ENXIO) {
 		if (verbose > 0)
 			ui__warning("%s event is not supported by the kernel.\n",
-				    perf_evsel__name(counter));
+				    evsel__name(counter));
 		counter->supported = false;
 		/*
 		 * errored is a sticky flag that means one of the counter's
@@ -465,7 +465,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 		if ((counter->leader != counter) ||
 		    !(counter->leader->core.nr_members > 1))
 			return COUNTER_SKIP;
-	} else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
+	} else if (evsel__fallback(counter, errno, msg, sizeof(msg))) {
 		if (verbose > 0)
 			ui__warning("%s\n", msg);
 		return COUNTER_RETRY;
@@ -483,8 +483,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 		}
 	}
 
-	perf_evsel__open_strerror(counter, &target,
-				  errno, msg, sizeof(msg));
+	evsel__open_strerror(counter, &target, errno, msg, sizeof(msg));
 	ui__error("%s\n", msg);
 
 	if (child_pid != -1)
@@ -604,7 +603,7 @@ try_again:
 				if (!counter->reset_group)
 					continue;
 try_again_reset:
-				pr_debug2("reopening weak %s\n", perf_evsel__name(counter));
+				pr_debug2("reopening weak %s\n", evsel__name(counter));
 				if (create_perf_stat_counter(counter, &stat_config, &target,
 							     counter->cpu_iter - 1) < 0) {
 
@@ -635,14 +634,14 @@ try_again_reset:
 		if (l > stat_config.unit_width)
 			stat_config.unit_width = l;
 
-		if (perf_evsel__should_store_id(counter) &&
-		    perf_evsel__store_ids(counter, evsel_list))
+		if (evsel__should_store_id(counter) &&
+		    evsel__store_ids(counter, evsel_list))
 			return -1;
 	}
 
 	if (perf_evlist__apply_filters(evsel_list, &counter)) {
 		pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n",
-			counter->filter, perf_evsel__name(counter), errno,
+			counter->filter, evsel__name(counter), errno,
 			str_error_r(errno, msg, sizeof(msg)));
 		return -1;
 	}
@@ -686,8 +685,11 @@ try_again_reset:
 					break;
 			}
 		}
-		if (child_pid != -1)
+		if (child_pid != -1) {
+			if (timeout)
+				kill(child_pid, SIGTERM);
 			wait4(child_pid, &status, 0, &stat_config.ru_data);
+		}
 
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 9e84fae9b096..c76f84b174c4 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -579,8 +579,8 @@ process_sample_cpu_idle(struct timechart *tchart __maybe_unused,
 			struct perf_sample *sample,
 			const char *backtrace __maybe_unused)
 {
-	u32 state = perf_evsel__intval(evsel, sample, "state");
-	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u32 state  = evsel__intval(evsel, sample, "state");
+	u32 cpu_id = evsel__intval(evsel, sample, "cpu_id");
 
 	if (state == (u32)PWR_EVENT_EXIT)
 		c_state_end(tchart, cpu_id, sample->time);
@@ -595,8 +595,8 @@ process_sample_cpu_frequency(struct timechart *tchart,
 			     struct perf_sample *sample,
 			     const char *backtrace __maybe_unused)
 {
-	u32 state = perf_evsel__intval(evsel, sample, "state");
-	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u32 state  = evsel__intval(evsel, sample, "state");
+	u32 cpu_id = evsel__intval(evsel, sample, "cpu_id");
 
 	p_state_change(tchart, cpu_id, sample->time, state);
 	return 0;
@@ -608,9 +608,9 @@ process_sample_sched_wakeup(struct timechart *tchart,
 			    struct perf_sample *sample,
 			    const char *backtrace)
 {
-	u8 flags = perf_evsel__intval(evsel, sample, "common_flags");
-	int waker = perf_evsel__intval(evsel, sample, "common_pid");
-	int wakee = perf_evsel__intval(evsel, sample, "pid");
+	u8 flags  = evsel__intval(evsel, sample, "common_flags");
+	int waker = evsel__intval(evsel, sample, "common_pid");
+	int wakee = evsel__intval(evsel, sample, "pid");
 
 	sched_wakeup(tchart, sample->cpu, sample->time, waker, wakee, flags, backtrace);
 	return 0;
@@ -622,9 +622,9 @@ process_sample_sched_switch(struct timechart *tchart,
 			    struct perf_sample *sample,
 			    const char *backtrace)
 {
-	int prev_pid = perf_evsel__intval(evsel, sample, "prev_pid");
-	int next_pid = perf_evsel__intval(evsel, sample, "next_pid");
-	u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
+	int prev_pid   = evsel__intval(evsel, sample, "prev_pid");
+	int next_pid   = evsel__intval(evsel, sample, "next_pid");
+	u64 prev_state = evsel__intval(evsel, sample, "prev_state");
 
 	sched_switch(tchart, sample->cpu, sample->time, prev_pid, next_pid,
 		     prev_state, backtrace);
@@ -638,8 +638,8 @@ process_sample_power_start(struct timechart *tchart __maybe_unused,
 			   struct perf_sample *sample,
 			   const char *backtrace __maybe_unused)
 {
-	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
-	u64 value = perf_evsel__intval(evsel, sample, "value");
+	u64 cpu_id = evsel__intval(evsel, sample, "cpu_id");
+	u64 value  = evsel__intval(evsel, sample, "value");
 
 	c_state_start(cpu_id, sample->time, value);
 	return 0;
@@ -661,8 +661,8 @@ process_sample_power_frequency(struct timechart *tchart,
 			       struct perf_sample *sample,
 			       const char *backtrace __maybe_unused)
 {
-	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
-	u64 value = perf_evsel__intval(evsel, sample, "value");
+	u64 cpu_id = evsel__intval(evsel, sample, "cpu_id");
+	u64 value  = evsel__intval(evsel, sample, "value");
 
 	p_state_change(tchart, cpu_id, sample->time, value);
 	return 0;
@@ -843,7 +843,7 @@ process_enter_read(struct timechart *tchart,
 		   struct evsel *evsel,
 		   struct perf_sample *sample)
 {
-	long fd = perf_evsel__intval(evsel, sample, "fd");
+	long fd = evsel__intval(evsel, sample, "fd");
 	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_READ,
 				   sample->time, fd);
 }
@@ -853,7 +853,7 @@ process_exit_read(struct timechart *tchart,
 		  struct evsel *evsel,
 		  struct perf_sample *sample)
 {
-	long ret = perf_evsel__intval(evsel, sample, "ret");
+	long ret = evsel__intval(evsel, sample, "ret");
 	return pid_end_io_sample(tchart, sample->tid, IOTYPE_READ,
 				 sample->time, ret);
 }
@@ -863,7 +863,7 @@ process_enter_write(struct timechart *tchart,
 		    struct evsel *evsel,
 		    struct perf_sample *sample)
 {
-	long fd = perf_evsel__intval(evsel, sample, "fd");
+	long fd = evsel__intval(evsel, sample, "fd");
 	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_WRITE,
 				   sample->time, fd);
 }
@@ -873,7 +873,7 @@ process_exit_write(struct timechart *tchart,
 		   struct evsel *evsel,
 		   struct perf_sample *sample)
 {
-	long ret = perf_evsel__intval(evsel, sample, "ret");
+	long ret = evsel__intval(evsel, sample, "ret");
 	return pid_end_io_sample(tchart, sample->tid, IOTYPE_WRITE,
 				 sample->time, ret);
 }
@@ -883,7 +883,7 @@ process_enter_sync(struct timechart *tchart,
 		   struct evsel *evsel,
 		   struct perf_sample *sample)
 {
-	long fd = perf_evsel__intval(evsel, sample, "fd");
+	long fd = evsel__intval(evsel, sample, "fd");
 	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_SYNC,
 				   sample->time, fd);
 }
@@ -893,7 +893,7 @@ process_exit_sync(struct timechart *tchart,
 		  struct evsel *evsel,
 		  struct perf_sample *sample)
 {
-	long ret = perf_evsel__intval(evsel, sample, "ret");
+	long ret = evsel__intval(evsel, sample, "ret");
 	return pid_end_io_sample(tchart, sample->tid, IOTYPE_SYNC,
 				 sample->time, ret);
 }
@@ -903,7 +903,7 @@ process_enter_tx(struct timechart *tchart,
 		 struct evsel *evsel,
 		 struct perf_sample *sample)
 {
-	long fd = perf_evsel__intval(evsel, sample, "fd");
+	long fd = evsel__intval(evsel, sample, "fd");
 	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_TX,
 				   sample->time, fd);
 }
@@ -913,7 +913,7 @@ process_exit_tx(struct timechart *tchart,
 		struct evsel *evsel,
 		struct perf_sample *sample)
 {
-	long ret = perf_evsel__intval(evsel, sample, "ret");
+	long ret = evsel__intval(evsel, sample, "ret");
 	return pid_end_io_sample(tchart, sample->tid, IOTYPE_TX,
 				 sample->time, ret);
 }
@@ -923,7 +923,7 @@ process_enter_rx(struct timechart *tchart,
 		 struct evsel *evsel,
 		 struct perf_sample *sample)
 {
-	long fd = perf_evsel__intval(evsel, sample, "fd");
+	long fd = evsel__intval(evsel, sample, "fd");
 	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_RX,
 				   sample->time, fd);
 }
@@ -933,7 +933,7 @@ process_exit_rx(struct timechart *tchart,
 		struct evsel *evsel,
 		struct perf_sample *sample)
 {
-	long ret = perf_evsel__intval(evsel, sample, "ret");
+	long ret = evsel__intval(evsel, sample, "ret");
 	return pid_end_io_sample(tchart, sample->tid, IOTYPE_RX,
 				 sample->time, ret);
 }
@@ -943,7 +943,7 @@ process_enter_poll(struct timechart *tchart,
 		   struct evsel *evsel,
 		   struct perf_sample *sample)
 {
-	long fd = perf_evsel__intval(evsel, sample, "fd");
+	long fd = evsel__intval(evsel, sample, "fd");
 	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_POLL,
 				   sample->time, fd);
 }
@@ -953,7 +953,7 @@ process_exit_poll(struct timechart *tchart,
 		  struct evsel *evsel,
 		  struct perf_sample *sample)
 {
-	long ret = perf_evsel__intval(evsel, sample, "ret");
+	long ret = evsel__intval(evsel, sample, "ret");
 	return pid_end_io_sample(tchart, sample->tid, IOTYPE_POLL,
 				 sample->time, ret);
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 289cf83e658a..372c38254654 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -33,6 +33,7 @@
 #include "util/map.h"
 #include "util/mmap.h"
 #include "util/session.h"
+#include "util/thread.h"
 #include "util/symbol.h"
 #include "util/synthetic-events.h"
 #include "util/top.h"
@@ -254,7 +255,7 @@ static void perf_top__show_details(struct perf_top *top)
 	if (notes->src == NULL)
 		goto out_unlock;
 
-	printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name);
+	printf("Showing %s for %s\n", evsel__name(top->sym_evsel), symbol->name);
 	printf("  Events  Pcnt (>=%d%%)\n", top->annotation_opts.min_pcnt);
 
 	more = symbol__annotate_printf(&he->ms, top->sym_evsel, &top->annotation_opts);
@@ -297,8 +298,7 @@ static void perf_top__resort_hists(struct perf_top *t)
 		hists__collapse_resort(hists, NULL);
 
 		/* Non-group events are considered as leader */
-		if (symbol_conf.event_group &&
-		    !perf_evsel__is_group_leader(pos)) {
+		if (symbol_conf.event_group && !evsel__is_group_leader(pos)) {
 			struct hists *leader_hists = evsel__hists(pos->leader);
 
 			hists__match(leader_hists, hists);
@@ -441,7 +441,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top)
 	fprintf(stdout, "\t[e]     display entries (lines).           \t(%d)\n", top->print_entries);
 
 	if (top->evlist->core.nr_entries > 1)
-		fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", perf_evsel__name(top->sym_evsel));
+		fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", evsel__name(top->sym_evsel));
 
 	fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", top->count_filter);
 
@@ -528,13 +528,13 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 				fprintf(stderr, "\nAvailable events:");
 
 				evlist__for_each_entry(top->evlist, top->sym_evsel)
-					fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
+					fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, evsel__name(top->sym_evsel));
 
 				prompt_integer(&counter, "Enter details event counter");
 
 				if (counter >= top->evlist->core.nr_entries) {
 					top->sym_evsel = evlist__first(top->evlist);
-					fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel));
+					fprintf(stderr, "Sorry, no such event, using %s.\n", evsel__name(top->sym_evsel));
 					sleep(1);
 					break;
 				}
@@ -775,6 +775,9 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (machine__resolve(machine, &al, sample) < 0)
 		return;
 
+	if (top->stitch_lbr)
+		al.thread->lbr_stitch_enable = true;
+
 	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
@@ -1042,14 +1045,13 @@ try_again:
 			    perf_top_overwrite_fallback(top, counter))
 				goto try_again;
 
-			if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
+			if (evsel__fallback(counter, errno, msg, sizeof(msg))) {
 				if (verbose > 0)
 					ui__warning("%s\n", msg);
 				goto try_again;
 			}
 
-			perf_evsel__open_strerror(counter, &opts->target,
-						  errno, msg, sizeof(msg));
+			evsel__open_strerror(counter, &opts->target, errno, msg, sizeof(msg));
 			ui__error("%s\n", msg);
 			goto out_err;
 		}
@@ -1571,10 +1573,11 @@ int cmd_top(int argc, const char **argv)
 		    "Sort the output by the event at the index n in group. "
 		    "If n is invalid, sort by the first event. "
 		    "WARNING: should be used on grouped events."),
+	OPT_BOOLEAN(0, "stitch-lbr", &top.stitch_lbr,
+		    "Enable LBR callgraph stitching approach"),
 	OPTS_EVSWITCH(&top.evswitch),
 	OPT_END()
 	};
-	struct evlist *sb_evlist = NULL;
 	const char * const top_usage[] = {
 		"perf top [<options>]",
 		NULL
@@ -1640,6 +1643,11 @@ int cmd_top(int argc, const char **argv)
 		}
 	}
 
+	if (top.stitch_lbr && !(callchain_param.record_mode == CALLCHAIN_LBR)) {
+		pr_err("Error: --stitch-lbr must be used with --call-graph lbr\n");
+		goto out_delete_evlist;
+	}
+
 	if (opts->branch_stack && callchain_param.enabled)
 		symbol_conf.show_branchflag_count = true;
 
@@ -1732,10 +1740,21 @@ int cmd_top(int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
-	if (!top.record_opts.no_bpf_event)
-		bpf_event__add_sb_event(&sb_evlist, &perf_env);
+	if (!top.record_opts.no_bpf_event) {
+		top.sb_evlist = evlist__new();
+
+		if (top.sb_evlist == NULL) {
+			pr_err("Couldn't create side band evlist.\n.");
+			goto out_delete_evlist;
+		}
+
+		if (evlist__add_bpf_sb_event(top.sb_evlist, &perf_env)) {
+			pr_err("Couldn't ask for PERF_RECORD_BPF_EVENT side band events.\n.");
+			goto out_delete_evlist;
+		}
+	}
 
-	if (perf_evlist__start_sb_thread(sb_evlist, target)) {
+	if (perf_evlist__start_sb_thread(top.sb_evlist, target)) {
 		pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
 		opts->no_bpf_event = true;
 	}
@@ -1743,7 +1762,7 @@ int cmd_top(int argc, const char **argv)
 	status = __cmd_top(&top);
 
 	if (!opts->no_bpf_event)
-		perf_evlist__stop_sb_thread(sb_evlist);
+		perf_evlist__stop_sb_thread(top.sb_evlist);
 
 out_delete_evlist:
 	evlist__delete(top.evlist);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 01d542007c8b..a46efb907bd4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -366,11 +366,9 @@ out_delete:
 	return NULL;
 }
 
-static int perf_evsel__init_tp_uint_field(struct evsel *evsel,
-					  struct tp_field *field,
-					  const char *name)
+static int evsel__init_tp_uint_field(struct evsel *evsel, struct tp_field *field, const char *name)
 {
-	struct tep_format_field *format_field = perf_evsel__field(evsel, name);
+	struct tep_format_field *format_field = evsel__field(evsel, name);
 
 	if (format_field == NULL)
 		return -1;
@@ -380,13 +378,11 @@ static int perf_evsel__init_tp_uint_field(struct evsel *evsel,
 
 #define perf_evsel__init_sc_tp_uint_field(evsel, name) \
 	({ struct syscall_tp *sc = __evsel__syscall_tp(evsel);\
-	   perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); })
+	   evsel__init_tp_uint_field(evsel, &sc->name, #name); })
 
-static int perf_evsel__init_tp_ptr_field(struct evsel *evsel,
-					 struct tp_field *field,
-					 const char *name)
+static int evsel__init_tp_ptr_field(struct evsel *evsel, struct tp_field *field, const char *name)
 {
-	struct tep_format_field *format_field = perf_evsel__field(evsel, name);
+	struct tep_format_field *format_field = evsel__field(evsel, name);
 
 	if (format_field == NULL)
 		return -1;
@@ -396,7 +392,7 @@ static int perf_evsel__init_tp_ptr_field(struct evsel *evsel,
 
 #define perf_evsel__init_sc_tp_ptr_field(evsel, name) \
 	({ struct syscall_tp *sc = __evsel__syscall_tp(evsel);\
-	   perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); })
+	   evsel__init_tp_ptr_field(evsel, &sc->name, #name); })
 
 static void evsel__delete_priv(struct evsel *evsel)
 {
@@ -404,13 +400,13 @@ static void evsel__delete_priv(struct evsel *evsel)
 	evsel__delete(evsel);
 }
 
-static int perf_evsel__init_syscall_tp(struct evsel *evsel)
+static int evsel__init_syscall_tp(struct evsel *evsel)
 {
 	struct syscall_tp *sc = evsel__syscall_tp(evsel);
 
 	if (sc != NULL) {
-		if (perf_evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr") &&
-		    perf_evsel__init_tp_uint_field(evsel, &sc->id, "nr"))
+		if (evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr") &&
+		    evsel__init_tp_uint_field(evsel, &sc->id, "nr"))
 			return -ENOENT;
 		return 0;
 	}
@@ -418,14 +414,14 @@ static int perf_evsel__init_syscall_tp(struct evsel *evsel)
 	return -ENOMEM;
 }
 
-static int perf_evsel__init_augmented_syscall_tp(struct evsel *evsel, struct evsel *tp)
+static int evsel__init_augmented_syscall_tp(struct evsel *evsel, struct evsel *tp)
 {
 	struct syscall_tp *sc = evsel__syscall_tp(evsel);
 
 	if (sc != NULL) {
-		struct tep_format_field *syscall_id = perf_evsel__field(tp, "id");
+		struct tep_format_field *syscall_id = evsel__field(tp, "id");
 		if (syscall_id == NULL)
-			syscall_id = perf_evsel__field(tp, "__syscall_nr");
+			syscall_id = evsel__field(tp, "__syscall_nr");
 		if (syscall_id == NULL ||
 		    __tp_field__init_uint(&sc->id, syscall_id->size, syscall_id->offset, evsel->needs_swap))
 			return -EINVAL;
@@ -436,21 +432,21 @@ static int perf_evsel__init_augmented_syscall_tp(struct evsel *evsel, struct evs
 	return -ENOMEM;
 }
 
-static int perf_evsel__init_augmented_syscall_tp_args(struct evsel *evsel)
+static int evsel__init_augmented_syscall_tp_args(struct evsel *evsel)
 {
 	struct syscall_tp *sc = __evsel__syscall_tp(evsel);
 
 	return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
 }
 
-static int perf_evsel__init_augmented_syscall_tp_ret(struct evsel *evsel)
+static int evsel__init_augmented_syscall_tp_ret(struct evsel *evsel)
 {
 	struct syscall_tp *sc = __evsel__syscall_tp(evsel);
 
 	return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap);
 }
 
-static int perf_evsel__init_raw_syscall_tp(struct evsel *evsel, void *handler)
+static int evsel__init_raw_syscall_tp(struct evsel *evsel, void *handler)
 {
 	if (evsel__syscall_tp(evsel) != NULL) {
 		if (perf_evsel__init_sc_tp_uint_field(evsel, id))
@@ -474,7 +470,7 @@ static struct evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *
 	if (IS_ERR(evsel))
 		return NULL;
 
-	if (perf_evsel__init_raw_syscall_tp(evsel, handler))
+	if (evsel__init_raw_syscall_tp(evsel, handler))
 		goto out_delete;
 
 	return evsel;
@@ -1801,7 +1797,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	return syscall__set_arg_fmts(sc);
 }
 
-static int perf_evsel__init_tp_arg_scnprintf(struct evsel *evsel)
+static int evsel__init_tp_arg_scnprintf(struct evsel *evsel)
 {
 	struct syscall_arg_fmt *fmt = evsel__syscall_arg_fmt(evsel);
 
@@ -2074,7 +2070,7 @@ static struct syscall *trace__syscall_info(struct trace *trace,
 		if (verbose > 1) {
 			static u64 n;
 			fprintf(trace->output, "Invalid syscall %d id, skipping (%s, %" PRIu64 ") ...\n",
-				id, perf_evsel__name(evsel), ++n);
+				id, evsel__name(evsel), ++n);
 		}
 		return NULL;
 	}
@@ -2206,7 +2202,7 @@ static int trace__fprintf_sample(struct trace *trace, struct evsel *evsel,
 		double ts = (double)sample->time / NSEC_PER_MSEC;
 
 		printed += fprintf(trace->output, "%22s %10.3f %s %d/%d [%d]\n",
-				   perf_evsel__name(evsel), ts,
+				   evsel__name(evsel), ts,
 				   thread__comm_str(thread),
 				   sample->pid, sample->tid, sample->cpu);
 	}
@@ -2382,7 +2378,7 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam
 
 static const char *errno_to_name(struct evsel *evsel, int err)
 {
-	struct perf_env *env = perf_evsel__env(evsel);
+	struct perf_env *env = evsel__env(evsel);
 	const char *arch_name = perf_env__arch(env);
 
 	return arch_syscalls__strerrno(arch_name, err);
@@ -2513,7 +2509,7 @@ errno_print: {
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
-		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+		pr_err("Problem processing %s callchain, skipping...\n", evsel__name(evsel));
 out:
 	ttrace->entry_pending = false;
 	err = 0;
@@ -2531,7 +2527,7 @@ static int trace__vfs_getname(struct trace *trace, struct evsel *evsel,
 	size_t filename_len, entry_str_len, to_move;
 	ssize_t remaining_space;
 	char *pos;
-	const char *filename = perf_evsel__rawptr(evsel, sample, "pathname");
+	const char *filename = evsel__rawptr(evsel, sample, "pathname");
 
 	if (!thread)
 		goto out;
@@ -2587,7 +2583,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct evsel *evsel,
 				     union perf_event *event __maybe_unused,
 				     struct perf_sample *sample)
 {
-        u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
+        u64 runtime = evsel__intval(evsel, sample, "runtime");
 	double runtime_ms = (double)runtime / NSEC_PER_MSEC;
 	struct thread *thread = machine__findnew_thread(trace->host,
 							sample->pid,
@@ -2606,10 +2602,10 @@ out_put:
 out_dump:
 	fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
 	       evsel->name,
-	       perf_evsel__strval(evsel, sample, "comm"),
-	       (pid_t)perf_evsel__intval(evsel, sample, "pid"),
+	       evsel__strval(evsel, sample, "comm"),
+	       (pid_t)evsel__intval(evsel, sample, "pid"),
 	       runtime,
-	       perf_evsel__intval(evsel, sample, "vruntime"));
+	       evsel__intval(evsel, sample, "vruntime"));
 	goto out_put;
 }
 
@@ -2774,7 +2770,7 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel,
 
 	fprintf(trace->output, "%s(", evsel->name);
 
-	if (perf_evsel__is_bpf_output(evsel)) {
+	if (evsel__is_bpf_output(evsel)) {
 		bpf_output__fprintf(trace, sample);
 	} else if (evsel->tp_format) {
 		if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
@@ -2795,7 +2791,7 @@ newline:
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
-		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+		pr_err("Problem processing %s callchain, skipping...\n", evsel__name(evsel));
 
 	++trace->nr_events_printed;
 
@@ -2890,7 +2886,7 @@ static int trace__pgfault(struct trace *trace,
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
-		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+		pr_err("Problem processing %s callchain, skipping...\n", evsel__name(evsel));
 
 	++trace->nr_events_printed;
 out:
@@ -3032,10 +3028,10 @@ static bool evlist__add_vfs_getname(struct evlist *evlist)
 	}
 
 	evlist__for_each_entry_safe(evlist, evsel, tmp) {
-		if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname"))
+		if (!strstarts(evsel__name(evsel), "probe:vfs_getname"))
 			continue;
 
-		if (perf_evsel__field(evsel, "pathname")) {
+		if (evsel__field(evsel, "pathname")) {
 			evsel->handler = trace__vfs_getname;
 			found = true;
 			continue;
@@ -3093,7 +3089,7 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 	if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT &&
 	    sample->raw_data == NULL) {
 		fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
-		       perf_evsel__name(evsel), sample->tid,
+		       evsel__name(evsel), sample->tid,
 		       sample->cpu, sample->raw_size);
 	} else {
 		tracepoint_handler handler = evsel->handler;
@@ -3124,8 +3120,8 @@ static int trace__add_syscall_newtp(struct trace *trace)
 	if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret))
 		goto out_delete_sys_exit;
 
-	perf_evsel__config_callchain(sys_enter, &trace->opts, &callchain_param);
-	perf_evsel__config_callchain(sys_exit, &trace->opts, &callchain_param);
+	evsel__config_callchain(sys_enter, &trace->opts, &callchain_param);
+	evsel__config_callchain(sys_exit, &trace->opts, &callchain_param);
 
 	evlist__add(evlist, sys_enter);
 	evlist__add(evlist, sys_exit);
@@ -3164,10 +3160,9 @@ static int trace__set_ev_qualifier_tp_filter(struct trace *trace)
 	if (filter == NULL)
 		goto out_enomem;
 
-	if (!perf_evsel__append_tp_filter(trace->syscalls.events.sys_enter,
-					  filter)) {
+	if (!evsel__append_tp_filter(trace->syscalls.events.sys_enter, filter)) {
 		sys_exit = trace->syscalls.events.sys_exit;
-		err = perf_evsel__append_tp_filter(sys_exit, filter);
+		err = evsel__append_tp_filter(sys_exit, filter);
 	}
 
 	free(filter);
@@ -3695,7 +3690,7 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
 	return __trace__deliver_event(trace, event->event);
 }
 
-static struct syscall_arg_fmt *perf_evsel__syscall_arg_fmt(struct evsel *evsel, char *arg)
+static struct syscall_arg_fmt *evsel__find_syscall_arg_fmt_by_name(struct evsel *evsel, char *arg)
 {
 	struct tep_format_field *field;
 	struct syscall_arg_fmt *fmt = __evsel__syscall_arg_fmt(evsel);
@@ -3750,7 +3745,7 @@ static int trace__expand_filter(struct trace *trace __maybe_unused, struct evsel
 
 			scnprintf(arg, sizeof(arg), "%.*s", left_size, left);
 
-			fmt = perf_evsel__syscall_arg_fmt(evsel, arg);
+			fmt = evsel__find_syscall_arg_fmt_by_name(evsel, arg);
 			if (fmt == NULL) {
 				pr_err("\"%s\" not found in \"%s\", can't set filter \"%s\"\n",
 				       arg, evsel->name, evsel->filter);
@@ -3801,7 +3796,7 @@ static int trace__expand_filter(struct trace *trace __maybe_unused, struct evsel
 
 	if (new_filter != evsel->filter) {
 		pr_debug("New filter for %s: %s\n", evsel->name, new_filter);
-		perf_evsel__set_filter(evsel, new_filter);
+		evsel__set_filter(evsel, new_filter);
 		free(new_filter);
 	}
 
@@ -3849,7 +3844,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		pgfault_maj = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MAJ);
 		if (pgfault_maj == NULL)
 			goto out_error_mem;
-		perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
+		evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
 		evlist__add(evlist, pgfault_maj);
 	}
 
@@ -3857,7 +3852,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		pgfault_min = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MIN);
 		if (pgfault_min == NULL)
 			goto out_error_mem;
-		perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
+		evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
 		evlist__add(evlist, pgfault_min);
 	}
 
@@ -4108,7 +4103,7 @@ out_error:
 out_error_apply_filters:
 	fprintf(trace->output,
 		"Failed to set filter \"%s\" on event %s with %d (%s)\n",
-		evsel->filter, perf_evsel__name(evsel), errno,
+		evsel->filter, evsel__name(evsel), errno,
 		str_error_r(errno, errbuf, sizeof(errbuf)));
 	goto out_delete_evlist;
 }
@@ -4179,7 +4174,7 @@ static int trace__replay(struct trace *trace)
 							     "syscalls:sys_enter");
 
 	if (evsel &&
-	    (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 ||
+	    (evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 ||
 	    perf_evsel__init_sc_tp_ptr_field(evsel, args))) {
 		pr_err("Error during initialize raw_syscalls:sys_enter event\n");
 		goto out;
@@ -4191,7 +4186,7 @@ static int trace__replay(struct trace *trace)
 		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 							     "syscalls:sys_exit");
 	if (evsel &&
-	    (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 ||
+	    (evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 ||
 	    perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
 		pr_err("Error during initialize raw_syscalls:sys_exit event\n");
 		goto out;
@@ -4471,11 +4466,11 @@ static int evlist__set_syscall_tp_fields(struct evlist *evlist)
 			continue;
 
 		if (strcmp(evsel->tp_format->system, "syscalls")) {
-			perf_evsel__init_tp_arg_scnprintf(evsel);
+			evsel__init_tp_arg_scnprintf(evsel);
 			continue;
 		}
 
-		if (perf_evsel__init_syscall_tp(evsel))
+		if (evsel__init_syscall_tp(evsel))
 			return -1;
 
 		if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) {
@@ -4989,7 +4984,7 @@ int cmd_trace(int argc, const char **argv)
 	 */
 	if (trace.syscalls.events.augmented) {
 		evlist__for_each_entry(trace.evlist, evsel) {
-			bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
+			bool raw_syscalls_sys_exit = strcmp(evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
 
 			if (raw_syscalls_sys_exit) {
 				trace.raw_augmented_syscalls = true;
@@ -4997,10 +4992,10 @@ int cmd_trace(int argc, const char **argv)
 			}
 
 			if (trace.syscalls.events.augmented->priv == NULL &&
-			    strstr(perf_evsel__name(evsel), "syscalls:sys_enter")) {
+			    strstr(evsel__name(evsel), "syscalls:sys_enter")) {
 				struct evsel *augmented = trace.syscalls.events.augmented;
-				if (perf_evsel__init_augmented_syscall_tp(augmented, evsel) ||
-				    perf_evsel__init_augmented_syscall_tp_args(augmented))
+				if (evsel__init_augmented_syscall_tp(augmented, evsel) ||
+				    evsel__init_augmented_syscall_tp_args(augmented))
 					goto out;
 				/*
 				 * Augmented is __augmented_syscalls__ BPF_OUTPUT event
@@ -5014,16 +5009,16 @@ int cmd_trace(int argc, const char **argv)
 				 * as not to filter it, then we'll handle it just like we would
 				 * for the BPF_OUTPUT one:
 				 */
-				if (perf_evsel__init_augmented_syscall_tp(evsel, evsel) ||
-				    perf_evsel__init_augmented_syscall_tp_args(evsel))
+				if (evsel__init_augmented_syscall_tp(evsel, evsel) ||
+				    evsel__init_augmented_syscall_tp_args(evsel))
 					goto out;
 				evsel->handler = trace__sys_enter;
 			}
 
-			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+			if (strstarts(evsel__name(evsel), "syscalls:sys_exit_")) {
 				struct syscall_tp *sc;
 init_augmented_syscall_tp:
-				if (perf_evsel__init_augmented_syscall_tp(evsel, evsel))
+				if (evsel__init_augmented_syscall_tp(evsel, evsel))
 					goto out;
 				sc = __evsel__syscall_tp(evsel);
 				/*
@@ -5047,7 +5042,7 @@ init_augmented_syscall_tp:
 				 */
 				if (trace.raw_augmented_syscalls)
 					trace.raw_augmented_syscalls_args_size = (6 + 1) * sizeof(long) + sc->id.offset;
-				perf_evsel__init_augmented_syscall_tp_ret(evsel);
+				evsel__init_augmented_syscall_tp_ret(evsel);
 				evsel->handler = trace__sys_exit;
 			}
 		}
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index bfb21d049e6c..cf147db4e5ca 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -22,7 +22,9 @@ include/uapi/linux/usbdevice_fs.h
 include/uapi/linux/vhost.h
 include/uapi/sound/asound.h
 include/linux/bits.h
+include/vdso/bits.h
 include/linux/const.h
+include/vdso/const.h
 include/linux/hash.h
 include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
@@ -115,6 +117,7 @@ check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
 check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
+check include/linux/build_bug.h       '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"'
 check include/linux/ctype.h	      '-I "isdigit("'
 check lib/ctype.c		      '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
 check arch/x86/include/asm/inat.h     '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index 0453ba26cdbd..a42fab308ff6 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -258,7 +258,8 @@ gets schedule to. Per task counters can be created by any user, for
 their own tasks.
 
 A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts
-all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege.
+all events on CPU-x. Per CPU counters need CAP_PERFMON or CAP_SYS_ADMIN
+privilege.
 
 The 'flags' parameter is currently unused and must be zero.
 
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
new file mode 100644
index 000000000000..c121e526442a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
@@ -0,0 +1,19 @@
+[
+    {
+        "MetricExpr": "(hv_24x7@PM_MCS01_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_RD_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_RD_DISP_PORT23\\,chip\\=?@)",
+        "MetricName": "Memory_RD_BW_Chip",
+        "MetricGroup": "Memory_BW",
+        "ScaleUnit": "1.6e-2MB"
+    },
+    {
+	"MetricExpr": "(hv_24x7@PM_MCS01_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS01_128B_WR_DISP_PORT23\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT01\\,chip\\=?@ + hv_24x7@PM_MCS23_128B_WR_DISP_PORT23\\,chip\\=?@ )",
+        "MetricName": "Memory_WR_BW_Chip",
+        "MetricGroup": "Memory_BW",
+        "ScaleUnit": "1.6e-2MB"
+    },
+    {
+	"MetricExpr": "(hv_24x7@PM_PB_CYC\\,chip\\=?@ )",
+        "MetricName": "PowerBUS_Frequency",
+        "ScaleUnit": "2.5e-7GHz"
+    }
+]
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 53e76d5d5b37..c8f306b572f4 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -26,7 +26,7 @@ struct pmu_event {
  * Map a CPU to its table of PMU events. The CPU is identified by the
  * cpuid field, which is an arch-specific identifier for the CPU.
  * The identifier specified in tools/perf/pmu-events/arch/xxx/mapfile
- * must match the get_cpustr() in tools/perf/arch/xxx/util/header.c)
+ * must match the get_cpuid_str() in tools/perf/arch/xxx/util/header.c)
  *
  * The  cpuid can contain any character other than the comma.
  */
diff --git a/tools/perf/scripts/python/bin/flamegraph-record b/tools/perf/scripts/python/bin/flamegraph-record
new file mode 100755
index 000000000000..7df5a19c0163
--- /dev/null
+++ b/tools/perf/scripts/python/bin/flamegraph-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -g "$@"
diff --git a/tools/perf/scripts/python/bin/flamegraph-report b/tools/perf/scripts/python/bin/flamegraph-report
new file mode 100755
index 000000000000..53c5dc90c87e
--- /dev/null
+++ b/tools/perf/scripts/python/bin/flamegraph-report
@@ -0,0 +1,3 @@
+#!/bin/bash
+# description: create flame graphs
+perf script -s "$PERF_EXEC_PATH"/scripts/python/flamegraph.py -- "$@"
diff --git a/tools/perf/scripts/python/flamegraph.py b/tools/perf/scripts/python/flamegraph.py
new file mode 100755
index 000000000000..61f3be9add6b
--- /dev/null
+++ b/tools/perf/scripts/python/flamegraph.py
@@ -0,0 +1,124 @@
+# flamegraph.py - create flame graphs from perf samples
+# SPDX-License-Identifier: GPL-2.0
+#
+# Usage:
+#
+#     perf record -a -g -F 99 sleep 60
+#     perf script report flamegraph
+#
+# Combined:
+#
+#     perf script flamegraph -a -F 99 sleep 60
+#
+# Written by Andreas Gerstmayr <agerstmayr@redhat.com>
+# Flame Graphs invented by Brendan Gregg <bgregg@netflix.com>
+# Works in tandem with d3-flame-graph by Martin Spier <mspier@netflix.com>
+
+from __future__ import print_function
+import sys
+import os
+import argparse
+import json
+
+
+class Node:
+    def __init__(self, name, libtype=""):
+        self.name = name
+        self.libtype = libtype
+        self.value = 0
+        self.children = []
+
+    def toJSON(self):
+        return {
+            "n": self.name,
+            "l": self.libtype,
+            "v": self.value,
+            "c": self.children
+        }
+
+
+class FlameGraphCLI:
+    def __init__(self, args):
+        self.args = args
+        self.stack = Node("root")
+
+        if self.args.format == "html" and \
+                not os.path.isfile(self.args.template):
+            print("Flame Graph template {} does not exist. Please install "
+                  "the js-d3-flame-graph (RPM) or libjs-d3-flame-graph (deb) "
+                  "package, specify an existing flame graph template "
+                  "(--template PATH) or another output format "
+                  "(--format FORMAT).".format(self.args.template),
+                  file=sys.stderr)
+            sys.exit(1)
+
+    def find_or_create_node(self, node, name, dso):
+        libtype = "kernel" if dso == "[kernel.kallsyms]" else ""
+        if name is None:
+            name = "[unknown]"
+
+        for child in node.children:
+            if child.name == name and child.libtype == libtype:
+                return child
+
+        child = Node(name, libtype)
+        node.children.append(child)
+        return child
+
+    def process_event(self, event):
+        node = self.find_or_create_node(self.stack, event["comm"], None)
+        if "callchain" in event:
+            for entry in reversed(event['callchain']):
+                node = self.find_or_create_node(
+                    node, entry.get("sym", {}).get("name"), event.get("dso"))
+        else:
+            node = self.find_or_create_node(
+                node, entry.get("symbol"), event.get("dso"))
+        node.value += 1
+
+    def trace_end(self):
+        json_str = json.dumps(self.stack, default=lambda x: x.toJSON())
+
+        if self.args.format == "html":
+            try:
+                with open(self.args.template) as f:
+                    output_str = f.read().replace("/** @flamegraph_json **/",
+                                                  json_str)
+            except IOError as e:
+                print("Error reading template file: {}".format(e), file=sys.stderr)
+                sys.exit(1)
+            output_fn = self.args.output or "flamegraph.html"
+        else:
+            output_str = json_str
+            output_fn = self.args.output or "stacks.json"
+
+        if output_fn == "-":
+            sys.stdout.write(output_str)
+        else:
+            print("dumping data to {}".format(output_fn))
+            try:
+                with open(output_fn, "w") as out:
+                    out.write(output_str)
+            except IOError as e:
+                print("Error writing output file: {}".format(e), file=sys.stderr)
+                sys.exit(1)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Create flame graphs.")
+    parser.add_argument("-f", "--format",
+                        default="html", choices=["json", "html"],
+                        help="output file format")
+    parser.add_argument("-o", "--output",
+                        help="output file name")
+    parser.add_argument("--template",
+                        default="/usr/share/d3-flame-graph/d3-flamegraph-base.html",
+                        help="path to flamegraph HTML template")
+    parser.add_argument("-i", "--input",
+                        help=argparse.SUPPRESS)
+
+    args = parser.parse_args()
+    cli = FlameGraphCLI(args)
+
+    process_event = cli.process_event
+    trace_end = cli.trace_end
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index b3d1bf13ca07..c75557aeef0e 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -56,6 +56,7 @@ perf-y += mem2node.o
 perf-y += maps.o
 perf-y += time-utils-test.o
 perf-y += genelf.o
+perf-y += api-io.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/api-io.c b/tools/perf/tests/api-io.c
new file mode 100644
index 000000000000..2ada86ad6084
--- /dev/null
+++ b/tools/perf/tests/api-io.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "debug.h"
+#include "tests.h"
+#include <api/io.h>
+#include <linux/kernel.h>
+
+#define TEMPL "/tmp/perf-test-XXXXXX"
+
+#define EXPECT_EQUAL(val, expected)                             \
+do {								\
+	if (val != expected) {					\
+		pr_debug("%s:%d: %d != %d\n",			\
+			__FILE__, __LINE__, val, expected);	\
+		ret = -1;					\
+	}							\
+} while (0)
+
+#define EXPECT_EQUAL64(val, expected)                           \
+do {								\
+	if (val != expected) {					\
+		pr_debug("%s:%d: %lld != %lld\n",		\
+			__FILE__, __LINE__, val, expected);	\
+		ret = -1;					\
+	}							\
+} while (0)
+
+static int make_test_file(char path[PATH_MAX], const char *contents)
+{
+	ssize_t contents_len = strlen(contents);
+	int fd;
+
+	strcpy(path, TEMPL);
+	fd = mkstemp(path);
+	if (fd < 0) {
+		pr_debug("mkstemp failed");
+		return -1;
+	}
+	if (write(fd, contents, contents_len) < contents_len) {
+		pr_debug("short write");
+		close(fd);
+		unlink(path);
+		return -1;
+	}
+	close(fd);
+	return 0;
+}
+
+static int setup_test(char path[PATH_MAX], const char *contents,
+		      size_t buf_size, struct io *io)
+{
+	if (make_test_file(path, contents))
+		return -1;
+
+	io->fd = open(path, O_RDONLY);
+	if (io->fd < 0) {
+		pr_debug("Failed to open '%s'\n", path);
+		unlink(path);
+		return -1;
+	}
+	io->buf = malloc(buf_size);
+	if (io->buf == NULL) {
+		pr_debug("Failed to allocate memory");
+		close(io->fd);
+		unlink(path);
+		return -1;
+	}
+	io__init(io, io->fd, io->buf, buf_size);
+	return 0;
+}
+
+static void cleanup_test(char path[PATH_MAX], struct io *io)
+{
+	free(io->buf);
+	close(io->fd);
+	unlink(path);
+}
+
+static int do_test_get_char(const char *test_string, size_t buf_size)
+{
+	char path[PATH_MAX];
+	struct io io;
+	int ch, ret = 0;
+	size_t i;
+
+	if (setup_test(path, test_string, buf_size, &io))
+		return -1;
+
+	for (i = 0; i < strlen(test_string); i++) {
+		ch = io__get_char(&io);
+
+		EXPECT_EQUAL(ch, test_string[i]);
+		EXPECT_EQUAL(io.eof, false);
+	}
+	ch = io__get_char(&io);
+	EXPECT_EQUAL(ch, -1);
+	EXPECT_EQUAL(io.eof, true);
+
+	cleanup_test(path, &io);
+	return ret;
+}
+
+static int test_get_char(void)
+{
+	int i, ret = 0;
+	size_t j;
+
+	static const char *const test_strings[] = {
+		"12345678abcdef90",
+		"a\nb\nc\nd\n",
+		"\a\b\t\v\f\r",
+	};
+	for (i = 0; i <= 10; i++) {
+		for (j = 0; j < ARRAY_SIZE(test_strings); j++) {
+			if (do_test_get_char(test_strings[j], 1 << i))
+				ret = -1;
+		}
+	}
+	return ret;
+}
+
+static int do_test_get_hex(const char *test_string,
+			__u64 val1, int ch1,
+			__u64 val2, int ch2,
+			__u64 val3, int ch3,
+			bool end_eof)
+{
+	char path[PATH_MAX];
+	struct io io;
+	int ch, ret = 0;
+	__u64 hex;
+
+	if (setup_test(path, test_string, 4, &io))
+		return -1;
+
+	ch = io__get_hex(&io, &hex);
+	EXPECT_EQUAL64(hex, val1);
+	EXPECT_EQUAL(ch, ch1);
+
+	ch = io__get_hex(&io, &hex);
+	EXPECT_EQUAL64(hex, val2);
+	EXPECT_EQUAL(ch, ch2);
+
+	ch = io__get_hex(&io, &hex);
+	EXPECT_EQUAL64(hex, val3);
+	EXPECT_EQUAL(ch, ch3);
+
+	EXPECT_EQUAL(io.eof, end_eof);
+
+	cleanup_test(path, &io);
+	return ret;
+}
+
+static int test_get_hex(void)
+{
+	int ret = 0;
+
+	if (do_test_get_hex("12345678abcdef90",
+				0x12345678abcdef90, -1,
+				0, -1,
+				0, -1,
+				true))
+		ret = -1;
+
+	if (do_test_get_hex("1\n2\n3\n",
+				1, '\n',
+				2, '\n',
+				3, '\n',
+				false))
+		ret = -1;
+
+	if (do_test_get_hex("12345678ABCDEF90;a;b",
+				0x12345678abcdef90, ';',
+				0xa, ';',
+				0xb, -1,
+				true))
+		ret = -1;
+
+	if (do_test_get_hex("0x1x2x",
+				0, 'x',
+				1, 'x',
+				2, 'x',
+				false))
+		ret = -1;
+
+	if (do_test_get_hex("x1x",
+				0, -2,
+				1, 'x',
+				0, -1,
+				true))
+		ret = -1;
+
+	if (do_test_get_hex("10000000000000000000000000000abcdefgh99i",
+				0xabcdef, 'g',
+				0, -2,
+				0x99, 'i',
+				false))
+		ret = -1;
+
+	return ret;
+}
+
+static int do_test_get_dec(const char *test_string,
+			__u64 val1, int ch1,
+			__u64 val2, int ch2,
+			__u64 val3, int ch3,
+			bool end_eof)
+{
+	char path[PATH_MAX];
+	struct io io;
+	int ch, ret = 0;
+	__u64 dec;
+
+	if (setup_test(path, test_string, 4, &io))
+		return -1;
+
+	ch = io__get_dec(&io, &dec);
+	EXPECT_EQUAL64(dec, val1);
+	EXPECT_EQUAL(ch, ch1);
+
+	ch = io__get_dec(&io, &dec);
+	EXPECT_EQUAL64(dec, val2);
+	EXPECT_EQUAL(ch, ch2);
+
+	ch = io__get_dec(&io, &dec);
+	EXPECT_EQUAL64(dec, val3);
+	EXPECT_EQUAL(ch, ch3);
+
+	EXPECT_EQUAL(io.eof, end_eof);
+
+	cleanup_test(path, &io);
+	return ret;
+}
+
+static int test_get_dec(void)
+{
+	int ret = 0;
+
+	if (do_test_get_dec("12345678abcdef90",
+				12345678, 'a',
+				0, -2,
+				0, -2,
+				false))
+		ret = -1;
+
+	if (do_test_get_dec("1\n2\n3\n",
+				1, '\n',
+				2, '\n',
+				3, '\n',
+				false))
+		ret = -1;
+
+	if (do_test_get_dec("12345678;1;2",
+				12345678, ';',
+				1, ';',
+				2, -1,
+				true))
+		ret = -1;
+
+	if (do_test_get_dec("0x1x2x",
+				0, 'x',
+				1, 'x',
+				2, 'x',
+				false))
+		ret = -1;
+
+	if (do_test_get_dec("x1x",
+				0, -2,
+				1, 'x',
+				0, -1,
+				true))
+		ret = -1;
+
+	if (do_test_get_dec("10000000000000000000000000000000000000000000000000000000000123456789ab99c",
+				123456789, 'a',
+				0, -2,
+				99, 'c',
+				false))
+		ret = -1;
+
+	return ret;
+}
+
+int test__api_io(struct test *test __maybe_unused,
+		int subtest __maybe_unused)
+{
+	int ret = 0;
+
+	if (test_get_char())
+		ret = TEST_FAIL;
+	if (test_get_hex())
+		ret = TEST_FAIL;
+	if (test_get_dec())
+		ret = TEST_FAIL;
+	return ret;
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index b6322eb0f423..3471ec52ea11 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -310,6 +310,10 @@ static struct test generic_tests[] = {
 		.func = test__jit_write_elf,
 	},
 	{
+		.desc = "Test api io",
+		.func = test__api_io,
+	},
+	{
 		.desc = "maps__merge_in",
 		.func = test__maps__merge_in,
 	},
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 1e8a9f5c356d..db68894a6f40 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -72,7 +72,7 @@ static int attach__current_disabled(struct evlist *evlist)
 
 	evsel->core.attr.disabled = 1;
 
-	err = perf_evsel__open_per_thread(evsel, threads);
+	err = evsel__open_per_thread(evsel, threads);
 	if (err) {
 		pr_debug("Failed to open event cpu-clock:u\n");
 		return err;
@@ -96,7 +96,7 @@ static int attach__current_enabled(struct evlist *evlist)
 		return -1;
 	}
 
-	err = perf_evsel__open_per_thread(evsel, threads);
+	err = evsel__open_per_thread(evsel, threads);
 
 	perf_thread_map__put(threads);
 	return err == 0 ? TEST_OK : TEST_FAIL;
@@ -125,7 +125,7 @@ static int attach__cpu_disabled(struct evlist *evlist)
 
 	evsel->core.attr.disabled = 1;
 
-	err = perf_evsel__open_per_cpu(evsel, cpus, -1);
+	err = evsel__open_per_cpu(evsel, cpus, -1);
 	if (err) {
 		if (err == -EACCES)
 			return TEST_SKIP;
@@ -152,7 +152,7 @@ static int attach__cpu_enabled(struct evlist *evlist)
 		return -1;
 	}
 
-	err = perf_evsel__open_per_cpu(evsel, cpus, -1);
+	err = evsel__open_per_cpu(evsel, cpus, -1);
 	if (err == -EACCES)
 		return TEST_SKIP;
 
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index c727379cf20e..bdcf032f8516 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -109,7 +109,7 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu
 	TEST_ASSERT_VAL("failed to synthesize attr update scale",
 			!perf_event__synthesize_event_update_scale(NULL, evsel, process_event_scale));
 
-	tmp.name = perf_evsel__name(evsel);
+	tmp.name = evsel__name(evsel);
 
 	TEST_ASSERT_VAL("failed to synthesize attr update name",
 			!perf_event__synthesize_event_update_name(&tmp.tool, evsel, process_event_name));
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 956205bf9326..61ecd8e33a01 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -20,12 +20,11 @@ static int perf_evsel__roundtrip_cache_name_test(void)
 	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
 		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
 			/* skip invalid cache type */
-			if (!perf_evsel__is_cache_op_valid(type, op))
+			if (!evsel__is_cache_op_valid(type, op))
 				continue;
 
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
-				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
-									name, sizeof(name));
+				__evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name));
 				err = parse_events(evlist, name, NULL);
 				if (err)
 					ret = err;
@@ -39,23 +38,22 @@ static int perf_evsel__roundtrip_cache_name_test(void)
 	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
 		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
 			/* skip invalid cache type */
-			if (!perf_evsel__is_cache_op_valid(type, op))
+			if (!evsel__is_cache_op_valid(type, op))
 				continue;
 
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
-				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
-									name, sizeof(name));
+				__evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name));
 				if (evsel->idx != idx)
 					continue;
 
 				++idx;
 
-				if (strcmp(perf_evsel__name(evsel), name)) {
-					pr_debug("%s != %s\n", perf_evsel__name(evsel), name);
+				if (strcmp(evsel__name(evsel), name)) {
+					pr_debug("%s != %s\n", evsel__name(evsel), name);
 					ret = -1;
 				}
 
-				evsel = perf_evsel__next(evsel);
+				evsel = evsel__next(evsel);
 			}
 		}
 	}
@@ -84,9 +82,9 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
 
 	err = 0;
 	evlist__for_each_entry(evlist, evsel) {
-		if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) {
+		if (strcmp(evsel__name(evsel), names[evsel->idx])) {
 			--err;
-			pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]);
+			pr_debug("%s != %s\n", evsel__name(evsel), names[evsel->idx]);
 		}
 	}
 
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 261e6eaaee99..ce8aa32bc3ee 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -8,7 +8,7 @@
 static int perf_evsel__test_field(struct evsel *evsel, const char *name,
 				  int size, bool should_be_signed)
 {
-	struct tep_format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = evsel__field(evsel, name);
 	int is_signed;
 	int ret = 0;
 
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 28313e59d6f6..f9e8e5628836 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -6,11 +6,11 @@
 #include <string.h>
 #include <linux/zalloc.h>
 
-static int test(struct parse_ctx *ctx, const char *e, double val2)
+static int test(struct expr_parse_ctx *ctx, const char *e, double val2)
 {
 	double val;
 
-	if (expr__parse(&val, ctx, e))
+	if (expr__parse(&val, ctx, e, 1))
 		TEST_ASSERT_VAL("parse test failed", 0);
 	TEST_ASSERT_VAL("unexpected value", val == val2);
 	return 0;
@@ -22,7 +22,7 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 	const char **other;
 	double val;
 	int i, ret;
-	struct parse_ctx ctx;
+	struct expr_parse_ctx ctx;
 	int num_other;
 
 	expr__ctx_init(&ctx);
@@ -44,21 +44,29 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 		return ret;
 
 	p = "FOO/0";
-	ret = expr__parse(&val, &ctx, p);
+	ret = expr__parse(&val, &ctx, p, 1);
 	TEST_ASSERT_VAL("division by zero", ret == -1);
 
 	p = "BAR/";
-	ret = expr__parse(&val, &ctx, p);
+	ret = expr__parse(&val, &ctx, p, 1);
 	TEST_ASSERT_VAL("missing operand", ret == -1);
 
 	TEST_ASSERT_VAL("find other",
-			expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0);
+			expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other, 1) == 0);
 	TEST_ASSERT_VAL("find other", num_other == 3);
 	TEST_ASSERT_VAL("find other", !strcmp(other[0], "BAR"));
 	TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ"));
 	TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO"));
 	TEST_ASSERT_VAL("find other", other[3] == NULL);
 
+	TEST_ASSERT_VAL("find other",
+			expr__find_other("EVENT1\\,param\\=?@ + EVENT2\\,param\\=?@", NULL,
+				   &other, &num_other, 3) == 0);
+	TEST_ASSERT_VAL("find other", num_other == 2);
+	TEST_ASSERT_VAL("find other", !strcmp(other[0], "EVENT1,param=3/"));
+	TEST_ASSERT_VAL("find other", !strcmp(other[1], "EVENT2,param=3/"));
+	TEST_ASSERT_VAL("find other", other[2] == NULL);
+
 	for (i = 0; i < num_other; i++)
 		zfree(&other[i]);
 	free((void *)other);
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 6367c8f6ca22..7a542f1c1c78 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -280,7 +280,7 @@ static int test1(struct evsel *evsel, struct machine *machine)
 
 	symbol_conf.use_callchain = false;
 	symbol_conf.cumulate_callchain = false;
-	perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
+	evsel__reset_sample_bit(evsel, CALLCHAIN);
 
 	setup_sorting(NULL);
 	callchain_register_param(&callchain_param);
@@ -427,7 +427,7 @@ static int test2(struct evsel *evsel, struct machine *machine)
 
 	symbol_conf.use_callchain = true;
 	symbol_conf.cumulate_callchain = false;
-	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
+	evsel__set_sample_bit(evsel, CALLCHAIN);
 
 	setup_sorting(NULL);
 	callchain_register_param(&callchain_param);
@@ -485,7 +485,7 @@ static int test3(struct evsel *evsel, struct machine *machine)
 
 	symbol_conf.use_callchain = false;
 	symbol_conf.cumulate_callchain = true;
-	perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
+	evsel__reset_sample_bit(evsel, CALLCHAIN);
 
 	setup_sorting(NULL);
 	callchain_register_param(&callchain_param);
@@ -669,7 +669,7 @@ static int test4(struct evsel *evsel, struct machine *machine)
 
 	symbol_conf.use_callchain = true;
 	symbol_conf.cumulate_callchain = true;
-	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
+	evsel__set_sample_bit(evsel, CALLCHAIN);
 
 	setup_sorting(NULL);
 
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5f4c0dbb4715..d4b8eb6e337a 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -86,7 +86,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		}
 
 		evsels[i]->core.attr.wakeup_events = 1;
-		perf_evsel__set_sample_id(evsels[i], false);
+		evsel__set_sample_id(evsels[i], false);
 
 		evlist__add(evlist, evsels[i]);
 
@@ -150,7 +150,7 @@ out_init:
 		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
 			pr_debug("expected %d %s events, got %d\n",
 				 expected_nr_events[evsel->idx],
-				 perf_evsel__name(evsel), nr_events[evsel->idx]);
+				 evsel__name(evsel), nr_events[evsel->idx]);
 			err = -1;
 			goto out_delete_evlist;
 		}
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 93c176523e38..900934be22d2 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -103,15 +103,15 @@ int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int
 		if (cpus->map[cpu] >= CPU_SETSIZE)
 			continue;
 
-		if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
-			pr_debug("perf_evsel__read_on_cpu\n");
+		if (evsel__read_on_cpu(evsel, cpu, 0) < 0) {
+			pr_debug("evsel__read_on_cpu\n");
 			err = -1;
 			break;
 		}
 
 		expected = nr_openat_calls + cpu;
 		if (perf_counts(evsel->counts, cpu, 0)->val != expected) {
-			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
+			pr_debug("evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
 				 expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val);
 			err = -1;
 		}
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index c6b2d7aab608..1dc2897d2df9 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -60,7 +60,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 		goto out_delete_evlist;
 	}
 
-	perf_evsel__config(evsel, &opts, NULL);
+	evsel__config(evsel, &opts, NULL);
 
 	perf_thread_map__set_pid(evlist->core.threads, 0, getpid());
 
@@ -108,13 +108,13 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 					continue;
 				}
 
-				err = perf_evsel__parse_sample(evsel, event, &sample);
+				err = evsel__parse_sample(evsel, event, &sample);
 				if (err) {
 					pr_debug("Can't parse sample, err = %d\n", err);
 					goto out_delete_evlist;
 				}
 
-				tp_flags = perf_evsel__intval(evsel, &sample, "flags");
+				tp_flags = evsel__intval(evsel, &sample, "flags");
 
 				if (flags != tp_flags) {
 					pr_debug("%s: Expected flags=%#x, got %#x\n",
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 5ebffae18605..db5d8bb8cd06 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -34,7 +34,7 @@ int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __m
 		goto out_thread_map_delete;
 	}
 
-	if (perf_evsel__open_per_thread(evsel, threads) < 0) {
+	if (evsel__open_per_thread(evsel, threads) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 			 str_error_r(errno, sbuf, sizeof(sbuf)));
@@ -46,13 +46,13 @@ int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __m
 		close(fd);
 	}
 
-	if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
-		pr_debug("perf_evsel__read_on_cpu\n");
+	if (evsel__read_on_cpu(evsel, 0, 0) < 0) {
+		pr_debug("evsel__read_on_cpu\n");
 		goto out_close_fd;
 	}
 
 	if (perf_counts(evsel->counts, 0, 0)->val != nr_openat_calls) {
-		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
+		pr_debug("evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
 			 nr_openat_calls, perf_counts(evsel->counts, 0, 0)->val);
 		goto out_close_fd;
 	}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 091c3aeccc27..895188b63f96 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -371,7 +371,7 @@ static int test__checkevent_breakpoint_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong name",
-			!strcmp(perf_evsel__name(evsel), "mem:0:u"));
+			!strcmp(evsel__name(evsel), "mem:0:u"));
 
 	return test__checkevent_breakpoint(evlist);
 }
@@ -385,7 +385,7 @@ static int test__checkevent_breakpoint_x_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong name",
-			!strcmp(perf_evsel__name(evsel), "mem:0:x:k"));
+			!strcmp(evsel__name(evsel), "mem:0:x:k"));
 
 	return test__checkevent_breakpoint_x(evlist);
 }
@@ -399,7 +399,7 @@ static int test__checkevent_breakpoint_r_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong name",
-			!strcmp(perf_evsel__name(evsel), "mem:0:r:hp"));
+			!strcmp(evsel__name(evsel), "mem:0:r:hp"));
 
 	return test__checkevent_breakpoint_r(evlist);
 }
@@ -413,7 +413,7 @@ static int test__checkevent_breakpoint_w_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong name",
-			!strcmp(perf_evsel__name(evsel), "mem:0:w:up"));
+			!strcmp(evsel__name(evsel), "mem:0:w:up"));
 
 	return test__checkevent_breakpoint_w(evlist);
 }
@@ -427,7 +427,7 @@ static int test__checkevent_breakpoint_rw_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong name",
-			!strcmp(perf_evsel__name(evsel), "mem:0:rw:kp"));
+			!strcmp(evsel__name(evsel), "mem:0:rw:kp"));
 
 	return test__checkevent_breakpoint_rw(evlist);
 }
@@ -468,7 +468,7 @@ static int test__checkevent_list(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 
 	/* syscalls:sys_enter_openat:k */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
 		PERF_TP_SAMPLE_TYPE == evsel->core.attr.sample_type);
@@ -479,7 +479,7 @@ static int test__checkevent_list(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 
 	/* 1:1:hp */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", 1 == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config);
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
@@ -498,15 +498,15 @@ static int test__checkevent_pmu_name(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",  1 == evsel->core.attr.config);
-	TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava"));
+	TEST_ASSERT_VAL("wrong name", !strcmp(evsel__name(evsel), "krava"));
 
 	/* cpu/config=2/u" */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",  2 == evsel->core.attr.config);
 	TEST_ASSERT_VAL("wrong name",
-			!strcmp(perf_evsel__name(evsel), "cpu/config=2/u"));
+			!strcmp(evsel__name(evsel), "cpu/config=2/u"));
 
 	return 0;
 }
@@ -529,7 +529,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong time",  !(PERF_SAMPLE_TIME & evsel->core.attr.sample_type));
 
 	/* cpu/config=2,call-graph=no,time=0,period=2000/ */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",  2 == evsel->core.attr.config);
 	/*
@@ -577,7 +577,7 @@ static int test__checkevent_pmu_events_mix(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned);
 
 	/* cpu/pmu-event/u*/
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong exclude_user",
@@ -652,13 +652,13 @@ static int test__group1(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* cycles:upp */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config);
@@ -670,7 +670,7 @@ static int test__group1(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	return 0;
@@ -694,13 +694,13 @@ static int test__group2(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* cache-references + :u modifier */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CACHE_REFERENCES == evsel->core.attr.config);
@@ -711,11 +711,11 @@ static int test__group2(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* cycles:k */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config);
@@ -725,7 +725,7 @@ static int test__group2(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	return 0;
@@ -750,15 +750,15 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group1"));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* group1 cycles:kppp */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config);
@@ -771,11 +771,11 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 3);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* group2 cycles + G modifier */
-	evsel = leader = perf_evsel__next(evsel);
+	evsel = leader = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config);
@@ -785,15 +785,15 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group2"));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* group2 1:3 + G modifier */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", 1 == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config", 3 == evsel->core.attr.config);
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
@@ -803,11 +803,11 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* instructions:u */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config);
@@ -817,7 +817,7 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	return 0;
@@ -843,13 +843,13 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 1);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* instructions:kp + p */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config);
@@ -861,7 +861,7 @@ static int test__group4(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	return 0;
@@ -886,13 +886,13 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* instructions + G */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config);
@@ -903,11 +903,11 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* cycles:G */
-	evsel = leader = perf_evsel__next(evsel);
+	evsel = leader = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config);
@@ -918,13 +918,13 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 	TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
 	/* instructions:G */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config);
@@ -935,10 +935,10 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 
 	/* cycles */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config);
@@ -948,7 +948,7 @@ static int test__group5(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 
 	return 0;
 }
@@ -972,12 +972,12 @@ static int test__group_gh1(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 
 	/* cache-misses:G + :H group modifier */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config);
@@ -988,7 +988,7 @@ static int test__group_gh1(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 
 	return 0;
 }
@@ -1012,12 +1012,12 @@ static int test__group_gh2(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 
 	/* cache-misses:H + :G group modifier */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config);
@@ -1028,7 +1028,7 @@ static int test__group_gh2(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 
 	return 0;
 }
@@ -1052,12 +1052,12 @@ static int test__group_gh3(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 
 	/* cache-misses:H + :u group modifier */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config);
@@ -1068,7 +1068,7 @@ static int test__group_gh3(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 
 	return 0;
 }
@@ -1092,12 +1092,12 @@ static int test__group_gh4(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong core.nr_members", evsel->core.nr_members == 2);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 0);
 
 	/* cache-misses:H + :uG group modifier */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config);
@@ -1108,7 +1108,7 @@ static int test__group_gh4(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
-	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+	TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
 
 	return 0;
 }
@@ -1135,7 +1135,7 @@ static int test__leader_sample1(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
 
 	/* cache-misses - not sampling */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config);
@@ -1149,7 +1149,7 @@ static int test__leader_sample1(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
 
 	/* branch-misses - not sampling */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config);
@@ -1188,7 +1188,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
 
 	/* branch-misses - not sampling */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config);
@@ -1234,14 +1234,14 @@ static int test__pinned_group(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong pinned", evsel->core.attr.pinned);
 
 	/* cache-misses - can not be pinned, but will go on with the leader */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config);
 	TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned);
 
 	/* branch-misses - ditto */
-	evsel = perf_evsel__next(evsel);
+	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config);
 	TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned);
@@ -1356,6 +1356,16 @@ static int test__checkevent_complex_name(struct evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_raw_pmu(struct evlist *evlist)
+{
+	struct evsel *evsel = evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config);
+	return 0;
+}
+
 static int test__sym_event_slash(struct evlist *evlist)
 {
 	struct evsel *evsel = evlist__first(evlist);
@@ -1750,7 +1760,12 @@ static struct evlist_test test__events_pmu[] = {
 		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",
 		.check = test__checkevent_complex_name,
 		.id    = 3,
-	}
+	},
+	{
+		.name  = "software/r1a/",
+		.check = test__checkevent_raw_pmu,
+		.id    = 4,
+	},
 };
 
 struct terms_test {
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 2195fc205e72..83adfd846ccd 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -106,9 +106,9 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 	 * Config the evsels, setting attr->comm on the first one, etc.
 	 */
 	evsel = evlist__first(evlist);
-	perf_evsel__set_sample_bit(evsel, CPU);
-	perf_evsel__set_sample_bit(evsel, TID);
-	perf_evsel__set_sample_bit(evsel, TIME);
+	evsel__set_sample_bit(evsel, CPU);
+	evsel__set_sample_bit(evsel, TID);
+	evsel__set_sample_bit(evsel, TIME);
 	perf_evlist__config(evlist, &opts, NULL);
 
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 61865699c3f4..a0bdaf390ac8 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -296,12 +296,12 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		goto out_free;
 	}
 
-	evsel.sample_size = __perf_evsel__sample_size(sample_type);
+	evsel.sample_size = __evsel__sample_size(sample_type);
 
-	err = perf_evsel__parse_sample(&evsel, event, &sample_out);
+	err = evsel__parse_sample(&evsel, event, &sample_out);
 	if (err) {
 		pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
-			 "perf_evsel__parse_sample", sample_type, err);
+			 "evsel__parse_sample", sample_type, err);
 		goto out_free;
 	}
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index fcb0d03dba4e..db5e1f70053a 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -135,8 +135,8 @@ static int process_sample_event(struct evlist *evlist,
 
 	evsel = perf_evlist__id2evsel(evlist, sample.id);
 	if (evsel == switch_tracking->switch_evsel) {
-		next_tid = perf_evsel__intval(evsel, &sample, "next_pid");
-		prev_tid = perf_evsel__intval(evsel, &sample, "prev_pid");
+		next_tid = evsel__intval(evsel, &sample, "next_pid");
+		prev_tid = evsel__intval(evsel, &sample, "prev_pid");
 		cpu = sample.cpu;
 		pr_debug3("sched_switch: cpu: %d prev_tid %d next_tid %d\n",
 			  cpu, prev_tid, next_tid);
@@ -394,8 +394,8 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 
 	switch_evsel = evlist__last(evlist);
 
-	perf_evsel__set_sample_bit(switch_evsel, CPU);
-	perf_evsel__set_sample_bit(switch_evsel, TIME);
+	evsel__set_sample_bit(switch_evsel, CPU);
+	evsel__set_sample_bit(switch_evsel, TIME);
 
 	switch_evsel->core.system_wide = true;
 	switch_evsel->no_aux_samples = true;
@@ -412,8 +412,8 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 		goto out_err;
 	}
 
-	perf_evsel__set_sample_bit(cycles_evsel, CPU);
-	perf_evsel__set_sample_bit(cycles_evsel, TIME);
+	evsel__set_sample_bit(cycles_evsel, CPU);
+	evsel__set_sample_bit(cycles_evsel, TIME);
 
 	/* Fourth event */
 	err = parse_events(evlist, "dummy:u", NULL);
@@ -429,7 +429,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 	tracking_evsel->core.attr.freq = 0;
 	tracking_evsel->core.attr.sample_period = 1;
 
-	perf_evsel__set_sample_bit(tracking_evsel, TIME);
+	evsel__set_sample_bit(tracking_evsel, TIME);
 
 	/* Config events */
 	perf_evlist__config(evlist, &opts, NULL);
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 61a1ab032080..d6d4ac34eeb7 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -112,6 +112,7 @@ int test__mem2node(struct test *t, int subtest);
 int test__maps__merge_in(struct test *t, int subtest);
 int test__time_utils(struct test *t, int subtest);
 int test__jit_write_elf(struct test *test, int subtest);
+int test__api_io(struct test *test, int subtest);
 
 bool test__bp_signal_is_supported(void);
 bool test__bp_account_is_supported(void);
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 4a800499d7c3..22daf2bdf5fa 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -33,10 +33,8 @@ static int session_write_header(char *path)
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file      = {
-			.path = path,
-		},
-		.mode      = PERF_DATA_MODE_WRITE,
+		.path = path,
+		.mode = PERF_DATA_MODE_WRITE,
 	};
 
 	session = perf_session__new(&data, false, NULL);
@@ -63,10 +61,8 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file      = {
-			.path = path,
-		},
-		.mode      = PERF_DATA_MODE_READ,
+		.path = path,
+		.mode = PERF_DATA_MODE_READ,
 	};
 	int i;
 
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index 062ca849c8fd..f4db894e0af6 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -46,6 +46,7 @@ static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size,
 	P_FLAG(NEWNET);
 	P_FLAG(IO);
 	P_FLAG(CLEAR_SIGHAND);
+	P_FLAG(INTO_CGROUP);
 #undef P_FLAG
 
 	if (flags)
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 9fa771a90d79..862c8331dded 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -69,6 +69,7 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 
 	P_MREMAP_FLAG(MAYMOVE);
 	P_MREMAP_FLAG(FIXED);
+	P_MREMAP_FLAG(DONTUNMAP);
 #undef P_MREMAP_FLAG
 
 	if (flags)
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 487e54ef56a9..f98a118dfc49 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -3416,7 +3416,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 	struct hists *hists = evsel__hists(evsel);
 	bool current_entry = ui_browser__is_current_entry(browser, row);
 	unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE];
-	const char *ev_name = perf_evsel__name(evsel);
+	const char *ev_name = evsel__name(evsel);
 	char bf[256], unit;
 	const char *warn = " ";
 	size_t printed;
@@ -3424,10 +3424,10 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
 						       HE_COLORSET_NORMAL);
 
-	if (perf_evsel__is_group_event(evsel)) {
+	if (evsel__is_group_event(evsel)) {
 		struct evsel *pos;
 
-		ev_name = perf_evsel__group_name(evsel);
+		ev_name = evsel__group_name(evsel);
 
 		for_each_group_member(pos, evsel) {
 			struct hists *pos_hists = evsel__hists(pos);
@@ -3512,13 +3512,13 @@ browse_hists:
 				if (pos->core.node.next == &evlist->core.entries)
 					pos = evlist__first(evlist);
 				else
-					pos = perf_evsel__next(pos);
+					pos = evsel__next(pos);
 				goto browse_hists;
 			case K_UNTAB:
 				if (pos->core.node.prev == &evlist->core.entries)
 					pos = evlist__last(evlist);
 				else
-					pos = perf_evsel__prev(pos);
+					pos = evsel__prev(pos);
 				goto browse_hists;
 			case K_SWITCH_INPUT_DATA:
 			case K_RELOAD:
@@ -3554,7 +3554,7 @@ static bool filter_group_entries(struct ui_browser *browser __maybe_unused,
 {
 	struct evsel *evsel = list_entry(entry, struct evsel, core.node);
 
-	if (symbol_conf.event_group && !perf_evsel__is_group_leader(evsel))
+	if (symbol_conf.event_group && !evsel__is_group_leader(evsel))
 		return true;
 
 	return false;
@@ -3587,7 +3587,7 @@ static int __perf_evlist__tui_browse_hists(struct evlist *evlist,
 	ui_helpline__push("Press ESC to exit");
 
 	evlist__for_each_entry(evlist, pos) {
-		const char *ev_name = perf_evsel__name(pos);
+		const char *ev_name = evsel__name(pos);
 		size_t line_len = strlen(ev_name) + 7;
 
 		if (menu.b.width < line_len)
@@ -3622,7 +3622,7 @@ single_entry:
 
 		nr_entries = 0;
 		evlist__for_each_entry(evlist, pos) {
-			if (perf_evsel__is_group_leader(pos))
+			if (evsel__is_group_leader(pos))
 				nr_entries++;
 		}
 
@@ -3640,7 +3640,7 @@ static int block_hists_browser__title(struct hist_browser *browser, char *bf,
 				      size_t size)
 {
 	struct hists *hists = evsel__hists(browser->block_evsel);
-	const char *evname = perf_evsel__name(browser->block_evsel);
+	const char *evname = evsel__name(browser->block_evsel);
 	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 	int ret;
 
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 35f9641bf670..a7dff77f2018 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -130,7 +130,7 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct map_symbol *ms,
 
 		gtk_list_store_append(store, &iter);
 
-		if (perf_evsel__is_group_event(evsel)) {
+		if (evsel__is_group_event(evsel)) {
 			for (i = 0; i < evsel->core.nr_members; i++) {
 				ret += perf_gtk__get_percent(s + ret,
 							     sizeof(s) - ret,
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index ed1a97b2c4b0..53ef71a1b15d 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -635,18 +635,18 @@ int perf_evlist__gtk_browse_hists(struct evlist *evlist,
 
 	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
-		const char *evname = perf_evsel__name(pos);
+		const char *evname = evsel__name(pos);
 		GtkWidget *scrolled_window;
 		GtkWidget *tab_label;
 		char buf[512];
 		size_t size = sizeof(buf);
 
 		if (symbol_conf.event_group) {
-			if (!perf_evsel__is_group_leader(pos))
+			if (!evsel__is_group_leader(pos))
 				continue;
 
 			if (pos->core.nr_members > 1) {
-				perf_evsel__group_desc(pos, buf, size);
+				evsel__group_desc(pos, buf, size);
 				evname = buf;
 			}
 		}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 025f4c7f96bf..c1f24d004852 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -43,12 +43,12 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	} else
 		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he));
 
-	if (perf_evsel__is_group_event(evsel)) {
+	if (evsel__is_group_event(evsel)) {
 		int prev_idx, idx_delta;
 		struct hist_entry *pair;
 		int nr_members = evsel->core.nr_members;
 
-		prev_idx = perf_evsel__group_idx(evsel);
+		prev_idx = evsel__group_idx(evsel);
 
 		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
 			u64 period = get_field(pair);
@@ -58,7 +58,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 				continue;
 
 			evsel = hists_to_evsel(pair->hists);
-			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
+			idx_delta = evsel__group_idx(evsel) - prev_idx - 1;
 
 			while (idx_delta--) {
 				/*
@@ -82,7 +82,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 							  len, period);
 			}
 
-			prev_idx = perf_evsel__group_idx(evsel);
+			prev_idx = evsel__group_idx(evsel);
 		}
 
 		idx_delta = nr_members - prev_idx - 1;
@@ -164,12 +164,12 @@ static int hist_entry__new_pair(struct hist_entry *a, struct hist_entry *b,
 
 	list_for_each_entry(pair, &a->pairs.head, pairs.node) {
 		struct evsel *evsel = hists_to_evsel(pair->hists);
-		fa[perf_evsel__group_idx(evsel)] = get_field(pair);
+		fa[evsel__group_idx(evsel)] = get_field(pair);
 	}
 
 	list_for_each_entry(pair, &b->pairs.head, pairs.node) {
 		struct evsel *evsel = hists_to_evsel(pair->hists);
-		fb[perf_evsel__group_idx(evsel)] = get_field(pair);
+		fb[evsel__group_idx(evsel)] = get_field(pair);
 	}
 
 	*fields_a = fa;
@@ -190,7 +190,7 @@ static int __hpp__group_sort_idx(struct hist_entry *a, struct hist_entry *b,
 	int cmp, nr_members, ret, i;
 
 	cmp = field_cmp(get_field(a), get_field(b));
-	if (!perf_evsel__is_group_event(evsel))
+	if (!evsel__is_group_event(evsel))
 		return cmp;
 
 	nr_members = evsel->core.nr_members;
@@ -240,7 +240,7 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b,
 		return ret;
 
 	evsel = hists_to_evsel(a->hists);
-	if (!perf_evsel__is_group_event(evsel))
+	if (!evsel__is_group_event(evsel))
 		return ret;
 
 	nr_members = evsel->core.nr_members;
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index c0cf8dff694e..ca07a162d602 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -10,6 +10,7 @@ perf-y += db-export.o
 perf-y += env.o
 perf-y += event.o
 perf-y += evlist.o
+perf-y += sideband_evlist.o
 perf-y += evsel.o
 perf-y += evsel_fprintf.o
 perf-y += perf_event_attr_fprintf.o
@@ -88,6 +89,7 @@ perf-y += counts.o
 perf-y += stat.o
 perf-y += stat-shadow.o
 perf-y += stat-display.o
+perf-y += perf_api_probe.o
 perf-y += record.o
 perf-y += srcline.o
 perf-y += srccode.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index f1ea0d61eb5b..d828c2d2edee 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1191,7 +1191,7 @@ static struct disasm_line *disasm_line__new(struct annotate_args *args)
 	struct disasm_line *dl = NULL;
 	int nr = 1;
 
-	if (perf_evsel__is_group_event(args->evsel))
+	if (evsel__is_group_event(args->evsel))
 		nr = args->evsel->core.nr_members;
 
 	dl = zalloc(disasm_line_size(nr));
@@ -1437,7 +1437,7 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 		if (queue)
 			return -1;
 
-		if (perf_evsel__is_group_event(evsel))
+		if (evsel__is_group_event(evsel))
 			width *= evsel->core.nr_members;
 
 		if (!*al->line)
@@ -1821,6 +1821,24 @@ static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
 }
 #endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
 
+static int
+symbol__disassemble_bpf_image(struct symbol *sym,
+			      struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *dl;
+
+	args->offset = -1;
+	args->line = strdup("to be implemented");
+	args->line_nr = 0;
+	dl = disasm_line__new(args);
+	if (dl)
+		annotation_line__add(&dl->al, &notes->src->source);
+
+	free(args->line);
+	return 0;
+}
+
 /*
  * Possibly create a new version of line with tabs expanded. Returns the
  * existing or new line, storage is updated if a new line is allocated. If
@@ -1920,6 +1938,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 
 	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
 		return symbol__disassemble_bpf(sym, args);
+	} else if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) {
+		return symbol__disassemble_bpf_image(sym, args);
 	} else if (dso__is_kcore(dso)) {
 		kce.kcore_filename = symfs_filename;
 		kce.addr = map__rip_2objdump(map, sym->start);
@@ -2136,7 +2156,7 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 		.evsel		= evsel,
 		.options	= options,
 	};
-	struct perf_env *env = perf_evsel__env(evsel);
+	struct perf_env *env = evsel__env(evsel);
 	const char *arch_name = perf_env__arch(env);
 	struct arch *arch;
 	int err;
@@ -2324,7 +2344,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
 	struct dso *dso = map->dso;
 	char *filename;
 	const char *d_filename;
-	const char *evsel_name = perf_evsel__name(evsel);
+	const char *evsel_name = evsel__name(evsel);
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evsel->idx);
 	struct annotation_line *pos, *queue = NULL;
@@ -2348,9 +2368,9 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
 
 	len = symbol__size(sym);
 
-	if (perf_evsel__is_group_event(evsel)) {
+	if (evsel__is_group_event(evsel)) {
 		width *= evsel->core.nr_members;
-		perf_evsel__group_desc(evsel, buf, sizeof(buf));
+		evsel__group_desc(evsel, buf, sizeof(buf));
 		evsel_name = buf;
 	}
 
@@ -2485,7 +2505,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
 int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
 				struct annotation_options *opts)
 {
-	const char *ev_name = perf_evsel__name(evsel);
+	const char *ev_name = evsel__name(evsel);
 	char buf[1024];
 	char *filename;
 	int err = -1;
@@ -2498,8 +2518,8 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
 	if (fp == NULL)
 		goto out_free_filename;
 
-	if (perf_evsel__is_group_event(evsel)) {
-		perf_evsel__group_desc(evsel, buf, sizeof(buf));
+	if (evsel__is_group_event(evsel)) {
+		evsel__group_desc(evsel, buf, sizeof(buf));
 		ev_name = buf;
 	}
 
@@ -3044,7 +3064,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	if (notes->offsets == NULL)
 		return ENOMEM;
 
-	if (perf_evsel__is_group_event(evsel))
+	if (evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
 
 	err = symbol__annotate(ms, evsel, options, parch);
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 53be12b23ff4..875a0dd540e5 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -176,6 +176,14 @@ static void arm_spe_free(struct perf_session *session)
 	free(spe);
 }
 
+static bool arm_spe_evsel_is_auxtrace(struct perf_session *session,
+				      struct evsel *evsel)
+{
+	struct arm_spe *spe = container_of(session->auxtrace, struct arm_spe, auxtrace);
+
+	return evsel->core.attr.type == spe->pmu_type;
+}
+
 static const char * const arm_spe_info_fmts[] = {
 	[ARM_SPE_PMU_TYPE]		= "  PMU Type           %"PRId64"\n",
 };
@@ -218,6 +226,7 @@ int arm_spe_process_auxtrace_info(union perf_event *event,
 	spe->auxtrace.flush_events = arm_spe_flush;
 	spe->auxtrace.free_events = arm_spe_free_events;
 	spe->auxtrace.free = arm_spe_free;
+	spe->auxtrace.evsel_is_auxtrace = arm_spe_evsel_is_auxtrace;
 	session->auxtrace = &spe->auxtrace;
 
 	arm_spe_print_info(&auxtrace_info->priv[0]);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 3571ce72ca28..749487a41cc7 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -33,6 +33,7 @@
 #include "evsel.h"
 #include "evsel_config.h"
 #include "symbol.h"
+#include "util/perf_api_probe.h"
 #include "util/synthetic-events.h"
 #include "thread_map.h"
 #include "asm/bug.h"
@@ -58,25 +59,6 @@
 #include "symbol/kallsyms.h"
 #include <internal/lib.h>
 
-static struct perf_pmu *perf_evsel__find_pmu(struct evsel *evsel)
-{
-	struct perf_pmu *pmu = NULL;
-
-	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-		if (pmu->type == evsel->core.attr.type)
-			break;
-	}
-
-	return pmu;
-}
-
-static bool perf_evsel__is_aux_event(struct evsel *evsel)
-{
-	struct perf_pmu *pmu = perf_evsel__find_pmu(evsel);
-
-	return pmu && pmu->auxtrace;
-}
-
 /*
  * Make a group from 'leader' to 'last', requiring that the events were not
  * already grouped to a different leader.
@@ -88,7 +70,7 @@ static int perf_evlist__regroup(struct evlist *evlist,
 	struct evsel *evsel;
 	bool grp;
 
-	if (!perf_evsel__is_group_leader(leader))
+	if (!evsel__is_group_leader(leader))
 		return -EINVAL;
 
 	grp = false;
@@ -703,8 +685,8 @@ static int auxtrace_validate_aux_sample_size(struct evlist *evlist,
 
 	evlist__for_each_entry(evlist, evsel) {
 		sz = evsel->core.attr.aux_sample_size;
-		if (perf_evsel__is_group_leader(evsel)) {
-			has_aux_leader = perf_evsel__is_aux_event(evsel);
+		if (evsel__is_group_leader(evsel)) {
+			has_aux_leader = evsel__is_aux_event(evsel);
 			if (sz) {
 				if (has_aux_leader)
 					pr_err("Cannot add AUX area sampling to an AUX area event\n");
@@ -723,10 +705,10 @@ static int auxtrace_validate_aux_sample_size(struct evlist *evlist,
 				pr_err("Cannot add AUX area sampling because group leader is not an AUX area event\n");
 				return -EINVAL;
 			}
-			perf_evsel__set_sample_bit(evsel, AUX);
+			evsel__set_sample_bit(evsel, AUX);
 			opts->auxtrace_sample_mode = true;
 		} else {
-			perf_evsel__reset_sample_bit(evsel, AUX);
+			evsel__reset_sample_bit(evsel, AUX);
 		}
 	}
 
@@ -777,8 +759,8 @@ int auxtrace_parse_sample_options(struct auxtrace_record *itr,
 
 	/* Set aux_sample_size based on --aux-sample option */
 	evlist__for_each_entry(evlist, evsel) {
-		if (perf_evsel__is_group_leader(evsel)) {
-			has_aux_leader = perf_evsel__is_aux_event(evsel);
+		if (evsel__is_group_leader(evsel)) {
+			has_aux_leader = evsel__is_aux_event(evsel);
 		} else if (has_aux_leader) {
 			evsel->core.attr.aux_sample_size = sz;
 		}
@@ -787,7 +769,7 @@ no_opt:
 	aux_evsel = NULL;
 	/* Override with aux_sample_size from config term */
 	evlist__for_each_entry(evlist, evsel) {
-		if (perf_evsel__is_aux_event(evsel))
+		if (evsel__is_aux_event(evsel))
 			aux_evsel = evsel;
 		term = perf_evsel__get_config_term(evsel, AUX_SAMPLE_SIZE);
 		if (term) {
@@ -1234,29 +1216,79 @@ out_free:
 	return err;
 }
 
+static void unleader_evsel(struct evlist *evlist, struct evsel *leader)
+{
+	struct evsel *new_leader = NULL;
+	struct evsel *evsel;
+
+	/* Find new leader for the group */
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->leader != leader || evsel == leader)
+			continue;
+		if (!new_leader)
+			new_leader = evsel;
+		evsel->leader = new_leader;
+	}
+
+	/* Update group information */
+	if (new_leader) {
+		zfree(&new_leader->group_name);
+		new_leader->group_name = leader->group_name;
+		leader->group_name = NULL;
+
+		new_leader->core.nr_members = leader->core.nr_members - 1;
+		leader->core.nr_members = 1;
+	}
+}
+
+static void unleader_auxtrace(struct perf_session *session)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(session->evlist, evsel) {
+		if (auxtrace__evsel_is_auxtrace(session, evsel) &&
+		    evsel__is_group_leader(evsel)) {
+			unleader_evsel(session->evlist, evsel);
+		}
+	}
+}
+
 int perf_event__process_auxtrace_info(struct perf_session *session,
 				      union perf_event *event)
 {
 	enum auxtrace_type type = event->auxtrace_info.type;
+	int err;
 
 	if (dump_trace)
 		fprintf(stdout, " type: %u\n", type);
 
 	switch (type) {
 	case PERF_AUXTRACE_INTEL_PT:
-		return intel_pt_process_auxtrace_info(event, session);
+		err = intel_pt_process_auxtrace_info(event, session);
+		break;
 	case PERF_AUXTRACE_INTEL_BTS:
-		return intel_bts_process_auxtrace_info(event, session);
+		err = intel_bts_process_auxtrace_info(event, session);
+		break;
 	case PERF_AUXTRACE_ARM_SPE:
-		return arm_spe_process_auxtrace_info(event, session);
+		err = arm_spe_process_auxtrace_info(event, session);
+		break;
 	case PERF_AUXTRACE_CS_ETM:
-		return cs_etm__process_auxtrace_info(event, session);
+		err = cs_etm__process_auxtrace_info(event, session);
+		break;
 	case PERF_AUXTRACE_S390_CPUMSF:
-		return s390_cpumsf_process_auxtrace_info(event, session);
+		err = s390_cpumsf_process_auxtrace_info(event, session);
+		break;
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;
 	}
+
+	if (err)
+		return err;
+
+	unleader_auxtrace(session);
+
+	return 0;
 }
 
 s64 perf_event__process_auxtrace(struct perf_session *session,
@@ -1412,8 +1444,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			synth_opts->branches = true;
 			synth_opts->returns = true;
 			break;
+		case 'G':
 		case 'g':
-			synth_opts->callchain = true;
+			if (p[-1] == 'G')
+				synth_opts->add_callchain = true;
+			else
+				synth_opts->callchain = true;
 			synth_opts->callchain_sz =
 					PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
 			while (*p == ' ' || *p == ',')
@@ -1428,8 +1464,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 				synth_opts->callchain_sz = val;
 			}
 			break;
+		case 'L':
 		case 'l':
-			synth_opts->last_branch = true;
+			if (p[-1] == 'L')
+				synth_opts->add_last_branch = true;
+			else
+				synth_opts->last_branch = true;
 			synth_opts->last_branch_sz =
 					PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 			while (*p == ' ' || *p == ',')
@@ -2482,7 +2522,7 @@ static int parse_addr_filter(struct evsel *evsel, const char *filter,
 			goto out_exit;
 		}
 
-		if (perf_evsel__append_addr_filter(evsel, new_filter)) {
+		if (evsel__append_addr_filter(evsel, new_filter)) {
 			err = -ENOMEM;
 			goto out_exit;
 		}
@@ -2500,9 +2540,9 @@ out_exit:
 	return err;
 }
 
-static int perf_evsel__nr_addr_filter(struct evsel *evsel)
+static int evsel__nr_addr_filter(struct evsel *evsel)
 {
-	struct perf_pmu *pmu = perf_evsel__find_pmu(evsel);
+	struct perf_pmu *pmu = evsel__find_pmu(evsel);
 	int nr_addr_filters = 0;
 
 	if (!pmu)
@@ -2521,7 +2561,7 @@ int auxtrace_parse_filters(struct evlist *evlist)
 
 	evlist__for_each_entry(evlist, evsel) {
 		filter = evsel->filter;
-		max_nr = perf_evsel__nr_addr_filter(evsel);
+		max_nr = evsel__nr_addr_filter(evsel);
 		if (!filter || !max_nr)
 			continue;
 		evsel->filter = NULL;
@@ -2577,3 +2617,12 @@ void auxtrace__free(struct perf_session *session)
 
 	return session->auxtrace->free(session);
 }
+
+bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
+				 struct evsel *evsel)
+{
+	if (!session->auxtrace || !session->auxtrace->evsel_is_auxtrace)
+		return false;
+
+	return session->auxtrace->evsel_is_auxtrace(session, evsel);
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index e58ef160b599..0220a2e86c16 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -21,6 +21,7 @@
 union perf_event;
 struct perf_session;
 struct evlist;
+struct evsel;
 struct perf_tool;
 struct mmap;
 struct perf_sample;
@@ -73,8 +74,10 @@ enum itrace_period_type {
  * @calls: limit branch samples to calls (can be combined with @returns)
  * @returns: limit branch samples to returns (can be combined with @calls)
  * @callchain: add callchain to 'instructions' events
+ * @add_callchain: add callchain to existing event records
  * @thread_stack: feed branches to the thread_stack
  * @last_branch: add branch context to 'instruction' events
+ * @add_last_branch: add branch context to existing event records
  * @callchain_sz: maximum callchain size
  * @last_branch_sz: branch context size
  * @period: 'instructions' events period
@@ -100,8 +103,10 @@ struct itrace_synth_opts {
 	bool			calls;
 	bool			returns;
 	bool			callchain;
+	bool			add_callchain;
 	bool			thread_stack;
 	bool			last_branch;
+	bool			add_last_branch;
 	unsigned int		callchain_sz;
 	unsigned int		last_branch_sz;
 	unsigned long long	period;
@@ -166,6 +171,8 @@ struct auxtrace {
 			    struct perf_tool *tool);
 	void (*free_events)(struct perf_session *session);
 	void (*free)(struct perf_session *session);
+	bool (*evsel_is_auxtrace)(struct perf_session *session,
+				  struct evsel *evsel);
 };
 
 /**
@@ -584,6 +591,8 @@ void auxtrace__dump_auxtrace_sample(struct perf_session *session,
 int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool);
 void auxtrace__free_events(struct perf_session *session);
 void auxtrace__free(struct perf_session *session);
+bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
+				 struct evsel *evsel);
 
 #define ITRACE_HELP \
 "				i:	    		synthesize instructions events\n"		\
@@ -750,6 +759,13 @@ void auxtrace_index__free(struct list_head *head __maybe_unused)
 }
 
 static inline
+bool auxtrace__evsel_is_auxtrace(struct perf_session *session __maybe_unused,
+				 struct evsel *evsel __maybe_unused)
+{
+	return false;
+}
+
+static inline
 int auxtrace_parse_filters(struct evlist *evlist __maybe_unused)
 {
 	return 0;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index a3207d900339..3742511a08d1 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -6,6 +6,9 @@
 #include <bpf/libbpf.h>
 #include <linux/btf.h>
 #include <linux/err.h>
+#include <linux/string.h>
+#include <internal/lib.h>
+#include <symbol/kallsyms.h>
 #include "bpf-event.h"
 #include "debug.h"
 #include "dso.h"
@@ -290,11 +293,82 @@ out:
 	return err ? -1 : 0;
 }
 
+struct kallsyms_parse {
+	union perf_event	*event;
+	perf_event__handler_t	 process;
+	struct machine		*machine;
+	struct perf_tool	*tool;
+};
+
+static int
+process_bpf_image(char *name, u64 addr, struct kallsyms_parse *data)
+{
+	struct machine *machine = data->machine;
+	union perf_event *event = data->event;
+	struct perf_record_ksymbol *ksymbol;
+	int len;
+
+	ksymbol = &event->ksymbol;
+
+	*ksymbol = (struct perf_record_ksymbol) {
+		.header = {
+			.type = PERF_RECORD_KSYMBOL,
+			.size = offsetof(struct perf_record_ksymbol, name),
+		},
+		.addr      = addr,
+		.len       = page_size,
+		.ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
+		.flags     = 0,
+	};
+
+	len = scnprintf(ksymbol->name, KSYM_NAME_LEN, "%s", name);
+	ksymbol->header.size += PERF_ALIGN(len + 1, sizeof(u64));
+	memset((void *) event + event->header.size, 0, machine->id_hdr_size);
+	event->header.size += machine->id_hdr_size;
+
+	return perf_tool__process_synth_event(data->tool, event, machine,
+					      data->process);
+}
+
+static int
+kallsyms_process_symbol(void *data, const char *_name,
+			char type __maybe_unused, u64 start)
+{
+	char disp[KSYM_NAME_LEN];
+	char *module, *name;
+	unsigned long id;
+	int err = 0;
+
+	module = strchr(_name, '\t');
+	if (!module)
+		return 0;
+
+	/* We are going after [bpf] module ... */
+	if (strcmp(module + 1, "[bpf]"))
+		return 0;
+
+	name = memdup(_name, (module - _name) + 1);
+	if (!name)
+		return -ENOMEM;
+
+	name[module - _name] = 0;
+
+	/* .. and only for trampolines and dispatchers */
+	if ((sscanf(name, "bpf_trampoline_%lu", &id) == 1) ||
+	    (sscanf(name, "bpf_dispatcher_%s", disp) == 1))
+		err = process_bpf_image(name, start, data);
+
+	free(name);
+	return err;
+}
+
 int perf_event__synthesize_bpf_events(struct perf_session *session,
 				      perf_event__handler_t process,
 				      struct machine *machine,
 				      struct record_opts *opts)
 {
+	const char *kallsyms_filename = "/proc/kallsyms";
+	struct kallsyms_parse arg;
 	union perf_event *event;
 	__u32 id = 0;
 	int err;
@@ -303,6 +377,8 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 	event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size);
 	if (!event)
 		return -1;
+
+	/* Synthesize all the bpf programs in system. */
 	while (true) {
 		err = bpf_prog_get_next_id(id, &id);
 		if (err) {
@@ -335,6 +411,23 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 			break;
 		}
 	}
+
+	/* Synthesize all the bpf images - trampolines/dispatchers. */
+	if (symbol_conf.kallsyms_name != NULL)
+		kallsyms_filename = symbol_conf.kallsyms_name;
+
+	arg = (struct kallsyms_parse) {
+		.event   = event,
+		.process = process,
+		.machine = machine,
+		.tool    = session->tool,
+	};
+
+	if (kallsyms__parse(kallsyms_filename, &arg, kallsyms_process_symbol)) {
+		pr_err("%s: failed to synthesize bpf images: %s\n",
+		       __func__, strerror(errno));
+	}
+
 	free(event);
 	return err;
 }
@@ -416,8 +509,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data)
 	return 0;
 }
 
-int bpf_event__add_sb_event(struct evlist **evlist,
-			    struct perf_env *env)
+int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
 {
 	struct perf_event_attr attr = {
 		.type	          = PERF_TYPE_SOFTWARE,
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 81fdc88e6c1a..68f315c3df5b 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -33,8 +33,7 @@ struct btf_node {
 #ifdef HAVE_LIBBPF_SUPPORT
 int machine__process_bpf(struct machine *machine, union perf_event *event,
 			 struct perf_sample *sample);
-int bpf_event__add_sb_event(struct evlist **evlist,
-				 struct perf_env *env);
+int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env);
 void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
 				    struct perf_env *env,
 				    FILE *fp);
@@ -46,8 +45,8 @@ static inline int machine__process_bpf(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-static inline int bpf_event__add_sb_event(struct evlist **evlist __maybe_unused,
-					  struct perf_env *env __maybe_unused)
+static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused,
+					   struct perf_env *env __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 10c187b8b8ea..83bfb8768235 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1430,7 +1430,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
 	}
 
-	if (perf_evsel__is_bpf_output(evsel))
+	if (evsel__is_bpf_output(evsel))
 		check_pass = true;
 	if (attr->type == PERF_TYPE_RAW)
 		check_pass = true;
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index 154a05cd03af..4d3f02fa223d 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -15,13 +15,18 @@
 #include "event.h"
 
 struct branch_flags {
-	u64 mispred:1;
-	u64 predicted:1;
-	u64 in_tx:1;
-	u64 abort:1;
-	u64 cycles:16;
-	u64 type:4;
-	u64 reserved:40;
+	union {
+		u64 value;
+		struct {
+			u64 mispred:1;
+			u64 predicted:1;
+			u64 in_tx:1;
+			u64 abort:1;
+			u64 cycles:16;
+			u64 type:4;
+			u64 reserved:40;
+		};
+	};
 };
 
 struct branch_info {
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 706bb7bbe1e1..8f668ee29f25 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -143,6 +143,9 @@ struct callchain_cursor_node {
 	u64				ip;
 	struct map_symbol		ms;
 	const char			*srcline;
+	/* Indicate valid cursor node for LBR stitch */
+	bool				valid;
+
 	bool				branch;
 	struct branch_flags		branch_flags;
 	u64				branch_from;
@@ -151,6 +154,11 @@ struct callchain_cursor_node {
 	struct callchain_cursor_node	*next;
 };
 
+struct stitch_list {
+	struct list_head		node;
+	struct callchain_cursor_node	cursor;
+};
+
 struct callchain_cursor {
 	u64				nr;
 	struct callchain_cursor_node	*first;
diff --git a/tools/perf/util/cap.h b/tools/perf/util/cap.h
index 051dc590ceee..ae52878c0b2e 100644
--- a/tools/perf/util/cap.h
+++ b/tools/perf/util/cap.h
@@ -29,4 +29,8 @@ static inline bool perf_cap__capable(int cap __maybe_unused)
 #define CAP_SYSLOG	34
 #endif
 
+#ifndef CAP_PERFMON
+#define CAP_PERFMON	38
+#endif
+
 #endif /* __PERF_CAP_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index b73fb7823048..050dea9f1e88 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -107,7 +107,8 @@ found:
 
 static void cgroup__delete(struct cgroup *cgroup)
 {
-	close(cgroup->fd);
+	if (cgroup->fd >= 0)
+		close(cgroup->fd);
 	zfree(&cgroup->name);
 	free(cgroup);
 }
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index a12872f2856a..6b3988a7aba8 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -28,7 +28,7 @@ int __weak sched_getcpu(void)
 
 static int perf_flag_probe(void)
 {
-	/* use 'safest' configuration as used in perf_evsel__fallback() */
+	/* use 'safest' configuration as used in evsel__fallback() */
 	struct perf_event_attr attr = {
 		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_CPU_CLOCK,
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index cd92a99eb89d..cd007cc9c283 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -564,6 +564,8 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 		resp = cs_etm_decoder__set_tid(etmq, packet_queue,
 					       elem, trace_chan_id);
 		break;
+	/* Unused packet types */
+	case OCSD_GEN_TRC_ELEM_I_RANGE_NOPATH:
 	case OCSD_GEN_TRC_ELEM_ADDR_NACC:
 	case OCSD_GEN_TRC_ELEM_CYCLE_COUNT:
 	case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN:
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 62d2f9b9ce1b..c283223fb31f 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -94,6 +94,9 @@ struct cs_etm_queue {
 	struct cs_etm_traceid_queue **traceid_queues;
 };
 
+/* RB tree for quick conversion between traceID and metadata pointers */
+static struct intlist *traceid_list;
+
 static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
 static int cs_etm__process_queues(struct cs_etm_auxtrace *etm);
 static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
@@ -631,6 +634,16 @@ static void cs_etm__free(struct perf_session *session)
 	zfree(&aux);
 }
 
+static bool cs_etm__evsel_is_auxtrace(struct perf_session *session,
+				      struct evsel *evsel)
+{
+	struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
+						   struct cs_etm_auxtrace,
+						   auxtrace);
+
+	return evsel->core.attr.type == aux->pmu_type;
+}
+
 static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
 {
 	struct machine *machine;
@@ -2618,6 +2631,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	etm->auxtrace.flush_events = cs_etm__flush_events;
 	etm->auxtrace.free_events = cs_etm__free_events;
 	etm->auxtrace.free = cs_etm__free;
+	etm->auxtrace.evsel_is_auxtrace = cs_etm__evsel_is_auxtrace;
 	session->auxtrace = &etm->auxtrace;
 
 	etm->unknown_thread = thread__new(999999999, 999999999);
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 650ecc2a6349..4ad925d6d799 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -114,9 +114,6 @@ enum cs_etm_isa {
 	CS_ETM_ISA_T32,
 };
 
-/* RB tree for quick conversion between traceID and metadata pointers */
-struct intlist *traceid_list;
-
 struct cs_etm_queue;
 
 struct cs_etm_packet {
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index dbc772bfb04e..5f36fc6a5578 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -835,7 +835,7 @@ static int process_sample_event(struct perf_tool *tool,
 			return -1;
 	}
 
-	if (perf_evsel__is_bpf_output(evsel)) {
+	if (evsel__is_bpf_output(evsel)) {
 		ret = add_bpf_output_values(event_class, event, sample);
 		if (ret)
 			return -1;
@@ -1155,7 +1155,7 @@ static int add_event(struct ctf_writer *cw, struct evsel *evsel)
 {
 	struct bt_ctf_event_class *event_class;
 	struct evsel_priv *priv;
-	const char *name = perf_evsel__name(evsel);
+	const char *name = evsel__name(evsel);
 	int ret;
 
 	pr("Adding event '%s' (type %d)\n", name, evsel->core.attr.type);
@@ -1174,7 +1174,7 @@ static int add_event(struct ctf_writer *cw, struct evsel *evsel)
 			goto err;
 	}
 
-	if (perf_evsel__is_bpf_output(evsel)) {
+	if (evsel__is_bpf_output(evsel)) {
 		ret = add_bpf_output_types(cw, event_class);
 		if (ret)
 			goto err;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 91f21239608b..f338990e0fe6 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -191,6 +191,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
 	case DSO_BINARY_TYPE__JAVA_JIT:
 	case DSO_BINARY_TYPE__BPF_PROG_INFO:
+	case DSO_BINARY_TYPE__BPF_IMAGE:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 		ret = -1;
 		break;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 2db64b79617a..9553a1fd9e8a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -40,6 +40,7 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__GUEST_KCORE,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__BPF_PROG_INFO,
+	DSO_BINARY_TYPE__BPF_IMAGE,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 7632075a8792..1ab2682d5d2b 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -48,6 +48,7 @@ struct perf_env {
 	char			*cpuid;
 	unsigned long long	total_mem;
 	unsigned int		msr_pmu_type;
+	unsigned int		max_branches;
 
 	int			nr_cmdline;
 	int			nr_sibling_cores;
@@ -57,12 +58,14 @@ struct perf_env {
 	int			nr_memory_nodes;
 	int			nr_pmu_mappings;
 	int			nr_groups;
+	int			nr_cpu_pmu_caps;
 	char			*cmdline;
 	const char		**cmdline_argv;
 	char			*sibling_cores;
 	char			*sibling_dies;
 	char			*sibling_threads;
 	char			*pmu_mappings;
+	char			*cpu_pmu_caps;
 	struct cpu_topology_map	*cpu;
 	struct cpu_cache_level	*caches;
 	int			 caches_cnt;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index dc0e11214ae1..f581550a3015 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -626,7 +626,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 			ret = strlist__has_entry(symbol_conf.sym_list,
 						al->sym->name);
 		}
-		if (!(ret && al->sym)) {
+		if (!ret && al->sym) {
 			snprintf(al_addr_str, sz, "0x%"PRIx64,
 				al->map->unmap_ip(al->map, al->sym->start));
 			ret = strlist__has_entry(symbol_conf.sym_list,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 1548237b6558..0a0b760d6948 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -23,6 +23,7 @@
 #include "asm/bug.h"
 #include "bpf-event.h"
 #include "util/string2.h"
+#include "util/perf_api_probe.h"
 #include <signal.h>
 #include <unistd.h>
 #include <sched.h>
@@ -118,7 +119,7 @@ static void perf_evlist__update_id_pos(struct evlist *evlist)
 	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel)
-		perf_evsel__calc_id_pos(evsel);
+		evsel__calc_id_pos(evsel);
 
 	perf_evlist__set_id_pos(evlist);
 }
@@ -390,14 +391,14 @@ void evlist__disable(struct evlist *evlist)
 		evlist__for_each_entry(evlist, pos) {
 			if (evsel__cpu_iter_skip(pos, cpu))
 				continue;
-			if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+			if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
 				continue;
 			evsel__disable_cpu(pos, pos->cpu_iter - 1);
 		}
 	}
 	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
-		if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+		if (!evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
 		pos->disabled = true;
 	}
@@ -420,14 +421,14 @@ void evlist__enable(struct evlist *evlist)
 		evlist__for_each_entry(evlist, pos) {
 			if (evsel__cpu_iter_skip(pos, cpu))
 				continue;
-			if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+			if (!evsel__is_group_leader(pos) || !pos->core.fd)
 				continue;
 			evsel__enable_cpu(pos, pos->cpu_iter - 1);
 		}
 	}
 	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
-		if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+		if (!evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
 		pos->disabled = false;
 	}
@@ -947,7 +948,7 @@ void __perf_evlist__set_sample_bit(struct evlist *evlist,
 	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel)
-		__perf_evsel__set_sample_bit(evsel, bit);
+		__evsel__set_sample_bit(evsel, bit);
 }
 
 void __perf_evlist__reset_sample_bit(struct evlist *evlist,
@@ -956,7 +957,7 @@ void __perf_evlist__reset_sample_bit(struct evlist *evlist,
 	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel)
-		__perf_evsel__reset_sample_bit(evsel, bit);
+		__evsel__reset_sample_bit(evsel, bit);
 }
 
 int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
@@ -994,7 +995,7 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter)
 		if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
-		err = perf_evsel__set_filter(evsel, filter);
+		err = evsel__set_filter(evsel, filter);
 		if (err)
 			break;
 	}
@@ -1014,7 +1015,7 @@ int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter)
 		if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
-		err = perf_evsel__append_tp_filter(evsel, filter);
+		err = evsel__append_tp_filter(evsel, filter);
 		if (err)
 			break;
 	}
@@ -1131,8 +1132,10 @@ bool perf_evlist__valid_read_format(struct evlist *evlist)
 	u64 sample_type = first->core.attr.sample_type;
 
 	evlist__for_each_entry(evlist, pos) {
-		if (read_format != pos->core.attr.read_format)
-			return false;
+		if (read_format != pos->core.attr.read_format) {
+			pr_debug("Read format differs %#" PRIx64 " vs %#" PRIx64 "\n",
+				 read_format, (u64)pos->core.attr.read_format);
+		}
 	}
 
 	/* PERF_SAMPLE_READ imples PERF_FORMAT_ID. */
@@ -1436,7 +1439,7 @@ int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event,
 
 	if (!evsel)
 		return -EFAULT;
-	return perf_evsel__parse_sample(evsel, event, sample);
+	return evsel__parse_sample(evsel, event, sample);
 }
 
 int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
@@ -1447,7 +1450,7 @@ int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
 
 	if (!evsel)
 		return -EFAULT;
-	return perf_evsel__parse_sample_timestamp(evsel, event, timestamp);
+	return evsel__parse_sample_timestamp(evsel, event, timestamp);
 }
 
 int perf_evlist__strerror_open(struct evlist *evlist,
@@ -1701,133 +1704,3 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
 	}
 	return leader;
 }
-
-int perf_evlist__add_sb_event(struct evlist **evlist,
-			      struct perf_event_attr *attr,
-			      perf_evsel__sb_cb_t cb,
-			      void *data)
-{
-	struct evsel *evsel;
-	bool new_evlist = (*evlist) == NULL;
-
-	if (*evlist == NULL)
-		*evlist = evlist__new();
-	if (*evlist == NULL)
-		return -1;
-
-	if (!attr->sample_id_all) {
-		pr_warning("enabling sample_id_all for all side band events\n");
-		attr->sample_id_all = 1;
-	}
-
-	evsel = perf_evsel__new_idx(attr, (*evlist)->core.nr_entries);
-	if (!evsel)
-		goto out_err;
-
-	evsel->side_band.cb = cb;
-	evsel->side_band.data = data;
-	evlist__add(*evlist, evsel);
-	return 0;
-
-out_err:
-	if (new_evlist) {
-		evlist__delete(*evlist);
-		*evlist = NULL;
-	}
-	return -1;
-}
-
-static void *perf_evlist__poll_thread(void *arg)
-{
-	struct evlist *evlist = arg;
-	bool draining = false;
-	int i, done = 0;
-	/*
-	 * In order to read symbols from other namespaces perf to needs to call
-	 * setns(2).  This isn't permitted if the struct_fs has multiple users.
-	 * unshare(2) the fs so that we may continue to setns into namespaces
-	 * that we're observing when, for instance, reading the build-ids at
-	 * the end of a 'perf record' session.
-	 */
-	unshare(CLONE_FS);
-
-	while (!done) {
-		bool got_data = false;
-
-		if (evlist->thread.done)
-			draining = true;
-
-		if (!draining)
-			evlist__poll(evlist, 1000);
-
-		for (i = 0; i < evlist->core.nr_mmaps; i++) {
-			struct mmap *map = &evlist->mmap[i];
-			union perf_event *event;
-
-			if (perf_mmap__read_init(&map->core))
-				continue;
-			while ((event = perf_mmap__read_event(&map->core)) != NULL) {
-				struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
-
-				if (evsel && evsel->side_band.cb)
-					evsel->side_band.cb(event, evsel->side_band.data);
-				else
-					pr_warning("cannot locate proper evsel for the side band event\n");
-
-				perf_mmap__consume(&map->core);
-				got_data = true;
-			}
-			perf_mmap__read_done(&map->core);
-		}
-
-		if (draining && !got_data)
-			break;
-	}
-	return NULL;
-}
-
-int perf_evlist__start_sb_thread(struct evlist *evlist,
-				 struct target *target)
-{
-	struct evsel *counter;
-
-	if (!evlist)
-		return 0;
-
-	if (perf_evlist__create_maps(evlist, target))
-		goto out_delete_evlist;
-
-	evlist__for_each_entry(evlist, counter) {
-		if (evsel__open(counter, evlist->core.cpus,
-				     evlist->core.threads) < 0)
-			goto out_delete_evlist;
-	}
-
-	if (evlist__mmap(evlist, UINT_MAX))
-		goto out_delete_evlist;
-
-	evlist__for_each_entry(evlist, counter) {
-		if (evsel__enable(counter))
-			goto out_delete_evlist;
-	}
-
-	evlist->thread.done = 0;
-	if (pthread_create(&evlist->thread.th, NULL, perf_evlist__poll_thread, evlist))
-		goto out_delete_evlist;
-
-	return 0;
-
-out_delete_evlist:
-	evlist__delete(evlist);
-	evlist = NULL;
-	return -1;
-}
-
-void perf_evlist__stop_sb_thread(struct evlist *evlist)
-{
-	if (!evlist)
-		return;
-	evlist->thread.done = 1;
-	pthread_join(evlist->thread.th, NULL);
-	evlist__delete(evlist);
-}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f5bd5c386df1..b6f325dfb4d2 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -107,10 +107,11 @@ int __perf_evlist__add_default_attrs(struct evlist *evlist,
 
 int perf_evlist__add_dummy(struct evlist *evlist);
 
-int perf_evlist__add_sb_event(struct evlist **evlist,
+int perf_evlist__add_sb_event(struct evlist *evlist,
 			      struct perf_event_attr *attr,
-			      perf_evsel__sb_cb_t cb,
+			      evsel__sb_cb_t cb,
 			      void *data);
+void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data);
 int perf_evlist__start_sb_thread(struct evlist *evlist,
 				 struct target *target);
 void perf_evlist__stop_sb_thread(struct evlist *evlist);
@@ -173,10 +174,6 @@ void evlist__close(struct evlist *evlist);
 struct callchain_param;
 
 void perf_evlist__set_id_pos(struct evlist *evlist);
-bool perf_can_sample_identifier(void);
-bool perf_can_record_switch_events(void);
-bool perf_can_record_cpu_wide(void);
-bool perf_can_aux_sample(void);
 void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
 			 struct callchain_param *callchain);
 int record_opts__config(struct record_opts *opts);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index eb880efbce16..f3e60c45d59a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -102,7 +102,7 @@ set_methods:
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
 
-int __perf_evsel__sample_size(u64 sample_type)
+int __evsel__sample_size(u64 sample_type)
 {
 	u64 mask = sample_type & PERF_SAMPLE_MASK;
 	int size = 0;
@@ -178,53 +178,53 @@ static int __perf_evsel__calc_is_pos(u64 sample_type)
 	return idx;
 }
 
-void perf_evsel__calc_id_pos(struct evsel *evsel)
+void evsel__calc_id_pos(struct evsel *evsel)
 {
 	evsel->id_pos = __perf_evsel__calc_id_pos(evsel->core.attr.sample_type);
 	evsel->is_pos = __perf_evsel__calc_is_pos(evsel->core.attr.sample_type);
 }
 
-void __perf_evsel__set_sample_bit(struct evsel *evsel,
+void __evsel__set_sample_bit(struct evsel *evsel,
 				  enum perf_event_sample_format bit)
 {
 	if (!(evsel->core.attr.sample_type & bit)) {
 		evsel->core.attr.sample_type |= bit;
 		evsel->sample_size += sizeof(u64);
-		perf_evsel__calc_id_pos(evsel);
+		evsel__calc_id_pos(evsel);
 	}
 }
 
-void __perf_evsel__reset_sample_bit(struct evsel *evsel,
+void __evsel__reset_sample_bit(struct evsel *evsel,
 				    enum perf_event_sample_format bit)
 {
 	if (evsel->core.attr.sample_type & bit) {
 		evsel->core.attr.sample_type &= ~bit;
 		evsel->sample_size -= sizeof(u64);
-		perf_evsel__calc_id_pos(evsel);
+		evsel__calc_id_pos(evsel);
 	}
 }
 
-void perf_evsel__set_sample_id(struct evsel *evsel,
+void evsel__set_sample_id(struct evsel *evsel,
 			       bool can_sample_identifier)
 {
 	if (can_sample_identifier) {
-		perf_evsel__reset_sample_bit(evsel, ID);
-		perf_evsel__set_sample_bit(evsel, IDENTIFIER);
+		evsel__reset_sample_bit(evsel, ID);
+		evsel__set_sample_bit(evsel, IDENTIFIER);
 	} else {
-		perf_evsel__set_sample_bit(evsel, ID);
+		evsel__set_sample_bit(evsel, ID);
 	}
 	evsel->core.attr.read_format |= PERF_FORMAT_ID;
 }
 
 /**
- * perf_evsel__is_function_event - Return whether given evsel is a function
+ * evsel__is_function_event - Return whether given evsel is a function
  * trace event
  *
  * @evsel - evsel selector to be tested
  *
  * Return %true if event is function trace event
  */
-bool perf_evsel__is_function_event(struct evsel *evsel)
+bool evsel__is_function_event(struct evsel *evsel)
 {
 #define FUNCTION_EVENT "ftrace:function"
 
@@ -249,8 +249,8 @@ void evsel__init(struct evsel *evsel,
 	evsel->bpf_fd	   = -1;
 	INIT_LIST_HEAD(&evsel->config_terms);
 	perf_evsel__object.init(evsel);
-	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
-	perf_evsel__calc_id_pos(evsel);
+	evsel->sample_size = __evsel__sample_size(attr->sample_type);
+	evsel__calc_id_pos(evsel);
 	evsel->cmdline_group_boundary = false;
 	evsel->metric_expr   = NULL;
 	evsel->metric_name   = NULL;
@@ -267,13 +267,13 @@ struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 		return NULL;
 	evsel__init(evsel, attr, idx);
 
-	if (perf_evsel__is_bpf_output(evsel)) {
+	if (evsel__is_bpf_output(evsel)) {
 		evsel->core.attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
 					    PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
 		evsel->core.attr.sample_period = 1;
 	}
 
-	if (perf_evsel__is_clock(evsel)) {
+	if (evsel__is_clock(evsel)) {
 		/*
 		 * The evsel->unit points to static alias->unit
 		 * so it's ok to use static string in here.
@@ -385,7 +385,7 @@ const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
 	"ref-cycles",
 };
 
-static const char *__perf_evsel__hw_name(u64 config)
+static const char *__evsel__hw_name(u64 config)
 {
 	if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config])
 		return perf_evsel__hw_names[config];
@@ -429,9 +429,9 @@ static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
 	return r;
 }
 
-static int perf_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
 {
-	int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->core.attr.config));
+	int r = scnprintf(bf, size, "%s", __evsel__hw_name(evsel->core.attr.config));
 	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
@@ -448,20 +448,20 @@ const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = {
 	"dummy",
 };
 
-static const char *__perf_evsel__sw_name(u64 config)
+static const char *__evsel__sw_name(u64 config)
 {
 	if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config])
 		return perf_evsel__sw_names[config];
 	return "unknown-software";
 }
 
-static int perf_evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
 {
-	int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->core.attr.config));
+	int r = scnprintf(bf, size, "%s", __evsel__sw_name(evsel->core.attr.config));
 	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
-static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
+static int __evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
 {
 	int r;
 
@@ -479,10 +479,10 @@ static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
 	return r;
 }
 
-static int perf_evsel__bp_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__bp_name(struct evsel *evsel, char *bf, size_t size)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
-	int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
+	int r = __evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
 	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
@@ -531,7 +531,7 @@ static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = {
  [C(NODE)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
 };
 
-bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
+bool evsel__is_cache_op_valid(u8 type, u8 op)
 {
 	if (perf_evsel__hw_cache_stat[type] & COP(op))
 		return true;	/* valid */
@@ -539,8 +539,7 @@ bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
 		return false;	/* invalid */
 }
 
-int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
-					    char *bf, size_t size)
+int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size)
 {
 	if (result) {
 		return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0],
@@ -552,7 +551,7 @@ int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
 			 perf_evsel__hw_cache_op[op][1]);
 }
 
-static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
+static int __evsel__hw_cache_name(u64 config, char *bf, size_t size)
 {
 	u8 op, result, type = (config >>  0) & 0xff;
 	const char *err = "unknown-ext-hardware-cache-type";
@@ -571,33 +570,33 @@ static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
 		goto out_err;
 
 	err = "invalid-cache";
-	if (!perf_evsel__is_cache_op_valid(type, op))
+	if (!evsel__is_cache_op_valid(type, op))
 		goto out_err;
 
-	return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
+	return __evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
 out_err:
 	return scnprintf(bf, size, "%s", err);
 }
 
-static int perf_evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size)
 {
-	int ret = __perf_evsel__hw_cache_name(evsel->core.attr.config, bf, size);
+	int ret = __evsel__hw_cache_name(evsel->core.attr.config, bf, size);
 	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
 }
 
-static int perf_evsel__raw_name(struct evsel *evsel, char *bf, size_t size)
+static int evsel__raw_name(struct evsel *evsel, char *bf, size_t size)
 {
 	int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config);
 	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
 }
 
-static int perf_evsel__tool_name(char *bf, size_t size)
+static int evsel__tool_name(char *bf, size_t size)
 {
 	int ret = scnprintf(bf, size, "duration_time");
 	return ret;
 }
 
-const char *perf_evsel__name(struct evsel *evsel)
+const char *evsel__name(struct evsel *evsel)
 {
 	char bf[128];
 
@@ -609,22 +608,22 @@ const char *perf_evsel__name(struct evsel *evsel)
 
 	switch (evsel->core.attr.type) {
 	case PERF_TYPE_RAW:
-		perf_evsel__raw_name(evsel, bf, sizeof(bf));
+		evsel__raw_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_HARDWARE:
-		perf_evsel__hw_name(evsel, bf, sizeof(bf));
+		evsel__hw_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_HW_CACHE:
-		perf_evsel__hw_cache_name(evsel, bf, sizeof(bf));
+		evsel__hw_cache_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_SOFTWARE:
 		if (evsel->tool_event)
-			perf_evsel__tool_name(bf, sizeof(bf));
+			evsel__tool_name(bf, sizeof(bf));
 		else
-			perf_evsel__sw_name(evsel, bf, sizeof(bf));
+			evsel__sw_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_TRACEPOINT:
@@ -632,7 +631,7 @@ const char *perf_evsel__name(struct evsel *evsel)
 		break;
 
 	case PERF_TYPE_BREAKPOINT:
-		perf_evsel__bp_name(evsel, bf, sizeof(bf));
+		evsel__bp_name(evsel, bf, sizeof(bf));
 		break;
 
 	default:
@@ -649,7 +648,7 @@ out_unknown:
 	return "unknown";
 }
 
-const char *perf_evsel__group_name(struct evsel *evsel)
+const char *evsel__group_name(struct evsel *evsel)
 {
 	return evsel->group_name ?: "anon group";
 }
@@ -664,21 +663,19 @@ const char *perf_evsel__group_name(struct evsel *evsel)
  *  For record -e 'cycles,instructions' and report --group
  *    'cycles:u, instructions:u'
  */
-int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size)
+int evsel__group_desc(struct evsel *evsel, char *buf, size_t size)
 {
 	int ret = 0;
 	struct evsel *pos;
-	const char *group_name = perf_evsel__group_name(evsel);
+	const char *group_name = evsel__group_name(evsel);
 
 	if (!evsel->forced_leader)
 		ret = scnprintf(buf, size, "%s { ", group_name);
 
-	ret += scnprintf(buf + ret, size - ret, "%s",
-			 perf_evsel__name(evsel));
+	ret += scnprintf(buf + ret, size - ret, "%s", evsel__name(evsel));
 
 	for_each_group_member(pos, evsel)
-		ret += scnprintf(buf + ret, size - ret, ", %s",
-				 perf_evsel__name(pos));
+		ret += scnprintf(buf + ret, size - ret, ", %s", evsel__name(pos));
 
 	if (!evsel->forced_leader)
 		ret += scnprintf(buf + ret, size - ret, " }");
@@ -686,14 +683,13 @@ int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size)
 	return ret;
 }
 
-static void __perf_evsel__config_callchain(struct evsel *evsel,
-					   struct record_opts *opts,
-					   struct callchain_param *param)
+static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *opts,
+				      struct callchain_param *param)
 {
-	bool function = perf_evsel__is_function_event(evsel);
+	bool function = evsel__is_function_event(evsel);
 	struct perf_event_attr *attr = &evsel->core.attr;
 
-	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
+	evsel__set_sample_bit(evsel, CALLCHAIN);
 
 	attr->sample_max_stack = param->max_stack;
 
@@ -708,7 +704,7 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
 					   "to get user callchain information. "
 					   "Falling back to framepointers.\n");
 			} else {
-				perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
+				evsel__set_sample_bit(evsel, BRANCH_STACK);
 				attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
 							PERF_SAMPLE_BRANCH_CALL_STACK |
 							PERF_SAMPLE_BRANCH_NO_CYCLES |
@@ -722,8 +718,8 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
 
 	if (param->record_mode == CALLCHAIN_DWARF) {
 		if (!function) {
-			perf_evsel__set_sample_bit(evsel, REGS_USER);
-			perf_evsel__set_sample_bit(evsel, STACK_USER);
+			evsel__set_sample_bit(evsel, REGS_USER);
+			evsel__set_sample_bit(evsel, STACK_USER);
 			if (opts->sample_user_regs && DWARF_MINIMAL_REGS != PERF_REGS_MASK) {
 				attr->sample_regs_user |= DWARF_MINIMAL_REGS;
 				pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
@@ -746,12 +742,11 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
 	}
 }
 
-void perf_evsel__config_callchain(struct evsel *evsel,
-				  struct record_opts *opts,
-				  struct callchain_param *param)
+void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts,
+			     struct callchain_param *param)
 {
 	if (param->enabled)
-		return __perf_evsel__config_callchain(evsel, opts, param);
+		return __evsel__config_callchain(evsel, opts, param);
 }
 
 static void
@@ -760,16 +755,16 @@ perf_evsel__reset_callgraph(struct evsel *evsel,
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 
-	perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
+	evsel__reset_sample_bit(evsel, CALLCHAIN);
 	if (param->record_mode == CALLCHAIN_LBR) {
-		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
+		evsel__reset_sample_bit(evsel, BRANCH_STACK);
 		attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER |
 					      PERF_SAMPLE_BRANCH_CALL_STACK |
 					      PERF_SAMPLE_BRANCH_HW_INDEX);
 	}
 	if (param->record_mode == CALLCHAIN_DWARF) {
-		perf_evsel__reset_sample_bit(evsel, REGS_USER);
-		perf_evsel__reset_sample_bit(evsel, STACK_USER);
+		evsel__reset_sample_bit(evsel, REGS_USER);
+		evsel__reset_sample_bit(evsel, STACK_USER);
 	}
 }
 
@@ -793,32 +788,32 @@ static void apply_config_terms(struct evsel *evsel,
 			if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
 				attr->sample_period = term->val.period;
 				attr->freq = 0;
-				perf_evsel__reset_sample_bit(evsel, PERIOD);
+				evsel__reset_sample_bit(evsel, PERIOD);
 			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_FREQ:
 			if (!(term->weak && opts->user_freq != UINT_MAX)) {
 				attr->sample_freq = term->val.freq;
 				attr->freq = 1;
-				perf_evsel__set_sample_bit(evsel, PERIOD);
+				evsel__set_sample_bit(evsel, PERIOD);
 			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_TIME:
 			if (term->val.time)
-				perf_evsel__set_sample_bit(evsel, TIME);
+				evsel__set_sample_bit(evsel, TIME);
 			else
-				perf_evsel__reset_sample_bit(evsel, TIME);
+				evsel__reset_sample_bit(evsel, TIME);
 			break;
 		case PERF_EVSEL__CONFIG_TERM_CALLGRAPH:
 			callgraph_buf = term->val.str;
 			break;
 		case PERF_EVSEL__CONFIG_TERM_BRANCH:
 			if (term->val.str && strcmp(term->val.str, "no")) {
-				perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
+				evsel__set_sample_bit(evsel, BRANCH_STACK);
 				parse_branch_str(term->val.str,
 						 &attr->branch_sample_type);
 			} else
-				perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
+				evsel__reset_sample_bit(evsel, BRANCH_STACK);
 			break;
 		case PERF_EVSEL__CONFIG_TERM_STACK_USER:
 			dump_size = term->val.stack_user;
@@ -832,7 +827,7 @@ static void apply_config_terms(struct evsel *evsel,
 		case PERF_EVSEL__CONFIG_TERM_INHERIT:
 			/*
 			 * attr->inherit should has already been set by
-			 * perf_evsel__config. If user explicitly set
+			 * evsel__config. If user explicitly set
 			 * inherit using config terms, override global
 			 * opt->no_inherit setting.
 			 */
@@ -897,11 +892,11 @@ static void apply_config_terms(struct evsel *evsel,
 		/* set perf-event callgraph */
 		if (param.enabled) {
 			if (sample_address) {
-				perf_evsel__set_sample_bit(evsel, ADDR);
-				perf_evsel__set_sample_bit(evsel, DATA_SRC);
+				evsel__set_sample_bit(evsel, ADDR);
+				evsel__set_sample_bit(evsel, DATA_SRC);
 				evsel->core.attr.mmap_data = track;
 			}
-			perf_evsel__config_callchain(evsel, opts, &param);
+			evsel__config_callchain(evsel, opts, &param);
 		}
 	}
 }
@@ -953,8 +948,8 @@ struct perf_evsel_config_term *__perf_evsel__get_config_term(struct evsel *evsel
  *     enable/disable events specifically, as there's no
  *     initial traced exec call.
  */
-void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
-			struct callchain_param *callchain)
+void evsel__config(struct evsel *evsel, struct record_opts *opts,
+		   struct callchain_param *callchain)
 {
 	struct evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->core.attr;
@@ -965,17 +960,17 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	attr->inherit	    = !opts->no_inherit;
 	attr->write_backward = opts->overwrite ? 1 : 0;
 
-	perf_evsel__set_sample_bit(evsel, IP);
-	perf_evsel__set_sample_bit(evsel, TID);
+	evsel__set_sample_bit(evsel, IP);
+	evsel__set_sample_bit(evsel, TID);
 
 	if (evsel->sample_read) {
-		perf_evsel__set_sample_bit(evsel, READ);
+		evsel__set_sample_bit(evsel, READ);
 
 		/*
 		 * We need ID even in case of single event, because
 		 * PERF_SAMPLE_READ process ID specific data.
 		 */
-		perf_evsel__set_sample_id(evsel, false);
+		evsel__set_sample_id(evsel, false);
 
 		/*
 		 * Apply group format only if we belong to group
@@ -994,7 +989,7 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
 				     opts->user_interval != ULLONG_MAX)) {
 		if (opts->freq) {
-			perf_evsel__set_sample_bit(evsel, PERIOD);
+			evsel__set_sample_bit(evsel, PERIOD);
 			attr->freq		= 1;
 			attr->sample_freq	= opts->freq;
 		} else {
@@ -1002,25 +997,6 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 		}
 	}
 
-	/*
-	 * Disable sampling for all group members other
-	 * than leader in case leader 'leads' the sampling.
-	 */
-	if ((leader != evsel) && leader->sample_read) {
-		attr->freq           = 0;
-		attr->sample_freq    = 0;
-		attr->sample_period  = 0;
-		attr->write_backward = 0;
-
-		/*
-		 * We don't get sample for slave events, we make them
-		 * when delivering group leader sample. Set the slave
-		 * event to follow the master sample_type to ease up
-		 * report.
-		 */
-		attr->sample_type = leader->core.attr.sample_type;
-	}
-
 	if (opts->no_samples)
 		attr->sample_freq = 0;
 
@@ -1033,7 +1009,7 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	}
 
 	if (opts->sample_address) {
-		perf_evsel__set_sample_bit(evsel, ADDR);
+		evsel__set_sample_bit(evsel, ADDR);
 		attr->mmap_data = track;
 	}
 
@@ -1042,24 +1018,24 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 * event, due to issues with page faults while tracing page
 	 * fault handler and its overall trickiness nature.
 	 */
-	if (perf_evsel__is_function_event(evsel))
+	if (evsel__is_function_event(evsel))
 		evsel->core.attr.exclude_callchain_user = 1;
 
 	if (callchain && callchain->enabled && !evsel->no_aux_samples)
-		perf_evsel__config_callchain(evsel, opts, callchain);
+		evsel__config_callchain(evsel, opts, callchain);
 
 	if (opts->sample_intr_regs) {
 		attr->sample_regs_intr = opts->sample_intr_regs;
-		perf_evsel__set_sample_bit(evsel, REGS_INTR);
+		evsel__set_sample_bit(evsel, REGS_INTR);
 	}
 
 	if (opts->sample_user_regs) {
 		attr->sample_regs_user |= opts->sample_user_regs;
-		perf_evsel__set_sample_bit(evsel, REGS_USER);
+		evsel__set_sample_bit(evsel, REGS_USER);
 	}
 
 	if (target__has_cpu(&opts->target) || opts->sample_cpu)
-		perf_evsel__set_sample_bit(evsel, CPU);
+		evsel__set_sample_bit(evsel, CPU);
 
 	/*
 	 * When the user explicitly disabled time don't force it here.
@@ -1068,31 +1044,31 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	    (!perf_missing_features.sample_id_all &&
 	    (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu ||
 	     opts->sample_time_set)))
-		perf_evsel__set_sample_bit(evsel, TIME);
+		evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples && !evsel->no_aux_samples) {
-		perf_evsel__set_sample_bit(evsel, TIME);
-		perf_evsel__set_sample_bit(evsel, RAW);
-		perf_evsel__set_sample_bit(evsel, CPU);
+		evsel__set_sample_bit(evsel, TIME);
+		evsel__set_sample_bit(evsel, RAW);
+		evsel__set_sample_bit(evsel, CPU);
 	}
 
 	if (opts->sample_address)
-		perf_evsel__set_sample_bit(evsel, DATA_SRC);
+		evsel__set_sample_bit(evsel, DATA_SRC);
 
 	if (opts->sample_phys_addr)
-		perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
+		evsel__set_sample_bit(evsel, PHYS_ADDR);
 
 	if (opts->no_buffering) {
 		attr->watermark = 0;
 		attr->wakeup_events = 1;
 	}
 	if (opts->branch_stack && !evsel->no_aux_samples) {
-		perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
+		evsel__set_sample_bit(evsel, BRANCH_STACK);
 		attr->branch_sample_type = opts->branch_stack;
 	}
 
 	if (opts->sample_weight)
-		perf_evsel__set_sample_bit(evsel, WEIGHT);
+		evsel__set_sample_bit(evsel, WEIGHT);
 
 	attr->task  = track;
 	attr->mmap  = track;
@@ -1106,14 +1082,14 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 
 	if (opts->record_cgroup) {
 		attr->cgroup = track && !perf_missing_features.cgroup;
-		perf_evsel__set_sample_bit(evsel, CGROUP);
+		evsel__set_sample_bit(evsel, CGROUP);
 	}
 
 	if (opts->record_switch_events)
 		attr->context_switch = track;
 
 	if (opts->sample_transaction)
-		perf_evsel__set_sample_bit(evsel, TRANSACTION);
+		evsel__set_sample_bit(evsel, TRANSACTION);
 
 	if (opts->running_time) {
 		evsel->core.attr.read_format |=
@@ -1127,15 +1103,15 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 * Disabling only independent events or group leaders,
 	 * keeping group members enabled.
 	 */
-	if (perf_evsel__is_group_leader(evsel))
+	if (evsel__is_group_leader(evsel))
 		attr->disabled = 1;
 
 	/*
 	 * Setting enable_on_exec for independent events and
 	 * group leaders for traced executed by perf.
 	 */
-	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
-		!opts->initial_delay)
+	if (target__none(&opts->target) && evsel__is_group_leader(evsel) &&
+	    !opts->initial_delay)
 		attr->enable_on_exec = 1;
 
 	if (evsel->immediate) {
@@ -1176,9 +1152,9 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	/* The --period option takes the precedence. */
 	if (opts->period_set) {
 		if (opts->period)
-			perf_evsel__set_sample_bit(evsel, PERIOD);
+			evsel__set_sample_bit(evsel, PERIOD);
 		else
-			perf_evsel__reset_sample_bit(evsel, PERIOD);
+			evsel__reset_sample_bit(evsel, PERIOD);
 	}
 
 	/*
@@ -1187,10 +1163,10 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 * if BRANCH_STACK bit is set.
 	 */
 	if (opts->initial_delay && is_dummy_event(evsel))
-		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
+		evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 
-int perf_evsel__set_filter(struct evsel *evsel, const char *filter)
+int evsel__set_filter(struct evsel *evsel, const char *filter)
 {
 	char *new_filter = strdup(filter);
 
@@ -1203,13 +1179,12 @@ int perf_evsel__set_filter(struct evsel *evsel, const char *filter)
 	return -1;
 }
 
-static int perf_evsel__append_filter(struct evsel *evsel,
-				     const char *fmt, const char *filter)
+static int evsel__append_filter(struct evsel *evsel, const char *fmt, const char *filter)
 {
 	char *new_filter;
 
 	if (evsel->filter == NULL)
-		return perf_evsel__set_filter(evsel, filter);
+		return evsel__set_filter(evsel, filter);
 
 	if (asprintf(&new_filter, fmt, evsel->filter, filter) > 0) {
 		free(evsel->filter);
@@ -1220,14 +1195,14 @@ static int perf_evsel__append_filter(struct evsel *evsel,
 	return -1;
 }
 
-int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter)
+int evsel__append_tp_filter(struct evsel *evsel, const char *filter)
 {
-	return perf_evsel__append_filter(evsel, "(%s) && (%s)", filter);
+	return evsel__append_filter(evsel, "(%s) && (%s)", filter);
 }
 
-int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter)
+int evsel__append_addr_filter(struct evsel *evsel, const char *filter)
 {
-	return perf_evsel__append_filter(evsel, "%s,%s", filter);
+	return evsel__append_filter(evsel, "%s,%s", filter);
 }
 
 /* Caller has to clear disabled after going through all CPUs. */
@@ -1278,7 +1253,7 @@ static void perf_evsel__free_config_terms(struct evsel *evsel)
 	}
 }
 
-void perf_evsel__exit(struct evsel *evsel)
+void evsel__exit(struct evsel *evsel)
 {
 	assert(list_empty(&evsel->core.node));
 	assert(evsel->evlist == NULL);
@@ -1298,12 +1273,12 @@ void perf_evsel__exit(struct evsel *evsel)
 
 void evsel__delete(struct evsel *evsel)
 {
-	perf_evsel__exit(evsel);
+	evsel__exit(evsel);
 	free(evsel);
 }
 
-void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
-				struct perf_counts_values *count)
+void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
+			   struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
 
@@ -1342,8 +1317,7 @@ void perf_counts_values__scale(struct perf_counts_values *count,
 		*pscaled = scaled;
 }
 
-static int
-perf_evsel__read_one(struct evsel *evsel, int cpu, int thread)
+static int evsel__read_one(struct evsel *evsel, int cpu, int thread)
 {
 	struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
 
@@ -1403,8 +1377,7 @@ perf_evsel__process_group_data(struct evsel *leader,
 	return 0;
 }
 
-static int
-perf_evsel__read_group(struct evsel *leader, int cpu, int thread)
+static int evsel__read_group(struct evsel *leader, int cpu, int thread)
 {
 	struct perf_stat_evsel *ps = leader->stats;
 	u64 read_format = leader->core.attr.read_format;
@@ -1414,7 +1387,7 @@ perf_evsel__read_group(struct evsel *leader, int cpu, int thread)
 	if (!(read_format & PERF_FORMAT_ID))
 		return -EINVAL;
 
-	if (!perf_evsel__is_group_leader(leader))
+	if (!evsel__is_group_leader(leader))
 		return -EINVAL;
 
 	if (!data) {
@@ -1434,18 +1407,17 @@ perf_evsel__read_group(struct evsel *leader, int cpu, int thread)
 	return perf_evsel__process_group_data(leader, cpu, thread, data);
 }
 
-int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread)
+int evsel__read_counter(struct evsel *evsel, int cpu, int thread)
 {
 	u64 read_format = evsel->core.attr.read_format;
 
 	if (read_format & PERF_FORMAT_GROUP)
-		return perf_evsel__read_group(evsel, cpu, thread);
-	else
-		return perf_evsel__read_one(evsel, cpu, thread);
+		return evsel__read_group(evsel, cpu, thread);
+
+	return evsel__read_one(evsel, cpu, thread);
 }
 
-int __perf_evsel__read_on_cpu(struct evsel *evsel,
-			      int cpu, int thread, bool scale)
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale)
 {
 	struct perf_counts_values count;
 	size_t nv = scale ? 3 : 1;
@@ -1459,7 +1431,7 @@ int __perf_evsel__read_on_cpu(struct evsel *evsel,
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
 		return -errno;
 
-	perf_evsel__compute_deltas(evsel, cpu, thread, &count);
+	evsel__compute_deltas(evsel, cpu, thread, &count);
 	perf_counts_values__scale(&count, scale, NULL);
 	*perf_counts(evsel->counts, cpu, thread) = count;
 	return 0;
@@ -1470,7 +1442,7 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread)
 	struct evsel *leader = evsel->leader;
 	int fd;
 
-	if (perf_evsel__is_group_leader(evsel))
+	if (evsel__is_group_leader(evsel))
 		return -1;
 
 	/*
@@ -1749,8 +1721,7 @@ retry_open:
 
 			/*
 			 * If we succeeded but had to kill clockid, fail and
-			 * have perf_evsel__open_strerror() print us a nice
-			 * error.
+			 * have evsel__open_strerror() print us a nice error.
 			 */
 			if (perf_missing_features.clockid ||
 			    perf_missing_features.clockid_wrong) {
@@ -1854,7 +1825,7 @@ try_fallback:
 	} else if (!perf_missing_features.group_read &&
 		    evsel->core.attr.inherit &&
 		   (evsel->core.attr.read_format & PERF_FORMAT_GROUP) &&
-		   perf_evsel__is_group_leader(evsel)) {
+		   evsel__is_group_leader(evsel)) {
 		perf_missing_features.group_read = true;
 		pr_debug2_peo("switching off group read\n");
 		goto fallback_missing_features;
@@ -1888,9 +1859,7 @@ void evsel__close(struct evsel *evsel)
 	perf_evsel__free_id(&evsel->core);
 }
 
-int perf_evsel__open_per_cpu(struct evsel *evsel,
-			     struct perf_cpu_map *cpus,
-			     int cpu)
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu)
 {
 	if (cpu == -1)
 		return evsel__open_cpu(evsel, cpus, NULL, 0,
@@ -1899,8 +1868,7 @@ int perf_evsel__open_per_cpu(struct evsel *evsel,
 	return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1);
 }
 
-int perf_evsel__open_per_thread(struct evsel *evsel,
-				struct perf_thread_map *threads)
+int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads)
 {
 	return evsel__open(evsel, NULL, threads);
 }
@@ -1995,8 +1963,8 @@ perf_event__check_size(union perf_event *event, unsigned int sample_size)
 	return 0;
 }
 
-int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
-			     struct perf_sample *data)
+int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
+			struct perf_sample *data)
 {
 	u64 type = evsel->core.attr.sample_type;
 	bool swapped = evsel->needs_swap;
@@ -2136,7 +2104,7 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 		}
 	}
 
-	if (evsel__has_callchain(evsel)) {
+	if (type & PERF_SAMPLE_CALLCHAIN) {
 		const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
 
 		OVERFLOW_CHECK_u64(array);
@@ -2190,7 +2158,7 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			return -EFAULT;
 
 		sz = data->branch_stack->nr * sizeof(struct branch_entry);
-		if (perf_evsel__has_branch_hw_idx(evsel))
+		if (evsel__has_branch_hw_idx(evsel))
 			sz += sizeof(u64);
 		else
 			data->no_hw_idx = true;
@@ -2298,9 +2266,8 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 	return 0;
 }
 
-int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
-				       union perf_event *event,
-				       u64 *timestamp)
+int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
+				  u64 *timestamp)
 {
 	u64 type = evsel->core.attr.sample_type;
 	const __u64 *array;
@@ -2342,15 +2309,14 @@ int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
 	return 0;
 }
 
-struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name)
+struct tep_format_field *evsel__field(struct evsel *evsel, const char *name)
 {
 	return tep_find_field(evsel->tp_format, name);
 }
 
-void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample,
-			 const char *name)
+void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name)
 {
-	struct tep_format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = evsel__field(evsel, name);
 	int offset;
 
 	if (!field)
@@ -2405,10 +2371,9 @@ u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sam
 	return 0;
 }
 
-u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample,
-		       const char *name)
+u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name)
 {
-	struct tep_format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = evsel__field(evsel, name);
 
 	if (!field)
 		return 0;
@@ -2416,8 +2381,7 @@ u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample,
 	return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
 }
 
-bool perf_evsel__fallback(struct evsel *evsel, int err,
-			  char *msg, size_t msgsize)
+bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize)
 {
 	int paranoid;
 
@@ -2442,10 +2406,14 @@ bool perf_evsel__fallback(struct evsel *evsel, int err,
 		return true;
 	} else if (err == EACCES && !evsel->core.attr.exclude_kernel &&
 		   (paranoid = perf_event_paranoid()) > 1) {
-		const char *name = perf_evsel__name(evsel);
+		const char *name = evsel__name(evsel);
 		char *new_name;
 		const char *sep = ":";
 
+		/* If event has exclude user then don't exclude kernel. */
+		if (evsel->core.attr.exclude_user)
+			return false;
+
 		/* Is there already the separator in the name. */
 		if (strchr(name, '/') ||
 		    strchr(name, ':'))
@@ -2505,8 +2473,8 @@ static bool find_process(const char *name)
 	return ret ? false : true;
 }
 
-int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
-			      int err, char *msg, size_t size)
+int evsel__open_strerror(struct evsel *evsel, struct target *target,
+			 int err, char *msg, size_t size)
 {
 	char sbuf[STRERR_BUFSIZE];
 	int printed = 0;
@@ -2516,28 +2484,26 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
 	case EACCES:
 		if (err == EPERM)
 			printed = scnprintf(msg, size,
-				"No permission to enable %s event.\n\n",
-				perf_evsel__name(evsel));
+				"No permission to enable %s event.\n\n", evsel__name(evsel));
 
 		return scnprintf(msg + printed, size - printed,
 		 "You may not have permission to collect %sstats.\n\n"
 		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
 		 "which controls use of the performance events system by\n"
-		 "unprivileged users (without CAP_SYS_ADMIN).\n\n"
+		 "unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).\n\n"
 		 "The current value is %d:\n\n"
 		 "  -1: Allow use of (almost) all events by all users\n"
 		 "      Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n"
-		 ">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n"
-		 "      Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n"
-		 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
-		 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n"
+		 ">= 0: Disallow ftrace function tracepoint by users without CAP_PERFMON or CAP_SYS_ADMIN\n"
+		 "      Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN\n"
+		 ">= 1: Disallow CPU event access by users without CAP_PERFMON or CAP_SYS_ADMIN\n"
+		 ">= 2: Disallow kernel profiling by users without CAP_PERFMON or CAP_SYS_ADMIN\n\n"
 		 "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n"
 		 "	kernel.perf_event_paranoid = -1\n" ,
 				 target->system_wide ? "system-wide " : "",
 				 perf_event_paranoid());
 	case ENOENT:
-		return scnprintf(msg, size, "The %s event is not supported.",
-				 perf_evsel__name(evsel));
+		return scnprintf(msg, size, "The %s event is not supported.", evsel__name(evsel));
 	case EMFILE:
 		return scnprintf(msg, size, "%s",
 			 "Too many events are opened.\n"
@@ -2561,7 +2527,7 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
 		if (evsel->core.attr.sample_period != 0)
 			return scnprintf(msg, size,
 	"%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'",
-					 perf_evsel__name(evsel));
+					 evsel__name(evsel));
 		if (evsel->core.attr.precise_ip)
 			return scnprintf(msg, size, "%s",
 	"\'precise\' request may not be supported. Try removing 'p' modifier.");
@@ -2594,11 +2560,10 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
 	return scnprintf(msg, size,
 	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
 	"/bin/dmesg | grep -i perf may provide additional information.\n",
-			 err, str_error_r(err, sbuf, sizeof(sbuf)),
-			 perf_evsel__name(evsel));
+			 err, str_error_r(err, sbuf, sizeof(sbuf)), evsel__name(evsel));
 }
 
-struct perf_env *perf_evsel__env(struct evsel *evsel)
+struct perf_env *evsel__env(struct evsel *evsel)
 {
 	if (evsel && evsel->evlist)
 		return evsel->evlist->env;
@@ -2623,7 +2588,7 @@ static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
 	return 0;
 }
 
-int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist)
+int evsel__store_ids(struct evsel *evsel, struct evlist *evlist)
 {
 	struct perf_cpu_map *cpus = evsel->core.cpus;
 	struct perf_thread_map *threads = evsel->core.threads;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 53187c501ee8..351c0aaf2a11 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -18,7 +18,7 @@ struct perf_counts;
 struct perf_stat_evsel;
 union perf_event;
 
-typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data);
+typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
 
 enum perf_tool_event {
 	PERF_TOOL_NONE		= 0,
@@ -101,9 +101,17 @@ struct evsel {
 	int			cpu_iter;
 	const char		*pmu_name;
 	struct {
-		perf_evsel__sb_cb_t	*cb;
-		void			*data;
+		evsel__sb_cb_t	*cb;
+		void		*data;
 	} side_band;
+	/*
+	 * For reporting purposes, an evsel sample can have a callchain
+	 * synthesized from AUX area data. Keep track of synthesized sample
+	 * types here. Note, the recorded sample_type cannot be changed because
+	 * it is needed to continue to parse events.
+	 * See also evsel__has_callchain().
+	 */
+	__u64			synth_sample_type;
 };
 
 struct perf_missing_features {
@@ -135,7 +143,7 @@ static inline struct perf_cpu_map *evsel__cpus(struct evsel *evsel)
 	return perf_evsel__cpus(&evsel->core);
 }
 
-static inline int perf_evsel__nr_cpus(struct evsel *evsel)
+static inline int evsel__nr_cpus(struct evsel *evsel)
 {
 	return evsel__cpus(evsel)->nr;
 }
@@ -143,13 +151,16 @@ static inline int perf_evsel__nr_cpus(struct evsel *evsel)
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, s8 *pscaled);
 
-void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
-				struct perf_counts_values *count);
+void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
+			   struct perf_counts_values *count);
 
 int perf_evsel__object_config(size_t object_size,
 			      int (*init)(struct evsel *evsel),
 			      void (*fini)(struct evsel *evsel));
 
+struct perf_pmu *evsel__find_pmu(struct evsel *evsel);
+bool evsel__is_aux_event(struct evsel *evsel);
+
 struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
 
 static inline struct evsel *evsel__new(struct perf_event_attr *attr)
@@ -172,22 +183,20 @@ struct evsel *perf_evsel__new_cycles(bool precise);
 struct tep_event *event_format__new(const char *sys, const char *name);
 
 void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx);
-void perf_evsel__exit(struct evsel *evsel);
+void evsel__exit(struct evsel *evsel);
 void evsel__delete(struct evsel *evsel);
 
 struct callchain_param;
 
-void perf_evsel__config(struct evsel *evsel,
-			struct record_opts *opts,
-			struct callchain_param *callchain);
-void perf_evsel__config_callchain(struct evsel *evsel,
-				  struct record_opts *opts,
-				  struct callchain_param *callchain);
+void evsel__config(struct evsel *evsel, struct record_opts *opts,
+		   struct callchain_param *callchain);
+void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts,
+			     struct callchain_param *callchain);
 
-int __perf_evsel__sample_size(u64 sample_type);
-void perf_evsel__calc_id_pos(struct evsel *evsel);
+int __evsel__sample_size(u64 sample_type);
+void evsel__calc_id_pos(struct evsel *evsel);
 
-bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
+bool evsel__is_cache_op_valid(u8 type, u8 op);
 
 #define PERF_EVSEL__MAX_ALIASES 8
 
@@ -199,177 +208,153 @@ extern const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
 					      [PERF_EVSEL__MAX_ALIASES];
 extern const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX];
 extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
-int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
-					    char *bf, size_t size);
-const char *perf_evsel__name(struct evsel *evsel);
+int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size);
+const char *evsel__name(struct evsel *evsel);
 
-const char *perf_evsel__group_name(struct evsel *evsel);
-int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size);
+const char *evsel__group_name(struct evsel *evsel);
+int evsel__group_desc(struct evsel *evsel, char *buf, size_t size);
 
-void __perf_evsel__set_sample_bit(struct evsel *evsel,
-				  enum perf_event_sample_format bit);
-void __perf_evsel__reset_sample_bit(struct evsel *evsel,
-				    enum perf_event_sample_format bit);
+void __evsel__set_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit);
+void __evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit);
 
-#define perf_evsel__set_sample_bit(evsel, bit) \
-	__perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit)
+#define evsel__set_sample_bit(evsel, bit) \
+	__evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit)
 
-#define perf_evsel__reset_sample_bit(evsel, bit) \
-	__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
+#define evsel__reset_sample_bit(evsel, bit) \
+	__evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
 
-void perf_evsel__set_sample_id(struct evsel *evsel,
-			       bool use_sample_identifier);
+void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier);
 
-int perf_evsel__set_filter(struct evsel *evsel, const char *filter);
-int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter);
-int perf_evsel__append_addr_filter(struct evsel *evsel,
-				   const char *filter);
+int evsel__set_filter(struct evsel *evsel, const char *filter);
+int evsel__append_tp_filter(struct evsel *evsel, const char *filter);
+int evsel__append_addr_filter(struct evsel *evsel, const char *filter);
 int evsel__enable_cpu(struct evsel *evsel, int cpu);
 int evsel__enable(struct evsel *evsel);
 int evsel__disable(struct evsel *evsel);
 int evsel__disable_cpu(struct evsel *evsel, int cpu);
 
-int perf_evsel__open_per_cpu(struct evsel *evsel,
-			     struct perf_cpu_map *cpus,
-			     int cpu);
-int perf_evsel__open_per_thread(struct evsel *evsel,
-				struct perf_thread_map *threads);
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu);
+int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads);
 int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads);
 void evsel__close(struct evsel *evsel);
 
 struct perf_sample;
 
-void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample,
-			 const char *name);
-u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample,
-		       const char *name);
+void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name);
+u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name);
 
-static inline char *perf_evsel__strval(struct evsel *evsel,
-				       struct perf_sample *sample,
-				       const char *name)
+static inline char *evsel__strval(struct evsel *evsel, struct perf_sample *sample, const char *name)
 {
-	return perf_evsel__rawptr(evsel, sample, name);
+	return evsel__rawptr(evsel, sample, name);
 }
 
 struct tep_format_field;
 
 u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap);
 
-struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name);
+struct tep_format_field *evsel__field(struct evsel *evsel, const char *name);
 
-#define perf_evsel__match(evsel, t, c)		\
+#define evsel__match(evsel, t, c)		\
 	(evsel->core.attr.type == PERF_TYPE_##t &&	\
 	 evsel->core.attr.config == PERF_COUNT_##c)
 
-static inline bool perf_evsel__match2(struct evsel *e1,
-				      struct evsel *e2)
+static inline bool evsel__match2(struct evsel *e1, struct evsel *e2)
 {
 	return (e1->core.attr.type == e2->core.attr.type) &&
 	       (e1->core.attr.config == e2->core.attr.config);
 }
 
-#define perf_evsel__cmp(a, b)			\
-	((a) &&					\
-	 (b) &&					\
-	 (a)->core.attr.type == (b)->core.attr.type &&	\
-	 (a)->core.attr.config == (b)->core.attr.config)
-
-int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread);
+int evsel__read_counter(struct evsel *evsel, int cpu, int thread);
 
-int __perf_evsel__read_on_cpu(struct evsel *evsel,
-			      int cpu, int thread, bool scale);
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale);
 
 /**
- * perf_evsel__read_on_cpu - Read out the results on a CPU and thread
+ * evsel__read_on_cpu - Read out the results on a CPU and thread
  *
  * @evsel - event selector to read value
  * @cpu - CPU of interest
  * @thread - thread of interest
  */
-static inline int perf_evsel__read_on_cpu(struct evsel *evsel,
-					  int cpu, int thread)
+static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread)
 {
-	return __perf_evsel__read_on_cpu(evsel, cpu, thread, false);
+	return __evsel__read_on_cpu(evsel, cpu, thread, false);
 }
 
 /**
- * perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
+ * evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
  *
  * @evsel - event selector to read value
  * @cpu - CPU of interest
  * @thread - thread of interest
  */
-static inline int perf_evsel__read_on_cpu_scaled(struct evsel *evsel,
-						 int cpu, int thread)
+static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu, int thread)
 {
-	return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
+	return __evsel__read_on_cpu(evsel, cpu, thread, true);
 }
 
-int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
-			     struct perf_sample *sample);
+int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
+			struct perf_sample *sample);
 
-int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
-				       union perf_event *event,
-				       u64 *timestamp);
+int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
+				  u64 *timestamp);
 
-static inline struct evsel *perf_evsel__next(struct evsel *evsel)
+static inline struct evsel *evsel__next(struct evsel *evsel)
 {
 	return list_entry(evsel->core.node.next, struct evsel, core.node);
 }
 
-static inline struct evsel *perf_evsel__prev(struct evsel *evsel)
+static inline struct evsel *evsel__prev(struct evsel *evsel)
 {
 	return list_entry(evsel->core.node.prev, struct evsel, core.node);
 }
 
 /**
- * perf_evsel__is_group_leader - Return whether given evsel is a leader event
+ * evsel__is_group_leader - Return whether given evsel is a leader event
  *
  * @evsel - evsel selector to be tested
  *
  * Return %true if @evsel is a group leader or a stand-alone event
  */
-static inline bool perf_evsel__is_group_leader(const struct evsel *evsel)
+static inline bool evsel__is_group_leader(const struct evsel *evsel)
 {
 	return evsel->leader == evsel;
 }
 
 /**
- * perf_evsel__is_group_event - Return whether given evsel is a group event
+ * evsel__is_group_event - Return whether given evsel is a group event
  *
  * @evsel - evsel selector to be tested
  *
  * Return %true iff event group view is enabled and @evsel is a actual group
  * leader which has other members in the group
  */
-static inline bool perf_evsel__is_group_event(struct evsel *evsel)
+static inline bool evsel__is_group_event(struct evsel *evsel)
 {
 	if (!symbol_conf.event_group)
 		return false;
 
-	return perf_evsel__is_group_leader(evsel) && evsel->core.nr_members > 1;
+	return evsel__is_group_leader(evsel) && evsel->core.nr_members > 1;
 }
 
-bool perf_evsel__is_function_event(struct evsel *evsel);
+bool evsel__is_function_event(struct evsel *evsel);
 
-static inline bool perf_evsel__is_bpf_output(struct evsel *evsel)
+static inline bool evsel__is_bpf_output(struct evsel *evsel)
 {
-	return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
+	return evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
 }
 
-static inline bool perf_evsel__is_clock(struct evsel *evsel)
+static inline bool evsel__is_clock(struct evsel *evsel)
 {
-	return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
-	       perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
+	return evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+	       evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
-bool perf_evsel__fallback(struct evsel *evsel, int err,
-			  char *msg, size_t msgsize);
-int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
-			      int err, char *msg, size_t size);
+bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize);
+int evsel__open_strerror(struct evsel *evsel, struct target *target,
+			 int err, char *msg, size_t size);
 
-static inline int perf_evsel__group_idx(struct evsel *evsel)
+static inline int evsel__group_idx(struct evsel *evsel)
 {
 	return evsel->idx - evsel->leader->idx;
 }
@@ -386,22 +371,37 @@ for ((_evsel) = _leader; 							\
      (_evsel) && (_evsel)->leader == (_leader);					\
      (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node))
 
-static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel)
+static inline bool evsel__has_branch_callstack(const struct evsel *evsel)
 {
 	return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
 }
 
-static inline bool perf_evsel__has_branch_hw_idx(const struct evsel *evsel)
+static inline bool evsel__has_branch_hw_idx(const struct evsel *evsel)
 {
 	return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
 }
 
 static inline bool evsel__has_callchain(const struct evsel *evsel)
 {
-	return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
+	/*
+	 * For reporting purposes, an evsel sample can have a recorded callchain
+	 * or a callchain synthesized from AUX area data.
+	 */
+	return evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN ||
+	       evsel->synth_sample_type & PERF_SAMPLE_CALLCHAIN;
+}
+
+static inline bool evsel__has_br_stack(const struct evsel *evsel)
+{
+	/*
+	 * For reporting purposes, an evsel sample can have a recorded branch
+	 * stack or a branch stack synthesized from AUX area data.
+	 */
+	return evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK ||
+	       evsel->synth_sample_type & PERF_SAMPLE_BRANCH_STACK;
 }
 
-struct perf_env *perf_evsel__env(struct evsel *evsel);
+struct perf_env *evsel__env(struct evsel *evsel);
 
-int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
+int evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h
index e026ab67b008..f8938916577c 100644
--- a/tools/perf/util/evsel_config.h
+++ b/tools/perf/util/evsel_config.h
@@ -7,7 +7,7 @@
 
 /*
  * The 'struct perf_evsel_config_term' is used to pass event
- * specific configuration data to perf_evsel__config routine.
+ * specific configuration data to evsel__config routine.
  * It is allocated within event parsing and attached to
  * perf_evsel::config_terms list head.
 */
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 3b4842840db0..99aed708bd5a 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -44,22 +44,22 @@ int perf_evsel__fprintf(struct evsel *evsel,
 	if (details->event_group) {
 		struct evsel *pos;
 
-		if (!perf_evsel__is_group_leader(evsel))
+		if (!evsel__is_group_leader(evsel))
 			return 0;
 
 		if (evsel->core.nr_members > 1)
 			printed += fprintf(fp, "%s{", evsel->group_name ?: "");
 
-		printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+		printed += fprintf(fp, "%s", evsel__name(evsel));
 		for_each_group_member(pos, evsel)
-			printed += fprintf(fp, ",%s", perf_evsel__name(pos));
+			printed += fprintf(fp, ",%s", evsel__name(pos));
 
 		if (evsel->core.nr_members > 1)
 			printed += fprintf(fp, "}");
 		goto out;
 	}
 
-	printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+	printed += fprintf(fp, "%s", evsel__name(evsel));
 
 	if (details->verbose) {
 		printed += perf_event_attr__fprintf(fp, &evsel->core.attr,
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index fd192ddf93c1..aa631e37ad1e 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -3,7 +3,6 @@
 #include <assert.h>
 #include "expr.h"
 #include "expr-bison.h"
-#define YY_EXTRA_TYPE int
 #include "expr-flex.h"
 
 #ifdef PARSER_DEBUG
@@ -11,7 +10,7 @@ extern int expr_debug;
 #endif
 
 /* Caller must make sure id is allocated */
-void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
+void expr__add_id(struct expr_parse_ctx *ctx, const char *name, double val)
 {
 	int idx;
 
@@ -21,20 +20,24 @@ void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
 	ctx->ids[idx].val = val;
 }
 
-void expr__ctx_init(struct parse_ctx *ctx)
+void expr__ctx_init(struct expr_parse_ctx *ctx)
 {
 	ctx->num_ids = 0;
 }
 
 static int
-__expr__parse(double *val, struct parse_ctx *ctx, const char *expr,
-	      int start)
+__expr__parse(double *val, struct expr_parse_ctx *ctx, const char *expr,
+	      int start, int runtime)
 {
+	struct expr_scanner_ctx scanner_ctx = {
+		.start_token = start,
+		.runtime = runtime,
+	};
 	YY_BUFFER_STATE buffer;
 	void *scanner;
 	int ret;
 
-	ret = expr_lex_init_extra(start, &scanner);
+	ret = expr_lex_init_extra(&scanner_ctx, &scanner);
 	if (ret)
 		return ret;
 
@@ -52,9 +55,9 @@ __expr__parse(double *val, struct parse_ctx *ctx, const char *expr,
 	return ret;
 }
 
-int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr)
+int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int runtime)
 {
-	return __expr__parse(final_val, ctx, expr, EXPR_PARSE) ? -1 : 0;
+	return __expr__parse(final_val, ctx, expr, EXPR_PARSE, runtime) ? -1 : 0;
 }
 
 static bool
@@ -72,13 +75,13 @@ already_seen(const char *val, const char *one, const char **other,
 }
 
 int expr__find_other(const char *expr, const char *one, const char ***other,
-		     int *num_other)
+		     int *num_other, int runtime)
 {
 	int err, i = 0, j = 0;
-	struct parse_ctx ctx;
+	struct expr_parse_ctx ctx;
 
 	expr__ctx_init(&ctx);
-	err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER);
+	err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER, runtime);
 	if (err)
 		return -1;
 
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 9377538f4097..87d627bb699b 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -5,20 +5,25 @@
 #define EXPR_MAX_OTHER 20
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
-struct parse_id {
+struct expr_parse_id {
 	const char *name;
 	double val;
 };
 
-struct parse_ctx {
+struct expr_parse_ctx {
 	int num_ids;
-	struct parse_id ids[MAX_PARSE_ID];
+	struct expr_parse_id ids[MAX_PARSE_ID];
 };
 
-void expr__ctx_init(struct parse_ctx *ctx);
-void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
-int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
+struct expr_scanner_ctx {
+	int start_token;
+	int runtime;
+};
+
+void expr__ctx_init(struct expr_parse_ctx *ctx);
+void expr__add_id(struct expr_parse_ctx *ctx, const char *id, double val);
+int expr__parse(double *final_val, struct expr_parse_ctx *ctx, const char *expr, int runtime);
 int expr__find_other(const char *expr, const char *one, const char ***other,
-		int *num_other);
+		int *num_other, int runtime);
 
 #endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index eaad29243c23..74b9b59b1aa5 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -35,7 +35,7 @@ static int value(yyscan_t scanner, int base)
  * Allow @ instead of / to be able to specify pmu/event/ without
  * conflicts with normal division.
  */
-static char *normalize(char *str)
+static char *normalize(char *str, int runtime)
 {
 	char *ret = str;
 	char *dst = str;
@@ -45,6 +45,19 @@ static char *normalize(char *str)
 			*dst++ = '/';
 		else if (*str == '\\')
 			*dst++ = *++str;
+		 else if (*str == '?') {
+			char *paramval;
+			int i = 0;
+			int size = asprintf(&paramval, "%d", runtime);
+
+			if (size < 0)
+				*dst++ = '0';
+			else {
+				while (i < size)
+					*dst++ = paramval[i++];
+				free(paramval);
+			}
+		}
 		else
 			*dst++ = *str;
 		str++;
@@ -54,16 +67,16 @@ static char *normalize(char *str)
 	return ret;
 }
 
-static int str(yyscan_t scanner, int token)
+static int str(yyscan_t scanner, int token, int runtime)
 {
 	YYSTYPE *yylval = expr_get_lval(scanner);
 	char *text = expr_get_text(scanner);
 
-	yylval->str = normalize(strdup(text));
+	yylval->str = normalize(strdup(text), runtime);
 	if (!yylval->str)
 		return EXPR_ERROR;
 
-	yylval->str = normalize(yylval->str);
+	yylval->str = normalize(yylval->str, runtime);
 	return token;
 }
 %}
@@ -72,17 +85,17 @@ number		[0-9]+
 
 sch		[-,=]
 spec		\\{sch}
-sym		[0-9a-zA-Z_\.:@]+
-symbol		{spec}*{sym}*{spec}*{sym}*
+sym		[0-9a-zA-Z_\.:@?]+
+symbol		{spec}*{sym}*{spec}*{sym}*{spec}*{sym}
 
 %%
-	{
-		int start_token;
+	struct expr_scanner_ctx *sctx = expr_get_extra(yyscanner);
 
-		start_token = expr_get_extra(yyscanner);
+	{
+		int start_token = sctx->start_token;
 
-		if (start_token) {
-			expr_set_extra(NULL, yyscanner);
+		if (sctx->start_token) {
+			sctx->start_token = 0;
 			return start_token;
 		}
 	}
@@ -93,7 +106,7 @@ if		{ return IF; }
 else		{ return ELSE; }
 #smt_on		{ return SMT_ON; }
 {number}	{ return value(yyscanner, 10); }
-{symbol}	{ return str(yyscanner, ID); }
+{symbol}	{ return str(yyscanner, ID, sctx->runtime); }
 "|"		{ return '|'; }
 "^"		{ return '^'; }
 "&"		{ return '&'; }
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 4720cbe79357..cd17486c1c5d 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -15,7 +15,7 @@
 %define api.pure full
 
 %parse-param { double *final_val }
-%parse-param { struct parse_ctx *ctx }
+%parse-param { struct expr_parse_ctx *ctx }
 %parse-param {void *scanner}
 %lex-param {void* scanner}
 
@@ -39,14 +39,14 @@
 
 %{
 static void expr_error(double *final_val __maybe_unused,
-		       struct parse_ctx *ctx __maybe_unused,
+		       struct expr_parse_ctx *ctx __maybe_unused,
 		       void *scanner,
 		       const char *s)
 {
 	pr_debug("%s\n", s);
 }
 
-static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
+static int lookup_id(struct expr_parse_ctx *ctx, char *id, double *val)
 {
 	int i;
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index acbd046bf95c..0ce47283a8a1 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -525,7 +525,7 @@ static int write_event_desc(struct feat_fd *ff,
 		/*
 		 * write event string as passed on cmdline
 		 */
-		ret = do_write_string(ff, perf_evsel__name(evsel));
+		ret = do_write_string(ff, evsel__name(evsel));
 		if (ret < 0)
 			return ret;
 		/*
@@ -783,8 +783,7 @@ static int write_group_desc(struct feat_fd *ff,
 		return ret;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (perf_evsel__is_group_leader(evsel) &&
-		    evsel->core.nr_members > 1) {
+		if (evsel__is_group_leader(evsel) && evsel->core.nr_members > 1) {
 			const char *name = evsel->group_name ?: "{anon_group}";
 			u32 leader_idx = evsel->idx;
 			u32 nr_members = evsel->core.nr_members;
@@ -1395,6 +1394,38 @@ static int write_compressed(struct feat_fd *ff __maybe_unused,
 	return do_write(ff, &(ff->ph->env.comp_mmap_len), sizeof(ff->ph->env.comp_mmap_len));
 }
 
+static int write_cpu_pmu_caps(struct feat_fd *ff,
+			      struct evlist *evlist __maybe_unused)
+{
+	struct perf_pmu *cpu_pmu = perf_pmu__find("cpu");
+	struct perf_pmu_caps *caps = NULL;
+	int nr_caps;
+	int ret;
+
+	if (!cpu_pmu)
+		return -ENOENT;
+
+	nr_caps = perf_pmu__caps_parse(cpu_pmu);
+	if (nr_caps < 0)
+		return nr_caps;
+
+	ret = do_write(ff, &nr_caps, sizeof(nr_caps));
+	if (ret < 0)
+		return ret;
+
+	list_for_each_entry(caps, &cpu_pmu->caps, list) {
+		ret = do_write_string(ff, caps->name);
+		if (ret < 0)
+			return ret;
+
+		ret = do_write_string(ff, caps->value);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
+}
+
 static void print_hostname(struct feat_fd *ff, FILE *fp)
 {
 	fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
@@ -1809,6 +1840,27 @@ static void print_compressed(struct feat_fd *ff, FILE *fp)
 		ff->ph->env.comp_level, ff->ph->env.comp_ratio);
 }
 
+static void print_cpu_pmu_caps(struct feat_fd *ff, FILE *fp)
+{
+	const char *delimiter = "# cpu pmu capabilities: ";
+	u32 nr_caps = ff->ph->env.nr_cpu_pmu_caps;
+	char *str;
+
+	if (!nr_caps) {
+		fprintf(fp, "# cpu pmu capabilities: not available\n");
+		return;
+	}
+
+	str = ff->ph->env.cpu_pmu_caps;
+	while (nr_caps--) {
+		fprintf(fp, "%s%s", delimiter, str);
+		delimiter = ", ";
+		str += strlen(str) + 1;
+	}
+
+	fprintf(fp, "\n");
+}
+
 static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)
 {
 	const char *delimiter = "# pmu mappings: ";
@@ -1854,14 +1906,12 @@ static void print_group_desc(struct feat_fd *ff, FILE *fp)
 	session = container_of(ff->ph, struct perf_session, header);
 
 	evlist__for_each_entry(session->evlist, evsel) {
-		if (perf_evsel__is_group_leader(evsel) &&
-		    evsel->core.nr_members > 1) {
-			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
-				perf_evsel__name(evsel));
+		if (evsel__is_group_leader(evsel) && evsel->core.nr_members > 1) {
+			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", evsel__name(evsel));
 
 			nr = evsel->core.nr_members - 1;
 		} else if (nr) {
-			fprintf(fp, ",%s", perf_evsel__name(evsel));
+			fprintf(fp, ",%s", evsel__name(evsel));
 
 			if (--nr == 0)
 				fprintf(fp, "}\n");
@@ -2846,6 +2896,60 @@ static int process_compressed(struct feat_fd *ff,
 	return 0;
 }
 
+static int process_cpu_pmu_caps(struct feat_fd *ff,
+				void *data __maybe_unused)
+{
+	char *name, *value;
+	struct strbuf sb;
+	u32 nr_caps;
+
+	if (do_read_u32(ff, &nr_caps))
+		return -1;
+
+	if (!nr_caps) {
+		pr_debug("cpu pmu capabilities not available\n");
+		return 0;
+	}
+
+	ff->ph->env.nr_cpu_pmu_caps = nr_caps;
+
+	if (strbuf_init(&sb, 128) < 0)
+		return -1;
+
+	while (nr_caps--) {
+		name = do_read_string(ff);
+		if (!name)
+			goto error;
+
+		value = do_read_string(ff);
+		if (!value)
+			goto free_name;
+
+		if (strbuf_addf(&sb, "%s=%s", name, value) < 0)
+			goto free_value;
+
+		/* include a NULL character at the end */
+		if (strbuf_add(&sb, "", 1) < 0)
+			goto free_value;
+
+		if (!strcmp(name, "branches"))
+			ff->ph->env.max_branches = atoi(value);
+
+		free(value);
+		free(name);
+	}
+	ff->ph->env.cpu_pmu_caps = strbuf_detach(&sb, NULL);
+	return 0;
+
+free_value:
+	free(value);
+free_name:
+	free(name);
+error:
+	strbuf_release(&sb);
+	return -1;
+}
+
 #define FEAT_OPR(n, func, __full_only) \
 	[HEADER_##n] = {					\
 		.name	    = __stringify(n),			\
@@ -2903,6 +3007,7 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(BPF_PROG_INFO, bpf_prog_info,  false),
 	FEAT_OPR(BPF_BTF,       bpf_btf,        false),
 	FEAT_OPR(COMPRESSED,	compressed,	false),
+	FEAT_OPR(CPU_PMU_CAPS,	cpu_pmu_caps,	false),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 840f95cee349..650bd1c7a99b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -43,6 +43,7 @@ enum {
 	HEADER_BPF_PROG_INFO,
 	HEADER_BPF_BTF,
 	HEADER_COMPRESSED,
+	HEADER_CPU_PMU_CAPS,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 283a69ff6a3d..12b65d00cf65 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1070,6 +1070,20 @@ iter_next_cumulative_entry(struct hist_entry_iter *iter,
 	return fill_callchain_info(al, node, iter->hide_unresolved);
 }
 
+static bool
+hist_entry__fast__sym_diff(struct hist_entry *left,
+			   struct hist_entry *right)
+{
+	struct symbol *sym_l = left->ms.sym;
+	struct symbol *sym_r = right->ms.sym;
+
+	if (!sym_l && !sym_r)
+		return left->ip != right->ip;
+
+	return !!_sort__sym_cmp(sym_l, sym_r);
+}
+
+
 static int
 iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 			       struct addr_location *al)
@@ -1096,6 +1110,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 	};
 	int i;
 	struct callchain_cursor cursor;
+	bool fast = hists__has(he_tmp.hists, sym);
 
 	callchain_cursor_snapshot(&cursor, &callchain_cursor);
 
@@ -1106,6 +1121,14 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 	 * It's possible that it has cycles or recursive calls.
 	 */
 	for (i = 0; i < iter->curr; i++) {
+		/*
+		 * For most cases, there are no duplicate entries in callchain.
+		 * The symbols are usually different. Do a quick check for
+		 * symbols first.
+		 */
+		if (fast && hist_entry__fast__sym_diff(he_cache[i], &he_tmp))
+			continue;
+
 		if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
 			/* to avoid calling callback function */
 			iter->he = NULL;
@@ -2637,7 +2660,7 @@ size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp)
 	size_t ret = 0;
 
 	evlist__for_each_entry(evlist, pos) {
-		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
+		ret += fprintf(fp, "%s stats:\n", evsel__name(pos));
 		ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp);
 	}
 
@@ -2661,7 +2684,7 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh
 	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 	u64 nr_events = hists->stats.total_period;
 	struct evsel *evsel = hists_to_evsel(hists);
-	const char *ev_name = perf_evsel__name(evsel);
+	const char *ev_name = evsel__name(evsel);
 	char buf[512], sample_freq_str[64] = "";
 	size_t buflen = sizeof(buf);
 	char ref[30] = " show reference callgraph, ";
@@ -2672,10 +2695,10 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh
 		nr_events = hists->stats.total_non_filtered_period;
 	}
 
-	if (perf_evsel__is_group_event(evsel)) {
+	if (evsel__is_group_event(evsel)) {
 		struct evsel *pos;
 
-		perf_evsel__group_desc(evsel, buf, buflen);
+		evsel__group_desc(evsel, buf, buflen);
 		ev_name = buf;
 
 		for_each_group_member(pos, evsel) {
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 34cb380d19a3..af1e78d76228 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -432,7 +432,7 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 					    le64_to_cpu(branch->from),
 					    le64_to_cpu(branch->to),
 					    btsq->intel_pt_insn.length,
-					    buffer->buffer_nr + 1);
+					    buffer->buffer_nr + 1, true, 0, 0);
 		if (filter && !(filter & btsq->sample_flags))
 			continue;
 		err = intel_bts_synth_branch_sample(btsq, branch);
@@ -728,6 +728,15 @@ static void intel_bts_free(struct perf_session *session)
 	free(bts);
 }
 
+static bool intel_bts_evsel_is_auxtrace(struct perf_session *session,
+					struct evsel *evsel)
+{
+	struct intel_bts *bts = container_of(session->auxtrace, struct intel_bts,
+					     auxtrace);
+
+	return evsel->core.attr.type == bts->pmu_type;
+}
+
 struct intel_bts_synth {
 	struct perf_tool dummy_tool;
 	struct perf_session *session;
@@ -816,10 +825,10 @@ static int intel_bts_synth_events(struct intel_bts *bts,
 		bts->branches_id = id;
 		/*
 		 * We only use sample types from PERF_SAMPLE_MASK so we can use
-		 * __perf_evsel__sample_size() here.
+		 * __evsel__sample_size() here.
 		 */
 		bts->branches_event_size = sizeof(struct perf_record_sample) +
-				__perf_evsel__sample_size(attr.sample_type);
+					   __evsel__sample_size(attr.sample_type);
 	}
 
 	return 0;
@@ -883,6 +892,7 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
 	bts->auxtrace.flush_events = intel_bts_flush;
 	bts->auxtrace.free_events = intel_bts_free_events;
 	bts->auxtrace.free = intel_bts_free;
+	bts->auxtrace.evsel_is_auxtrace = intel_bts_evsel_is_auxtrace;
 	session->auxtrace = &bts->auxtrace;
 
 	intel_bts_print_info(&auxtrace_info->priv[0], INTEL_BTS_PMU_TYPE,
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index 0ccf10a0bf44..4ce109993e74 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -552,7 +552,7 @@ static int intel_pt_do_get_packet(const unsigned char *buf, size_t len,
 		break;
 	default:
 		break;
-	};
+	}
 
 	if (!(byte & BIT(0))) {
 		if (byte == 0)
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 23c8289c2472..f17b1e769ae4 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -33,6 +33,7 @@
 #include "tsc.h"
 #include "intel-pt.h"
 #include "config.h"
+#include "util/perf_api_probe.h"
 #include "util/synthetic-events.h"
 #include "time-utils.h"
 
@@ -68,6 +69,10 @@ struct intel_pt {
 	bool est_tsc;
 	bool sync_switch;
 	bool mispred_all;
+	bool use_thread_stack;
+	bool callstack;
+	unsigned int br_stack_sz;
+	unsigned int br_stack_sz_plus;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -124,6 +129,9 @@ struct intel_pt {
 
 	struct range *time_ranges;
 	unsigned int range_cnt;
+
+	struct ip_callchain *chain;
+	struct branch_stack *br_stack;
 };
 
 enum switch_state {
@@ -143,8 +151,6 @@ struct intel_pt_queue {
 	const struct intel_pt_state *state;
 	struct ip_callchain *chain;
 	struct branch_stack *last_branch;
-	struct branch_stack *last_branch_rb;
-	size_t last_branch_pos;
 	union perf_event *event_buf;
 	bool on_heap;
 	bool stop;
@@ -868,6 +874,83 @@ static u64 intel_pt_ns_to_ticks(const struct intel_pt *pt, u64 ns)
 		pt->tc.time_mult;
 }
 
+static struct ip_callchain *intel_pt_alloc_chain(struct intel_pt *pt)
+{
+	size_t sz = sizeof(struct ip_callchain);
+
+	/* Add 1 to callchain_sz for callchain context */
+	sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
+	return zalloc(sz);
+}
+
+static int intel_pt_callchain_init(struct intel_pt *pt)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (!(evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN))
+			evsel->synth_sample_type |= PERF_SAMPLE_CALLCHAIN;
+	}
+
+	pt->chain = intel_pt_alloc_chain(pt);
+	if (!pt->chain)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void intel_pt_add_callchain(struct intel_pt *pt,
+				   struct perf_sample *sample)
+{
+	struct thread *thread = machine__findnew_thread(pt->machine,
+							sample->pid,
+							sample->tid);
+
+	thread_stack__sample_late(thread, sample->cpu, pt->chain,
+				  pt->synth_opts.callchain_sz + 1, sample->ip,
+				  pt->kernel_start);
+
+	sample->callchain = pt->chain;
+}
+
+static struct branch_stack *intel_pt_alloc_br_stack(struct intel_pt *pt)
+{
+	size_t sz = sizeof(struct branch_stack);
+
+	sz += pt->br_stack_sz * sizeof(struct branch_entry);
+	return zalloc(sz);
+}
+
+static int intel_pt_br_stack_init(struct intel_pt *pt)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (!(evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK))
+			evsel->synth_sample_type |= PERF_SAMPLE_BRANCH_STACK;
+	}
+
+	pt->br_stack = intel_pt_alloc_br_stack(pt);
+	if (!pt->br_stack)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void intel_pt_add_br_stack(struct intel_pt *pt,
+				  struct perf_sample *sample)
+{
+	struct thread *thread = machine__findnew_thread(pt->machine,
+							sample->pid,
+							sample->tid);
+
+	thread_stack__br_sample_late(thread, sample->cpu, pt->br_stack,
+				     pt->br_stack_sz, sample->ip,
+				     pt->kernel_start);
+
+	sample->branch_stack = pt->br_stack;
+}
+
 static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 						   unsigned int queue_nr)
 {
@@ -880,26 +963,15 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 		return NULL;
 
 	if (pt->synth_opts.callchain) {
-		size_t sz = sizeof(struct ip_callchain);
-
-		/* Add 1 to callchain_sz for callchain context */
-		sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
-		ptq->chain = zalloc(sz);
+		ptq->chain = intel_pt_alloc_chain(pt);
 		if (!ptq->chain)
 			goto out_free;
 	}
 
 	if (pt->synth_opts.last_branch) {
-		size_t sz = sizeof(struct branch_stack);
-
-		sz += pt->synth_opts.last_branch_sz *
-		      sizeof(struct branch_entry);
-		ptq->last_branch = zalloc(sz);
+		ptq->last_branch = intel_pt_alloc_br_stack(pt);
 		if (!ptq->last_branch)
 			goto out_free;
-		ptq->last_branch_rb = zalloc(sz);
-		if (!ptq->last_branch_rb)
-			goto out_free;
 	}
 
 	ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
@@ -968,7 +1040,6 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 out_free:
 	zfree(&ptq->event_buf);
 	zfree(&ptq->last_branch);
-	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 	return NULL;
@@ -984,7 +1055,6 @@ static void intel_pt_free_queue(void *priv)
 	intel_pt_decoder_free(ptq->decoder);
 	zfree(&ptq->event_buf);
 	zfree(&ptq->last_branch);
-	zfree(&ptq->last_branch_rb);
 	zfree(&ptq->chain);
 	free(ptq);
 }
@@ -1152,58 +1222,6 @@ static int intel_pt_setup_queues(struct intel_pt *pt)
 	return 0;
 }
 
-static inline void intel_pt_copy_last_branch_rb(struct intel_pt_queue *ptq)
-{
-	struct branch_stack *bs_src = ptq->last_branch_rb;
-	struct branch_stack *bs_dst = ptq->last_branch;
-	size_t nr = 0;
-
-	bs_dst->nr = bs_src->nr;
-
-	if (!bs_src->nr)
-		return;
-
-	nr = ptq->pt->synth_opts.last_branch_sz - ptq->last_branch_pos;
-	memcpy(&bs_dst->entries[0],
-	       &bs_src->entries[ptq->last_branch_pos],
-	       sizeof(struct branch_entry) * nr);
-
-	if (bs_src->nr >= ptq->pt->synth_opts.last_branch_sz) {
-		memcpy(&bs_dst->entries[nr],
-		       &bs_src->entries[0],
-		       sizeof(struct branch_entry) * ptq->last_branch_pos);
-	}
-}
-
-static inline void intel_pt_reset_last_branch_rb(struct intel_pt_queue *ptq)
-{
-	ptq->last_branch_pos = 0;
-	ptq->last_branch_rb->nr = 0;
-}
-
-static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq)
-{
-	const struct intel_pt_state *state = ptq->state;
-	struct branch_stack *bs = ptq->last_branch_rb;
-	struct branch_entry *be;
-
-	if (!ptq->last_branch_pos)
-		ptq->last_branch_pos = ptq->pt->synth_opts.last_branch_sz;
-
-	ptq->last_branch_pos -= 1;
-
-	be              = &bs->entries[ptq->last_branch_pos];
-	be->from        = state->from_ip;
-	be->to          = state->to_ip;
-	be->flags.abort = !!(state->flags & INTEL_PT_ABORT_TX);
-	be->flags.in_tx = !!(state->flags & INTEL_PT_IN_TX);
-	/* No support for mispredict */
-	be->flags.mispred = ptq->pt->mispred_all;
-
-	if (bs->nr < ptq->pt->synth_opts.last_branch_sz)
-		bs->nr += 1;
-}
-
 static inline bool intel_pt_skip_event(struct intel_pt *pt)
 {
 	return pt->synth_opts.initial_skip &&
@@ -1271,9 +1289,9 @@ static inline int intel_pt_opt_inject(struct intel_pt *pt,
 	return intel_pt_inject_event(event, sample, type);
 }
 
-static int intel_pt_deliver_synth_b_event(struct intel_pt *pt,
-					  union perf_event *event,
-					  struct perf_sample *sample, u64 type)
+static int intel_pt_deliver_synth_event(struct intel_pt *pt,
+					union perf_event *event,
+					struct perf_sample *sample, u64 type)
 {
 	int ret;
 
@@ -1333,8 +1351,8 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 		ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
 	}
 
-	return intel_pt_deliver_synth_b_event(pt, event, &sample,
-					      pt->branches_sample_type);
+	return intel_pt_deliver_synth_event(pt, event, &sample,
+					    pt->branches_sample_type);
 }
 
 static void intel_pt_prep_sample(struct intel_pt *pt,
@@ -1352,27 +1370,12 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 	}
 
 	if (pt->synth_opts.last_branch) {
-		intel_pt_copy_last_branch_rb(ptq);
+		thread_stack__br_sample(ptq->thread, ptq->cpu, ptq->last_branch,
+					pt->br_stack_sz);
 		sample->branch_stack = ptq->last_branch;
 	}
 }
 
-static inline int intel_pt_deliver_synth_event(struct intel_pt *pt,
-					       struct intel_pt_queue *ptq,
-					       union perf_event *event,
-					       struct perf_sample *sample,
-					       u64 type)
-{
-	int ret;
-
-	ret = intel_pt_deliver_synth_b_event(pt, event, sample, type);
-
-	if (pt->synth_opts.last_branch)
-		intel_pt_reset_last_branch_rb(ptq);
-
-	return ret;
-}
-
 static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 {
 	struct intel_pt *pt = ptq->pt;
@@ -1397,7 +1400,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 
 	ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->instructions_sample_type);
 }
 
@@ -1415,7 +1418,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 	sample.id = ptq->pt->transactions_id;
 	sample.stream_id = ptq->pt->transactions_id;
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->transactions_sample_type);
 }
 
@@ -1456,7 +1459,7 @@ static int intel_pt_synth_ptwrite_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->ptwrites_sample_type);
 }
 
@@ -1486,7 +1489,7 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1511,7 +1514,7 @@ static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1536,7 +1539,7 @@ static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1561,7 +1564,7 @@ static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1586,7 +1589,7 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
 	sample.raw_size = perf_synth__raw_size(raw);
 	sample.raw_data = perf_synth__raw_data(&raw);
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
+	return intel_pt_deliver_synth_event(pt, event, &sample,
 					    pt->pwr_events_sample_type);
 }
 
@@ -1680,15 +1683,14 @@ static u64 intel_pt_lbr_flags(u64 info)
 	union {
 		struct branch_flags flags;
 		u64 result;
-	} u = {
-		.flags = {
-			.mispred	= !!(info & LBR_INFO_MISPRED),
-			.predicted	= !(info & LBR_INFO_MISPRED),
-			.in_tx		= !!(info & LBR_INFO_IN_TX),
-			.abort		= !!(info & LBR_INFO_ABORT),
-			.cycles		= info & LBR_INFO_CYCLES,
-		}
-	};
+	} u;
+
+	u.result	  = 0;
+	u.flags.mispred	  = !!(info & LBR_INFO_MISPRED);
+	u.flags.predicted = !(info & LBR_INFO_MISPRED);
+	u.flags.in_tx	  = !!(info & LBR_INFO_IN_TX);
+	u.flags.abort	  = !!(info & LBR_INFO_ABORT);
+	u.flags.cycles	  = info & LBR_INFO_CYCLES;
 
 	return u.result;
 }
@@ -1807,7 +1809,9 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 			intel_pt_add_lbrs(&br.br_stack, items);
 			sample.branch_stack = &br.br_stack;
 		} else if (pt->synth_opts.last_branch) {
-			intel_pt_copy_last_branch_rb(ptq);
+			thread_stack__br_sample(ptq->thread, ptq->cpu,
+						ptq->last_branch,
+						pt->br_stack_sz);
 			sample.branch_stack = ptq->last_branch;
 		} else {
 			br.br_stack.nr = 0;
@@ -1842,7 +1846,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 		sample.transaction = txn;
 	}
 
-	return intel_pt_deliver_synth_event(pt, ptq, event, &sample, sample_type);
+	return intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
 }
 
 static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
@@ -1992,12 +1996,15 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (!(state->type & INTEL_PT_BRANCH))
 		return 0;
 
-	if (pt->synth_opts.callchain || pt->synth_opts.thread_stack)
-		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
-				    state->to_ip, ptq->insn_len,
-				    state->trace_nr);
-	else
+	if (pt->use_thread_stack) {
+		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags,
+				    state->from_ip, state->to_ip, ptq->insn_len,
+				    state->trace_nr, pt->callstack,
+				    pt->br_stack_sz_plus,
+				    pt->mispred_all);
+	} else {
 		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
+	}
 
 	if (pt->sample_branches) {
 		err = intel_pt_synth_branch_sample(ptq);
@@ -2005,9 +2012,6 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 			return err;
 	}
 
-	if (pt->synth_opts.last_branch)
-		intel_pt_update_last_branch_rb(ptq);
-
 	if (!ptq->sync_switch)
 		return 0;
 
@@ -2484,7 +2488,7 @@ static int intel_pt_process_switch(struct intel_pt *pt,
 	if (evsel != pt->switch_evsel)
 		return 0;
 
-	tid = perf_evsel__intval(evsel, sample, "next_pid");
+	tid = evsel__intval(evsel, sample, "next_pid");
 	cpu = sample->cpu;
 
 	intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
@@ -2639,6 +2643,13 @@ static int intel_pt_process_event(struct perf_session *session,
 	if (err)
 		return err;
 
+	if (event->header.type == PERF_RECORD_SAMPLE) {
+		if (pt->synth_opts.add_callchain && !sample->callchain)
+			intel_pt_add_callchain(pt, sample);
+		if (pt->synth_opts.add_last_branch && !sample->branch_stack)
+			intel_pt_add_br_stack(pt, sample);
+	}
+
 	if (event->header.type == PERF_RECORD_AUX &&
 	    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED) &&
 	    pt->synth_opts.errors) {
@@ -2710,11 +2721,21 @@ static void intel_pt_free(struct perf_session *session)
 	session->auxtrace = NULL;
 	thread__put(pt->unknown_thread);
 	addr_filters__exit(&pt->filts);
+	zfree(&pt->chain);
 	zfree(&pt->filter);
 	zfree(&pt->time_ranges);
 	free(pt);
 }
 
+static bool intel_pt_evsel_is_auxtrace(struct perf_session *session,
+				       struct evsel *evsel)
+{
+	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+					   auxtrace);
+
+	return evsel->core.attr.type == pt->pmu_type;
+}
+
 static int intel_pt_process_auxtrace_event(struct perf_session *session,
 					   union perf_event *event,
 					   struct perf_tool *tool __maybe_unused)
@@ -3016,7 +3037,7 @@ static struct evsel *intel_pt_find_sched_switch(struct evlist *evlist)
 	struct evsel *evsel;
 
 	evlist__for_each_entry_reverse(evlist, evsel) {
-		const char *name = perf_evsel__name(evsel);
+		const char *name = evsel__name(evsel);
 
 		if (!strcmp(name, "sched:sched_switch"))
 			return evsel;
@@ -3310,6 +3331,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	pt->auxtrace.flush_events = intel_pt_flush;
 	pt->auxtrace.free_events = intel_pt_free_events;
 	pt->auxtrace.free = intel_pt_free;
+	pt->auxtrace.evsel_is_auxtrace = intel_pt_evsel_is_auxtrace;
 	session->auxtrace = &pt->auxtrace;
 
 	if (dump_trace)
@@ -3338,6 +3360,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 		    !session->itrace_synth_opts->inject) {
 			pt->synth_opts.branches = false;
 			pt->synth_opts.callchain = true;
+			pt->synth_opts.add_callchain = true;
 		}
 		pt->synth_opts.thread_stack =
 				session->itrace_synth_opts->thread_stack;
@@ -3370,14 +3393,54 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 		pt->branches_filter |= PERF_IP_FLAG_RETURN |
 				       PERF_IP_FLAG_TRACE_BEGIN;
 
-	if (pt->synth_opts.callchain && !symbol_conf.use_callchain) {
+	if ((pt->synth_opts.callchain || pt->synth_opts.add_callchain) &&
+	    !symbol_conf.use_callchain) {
 		symbol_conf.use_callchain = true;
 		if (callchain_register_param(&callchain_param) < 0) {
 			symbol_conf.use_callchain = false;
 			pt->synth_opts.callchain = false;
+			pt->synth_opts.add_callchain = false;
 		}
 	}
 
+	if (pt->synth_opts.add_callchain) {
+		err = intel_pt_callchain_init(pt);
+		if (err)
+			goto err_delete_thread;
+	}
+
+	if (pt->synth_opts.last_branch || pt->synth_opts.add_last_branch) {
+		pt->br_stack_sz = pt->synth_opts.last_branch_sz;
+		pt->br_stack_sz_plus = pt->br_stack_sz;
+	}
+
+	if (pt->synth_opts.add_last_branch) {
+		err = intel_pt_br_stack_init(pt);
+		if (err)
+			goto err_delete_thread;
+		/*
+		 * Additional branch stack size to cater for tracing from the
+		 * actual sample ip to where the sample time is recorded.
+		 * Measured at about 200 branches, but generously set to 1024.
+		 * If kernel space is not being traced, then add just 1 for the
+		 * branch to kernel space.
+		 */
+		if (intel_pt_tracing_kernel(pt))
+			pt->br_stack_sz_plus += 1024;
+		else
+			pt->br_stack_sz_plus += 1;
+	}
+
+	pt->use_thread_stack = pt->synth_opts.callchain ||
+			       pt->synth_opts.add_callchain ||
+			       pt->synth_opts.thread_stack ||
+			       pt->synth_opts.last_branch ||
+			       pt->synth_opts.add_last_branch;
+
+	pt->callstack = pt->synth_opts.callchain ||
+			pt->synth_opts.add_callchain ||
+			pt->synth_opts.thread_stack;
+
 	err = intel_pt_synth_events(pt, session);
 	if (err)
 		goto err_delete_thread;
@@ -3400,6 +3463,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	return 0;
 
 err_delete_thread:
+	zfree(&pt->chain);
 	thread__zput(pt->unknown_thread);
 err_free_queues:
 	intel_pt_log_disable();
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 97142e9671be..8ed2135893bb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -736,6 +736,12 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+static int is_bpf_image(const char *name)
+{
+	return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) ||
+	       strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1);
+}
+
 static int machine__process_ksymbol_register(struct machine *machine,
 					     union perf_event *event,
 					     struct perf_sample *sample __maybe_unused)
@@ -759,6 +765,12 @@ static int machine__process_ksymbol_register(struct machine *machine,
 		map->start = event->ksymbol.addr;
 		map->end = map->start + event->ksymbol.len;
 		maps__insert(&machine->kmaps, map);
+		dso__set_loaded(dso);
+
+		if (is_bpf_image(event->ksymbol.name)) {
+			dso->binary_type = DSO_BINARY_TYPE__BPF_IMAGE;
+			dso__set_long_name(dso, "", false);
+		}
 	}
 
 	sym = symbol__new(map->map_ip(map, map->start),
@@ -2178,6 +2190,303 @@ static int remove_loops(struct branch_entry *l, int nr,
 	return nr;
 }
 
+static int lbr_callchain_add_kernel_ip(struct thread *thread,
+				       struct callchain_cursor *cursor,
+				       struct perf_sample *sample,
+				       struct symbol **parent,
+				       struct addr_location *root_al,
+				       u64 branch_from,
+				       bool callee, int end)
+{
+	struct ip_callchain *chain = sample->callchain;
+	u8 cpumode = PERF_RECORD_MISC_USER;
+	int err, i;
+
+	if (callee) {
+		for (i = 0; i < end + 1; i++) {
+			err = add_callchain_ip(thread, cursor, parent,
+					       root_al, &cpumode, chain->ips[i],
+					       false, NULL, NULL, branch_from);
+			if (err)
+				return err;
+		}
+		return 0;
+	}
+
+	for (i = end; i >= 0; i--) {
+		err = add_callchain_ip(thread, cursor, parent,
+				       root_al, &cpumode, chain->ips[i],
+				       false, NULL, NULL, branch_from);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void save_lbr_cursor_node(struct thread *thread,
+				 struct callchain_cursor *cursor,
+				 int idx)
+{
+	struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+
+	if (!lbr_stitch)
+		return;
+
+	if (cursor->pos == cursor->nr) {
+		lbr_stitch->prev_lbr_cursor[idx].valid = false;
+		return;
+	}
+
+	if (!cursor->curr)
+		cursor->curr = cursor->first;
+	else
+		cursor->curr = cursor->curr->next;
+	memcpy(&lbr_stitch->prev_lbr_cursor[idx], cursor->curr,
+	       sizeof(struct callchain_cursor_node));
+
+	lbr_stitch->prev_lbr_cursor[idx].valid = true;
+	cursor->pos++;
+}
+
+static int lbr_callchain_add_lbr_ip(struct thread *thread,
+				    struct callchain_cursor *cursor,
+				    struct perf_sample *sample,
+				    struct symbol **parent,
+				    struct addr_location *root_al,
+				    u64 *branch_from,
+				    bool callee)
+{
+	struct branch_stack *lbr_stack = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
+	u8 cpumode = PERF_RECORD_MISC_USER;
+	int lbr_nr = lbr_stack->nr;
+	struct branch_flags *flags;
+	int err, i;
+	u64 ip;
+
+	/*
+	 * The curr and pos are not used in writing session. They are cleared
+	 * in callchain_cursor_commit() when the writing session is closed.
+	 * Using curr and pos to track the current cursor node.
+	 */
+	if (thread->lbr_stitch) {
+		cursor->curr = NULL;
+		cursor->pos = cursor->nr;
+		if (cursor->nr) {
+			cursor->curr = cursor->first;
+			for (i = 0; i < (int)(cursor->nr - 1); i++)
+				cursor->curr = cursor->curr->next;
+		}
+	}
+
+	if (callee) {
+		/* Add LBR ip from first entries.to */
+		ip = entries[0].to;
+		flags = &entries[0].flags;
+		*branch_from = entries[0].from;
+		err = add_callchain_ip(thread, cursor, parent,
+				       root_al, &cpumode, ip,
+				       true, flags, NULL,
+				       *branch_from);
+		if (err)
+			return err;
+
+		/*
+		 * The number of cursor node increases.
+		 * Move the current cursor node.
+		 * But does not need to save current cursor node for entry 0.
+		 * It's impossible to stitch the whole LBRs of previous sample.
+		 */
+		if (thread->lbr_stitch && (cursor->pos != cursor->nr)) {
+			if (!cursor->curr)
+				cursor->curr = cursor->first;
+			else
+				cursor->curr = cursor->curr->next;
+			cursor->pos++;
+		}
+
+		/* Add LBR ip from entries.from one by one. */
+		for (i = 0; i < lbr_nr; i++) {
+			ip = entries[i].from;
+			flags = &entries[i].flags;
+			err = add_callchain_ip(thread, cursor, parent,
+					       root_al, &cpumode, ip,
+					       true, flags, NULL,
+					       *branch_from);
+			if (err)
+				return err;
+			save_lbr_cursor_node(thread, cursor, i);
+		}
+		return 0;
+	}
+
+	/* Add LBR ip from entries.from one by one. */
+	for (i = lbr_nr - 1; i >= 0; i--) {
+		ip = entries[i].from;
+		flags = &entries[i].flags;
+		err = add_callchain_ip(thread, cursor, parent,
+				       root_al, &cpumode, ip,
+				       true, flags, NULL,
+				       *branch_from);
+		if (err)
+			return err;
+		save_lbr_cursor_node(thread, cursor, i);
+	}
+
+	/* Add LBR ip from first entries.to */
+	ip = entries[0].to;
+	flags = &entries[0].flags;
+	*branch_from = entries[0].from;
+	err = add_callchain_ip(thread, cursor, parent,
+			       root_al, &cpumode, ip,
+			       true, flags, NULL,
+			       *branch_from);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int lbr_callchain_add_stitched_lbr_ip(struct thread *thread,
+					     struct callchain_cursor *cursor)
+{
+	struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+	struct callchain_cursor_node *cnode;
+	struct stitch_list *stitch_node;
+	int err;
+
+	list_for_each_entry(stitch_node, &lbr_stitch->lists, node) {
+		cnode = &stitch_node->cursor;
+
+		err = callchain_cursor_append(cursor, cnode->ip,
+					      &cnode->ms,
+					      cnode->branch,
+					      &cnode->branch_flags,
+					      cnode->nr_loop_iter,
+					      cnode->iter_cycles,
+					      cnode->branch_from,
+					      cnode->srcline);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static struct stitch_list *get_stitch_node(struct thread *thread)
+{
+	struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+	struct stitch_list *stitch_node;
+
+	if (!list_empty(&lbr_stitch->free_lists)) {
+		stitch_node = list_first_entry(&lbr_stitch->free_lists,
+					       struct stitch_list, node);
+		list_del(&stitch_node->node);
+
+		return stitch_node;
+	}
+
+	return malloc(sizeof(struct stitch_list));
+}
+
+static bool has_stitched_lbr(struct thread *thread,
+			     struct perf_sample *cur,
+			     struct perf_sample *prev,
+			     unsigned int max_lbr,
+			     bool callee)
+{
+	struct branch_stack *cur_stack = cur->branch_stack;
+	struct branch_entry *cur_entries = perf_sample__branch_entries(cur);
+	struct branch_stack *prev_stack = prev->branch_stack;
+	struct branch_entry *prev_entries = perf_sample__branch_entries(prev);
+	struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+	int i, j, nr_identical_branches = 0;
+	struct stitch_list *stitch_node;
+	u64 cur_base, distance;
+
+	if (!cur_stack || !prev_stack)
+		return false;
+
+	/* Find the physical index of the base-of-stack for current sample. */
+	cur_base = max_lbr - cur_stack->nr + cur_stack->hw_idx + 1;
+
+	distance = (prev_stack->hw_idx > cur_base) ? (prev_stack->hw_idx - cur_base) :
+						     (max_lbr + prev_stack->hw_idx - cur_base);
+	/* Previous sample has shorter stack. Nothing can be stitched. */
+	if (distance + 1 > prev_stack->nr)
+		return false;
+
+	/*
+	 * Check if there are identical LBRs between two samples.
+	 * Identicall LBRs must have same from, to and flags values. Also,
+	 * they have to be saved in the same LBR registers (same physical
+	 * index).
+	 *
+	 * Starts from the base-of-stack of current sample.
+	 */
+	for (i = distance, j = cur_stack->nr - 1; (i >= 0) && (j >= 0); i--, j--) {
+		if ((prev_entries[i].from != cur_entries[j].from) ||
+		    (prev_entries[i].to != cur_entries[j].to) ||
+		    (prev_entries[i].flags.value != cur_entries[j].flags.value))
+			break;
+		nr_identical_branches++;
+	}
+
+	if (!nr_identical_branches)
+		return false;
+
+	/*
+	 * Save the LBRs between the base-of-stack of previous sample
+	 * and the base-of-stack of current sample into lbr_stitch->lists.
+	 * These LBRs will be stitched later.
+	 */
+	for (i = prev_stack->nr - 1; i > (int)distance; i--) {
+
+		if (!lbr_stitch->prev_lbr_cursor[i].valid)
+			continue;
+
+		stitch_node = get_stitch_node(thread);
+		if (!stitch_node)
+			return false;
+
+		memcpy(&stitch_node->cursor, &lbr_stitch->prev_lbr_cursor[i],
+		       sizeof(struct callchain_cursor_node));
+
+		if (callee)
+			list_add(&stitch_node->node, &lbr_stitch->lists);
+		else
+			list_add_tail(&stitch_node->node, &lbr_stitch->lists);
+	}
+
+	return true;
+}
+
+static bool alloc_lbr_stitch(struct thread *thread, unsigned int max_lbr)
+{
+	if (thread->lbr_stitch)
+		return true;
+
+	thread->lbr_stitch = zalloc(sizeof(*thread->lbr_stitch));
+	if (!thread->lbr_stitch)
+		goto err;
+
+	thread->lbr_stitch->prev_lbr_cursor = calloc(max_lbr + 1, sizeof(struct callchain_cursor_node));
+	if (!thread->lbr_stitch->prev_lbr_cursor)
+		goto free_lbr_stitch;
+
+	INIT_LIST_HEAD(&thread->lbr_stitch->lists);
+	INIT_LIST_HEAD(&thread->lbr_stitch->free_lists);
+
+	return true;
+
+free_lbr_stitch:
+	zfree(&thread->lbr_stitch);
+err:
+	pr_warning("Failed to allocate space for stitched LBRs. Disable LBR stitch\n");
+	thread->lbr_stitch_enable = false;
+	return false;
+}
+
 /*
  * Recolve LBR callstack chain sample
  * Return:
@@ -2190,12 +2499,16 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					struct perf_sample *sample,
 					struct symbol **parent,
 					struct addr_location *root_al,
-					int max_stack)
+					int max_stack,
+					unsigned int max_lbr)
 {
+	bool callee = (callchain_param.order == ORDER_CALLEE);
 	struct ip_callchain *chain = sample->callchain;
 	int chain_nr = min(max_stack, (int)chain->nr), i;
-	u8 cpumode = PERF_RECORD_MISC_USER;
-	u64 ip, branch_from = 0;
+	struct lbr_stitch *lbr_stitch;
+	bool stitched_lbr = false;
+	u64 branch_from = 0;
+	int err;
 
 	for (i = 0; i < chain_nr; i++) {
 		if (chain->ips[i] == PERF_CONTEXT_USER)
@@ -2203,71 +2516,65 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	}
 
 	/* LBR only affects the user callchain */
-	if (i != chain_nr) {
-		struct branch_stack *lbr_stack = sample->branch_stack;
-		struct branch_entry *entries = perf_sample__branch_entries(sample);
-		int lbr_nr = lbr_stack->nr, j, k;
-		bool branch;
-		struct branch_flags *flags;
-		/*
-		 * LBR callstack can only get user call chain.
-		 * The mix_chain_nr is kernel call chain
-		 * number plus LBR user call chain number.
-		 * i is kernel call chain number,
-		 * 1 is PERF_CONTEXT_USER,
-		 * lbr_nr + 1 is the user call chain number.
-		 * For details, please refer to the comments
-		 * in callchain__printf
-		 */
-		int mix_chain_nr = i + 1 + lbr_nr + 1;
+	if (i == chain_nr)
+		return 0;
 
-		for (j = 0; j < mix_chain_nr; j++) {
-			int err;
-			branch = false;
-			flags = NULL;
+	if (thread->lbr_stitch_enable && !sample->no_hw_idx &&
+	    (max_lbr > 0) && alloc_lbr_stitch(thread, max_lbr)) {
+		lbr_stitch = thread->lbr_stitch;
 
-			if (callchain_param.order == ORDER_CALLEE) {
-				if (j < i + 1)
-					ip = chain->ips[j];
-				else if (j > i + 1) {
-					k = j - i - 2;
-					ip = entries[k].from;
-					branch = true;
-					flags = &entries[k].flags;
-				} else {
-					ip = entries[0].to;
-					branch = true;
-					flags = &entries[0].flags;
-					branch_from = entries[0].from;
-				}
-			} else {
-				if (j < lbr_nr) {
-					k = lbr_nr - j - 1;
-					ip = entries[k].from;
-					branch = true;
-					flags = &entries[k].flags;
-				}
-				else if (j > lbr_nr)
-					ip = chain->ips[i + 1 - (j - lbr_nr)];
-				else {
-					ip = entries[0].to;
-					branch = true;
-					flags = &entries[0].flags;
-					branch_from = entries[0].from;
-				}
-			}
+		stitched_lbr = has_stitched_lbr(thread, sample,
+						&lbr_stitch->prev_sample,
+						max_lbr, callee);
 
-			err = add_callchain_ip(thread, cursor, parent,
-					       root_al, &cpumode, ip,
-					       branch, flags, NULL,
-					       branch_from);
+		if (!stitched_lbr && !list_empty(&lbr_stitch->lists)) {
+			list_replace_init(&lbr_stitch->lists,
+					  &lbr_stitch->free_lists);
+		}
+		memcpy(&lbr_stitch->prev_sample, sample, sizeof(*sample));
+	}
+
+	if (callee) {
+		/* Add kernel ip */
+		err = lbr_callchain_add_kernel_ip(thread, cursor, sample,
+						  parent, root_al, branch_from,
+						  true, i);
+		if (err)
+			goto error;
+
+		err = lbr_callchain_add_lbr_ip(thread, cursor, sample, parent,
+					       root_al, &branch_from, true);
+		if (err)
+			goto error;
+
+		if (stitched_lbr) {
+			err = lbr_callchain_add_stitched_lbr_ip(thread, cursor);
 			if (err)
-				return (err < 0) ? err : 0;
+				goto error;
 		}
-		return 1;
+
+	} else {
+		if (stitched_lbr) {
+			err = lbr_callchain_add_stitched_lbr_ip(thread, cursor);
+			if (err)
+				goto error;
+		}
+		err = lbr_callchain_add_lbr_ip(thread, cursor, sample, parent,
+					       root_al, &branch_from, false);
+		if (err)
+			goto error;
+
+		/* Add kernel ip */
+		err = lbr_callchain_add_kernel_ip(thread, cursor, sample,
+						  parent, root_al, branch_from,
+						  false, i);
+		if (err)
+			goto error;
 	}
+	return 1;
 
-	return 0;
+error:
+	return (err < 0) ? err : 0;
 }
 
 static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
@@ -2311,9 +2618,12 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	if (chain)
 		chain_nr = chain->nr;
 
-	if (perf_evsel__has_branch_callstack(evsel)) {
+	if (evsel__has_branch_callstack(evsel)) {
+		struct perf_env *env = evsel__env(evsel);
+
 		err = resolve_lbr_callchain_sample(thread, cursor, sample, parent,
-						   root_al, max_stack);
+						   root_al, max_stack,
+						   !env ? 0 : env->max_branches);
 		if (err)
 			return (err < 0) ? err : 0;
 	}
diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c
index 797d86a1ab09..c84f5841c7ab 100644
--- a/tools/perf/util/mem2node.c
+++ b/tools/perf/util/mem2node.c
@@ -1,5 +1,6 @@
 #include <errno.h>
 #include <inttypes.h>
+#include <asm/bug.h>
 #include <linux/bitmap.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
@@ -95,7 +96,7 @@ int mem2node__init(struct mem2node *map, struct perf_env *env)
 
 	/* Cut unused entries, due to merging. */
 	tmp_entries = realloc(entries, sizeof(*entries) * j);
-	if (tmp_entries)
+	if (tmp_entries || WARN_ON_ONCE(j == 0))
 		entries = tmp_entries;
 
 	for (i = 0; i < j; i++) {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 926449a7cdbf..b071df373f8b 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -90,6 +90,7 @@ struct egroup {
 	const char *metric_name;
 	const char *metric_expr;
 	const char *metric_unit;
+	int runtime;
 };
 
 static struct evsel *find_evsel_group(struct evlist *perf_evlist,
@@ -202,6 +203,7 @@ static int metricgroup__setup_events(struct list_head *groups,
 		expr->metric_name = eg->metric_name;
 		expr->metric_unit = eg->metric_unit;
 		expr->metric_events = metric_events;
+		expr->runtime = eg->runtime;
 		list_add(&expr->nd, &me->head);
 	}
 
@@ -485,6 +487,45 @@ static bool metricgroup__has_constraint(struct pmu_event *pe)
 	return false;
 }
 
+int __weak arch_get_runtimeparam(void)
+{
+	return 1;
+}
+
+static int __metricgroup__add_metric(struct strbuf *events,
+		struct list_head *group_list, struct pmu_event *pe, int runtime)
+{
+
+	const char **ids;
+	int idnum;
+	struct egroup *eg;
+
+	if (expr__find_other(pe->metric_expr, NULL, &ids, &idnum, runtime) < 0)
+		return -EINVAL;
+
+	if (events->len > 0)
+		strbuf_addf(events, ",");
+
+	if (metricgroup__has_constraint(pe))
+		metricgroup__add_metric_non_group(events, ids, idnum);
+	else
+		metricgroup__add_metric_weak_group(events, ids, idnum);
+
+	eg = malloc(sizeof(*eg));
+	if (!eg)
+		return -ENOMEM;
+
+	eg->ids = ids;
+	eg->idnum = idnum;
+	eg->metric_name = pe->metric_name;
+	eg->metric_expr = pe->metric_expr;
+	eg->metric_unit = pe->unit;
+	eg->runtime = runtime;
+	list_add_tail(&eg->nd, group_list);
+
+	return 0;
+}
+
 static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				   struct list_head *group_list)
 {
@@ -504,35 +545,26 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 			continue;
 		if (match_metric(pe->metric_group, metric) ||
 		    match_metric(pe->metric_name, metric)) {
-			const char **ids;
-			int idnum;
-			struct egroup *eg;
 
 			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
 
-			if (expr__find_other(pe->metric_expr,
-					     NULL, &ids, &idnum) < 0)
-				continue;
-			if (events->len > 0)
-				strbuf_addf(events, ",");
+			if (!strstr(pe->metric_expr, "?")) {
+				ret = __metricgroup__add_metric(events, group_list, pe, 1);
+			} else {
+				int j, count;
 
-			if (metricgroup__has_constraint(pe))
-				metricgroup__add_metric_non_group(events, ids, idnum);
-			else
-				metricgroup__add_metric_weak_group(events, ids, idnum);
+				count = arch_get_runtimeparam();
 
-			eg = malloc(sizeof(struct egroup));
-			if (!eg) {
-				ret = -ENOMEM;
-				break;
+				/* This loop is added to create multiple
+				 * events depend on count value and add
+				 * those events to group_list.
+				 */
+
+				for (j = 0; j < count; j++)
+					ret = __metricgroup__add_metric(events, group_list, pe, j);
 			}
-			eg->ids = ids;
-			eg->idnum = idnum;
-			eg->metric_name = pe->metric_name;
-			eg->metric_expr = pe->metric_expr;
-			eg->metric_unit = pe->unit;
-			list_add_tail(&eg->nd, group_list);
-			ret = 0;
+			if (ret == -ENOMEM)
+				break;
 		}
 	}
 	return ret;
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 475c7f912864..6b09eb30b4ec 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -22,6 +22,7 @@ struct metric_expr {
 	const char *metric_name;
 	const char *metric_unit;
 	struct evsel **metric_events;
+	int runtime;
 };
 
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
@@ -34,4 +35,5 @@ int metricgroup__parse_groups(const struct option *opt,
 void metricgroup__print(bool metrics, bool groups, char *filter,
 			bool raw, bool details);
 bool metricgroup__has_metric(const char *metric);
+int arch_get_runtimeparam(void);
 #endif
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 359db2b1fcef..48c8f609441b 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -314,7 +314,7 @@ static int __ordered_events__flush(struct ordered_events *oe, enum oe_flush how,
 	case OE_FLUSH__NONE:
 	default:
 		break;
-	};
+	}
 
 	pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush PRE  %s, nr_events %u\n",
 		   str[how], oe->nr_events);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 10107747b361..b7a0518d607d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -461,7 +461,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 			cache_op = parse_aliases(str, perf_evsel__hw_cache_op,
 						 PERF_COUNT_HW_CACHE_OP_MAX);
 			if (cache_op >= 0) {
-				if (!perf_evsel__is_cache_op_valid(cache_type, cache_op))
+				if (!evsel__is_cache_op_valid(cache_type, cache_op))
 					return -EINVAL;
 				continue;
 			}
@@ -1482,6 +1482,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 		list_for_each_entry_safe(pos, tmp, &config_terms, list) {
 			list_del_init(&pos->list);
+			zfree(&pos->val.str);
 			free(pos);
 		}
 		return -EINVAL;
@@ -1870,7 +1871,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 		evsel->precise_max         = mod.precise_max;
 		evsel->weak_group	   = mod.weak;
 
-		if (perf_evsel__is_group_leader(evsel))
+		if (evsel__is_group_leader(evsel))
 			evsel->core.attr.pinned = mod.pinned;
 	}
 
@@ -2190,6 +2191,29 @@ int parse_events_option(const struct option *opt, const char *str,
 	return ret;
 }
 
+int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset)
+{
+	struct evlist **evlistp = opt->value;
+	int ret;
+
+	if (*evlistp == NULL) {
+		*evlistp = evlist__new();
+
+		if (*evlistp == NULL) {
+			fprintf(stderr, "Not enough memory to create evlist\n");
+			return -1;
+		}
+	}
+
+	ret = parse_events_option(opt, str, unset);
+	if (ret) {
+		evlist__delete(*evlistp);
+		*evlistp = NULL;
+	}
+
+	return ret;
+}
+
 static int
 foreach_evsel_in_last_glob(struct evlist *evlist,
 			   int (*func)(struct evsel *evsel,
@@ -2237,7 +2261,7 @@ static int set_filter(struct evsel *evsel, const void *arg)
 	}
 
 	if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
-		if (perf_evsel__append_tp_filter(evsel, str) < 0) {
+		if (evsel__append_tp_filter(evsel, str) < 0) {
 			fprintf(stderr,
 				"not enough memory to hold filter string\n");
 			return -1;
@@ -2262,7 +2286,7 @@ static int set_filter(struct evsel *evsel, const void *arg)
 		return -1;
 	}
 
-	if (perf_evsel__append_addr_filter(evsel, str) < 0) {
+	if (evsel__append_addr_filter(evsel, str) < 0) {
 		fprintf(stderr,
 			"not enough memory to hold filter string\n");
 		return -1;
@@ -2293,7 +2317,7 @@ static int add_exclude_perf_filter(struct evsel *evsel,
 
 	snprintf(new_filter, sizeof(new_filter), "common_pid != %d", getpid());
 
-	if (perf_evsel__append_tp_filter(evsel, new_filter) < 0) {
+	if (evsel__append_tp_filter(evsel, new_filter) < 0) {
 		fprintf(stderr,
 			"not enough memory to hold filter string\n");
 		return -1;
@@ -2603,12 +2627,11 @@ restart:
 	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
 		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
 			/* skip invalid cache type */
-			if (!perf_evsel__is_cache_op_valid(type, op))
+			if (!evsel__is_cache_op_valid(type, op))
 				continue;
 
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
-				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
-									name, sizeof(name));
+				__evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name));
 				if (event_glob != NULL && !strglobmatch(name, event_glob))
 					continue;
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 27596cbd0ba0..6ead9661238c 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -31,6 +31,7 @@ bool have_tracepoints(struct list_head *evlist);
 const char *event_type(int type);
 
 int parse_events_option(const struct option *opt, const char *str, int unset);
+int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset);
 int parse_events(struct evlist *evlist, const char *str,
 		 struct parse_events_error *error);
 int parse_events_terms(struct list_head *terms, const char *str);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index baa48f28d57d..c589fc42f058 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -286,6 +286,7 @@ no-overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
 percore			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
 aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 aux-sample-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
+r{num_raw_hex}		{ return raw(yyscanner); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 94f8bcd83582..c4ca932d092d 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -44,7 +44,7 @@ static void free_list_evsel(struct list_head* list_evsel)
 
 	list_for_each_entry_safe(evsel, tmp, list_evsel, core.node) {
 		list_del_init(&evsel->core.node);
-		perf_evsel__delete(evsel);
+		evsel__delete(evsel);
 	}
 	free(list_evsel);
 }
@@ -326,6 +326,7 @@ PE_NAME opt_pmu_config
 	}
 	parse_events_terms__delete($2);
 	parse_events_terms__delete(orig_terms);
+	free(pattern);
 	free($1);
 	$$ = list;
 #undef CLEANUP_YYABORT
@@ -706,6 +707,15 @@ event_term
 }
 
 event_term:
+PE_RAW
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_CONFIG,
+					NULL, $1, false, &@1, NULL));
+	$$ = term;
+}
+|
 PE_NAME '=' PE_NAME
 {
 	struct parse_events_term *term;
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
new file mode 100644
index 000000000000..1337965673d7
--- /dev/null
+++ b/tools/perf/util/perf_api_probe.c
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include "perf-sys.h"
+#include "util/cloexec.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/parse-events.h"
+#include "util/perf_api_probe.h"
+#include <perf/cpumap.h>
+#include <errno.h>
+
+typedef void (*setup_probe_fn_t)(struct evsel *evsel);
+
+static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+{
+	struct evlist *evlist;
+	struct evsel *evsel;
+	unsigned long flags = perf_event_open_cloexec_flag();
+	int err = -EAGAIN, fd;
+	static pid_t pid = -1;
+
+	evlist = evlist__new();
+	if (!evlist)
+		return -ENOMEM;
+
+	if (parse_events(evlist, str, NULL))
+		goto out_delete;
+
+	evsel = evlist__first(evlist);
+
+	while (1) {
+		fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+		if (fd < 0) {
+			if (pid == -1 && errno == EACCES) {
+				pid = 0;
+				continue;
+			}
+			goto out_delete;
+		}
+		break;
+	}
+	close(fd);
+
+	fn(evsel);
+
+	fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+	if (fd < 0) {
+		if (errno == EINVAL)
+			err = -EINVAL;
+		goto out_delete;
+	}
+	close(fd);
+	err = 0;
+
+out_delete:
+	evlist__delete(evlist);
+	return err;
+}
+
+static bool perf_probe_api(setup_probe_fn_t fn)
+{
+	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
+	struct perf_cpu_map *cpus;
+	int cpu, ret, i = 0;
+
+	cpus = perf_cpu_map__new(NULL);
+	if (!cpus)
+		return false;
+	cpu = cpus->map[0];
+	perf_cpu_map__put(cpus);
+
+	do {
+		ret = perf_do_probe_api(fn, cpu, try[i++]);
+		if (!ret)
+			return true;
+	} while (ret == -EAGAIN && try[i]);
+
+	return false;
+}
+
+static void perf_probe_sample_identifier(struct evsel *evsel)
+{
+	evsel->core.attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
+}
+
+static void perf_probe_comm_exec(struct evsel *evsel)
+{
+	evsel->core.attr.comm_exec = 1;
+}
+
+static void perf_probe_context_switch(struct evsel *evsel)
+{
+	evsel->core.attr.context_switch = 1;
+}
+
+bool perf_can_sample_identifier(void)
+{
+	return perf_probe_api(perf_probe_sample_identifier);
+}
+
+bool perf_can_comm_exec(void)
+{
+	return perf_probe_api(perf_probe_comm_exec);
+}
+
+bool perf_can_record_switch_events(void)
+{
+	return perf_probe_api(perf_probe_context_switch);
+}
+
+bool perf_can_record_cpu_wide(void)
+{
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+		.exclude_kernel = 1,
+	};
+	struct perf_cpu_map *cpus;
+	int cpu, fd;
+
+	cpus = perf_cpu_map__new(NULL);
+	if (!cpus)
+		return false;
+	cpu = cpus->map[0];
+	perf_cpu_map__put(cpus);
+
+	fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
+	if (fd < 0)
+		return false;
+	close(fd);
+
+	return true;
+}
+
+/*
+ * Architectures are expected to know if AUX area sampling is supported by the
+ * hardware. Here we check for kernel support.
+ */
+bool perf_can_aux_sample(void)
+{
+	struct perf_event_attr attr = {
+		.size = sizeof(struct perf_event_attr),
+		.exclude_kernel = 1,
+		/*
+		 * Non-zero value causes the kernel to calculate the effective
+		 * attribute size up to that byte.
+		 */
+		.aux_sample_size = 1,
+	};
+	int fd;
+
+	fd = sys_perf_event_open(&attr, -1, 0, -1, 0);
+	/*
+	 * If the kernel attribute is big enough to contain aux_sample_size
+	 * then we assume that it is supported. We are relying on the kernel to
+	 * validate the attribute size before anything else that could be wrong.
+	 */
+	if (fd < 0 && errno == E2BIG)
+		return false;
+	if (fd >= 0)
+		close(fd);
+
+	return true;
+}
diff --git a/tools/perf/util/perf_api_probe.h b/tools/perf/util/perf_api_probe.h
new file mode 100644
index 000000000000..706c3c6426e2
--- /dev/null
+++ b/tools/perf/util/perf_api_probe.h
@@ -0,0 +1,14 @@
+
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_API_PROBE_H
+#define __PERF_API_PROBE_H
+
+#include <stdbool.h>
+
+bool perf_can_aux_sample(void);
+bool perf_can_comm_exec(void);
+bool perf_can_record_cpu_wide(void);
+bool perf_can_record_switch_events(void);
+bool perf_can_sample_identifier(void);
+
+#endif // __PERF_API_PROBE_H
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ef6a63f3d386..92bd7fafcce6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -18,6 +18,7 @@
 #include <regex.h>
 #include <perf/cpumap.h>
 #include "debug.h"
+#include "evsel.h"
 #include "pmu.h"
 #include "parse-events.h"
 #include "header.h"
@@ -849,6 +850,7 @@ static struct perf_pmu *pmu_lookup(const char *name)
 
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
+	INIT_LIST_HEAD(&pmu->caps);
 	list_splice(&format, &pmu->format);
 	list_splice(&aliases, &pmu->aliases);
 	list_add_tail(&pmu->list, &pmus);
@@ -869,6 +871,17 @@ static struct perf_pmu *pmu_find(const char *name)
 	return NULL;
 }
 
+struct perf_pmu *perf_pmu__find_by_type(unsigned int type)
+{
+	struct perf_pmu *pmu;
+
+	list_for_each_entry(pmu, &pmus, list)
+		if (pmu->type == type)
+			return pmu;
+
+	return NULL;
+}
+
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
 {
 	/*
@@ -884,6 +897,25 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
 	return NULL;
 }
 
+struct perf_pmu *evsel__find_pmu(struct evsel *evsel)
+{
+	struct perf_pmu *pmu = NULL;
+
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		if (pmu->type == evsel->core.attr.type)
+			break;
+	}
+
+	return pmu;
+}
+
+bool evsel__is_aux_event(struct evsel *evsel)
+{
+	struct perf_pmu *pmu = evsel__find_pmu(evsel);
+
+	return pmu && pmu->auxtrace;
+}
+
 struct perf_pmu *perf_pmu__find(const char *name)
 {
 	struct perf_pmu *pmu;
@@ -1574,3 +1606,84 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
 	va_end(args);
 	return ret;
 }
+
+static int perf_pmu__new_caps(struct list_head *list, char *name, char *value)
+{
+	struct perf_pmu_caps *caps = zalloc(sizeof(*caps));
+
+	if (!caps)
+		return -ENOMEM;
+
+	caps->name = strdup(name);
+	if (!caps->name)
+		goto free_caps;
+	caps->value = strndup(value, strlen(value) - 1);
+	if (!caps->value)
+		goto free_name;
+	list_add_tail(&caps->list, list);
+	return 0;
+
+free_name:
+	zfree(caps->name);
+free_caps:
+	free(caps);
+
+	return -ENOMEM;
+}
+
+/*
+ * Reading/parsing the given pmu capabilities, which should be located at:
+ * /sys/bus/event_source/devices/<dev>/caps as sysfs group attributes.
+ * Return the number of capabilities
+ */
+int perf_pmu__caps_parse(struct perf_pmu *pmu)
+{
+	struct stat st;
+	char caps_path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+	DIR *caps_dir;
+	struct dirent *evt_ent;
+	int nr_caps = 0;
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(caps_path, PATH_MAX,
+		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/caps", sysfs, pmu->name);
+
+	if (stat(caps_path, &st) < 0)
+		return 0;	/* no error if caps does not exist */
+
+	caps_dir = opendir(caps_path);
+	if (!caps_dir)
+		return -EINVAL;
+
+	while ((evt_ent = readdir(caps_dir)) != NULL) {
+		char path[PATH_MAX + NAME_MAX + 1];
+		char *name = evt_ent->d_name;
+		char value[128];
+		FILE *file;
+
+		if (!strcmp(name, ".") || !strcmp(name, ".."))
+			continue;
+
+		snprintf(path, sizeof(path), "%s/%s", caps_path, name);
+
+		file = fopen(path, "r");
+		if (!file)
+			continue;
+
+		if (!fgets(value, sizeof(value), file) ||
+		    (perf_pmu__new_caps(&pmu->caps, name, value) < 0)) {
+			fclose(file);
+			continue;
+		}
+
+		nr_caps++;
+		fclose(file);
+	}
+
+	closedir(caps_dir);
+
+	return nr_caps;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 5fb3f16828df..cb6fbec50313 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -22,6 +22,12 @@ enum {
 
 struct perf_event_attr;
 
+struct perf_pmu_caps {
+	char *name;
+	char *value;
+	struct list_head list;
+};
+
 struct perf_pmu {
 	char *name;
 	__u32 type;
@@ -33,6 +39,7 @@ struct perf_pmu {
 	struct perf_cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
 	struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
+	struct list_head caps;    /* HEAD struct perf_pmu_caps -> list */
 	struct list_head list;    /* ELEM */
 };
 
@@ -65,6 +72,7 @@ struct perf_pmu_alias {
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);
+struct perf_pmu *perf_pmu__find_by_type(unsigned int type);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms,
 		     struct parse_events_error *error);
@@ -107,4 +115,6 @@ bool pmu_uncore_alias_match(const char *pmu_name, const char *name);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
+int perf_pmu__caps_parse(struct perf_pmu *pmu);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 83212c65848b..75a9b1d62bba 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -801,7 +801,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
 
 static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
 {
-	perf_evsel__exit(&pevsel->evsel);
+	evsel__exit(&pevsel->evsel);
 	Py_TYPE(pevsel)->tp_free((PyObject*)pevsel);
 }
 
@@ -1044,7 +1044,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
 		pevent->evsel = evsel;
 
-		err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
+		err = evsel__parse_sample(evsel, event, &pevent->sample);
 
 		/* Consume the even only after we parsed it out. */
 		perf_mmap__consume(&md->core);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 7def66168503..a4cc11592f6b 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -10,161 +10,64 @@
 #include <subcmd/parse-options.h>
 #include <perf/cpumap.h>
 #include "cloexec.h"
+#include "util/perf_api_probe.h"
 #include "record.h"
 #include "../perf-sys.h"
 
-typedef void (*setup_probe_fn_t)(struct evsel *evsel);
-
-static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+/*
+ * evsel__config_leader_sampling() uses special rules for leader sampling.
+ * However, if the leader is an AUX area event, then assume the event to sample
+ * is the next event.
+ */
+static struct evsel *evsel__read_sampler(struct evsel *evsel, struct evlist *evlist)
 {
-	struct evlist *evlist;
-	struct evsel *evsel;
-	unsigned long flags = perf_event_open_cloexec_flag();
-	int err = -EAGAIN, fd;
-	static pid_t pid = -1;
-
-	evlist = evlist__new();
-	if (!evlist)
-		return -ENOMEM;
-
-	if (parse_events(evlist, str, NULL))
-		goto out_delete;
-
-	evsel = evlist__first(evlist);
+	struct evsel *leader = evsel->leader;
 
-	while (1) {
-		fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
-		if (fd < 0) {
-			if (pid == -1 && errno == EACCES) {
-				pid = 0;
-				continue;
-			}
-			goto out_delete;
+	if (evsel__is_aux_event(leader)) {
+		evlist__for_each_entry(evlist, evsel) {
+			if (evsel->leader == leader && evsel != evsel->leader)
+				return evsel;
 		}
-		break;
-	}
-	close(fd);
-
-	fn(evsel);
-
-	fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
-	if (fd < 0) {
-		if (errno == EINVAL)
-			err = -EINVAL;
-		goto out_delete;
 	}
-	close(fd);
-	err = 0;
-
-out_delete:
-	evlist__delete(evlist);
-	return err;
-}
-
-static bool perf_probe_api(setup_probe_fn_t fn)
-{
-	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
-	struct perf_cpu_map *cpus;
-	int cpu, ret, i = 0;
-
-	cpus = perf_cpu_map__new(NULL);
-	if (!cpus)
-		return false;
-	cpu = cpus->map[0];
-	perf_cpu_map__put(cpus);
-
-	do {
-		ret = perf_do_probe_api(fn, cpu, try[i++]);
-		if (!ret)
-			return true;
-	} while (ret == -EAGAIN && try[i]);
 
-	return false;
+	return leader;
 }
 
-static void perf_probe_sample_identifier(struct evsel *evsel)
+static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *evlist)
 {
-	evsel->core.attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
-}
-
-static void perf_probe_comm_exec(struct evsel *evsel)
-{
-	evsel->core.attr.comm_exec = 1;
-}
-
-static void perf_probe_context_switch(struct evsel *evsel)
-{
-	evsel->core.attr.context_switch = 1;
-}
-
-bool perf_can_sample_identifier(void)
-{
-	return perf_probe_api(perf_probe_sample_identifier);
-}
+	struct perf_event_attr *attr = &evsel->core.attr;
+	struct evsel *leader = evsel->leader;
+	struct evsel *read_sampler;
 
-static bool perf_can_comm_exec(void)
-{
-	return perf_probe_api(perf_probe_comm_exec);
-}
+	if (!leader->sample_read)
+		return;
 
-bool perf_can_record_switch_events(void)
-{
-	return perf_probe_api(perf_probe_context_switch);
-}
+	read_sampler = evsel__read_sampler(evsel, evlist);
 
-bool perf_can_record_cpu_wide(void)
-{
-	struct perf_event_attr attr = {
-		.type = PERF_TYPE_SOFTWARE,
-		.config = PERF_COUNT_SW_CPU_CLOCK,
-		.exclude_kernel = 1,
-	};
-	struct perf_cpu_map *cpus;
-	int cpu, fd;
-
-	cpus = perf_cpu_map__new(NULL);
-	if (!cpus)
-		return false;
-	cpu = cpus->map[0];
-	perf_cpu_map__put(cpus);
+	if (evsel == read_sampler)
+		return;
 
-	fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
-	if (fd < 0)
-		return false;
-	close(fd);
-
-	return true;
-}
-
-/*
- * Architectures are expected to know if AUX area sampling is supported by the
- * hardware. Here we check for kernel support.
- */
-bool perf_can_aux_sample(void)
-{
-	struct perf_event_attr attr = {
-		.size = sizeof(struct perf_event_attr),
-		.exclude_kernel = 1,
-		/*
-		 * Non-zero value causes the kernel to calculate the effective
-		 * attribute size up to that byte.
-		 */
-		.aux_sample_size = 1,
-	};
-	int fd;
-
-	fd = sys_perf_event_open(&attr, -1, 0, -1, 0);
 	/*
-	 * If the kernel attribute is big enough to contain aux_sample_size
-	 * then we assume that it is supported. We are relying on the kernel to
-	 * validate the attribute size before anything else that could be wrong.
+	 * Disable sampling for all group members other than the leader in
+	 * case the leader 'leads' the sampling, except when the leader is an
+	 * AUX area event, in which case the 2nd event in the group is the one
+	 * that 'leads' the sampling.
 	 */
-	if (fd < 0 && errno == E2BIG)
-		return false;
-	if (fd >= 0)
-		close(fd);
+	attr->freq           = 0;
+	attr->sample_freq    = 0;
+	attr->sample_period  = 0;
+	attr->write_backward = 0;
 
-	return true;
+	/*
+	 * We don't get a sample for slave events, we make them when delivering
+	 * the group leader sample. Set the slave event to follow the master
+	 * sample_type to ease up reporting.
+	 * An AUX area event also has sample_type requirements, so also include
+	 * the sample type bits from the leader's sample_type to cover that
+	 * case.
+	 */
+	attr->sample_type = read_sampler->core.attr.sample_type |
+			    leader->core.attr.sample_type;
 }
 
 void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
@@ -188,11 +91,15 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
 	use_comm_exec = perf_can_comm_exec();
 
 	evlist__for_each_entry(evlist, evsel) {
-		perf_evsel__config(evsel, opts, callchain);
+		evsel__config(evsel, opts, callchain);
 		if (evsel->tracking && use_comm_exec)
 			evsel->core.attr.comm_exec = 1;
 	}
 
+	/* Configure leader sampling here now that the sample type is known */
+	evlist__for_each_entry(evlist, evsel)
+		evsel__config_leader_sampling(evsel, evlist);
+
 	if (opts->full_auxtrace) {
 		/*
 		 * Need to be able to synthesize and parse selected events with
@@ -215,7 +122,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
 
 	if (sample_id) {
 		evlist__for_each_entry(evlist, evsel)
-			perf_evsel__set_sample_id(evsel, use_sample_identifier);
+			evsel__set_sample_id(evsel, use_sample_identifier);
 	}
 
 	perf_evlist__set_id_pos(evlist);
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
index 24316458be20..923565c3b155 100644
--- a/tools/perf/util/record.h
+++ b/tools/perf/util/record.h
@@ -68,6 +68,7 @@ struct record_opts {
 	int	      affinity;
 	int	      mmap_flush;
 	unsigned int  comp_level;
+	unsigned int  nr_threads_synthesize;
 };
 
 extern const char * const *record_usage;
diff --git a/tools/perf/util/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h
index d4356030b504..f55ca07f3ca1 100644
--- a/tools/perf/util/s390-cpumcf-kernel.h
+++ b/tools/perf/util/s390-cpumcf-kernel.h
@@ -11,6 +11,7 @@
 
 #define	S390_CPUMCF_DIAG_DEF	0xfeef	/* Counter diagnostic entry ID */
 #define	PERF_EVENT_CPUM_CF_DIAG	0xBC000	/* Event: Counter sets */
+#define PERF_EVENT_CPUM_SF_DIAG	0xBD000 /* Event: Combined-sampling */
 
 struct cf_ctrset_entry {	/* CPU-M CF counter set entry (8 byte) */
 	unsigned int def:16;	/* 0-15  Data Entry Format */
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 6785cd87aa4d..f8861998e5bd 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -1047,6 +1047,14 @@ static void s390_cpumsf_free(struct perf_session *session)
 	free(sf);
 }
 
+static bool
+s390_cpumsf_evsel_is_auxtrace(struct perf_session *session __maybe_unused,
+			      struct evsel *evsel)
+{
+	return evsel->core.attr.type == PERF_TYPE_RAW &&
+	       evsel->core.attr.config == PERF_EVENT_CPUM_SF_DIAG;
+}
+
 static int s390_cpumsf_get_type(const char *cpuid)
 {
 	int ret, family = 0;
@@ -1071,7 +1079,8 @@ static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
 		itops->pwr_events || itops->errors ||
 		itops->dont_decode || itops->calls || itops->returns ||
 		itops->callchain || itops->thread_stack ||
-		itops->last_branch;
+		itops->last_branch || itops->add_callchain ||
+		itops->add_last_branch;
 	if (!ison)
 		return true;
 	pr_err("Unsupported --itrace options specified\n");
@@ -1142,6 +1151,7 @@ int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 	sf->auxtrace.flush_events = s390_cpumsf_flush;
 	sf->auxtrace.free_events = s390_cpumsf_free_events;
 	sf->auxtrace.free = s390_cpumsf_free;
+	sf->auxtrace.evsel_is_auxtrace = s390_cpumsf_evsel_is_auxtrace;
 	session->auxtrace = &sf->auxtrace;
 
 	if (dump_trace)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 2c372cf5495e..739516fdf6e3 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -741,7 +741,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 	if (!dict_sample)
 		Py_FatalError("couldn't create Python dictionary");
 
-	pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel)));
+	pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(evsel__name(evsel)));
 	pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->core.attr, sizeof(evsel->core.attr)));
 
 	pydict_set_item_string_decref(dict_sample, "pid",
@@ -968,7 +968,7 @@ static int python_export_evsel(struct db_export *dbe, struct evsel *evsel)
 	t = tuple_new(2);
 
 	tuple_set_u64(t, 0, evsel->db_id);
-	tuple_set_string(t, 1, perf_evsel__name(evsel));
+	tuple_set_string(t, 1, evsel__name(evsel));
 
 	call_object(tables->evsel_handler, t, "evsel_table");
 
@@ -1349,7 +1349,7 @@ static void get_handler_name(char *str, size_t size,
 {
 	char *p = str;
 
-	scnprintf(str, size, "stat__%s", perf_evsel__name(evsel));
+	scnprintf(str, size, "stat__%s", evsel__name(evsel));
 
 	while ((p = strchr(p, ':'))) {
 		*p = '_';
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0b0bfe5bef17..c11d89e0ee55 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1059,7 +1059,7 @@ static void callchain__printf(struct evsel *evsel,
 	unsigned int i;
 	struct ip_callchain *callchain = sample->callchain;
 
-	if (perf_evsel__has_branch_callstack(evsel))
+	if (evsel__has_branch_callstack(evsel))
 		callchain__lbr_callstack_printf(sample);
 
 	printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr);
@@ -1243,8 +1243,8 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 	if (evsel__has_callchain(evsel))
 		callchain__printf(evsel, sample);
 
-	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
-		branch_stack__printf(sample, perf_evsel__has_branch_callstack(evsel));
+	if (evsel__has_br_stack(evsel))
+		branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample);
@@ -1280,8 +1280,7 @@ static void dump_read(struct evsel *evsel, union perf_event *event)
 		return;
 
 	printf(": %d %d %s %" PRI_lu64 "\n", event->read.pid, event->read.tid,
-	       perf_evsel__name(evsel),
-	       event->read.value);
+	       evsel__name(evsel), event->read.value);
 
 	if (!evsel)
 		return;
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 347b2c0789e4..c5e3e9a68162 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -21,6 +21,8 @@ if cc_is_clang:
             vars[var] = sub("-fstack-clash-protection", "", vars[var])
         if not clang_has_option("-fstack-protector-strong"):
             vars[var] = sub("-fstack-protector-strong", "", vars[var])
+        if not clang_has_option("-fno-semantic-interposition"):
+            vars[var] = sub("-fno-semantic-interposition", "", vars[var])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c
new file mode 100644
index 000000000000..1580a3cbec2d
--- /dev/null
+++ b/tools/perf/util/sideband_evlist.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "util/debug.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/mmap.h"
+#include "util/perf_api_probe.h"
+#include <perf/mmap.h>
+#include <linux/perf_event.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdbool.h>
+
+int perf_evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
+			      evsel__sb_cb_t cb, void *data)
+{
+	struct evsel *evsel;
+
+	if (!attr->sample_id_all) {
+		pr_warning("enabling sample_id_all for all side band events\n");
+		attr->sample_id_all = 1;
+	}
+
+	evsel = perf_evsel__new_idx(attr, evlist->core.nr_entries);
+	if (!evsel)
+		return -1;
+
+	evsel->side_band.cb = cb;
+	evsel->side_band.data = data;
+	evlist__add(evlist, evsel);
+	return 0;
+}
+
+static void *perf_evlist__poll_thread(void *arg)
+{
+	struct evlist *evlist = arg;
+	bool draining = false;
+	int i, done = 0;
+	/*
+	 * In order to read symbols from other namespaces perf to needs to call
+	 * setns(2).  This isn't permitted if the struct_fs has multiple users.
+	 * unshare(2) the fs so that we may continue to setns into namespaces
+	 * that we're observing when, for instance, reading the build-ids at
+	 * the end of a 'perf record' session.
+	 */
+	unshare(CLONE_FS);
+
+	while (!done) {
+		bool got_data = false;
+
+		if (evlist->thread.done)
+			draining = true;
+
+		if (!draining)
+			evlist__poll(evlist, 1000);
+
+		for (i = 0; i < evlist->core.nr_mmaps; i++) {
+			struct mmap *map = &evlist->mmap[i];
+			union perf_event *event;
+
+			if (perf_mmap__read_init(&map->core))
+				continue;
+			while ((event = perf_mmap__read_event(&map->core)) != NULL) {
+				struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+				if (evsel && evsel->side_band.cb)
+					evsel->side_band.cb(event, evsel->side_band.data);
+				else
+					pr_warning("cannot locate proper evsel for the side band event\n");
+
+				perf_mmap__consume(&map->core);
+				got_data = true;
+			}
+			perf_mmap__read_done(&map->core);
+		}
+
+		if (draining && !got_data)
+			break;
+	}
+	return NULL;
+}
+
+void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data)
+{
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		evsel->core.attr.sample_id_all    = 1;
+		evsel->core.attr.watermark        = 1;
+		evsel->core.attr.wakeup_watermark = 1;
+		evsel->side_band.cb   = cb;
+		evsel->side_band.data = data;
+      }
+}
+
+int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target)
+{
+	struct evsel *counter;
+
+	if (!evlist)
+		return 0;
+
+	if (perf_evlist__create_maps(evlist, target))
+		goto out_delete_evlist;
+
+	if (evlist->core.nr_entries > 1) {
+		bool can_sample_identifier = perf_can_sample_identifier();
+
+		evlist__for_each_entry(evlist, counter)
+			evsel__set_sample_id(counter, can_sample_identifier);
+
+		perf_evlist__set_id_pos(evlist);
+	}
+
+	evlist__for_each_entry(evlist, counter) {
+		if (evsel__open(counter, evlist->core.cpus, evlist->core.threads) < 0)
+			goto out_delete_evlist;
+	}
+
+	if (evlist__mmap(evlist, UINT_MAX))
+		goto out_delete_evlist;
+
+	evlist__for_each_entry(evlist, counter) {
+		if (evsel__enable(counter))
+			goto out_delete_evlist;
+	}
+
+	evlist->thread.done = 0;
+	if (pthread_create(&evlist->thread.th, NULL, perf_evlist__poll_thread, evlist))
+		goto out_delete_evlist;
+
+	return 0;
+
+out_delete_evlist:
+	evlist__delete(evlist);
+	evlist = NULL;
+	return -1;
+}
+
+void perf_evlist__stop_sb_thread(struct evlist *evlist)
+{
+	if (!evlist)
+		return;
+	evlist->thread.done = 1;
+	pthread_join(evlist->thread.th, NULL);
+	evlist__delete(evlist);
+}
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 3b791ef2cd50..20bacd5972ad 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -15,6 +15,9 @@ int smt_on(void)
 	if (cached)
 		return cached_result;
 
+	if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0)
+		goto done;
+
 	ncpu = sysconf(_SC_NPROCESSORS_CONF);
 	for (cpu = 0; cpu < ncpu; cpu++) {
 		unsigned long long siblings;
@@ -24,13 +27,13 @@ int smt_on(void)
 
 		snprintf(fn, sizeof fn,
 			"devices/system/cpu/cpu%d/topology/core_cpus", cpu);
-		if (access(fn, F_OK) == -1) {
+		if (sysfs__read_str(fn, &str, &strlen) < 0) {
 			snprintf(fn, sizeof fn,
 				"devices/system/cpu/cpu%d/topology/thread_siblings",
 				cpu);
+			if (sysfs__read_str(fn, &str, &strlen) < 0)
+				continue;
 		}
-		if (sysfs__read_str(fn, &str, &strlen) < 0)
-			continue;
 		/* Entry is hex, but does not have 0x, so need custom parser */
 		siblings = strtoull(str, NULL, 16);
 		free(str);
@@ -42,6 +45,7 @@ int smt_on(void)
 	}
 	if (!cached) {
 		cached_result = 0;
+done:
 		cached = true;
 	}
 	return cached_result;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index f14cc728c358..c1f8879f92cc 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -237,7 +237,7 @@ static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
 	return (int64_t)(right_ip - left_ip);
 }
 
-static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
+int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 {
 	if (!sym_l || !sym_r)
 		return cmp_null(sym_l, sym_r);
@@ -300,8 +300,14 @@ static int _hist_entry__sym_snprintf(struct map_symbol *ms,
 
 	if (verbose > 0) {
 		char o = map ? dso__symtab_origin(map->dso) : '!';
+		u64 rip = ip;
+
+		if (map && map->dso && map->dso->kernel
+		    && map->dso->adjust_symbols)
+			rip = map->unmap_ip(map, ip);
+
 		ret += repsep_snprintf(bf, size, "%-#*llx %c ",
-				       BITS_PER_LONG / 4 + 2, ip, o);
+				       BITS_PER_LONG / 4 + 2, rip, o);
 	}
 
 	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
@@ -2354,7 +2360,7 @@ static struct evsel *find_evsel(struct evlist *evlist, char *event_name)
 
 		evsel = evlist__first(evlist);
 		while (--nr > 0)
-			evsel = perf_evsel__next(evsel);
+			evsel = evsel__next(evsel);
 
 		return evsel;
 	}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index cfa6ac6f7d06..66d39c4cfe2b 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -311,5 +311,7 @@ int64_t
 sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right);
+int64_t
+_sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r);
 char *hist_entry__srcline(struct hist_entry *he);
 #endif	/* __PERF_SORT_H */
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 9e757d18d713..3c6976f7574c 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -237,8 +237,6 @@ static bool valid_only_metric(const char *unit)
 	if (!unit)
 		return false;
 	if (strstr(unit, "/sec") ||
-	    strstr(unit, "hz") ||
-	    strstr(unit, "Hz") ||
 	    strstr(unit, "CPUs utilized"))
 		return false;
 	return true;
@@ -248,7 +246,7 @@ static const char *fixunit(char *buf, struct evsel *evsel,
 			   const char *unit)
 {
 	if (!strncmp(unit, "of all", 6)) {
-		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+		snprintf(buf, 1024, "%s %s", evsel__name(evsel),
 			 unit);
 		return buf;
 	}
@@ -335,7 +333,7 @@ static int first_shadow_cpu(struct perf_stat_config *config,
 	if (config->aggr_mode == AGGR_GLOBAL)
 		return 0;
 
-	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+	for (i = 0; i < evsel__nr_cpus(evsel); i++) {
 		int cpu2 = evsel__cpus(evsel)->map[i];
 
 		if (config->aggr_get_id(config, evlist->core.cpus, cpu2) == id)
@@ -369,7 +367,7 @@ static void abs_printout(struct perf_stat_config *config,
 			config->csv_output ? 0 : config->unit_width,
 			evsel->unit, config->csv_sep);
 
-	fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
+	fprintf(output, "%-*s", config->csv_output ? 0 : 25, evsel__name(evsel));
 
 	print_cgroup(config, evsel);
 }
@@ -463,8 +461,7 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 			counter->unit, config->csv_sep);
 
 		fprintf(config->output, "%*s",
-			config->csv_output ? 0 : -25,
-			perf_evsel__name(counter));
+			config->csv_output ? 0 : -25, evsel__name(counter));
 
 		print_cgroup(config, counter);
 
@@ -510,7 +507,7 @@ static void aggr_update_shadow(struct perf_stat_config *config,
 		id = config->aggr_map->map[s];
 		evlist__for_each_entry(evlist, counter) {
 			val = 0;
-			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+			for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
 				s2 = config->aggr_get_id(config, evlist->core.cpus, cpu);
 				if (s2 != id)
 					continue;
@@ -561,11 +558,11 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c
 
 	alias = list_prepare_entry(counter, &(evlist->core.entries), core.node);
 	list_for_each_entry_continue (alias, &evlist->core.entries, core.node) {
-		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+		if (strcmp(evsel__name(alias), evsel__name(counter)) ||
 		    alias->scale != counter->scale ||
 		    alias->cgrp != counter->cgrp ||
 		    strcmp(alias->unit, counter->unit) ||
-		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter) ||
+		    evsel__is_clock(alias) != evsel__is_clock(counter) ||
 		    !strcmp(alias->pmu_name, counter->pmu_name))
 			break;
 		alias->merged_stat = true;
@@ -601,7 +598,7 @@ static void aggr_cb(struct perf_stat_config *config,
 	struct aggr_data *ad = data;
 	int cpu, s2;
 
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+	for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
 		struct perf_counts_values *counts;
 
 		s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu);
@@ -849,7 +846,7 @@ static void print_counter(struct perf_stat_config *config,
 	double uval;
 	int cpu;
 
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+	for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
 		struct aggr_data ad = { .cpu = cpu };
 
 		if (!collect_data(config, counter, counter_cb, &ad))
@@ -1150,7 +1147,7 @@ static void print_percore_thread(struct perf_stat_config *config,
 	int s, s2, id;
 	bool first = true;
 
-	for (int i = 0; i < perf_evsel__nr_cpus(counter); i++) {
+	for (int i = 0; i < evsel__nr_cpus(counter); i++) {
 		s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
 		for (s = 0; s < config->aggr_map->nr; s++) {
 			id = config->aggr_map->map[s];
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 0fd713d3674f..129b8c5f2538 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -216,9 +216,9 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 
 	count *= counter->scale;
 
-	if (perf_evsel__is_clock(counter))
+	if (evsel__is_clock(counter))
 		update_runtime_stat(st, STAT_NSECS, 0, cpu, count_ns);
-	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+	else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
 	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
 		update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count);
@@ -241,25 +241,25 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 	else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
 		update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
 				    ctx, cpu, count);
-	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+	else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
 				    ctx, cpu, count);
-	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+	else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
 				    ctx, cpu, count);
-	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+	else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
 		update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count);
-	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+	else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
 		update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+	else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
 		update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+	else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
 		update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+	else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
 		update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+	else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
 		update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+	else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
 		update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count);
 	else if (perf_stat_evsel__is(counter, SMI_NUM))
 		update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count);
@@ -336,7 +336,7 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 		metric_events = counter->metric_events;
 		if (!metric_events) {
 			if (expr__find_other(counter->metric_expr, counter->name,
-						&metric_names, &num_metric_names) < 0)
+						&metric_names, &num_metric_names, 1) < 0)
 				continue;
 
 			metric_events = calloc(sizeof(struct evsel *),
@@ -723,13 +723,14 @@ static void generic_metric(struct perf_stat_config *config,
 			   char *name,
 			   const char *metric_name,
 			   const char *metric_unit,
+			   int runtime,
 			   double avg,
 			   int cpu,
 			   struct perf_stat_output_ctx *out,
 			   struct runtime_stat *st)
 {
 	print_metric_t print_metric = out->print_metric;
-	struct parse_ctx pctx;
+	struct expr_parse_ctx pctx;
 	double ratio, scale;
 	int i;
 	void *ctxp = out->ctx;
@@ -777,7 +778,7 @@ static void generic_metric(struct perf_stat_config *config,
 	}
 
 	if (!metric_events[i]) {
-		if (expr__parse(&ratio, &pctx, metric_expr) == 0) {
+		if (expr__parse(&ratio, &pctx, metric_expr, runtime) == 0) {
 			char *unit;
 			char metric_bf[64];
 
@@ -786,9 +787,13 @@ static void generic_metric(struct perf_stat_config *config,
 					&unit, &scale) >= 0) {
 					ratio *= scale;
 				}
-
-				scnprintf(metric_bf, sizeof(metric_bf),
+				if (strstr(metric_expr, "?"))
+					scnprintf(metric_bf, sizeof(metric_bf),
+					  "%s  %s_%d", unit, metric_name, runtime);
+				else
+					scnprintf(metric_bf, sizeof(metric_bf),
 					  "%s  %s", unit, metric_name);
+
 				print_metric(config, ctxp, NULL, "%8.1f",
 					     metric_bf, ratio);
 			} else {
@@ -803,8 +808,11 @@ static void generic_metric(struct perf_stat_config *config,
 				     out->force_header ?
 				     (metric_name ? metric_name : name) : "", 0);
 		}
-	} else
-		print_metric(config, ctxp, NULL, NULL, "", 0);
+	} else {
+		print_metric(config, ctxp, NULL, NULL,
+			     out->force_header ?
+			     (metric_name ? metric_name : name) : "", 0);
+	}
 
 	for (i = 1; i < pctx.num_ids; i++)
 		zfree(&pctx.ids[i].name);
@@ -825,7 +833,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 	struct metric_event *me;
 	int num = 1;
 
-	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
+	if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
 
 		if (total) {
@@ -850,7 +858,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					"stalled cycles per insn",
 					ratio);
 		}
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+	} else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
 		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
 			print_branch_misses(config, cpu, evsel, avg, out, st);
 		else
@@ -905,7 +913,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
+	} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
 
 		if (total)
@@ -916,11 +924,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 				     "of all cache refs", ratio);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+	} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
 		print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+	} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
 		print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+	} else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
 
 		if (total) {
@@ -971,7 +979,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			ratio = total / avg;
 
 		print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-	} else if (perf_evsel__is_clock(evsel)) {
+	} else if (evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
 			print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
 				     avg / (ratio * evsel->scale));
@@ -1019,7 +1027,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
-				evsel->metric_name, NULL, avg, cpu, out, st);
+				evsel->metric_name, NULL, 1, avg, cpu, out, st);
 	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
 		char unit = 'M';
 		char unit_buf[10];
@@ -1048,7 +1056,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 				out->new_line(config, ctxp);
 			generic_metric(config, mexp->metric_expr, mexp->metric_events,
 					evsel->name, mexp->metric_name,
-					mexp->metric_unit, avg, cpu, out, st);
+					mexp->metric_unit, mexp->runtime, avg, cpu, out, st);
 		}
 	}
 	if (num == 0)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 5f26137b8d60..774468341851 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -108,7 +108,7 @@ static void perf_stat_evsel_id_init(struct evsel *evsel)
 	/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
 
 	for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
-		if (!strcmp(perf_evsel__name(evsel), id_str[i])) {
+		if (!strcmp(evsel__name(evsel), id_str[i])) {
 			ps->id = i;
 			break;
 		}
@@ -173,7 +173,7 @@ static void perf_evsel__reset_prev_raw_counts(struct evsel *evsel)
 
 static int perf_evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
 {
-	int ncpus = perf_evsel__nr_cpus(evsel);
+	int ncpus = evsel__nr_cpus(evsel);
 	int nthreads = perf_thread_map__nr(evsel->core.threads);
 
 	if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
@@ -302,7 +302,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 	case AGGR_NODE:
 	case AGGR_NONE:
 		if (!evsel->snapshot)
-			perf_evsel__compute_deltas(evsel, cpu, thread, count);
+			evsel__compute_deltas(evsel, cpu, thread, count);
 		perf_counts_values__scale(count, config->scale, NULL);
 		if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
 			perf_stat__update_shadow_stats(evsel, count->val,
@@ -334,7 +334,7 @@ static int process_counter_maps(struct perf_stat_config *config,
 				struct evsel *counter)
 {
 	int nthreads = perf_thread_map__nr(counter->core.threads);
-	int ncpus = perf_evsel__nr_cpus(counter);
+	int ncpus = evsel__nr_cpus(counter);
 	int cpu, thread;
 
 	if (counter->core.system_wide)
@@ -368,8 +368,10 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	 * interval mode, otherwise overall avg running
 	 * averages will be shown for each interval.
 	 */
-	if (config->interval)
-		init_stats(ps->res_stats);
+	if (config->interval) {
+		for (i = 0; i < 3; i++)
+			init_stats(&ps->res_stats[i]);
+	}
 
 	if (counter->per_pkg)
 		zero_per_pkg(counter);
@@ -382,7 +384,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 		return 0;
 
 	if (!counter->snapshot)
-		perf_evsel__compute_deltas(counter, -1, -1, aggr);
+		evsel__compute_deltas(counter, -1, -1, aggr);
 	perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);
 
 	for (i = 0; i < 3; i++)
@@ -390,7 +392,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 
 	if (verbose > 0) {
 		fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
-			perf_evsel__name(counter), count[0], count[1], count[2]);
+			evsel__name(counter), count[0], count[1], count[2]);
 	}
 
 	/*
@@ -507,7 +509,7 @@ int create_perf_stat_counter(struct evsel *evsel,
 	 * either manually by us or by kernel via enable_on_exec
 	 * set later.
 	 */
-	if (perf_evsel__is_group_leader(evsel)) {
+	if (evsel__is_group_leader(evsel)) {
 		attr->disabled = 1;
 
 		/*
@@ -519,7 +521,7 @@ int create_perf_stat_counter(struct evsel *evsel,
 	}
 
 	if (target__has_cpu(target) && !target__has_per_thread(target))
-		return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
+		return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
 
-	return perf_evsel__open_per_thread(evsel, evsel->core.threads);
+	return evsel__open_per_thread(evsel, evsel->core.threads);
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 26bc6a0096ce..381da6b39f89 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -566,6 +566,20 @@ void dso__sort_by_name(struct dso *dso)
 	return symbols__sort_by_name(&dso->symbol_names, &dso->symbols);
 }
 
+/*
+ * While we find nice hex chars, build a long_val.
+ * Return number of chars processed.
+ */
+static int hex2u64(const char *ptr, u64 *long_val)
+{
+	char *p;
+
+	*long_val = strtoull(ptr, &p, 16);
+
+	return p - ptr;
+}
+
+
 int modules__parse(const char *filename, void *arg,
 		   int (*process_module)(void *arg, const char *name,
 					 u64 start, u64 size))
@@ -1544,6 +1558,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 		return true;
 
 	case DSO_BINARY_TYPE__BPF_PROG_INFO:
+	case DSO_BINARY_TYPE__BPF_IMAGE:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 	default:
 		return false;
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index a661b122d9d8..89b390623b63 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -37,6 +37,7 @@
 #include <string.h>
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
 #include <api/fs/fs.h>
+#include <api/io.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
@@ -71,7 +72,6 @@ int perf_tool__process_synth_event(struct perf_tool *tool,
 static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
 				    pid_t *tgid, pid_t *ppid)
 {
-	char filename[PATH_MAX];
 	char bf[4096];
 	int fd;
 	size_t size = 0;
@@ -81,11 +81,11 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
 	*tgid = -1;
 	*ppid = -1;
 
-	snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
+	snprintf(bf, sizeof(bf), "/proc/%d/status", pid);
 
-	fd = open(filename, O_RDONLY);
+	fd = open(bf, O_RDONLY);
 	if (fd < 0) {
-		pr_debug("couldn't open %s\n", filename);
+		pr_debug("couldn't open %s\n", bf);
 		return -1;
 	}
 
@@ -274,6 +274,79 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 	return 0;
 }
 
+static bool read_proc_maps_line(struct io *io, __u64 *start, __u64 *end,
+				u32 *prot, u32 *flags, __u64 *offset,
+				u32 *maj, u32 *min,
+				__u64 *inode,
+				ssize_t pathname_size, char *pathname)
+{
+	__u64 temp;
+	int ch;
+	char *start_pathname = pathname;
+
+	if (io__get_hex(io, start) != '-')
+		return false;
+	if (io__get_hex(io, end) != ' ')
+		return false;
+
+	/* map protection and flags bits */
+	*prot = 0;
+	ch = io__get_char(io);
+	if (ch == 'r')
+		*prot |= PROT_READ;
+	else if (ch != '-')
+		return false;
+	ch = io__get_char(io);
+	if (ch == 'w')
+		*prot |= PROT_WRITE;
+	else if (ch != '-')
+		return false;
+	ch = io__get_char(io);
+	if (ch == 'x')
+		*prot |= PROT_EXEC;
+	else if (ch != '-')
+		return false;
+	ch = io__get_char(io);
+	if (ch == 's')
+		*flags = MAP_SHARED;
+	else if (ch == 'p')
+		*flags = MAP_PRIVATE;
+	else
+		return false;
+	if (io__get_char(io) != ' ')
+		return false;
+
+	if (io__get_hex(io, offset) != ' ')
+		return false;
+
+	if (io__get_hex(io, &temp) != ':')
+		return false;
+	*maj = temp;
+	if (io__get_hex(io, &temp) != ' ')
+		return false;
+	*min = temp;
+
+	ch = io__get_dec(io, inode);
+	if (ch != ' ') {
+		*pathname = '\0';
+		return ch == '\n';
+	}
+	do {
+		ch = io__get_char(io);
+	} while (ch == ' ');
+	while (true) {
+		if (ch < 0)
+			return false;
+		if (ch == '\0' || ch == '\n' ||
+		    (pathname + 1 - start_pathname) >= pathname_size) {
+			*pathname = '\0';
+			return true;
+		}
+		*pathname++ = ch;
+		ch = io__get_char(io);
+	}
+}
+
 int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid,
@@ -281,9 +354,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       struct machine *machine,
 				       bool mmap_data)
 {
-	char filename[PATH_MAX];
-	FILE *fp;
 	unsigned long long t;
+	char bf[BUFSIZ];
+	struct io io;
 	bool truncation = false;
 	unsigned long long timeout = proc_map_timeout * 1000000ULL;
 	int rc = 0;
@@ -293,59 +366,52 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	if (machine__is_default_guest(machine))
 		return 0;
 
-	snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
-		 machine->root_dir, pid, pid);
+	snprintf(bf, sizeof(bf), "%s/proc/%d/task/%d/maps",
+		machine->root_dir, pid, pid);
 
-	fp = fopen(filename, "r");
-	if (fp == NULL) {
+	io.fd = open(bf, O_RDONLY, 0);
+	if (io.fd < 0) {
 		/*
 		 * We raced with a task exiting - just return:
 		 */
-		pr_debug("couldn't open %s\n", filename);
+		pr_debug("couldn't open %s\n", bf);
 		return -1;
 	}
+	io__init(&io, io.fd, bf, sizeof(bf));
 
 	event->header.type = PERF_RECORD_MMAP2;
 	t = rdclock();
 
-	while (1) {
-		char bf[BUFSIZ];
-		char prot[5];
-		char execname[PATH_MAX];
-		char anonstr[] = "//anon";
-		unsigned int ino;
+	while (!io.eof) {
+		static const char anonstr[] = "//anon";
 		size_t size;
-		ssize_t n;
 
-		if (fgets(bf, sizeof(bf), fp) == NULL)
-			break;
+		/* ensure null termination since stack will be reused. */
+		event->mmap2.filename[0] = '\0';
+
+		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
+		if (!read_proc_maps_line(&io,
+					&event->mmap2.start,
+					&event->mmap2.len,
+					&event->mmap2.prot,
+					&event->mmap2.flags,
+					&event->mmap2.pgoff,
+					&event->mmap2.maj,
+					&event->mmap2.min,
+					&event->mmap2.ino,
+					sizeof(event->mmap2.filename),
+					event->mmap2.filename))
+			continue;
 
 		if ((rdclock() - t) > timeout) {
-			pr_warning("Reading %s time out. "
+			pr_warning("Reading %s/proc/%d/task/%d/maps time out. "
 				   "You may want to increase "
 				   "the time limit by --proc-map-timeout\n",
-				   filename);
+				   machine->root_dir, pid, pid);
 			truncation = true;
 			goto out;
 		}
 
-		/* ensure null termination since stack will be reused. */
-		strcpy(execname, "");
-
-		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n",
-		       &event->mmap2.start, &event->mmap2.len, prot,
-		       &event->mmap2.pgoff, &event->mmap2.maj,
-		       &event->mmap2.min,
-		       &ino, execname);
-
-		/*
- 		 * Anon maps don't have the execname.
- 		 */
-		if (n < 7)
-			continue;
-
-		event->mmap2.ino = (u64)ino;
 		event->mmap2.ino_generation = 0;
 
 		/*
@@ -356,23 +422,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		else
 			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
 
-		/* map protection and flags bits */
-		event->mmap2.prot = 0;
-		event->mmap2.flags = 0;
-		if (prot[0] == 'r')
-			event->mmap2.prot |= PROT_READ;
-		if (prot[1] == 'w')
-			event->mmap2.prot |= PROT_WRITE;
-		if (prot[2] == 'x')
-			event->mmap2.prot |= PROT_EXEC;
-
-		if (prot[3] == 's')
-			event->mmap2.flags |= MAP_SHARED;
-		else
-			event->mmap2.flags |= MAP_PRIVATE;
-
-		if (prot[2] != 'x') {
-			if (!mmap_data || prot[0] != 'r')
+		if ((event->mmap2.prot & PROT_EXEC) == 0) {
+			if (!mmap_data || (event->mmap2.prot & PROT_READ) == 0)
 				continue;
 
 			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
@@ -382,17 +433,17 @@ out:
 		if (truncation)
 			event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
 
-		if (!strcmp(execname, ""))
-			strcpy(execname, anonstr);
+		if (!strcmp(event->mmap2.filename, ""))
+			strcpy(event->mmap2.filename, anonstr);
 
 		if (hugetlbfs_mnt_len &&
-		    !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
-			strcpy(execname, anonstr);
+		    !strncmp(event->mmap2.filename, hugetlbfs_mnt,
+			     hugetlbfs_mnt_len)) {
+			strcpy(event->mmap2.filename, anonstr);
 			event->mmap2.flags |= MAP_HUGETLB;
 		}
 
-		size = strlen(execname) + 1;
-		memcpy(event->mmap2.filename, execname, size);
+		size = strlen(event->mmap2.filename) + 1;
 		size = PERF_ALIGN(size, sizeof(u64));
 		event->mmap2.len -= event->mmap.start;
 		event->mmap2.header.size = (sizeof(event->mmap2) -
@@ -411,7 +462,7 @@ out:
 			break;
 	}
 
-	fclose(fp);
+	close(io.fd);
 	return rc;
 }
 
@@ -1130,7 +1181,7 @@ void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf
 		synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max);
 	default:
 		break;
-	};
+	}
 }
 
 static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 0885967d5bc3..1b992bbba4e8 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -80,6 +80,10 @@ struct thread_stack_entry {
  * @comm: current comm
  * @arr_sz: size of array if this is the first element of an array
  * @rstate: used to detect retpolines
+ * @br_stack_rb: branch stack (ring buffer)
+ * @br_stack_sz: maximum branch stack size
+ * @br_stack_pos: current position in @br_stack_rb
+ * @mispred_all: mark all branches as mispredicted
  */
 struct thread_stack {
 	struct thread_stack_entry *stack;
@@ -95,6 +99,10 @@ struct thread_stack {
 	struct comm *comm;
 	unsigned int arr_sz;
 	enum retpoline_state_t rstate;
+	struct branch_stack *br_stack_rb;
+	unsigned int br_stack_sz;
+	unsigned int br_stack_pos;
+	bool mispred_all;
 };
 
 /*
@@ -126,13 +134,26 @@ static int thread_stack__grow(struct thread_stack *ts)
 }
 
 static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
-			      struct call_return_processor *crp)
+			      struct call_return_processor *crp,
+			      bool callstack, unsigned int br_stack_sz)
 {
 	int err;
 
-	err = thread_stack__grow(ts);
-	if (err)
-		return err;
+	if (callstack) {
+		err = thread_stack__grow(ts);
+		if (err)
+			return err;
+	}
+
+	if (br_stack_sz) {
+		size_t sz = sizeof(struct branch_stack);
+
+		sz += br_stack_sz * sizeof(struct branch_entry);
+		ts->br_stack_rb = zalloc(sz);
+		if (!ts->br_stack_rb)
+			return -ENOMEM;
+		ts->br_stack_sz = br_stack_sz;
+	}
 
 	if (thread->maps && thread->maps->machine) {
 		struct machine *machine = thread->maps->machine;
@@ -150,7 +171,9 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
 }
 
 static struct thread_stack *thread_stack__new(struct thread *thread, int cpu,
-					      struct call_return_processor *crp)
+					      struct call_return_processor *crp,
+					      bool callstack,
+					      unsigned int br_stack_sz)
 {
 	struct thread_stack *ts = thread->ts, *new_ts;
 	unsigned int old_sz = ts ? ts->arr_sz : 0;
@@ -176,7 +199,7 @@ static struct thread_stack *thread_stack__new(struct thread *thread, int cpu,
 		ts += cpu;
 
 	if (!ts->stack &&
-	    thread_stack__init(ts, thread, crp))
+	    thread_stack__init(ts, thread, crp, callstack, br_stack_sz))
 		return NULL;
 
 	return ts;
@@ -319,6 +342,9 @@ static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 
 	if (!crp) {
 		ts->cnt = 0;
+		ts->br_stack_pos = 0;
+		if (ts->br_stack_rb)
+			ts->br_stack_rb->nr = 0;
 		return 0;
 	}
 
@@ -353,8 +379,33 @@ int thread_stack__flush(struct thread *thread)
 	return err;
 }
 
+static void thread_stack__update_br_stack(struct thread_stack *ts, u32 flags,
+					  u64 from_ip, u64 to_ip)
+{
+	struct branch_stack *bs = ts->br_stack_rb;
+	struct branch_entry *be;
+
+	if (!ts->br_stack_pos)
+		ts->br_stack_pos = ts->br_stack_sz;
+
+	ts->br_stack_pos -= 1;
+
+	be              = &bs->entries[ts->br_stack_pos];
+	be->from        = from_ip;
+	be->to          = to_ip;
+	be->flags.value = 0;
+	be->flags.abort = !!(flags & PERF_IP_FLAG_TX_ABORT);
+	be->flags.in_tx = !!(flags & PERF_IP_FLAG_IN_TX);
+	/* No support for mispredict */
+	be->flags.mispred = ts->mispred_all;
+
+	if (bs->nr < ts->br_stack_sz)
+		bs->nr += 1;
+}
+
 int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
-			u64 to_ip, u16 insn_len, u64 trace_nr)
+			u64 to_ip, u16 insn_len, u64 trace_nr, bool callstack,
+			unsigned int br_stack_sz, bool mispred_all)
 {
 	struct thread_stack *ts = thread__stack(thread, cpu);
 
@@ -362,12 +413,13 @@ int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 		return -EINVAL;
 
 	if (!ts) {
-		ts = thread_stack__new(thread, cpu, NULL);
+		ts = thread_stack__new(thread, cpu, NULL, callstack, br_stack_sz);
 		if (!ts) {
 			pr_warning("Out of memory: no thread stack\n");
 			return -ENOMEM;
 		}
 		ts->trace_nr = trace_nr;
+		ts->mispred_all = mispred_all;
 	}
 
 	/*
@@ -381,8 +433,14 @@ int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 		ts->trace_nr = trace_nr;
 	}
 
-	/* Stop here if thread_stack__process() is in use */
-	if (ts->crp)
+	if (br_stack_sz)
+		thread_stack__update_br_stack(ts, flags, from_ip, to_ip);
+
+	/*
+	 * Stop here if thread_stack__process() is in use, or not recording call
+	 * stack.
+	 */
+	if (ts->crp || !callstack)
 		return 0;
 
 	if (flags & PERF_IP_FLAG_CALL) {
@@ -430,6 +488,7 @@ static void __thread_stack__free(struct thread *thread, struct thread_stack *ts)
 {
 	__thread_stack__flush(thread, ts);
 	zfree(&ts->stack);
+	zfree(&ts->br_stack_rb);
 }
 
 static void thread_stack__reset(struct thread *thread, struct thread_stack *ts)
@@ -497,6 +556,199 @@ void thread_stack__sample(struct thread *thread, int cpu,
 	chain->nr = i;
 }
 
+/*
+ * Hardware sample records, created some time after the event occurred, need to
+ * have subsequent addresses removed from the call chain.
+ */
+void thread_stack__sample_late(struct thread *thread, int cpu,
+			       struct ip_callchain *chain, size_t sz,
+			       u64 sample_ip, u64 kernel_start)
+{
+	struct thread_stack *ts = thread__stack(thread, cpu);
+	u64 sample_context = callchain_context(sample_ip, kernel_start);
+	u64 last_context, context, ip;
+	size_t nr = 0, j;
+
+	if (sz < 2) {
+		chain->nr = 0;
+		return;
+	}
+
+	if (!ts)
+		goto out;
+
+	/*
+	 * When tracing kernel space, kernel addresses occur at the top of the
+	 * call chain after the event occurred but before tracing stopped.
+	 * Skip them.
+	 */
+	for (j = 1; j <= ts->cnt; j++) {
+		ip = ts->stack[ts->cnt - j].ret_addr;
+		context = callchain_context(ip, kernel_start);
+		if (context == PERF_CONTEXT_USER ||
+		    (context == sample_context && ip == sample_ip))
+			break;
+	}
+
+	last_context = sample_ip; /* Use sample_ip as an invalid context */
+
+	for (; nr < sz && j <= ts->cnt; nr++, j++) {
+		ip = ts->stack[ts->cnt - j].ret_addr;
+		context = callchain_context(ip, kernel_start);
+		if (context != last_context) {
+			if (nr >= sz - 1)
+				break;
+			chain->ips[nr++] = context;
+			last_context = context;
+		}
+		chain->ips[nr] = ip;
+	}
+out:
+	if (nr) {
+		chain->nr = nr;
+	} else {
+		chain->ips[0] = sample_context;
+		chain->ips[1] = sample_ip;
+		chain->nr = 2;
+	}
+}
+
+void thread_stack__br_sample(struct thread *thread, int cpu,
+			     struct branch_stack *dst, unsigned int sz)
+{
+	struct thread_stack *ts = thread__stack(thread, cpu);
+	const size_t bsz = sizeof(struct branch_entry);
+	struct branch_stack *src;
+	struct branch_entry *be;
+	unsigned int nr;
+
+	dst->nr = 0;
+
+	if (!ts)
+		return;
+
+	src = ts->br_stack_rb;
+	if (!src->nr)
+		return;
+
+	dst->nr = min((unsigned int)src->nr, sz);
+
+	be = &dst->entries[0];
+	nr = min(ts->br_stack_sz - ts->br_stack_pos, (unsigned int)dst->nr);
+	memcpy(be, &src->entries[ts->br_stack_pos], bsz * nr);
+
+	if (src->nr >= ts->br_stack_sz) {
+		sz -= nr;
+		be = &dst->entries[nr];
+		nr = min(ts->br_stack_pos, sz);
+		memcpy(be, &src->entries[0], bsz * ts->br_stack_pos);
+	}
+}
+
+/* Start of user space branch entries */
+static bool us_start(struct branch_entry *be, u64 kernel_start, bool *start)
+{
+	if (!*start)
+		*start = be->to && be->to < kernel_start;
+
+	return *start;
+}
+
+/*
+ * Start of branch entries after the ip fell in between 2 branches, or user
+ * space branch entries.
+ */
+static bool ks_start(struct branch_entry *be, u64 sample_ip, u64 kernel_start,
+		     bool *start, struct branch_entry *nb)
+{
+	if (!*start) {
+		*start = (nb && sample_ip >= be->to && sample_ip <= nb->from) ||
+			 be->from < kernel_start ||
+			 (be->to && be->to < kernel_start);
+	}
+
+	return *start;
+}
+
+/*
+ * Hardware sample records, created some time after the event occurred, need to
+ * have subsequent addresses removed from the branch stack.
+ */
+void thread_stack__br_sample_late(struct thread *thread, int cpu,
+				  struct branch_stack *dst, unsigned int sz,
+				  u64 ip, u64 kernel_start)
+{
+	struct thread_stack *ts = thread__stack(thread, cpu);
+	struct branch_entry *d, *s, *spos, *ssz;
+	struct branch_stack *src;
+	unsigned int nr = 0;
+	bool start = false;
+
+	dst->nr = 0;
+
+	if (!ts)
+		return;
+
+	src = ts->br_stack_rb;
+	if (!src->nr)
+		return;
+
+	spos = &src->entries[ts->br_stack_pos];
+	ssz  = &src->entries[ts->br_stack_sz];
+
+	d = &dst->entries[0];
+	s = spos;
+
+	if (ip < kernel_start) {
+		/*
+		 * User space sample: start copying branch entries when the
+		 * branch is in user space.
+		 */
+		for (s = spos; s < ssz && nr < sz; s++) {
+			if (us_start(s, kernel_start, &start)) {
+				*d++ = *s;
+				nr += 1;
+			}
+		}
+
+		if (src->nr >= ts->br_stack_sz) {
+			for (s = &src->entries[0]; s < spos && nr < sz; s++) {
+				if (us_start(s, kernel_start, &start)) {
+					*d++ = *s;
+					nr += 1;
+				}
+			}
+		}
+	} else {
+		struct branch_entry *nb = NULL;
+
+		/*
+		 * Kernel space sample: start copying branch entries when the ip
+		 * falls in between 2 branches (or the branch is in user space
+		 * because then the start must have been missed).
+		 */
+		for (s = spos; s < ssz && nr < sz; s++) {
+			if (ks_start(s, ip, kernel_start, &start, nb)) {
+				*d++ = *s;
+				nr += 1;
+			}
+			nb = s;
+		}
+
+		if (src->nr >= ts->br_stack_sz) {
+			for (s = &src->entries[0]; s < spos && nr < sz; s++) {
+				if (ks_start(s, ip, kernel_start, &start, nb)) {
+					*d++ = *s;
+					nr += 1;
+				}
+				nb = s;
+			}
+		}
+	}
+
+	dst->nr = nr;
+}
+
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data)
@@ -864,7 +1116,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 	}
 
 	if (!ts) {
-		ts = thread_stack__new(thread, sample->cpu, crp);
+		ts = thread_stack__new(thread, sample->cpu, crp, true, 0);
 		if (!ts)
 			return -ENOMEM;
 		ts->comm = comm;
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index e1ec5a58f1b2..3bc47a42af8e 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -81,10 +81,19 @@ struct call_return_processor {
 };
 
 int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
-			u64 to_ip, u16 insn_len, u64 trace_nr);
+			u64 to_ip, u16 insn_len, u64 trace_nr, bool callstack,
+			unsigned int br_stack_sz, bool mispred_all);
 void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, int cpu, struct ip_callchain *chain,
 			  size_t sz, u64 ip, u64 kernel_start);
+void thread_stack__sample_late(struct thread *thread, int cpu,
+			       struct ip_callchain *chain, size_t sz, u64 ip,
+			       u64 kernel_start);
+void thread_stack__br_sample(struct thread *thread, int cpu,
+			     struct branch_stack *dst, unsigned int sz);
+void thread_stack__br_sample_late(struct thread *thread, int cpu,
+				  struct branch_stack *dst, unsigned int sz,
+				  u64 sample_ip, u64 kernel_start);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread, int cpu);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 28b719388028..665e5c0618ed 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -47,6 +47,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->tid = tid;
 		thread->ppid = -1;
 		thread->cpu = -1;
+		thread->lbr_stitch_enable = false;
 		INIT_LIST_HEAD(&thread->namespaces_list);
 		INIT_LIST_HEAD(&thread->comm_list);
 		init_rwsem(&thread->namespaces_lock);
@@ -110,6 +111,7 @@ void thread__delete(struct thread *thread)
 
 	exit_rwsem(&thread->namespaces_lock);
 	exit_rwsem(&thread->comm_lock);
+	thread__free_stitch_list(thread);
 	free(thread);
 }
 
@@ -452,3 +454,25 @@ int thread__memcpy(struct thread *thread, struct machine *machine,
 
        return dso__data_read_offset(al.map->dso, machine, offset, buf, len);
 }
+
+void thread__free_stitch_list(struct thread *thread)
+{
+	struct lbr_stitch *lbr_stitch = thread->lbr_stitch;
+	struct stitch_list *pos, *tmp;
+
+	if (!lbr_stitch)
+		return;
+
+	list_for_each_entry_safe(pos, tmp, &lbr_stitch->lists, node) {
+		list_del_init(&pos->node);
+		free(pos);
+	}
+
+	list_for_each_entry_safe(pos, tmp, &lbr_stitch->free_lists, node) {
+		list_del_init(&pos->node);
+		free(pos);
+	}
+
+	zfree(&lbr_stitch->prev_lbr_cursor);
+	zfree(&thread->lbr_stitch);
+}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 20b96b5d1f15..b066fb30d203 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -13,6 +13,8 @@
 #include <strlist.h>
 #include <intlist.h>
 #include "rwsem.h"
+#include "event.h"
+#include "callchain.h"
 
 struct addr_location;
 struct map;
@@ -20,6 +22,13 @@ struct perf_record_namespaces;
 struct thread_stack;
 struct unwind_libunwind_ops;
 
+struct lbr_stitch {
+	struct list_head		lists;
+	struct list_head		free_lists;
+	struct perf_sample		prev_sample;
+	struct callchain_cursor_node	*prev_lbr_cursor;
+};
+
 struct thread {
 	union {
 		struct rb_node	 rb_node;
@@ -46,6 +55,10 @@ struct thread {
 	struct srccode_state	srccode_state;
 	bool			filter;
 	int			filter_entry_depth;
+
+	/* LBR call stack stitch */
+	bool			lbr_stitch_enable;
+	struct lbr_stitch	*lbr_stitch;
 };
 
 struct machine;
@@ -142,4 +155,6 @@ static inline bool thread__is_filtered(struct thread *thread)
 	return false;
 }
 
+void thread__free_stitch_list(struct thread *thread);
+
 #endif	/* __PERF_THREAD_H */
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 3dce2de9d005..27945eeb0cb5 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -77,7 +77,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 				opts->freq ? "Hz" : "");
 	}
 
-	ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel));
+	ret += SNPRINTF(bf + ret, size - ret, "%s", evsel__name(top->sym_evsel));
 
 	ret += SNPRINTF(bf + ret, size - ret, "], ");
 
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index f117d4f4821e..ff8391208ecd 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -18,7 +18,7 @@ struct perf_session;
 
 struct perf_top {
 	struct perf_tool   tool;
-	struct evlist *evlist;
+	struct evlist *evlist, *sb_evlist;
 	struct record_opts record_opts;
 	struct annotation_options annotation_opts;
 	struct evswitch	   evswitch;
@@ -36,6 +36,7 @@ struct perf_top {
 	bool		   use_tui, use_stdio;
 	bool		   vmlinux_warned;
 	bool		   dump_symtab;
+	bool		   stitch_lbr;
 	struct hist_entry  *sym_filter_entry;
 	struct evsel 	   *sym_evsel;
 	struct perf_session *session;
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 8593d3c200c6..f507dff713c9 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -75,7 +75,7 @@ static void skip(int size)
 		r = size > BUFSIZ ? BUFSIZ : size;
 		do_read(buf, r);
 		size -= r;
-	};
+	}
 }
 
 static unsigned int read4(struct tep_handle *pevent)
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index d707c9624dd9..37a9492edb3e 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -290,6 +290,7 @@ int perf_event_paranoid(void)
 bool perf_event_paranoid_check(int max_level)
 {
 	return perf_cap__capable(CAP_SYS_ADMIN) ||
+			perf_cap__capable(CAP_PERFMON) ||
 			perf_event_paranoid() <= max_level;
 }
 
diff --git a/tools/power/pm-graph/Makefile b/tools/power/pm-graph/Makefile
index 845541544570..b5310832c19c 100644
--- a/tools/power/pm-graph/Makefile
+++ b/tools/power/pm-graph/Makefile
@@ -41,6 +41,10 @@ uninstall :
 	if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph/config ] ; then \
 		rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph/config; \
 	fi;
+	rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/__pycache__/*
+	if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph/__pycache__ ] ; then \
+		rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph/__pycache__; \
+	fi;
 	rm -f $(DESTDIR)$(PREFIX)/lib/pm-graph/*
 	if [ -d $(DESTDIR)$(PREFIX)/lib/pm-graph ] ; then \
 		rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph; \
diff --git a/tools/power/pm-graph/README b/tools/power/pm-graph/README
index 96259f6e5715..afe6beb40ad9 100644
--- a/tools/power/pm-graph/README
+++ b/tools/power/pm-graph/README
@@ -1,7 +1,12 @@
-                     p m - g r a p h
+                                                _
+    _ __  _ __ ___         __ _ _ __ __ _ _ __ | |__
+   | '_ \| '_ ` _ \ _____ / _` | '__/ _` | '_ \| '_ \
+   | |_) | | | | | |_____| (_| | | | (_| | |_) | | | |
+   | .__/|_| |_| |_|      \__, |_|  \__,_| .__/|_| |_|
+   |_|                    |___/          |_|
 
    pm-graph: suspend/resume/boot timing analysis tools
-    Version: 5.5
+    Version: 5.6
      Author: Todd Brandt <todd.e.brandt@intel.com>
   Home Page: https://01.org/pm-graph
 
@@ -18,10 +23,6 @@
 	- upstream version in git:
 	  https://github.com/intel/pm-graph/
 
- Requirements:
-	- runs with python2 or python3, choice is made by /usr/bin/python link
-	- python2 now requires python-configparser be installed
-
  Table of Contents
 	- Overview
 	- Setup
@@ -29,6 +30,8 @@
 		- Basic Usage
 		- Dev Mode Usage
 		- Proc Mode Usage
+	- Endurance Testing
+		- Usage Examples
 	- Configuration Files
 		- Usage Examples
 		- Config File Options
@@ -54,15 +57,18 @@
 |                            SETUP                               |
 ------------------------------------------------------------------
 
-    These packages are required to execute the scripts
+    Package Requirements
+       - runs with python2 or python3, choice is made by /usr/bin/python link
        - python
-       - python-requests
+       - python-configparser (for python2 sleepgraph)
+       - python-requests (for googlesheet.py)
+       - linux-tools-common (for turbostat usage in sleepgraph)
 
        Ubuntu:
-          sudo apt-get install python python-requests
+          sudo apt-get install python python-configparser python-requests linux-tools-common
 
        Fedora:
-          sudo dnf install python python-requests
+          sudo dnf install python python-configparser python-requests linux-tools-common
 
     The tools can most easily be installed via git clone and make install
 
@@ -190,6 +196,104 @@ _______________
 
  %> sudo ./sleepgraph.py -config config/suspend-proc.cfg
 
+------------------------------------------------------------------
+|                     ENDURANCE TESTING                          |
+------------------------------------------------------------------
+
+ The best way to gauge the health of a system is to run a series of
+ suspend/resumes over an extended period and analyze the behavior. This can be
+ accomplished with sleepgraph's -multi argument. You specify two numbers: the
+ number of tests to run OR the duration in days, hours, or minutes, and the
+ delay in seconds between them. For instance, -multi 20 5: execute 20 tests with
+ a 5 second delay between each, or -multi 24h 0: execute tests over a 24 hour
+ period with no delay between tests. You can include any other options you like
+ to generate the data you want. It's most useful to collect dev mode timelines
+ as the kprobes don't alter the performance much and you get more insight.
+
+ On completion, the output folder contains a series of folders for the
+ individual test data and a set of summary pages in the root. The summary.html
+ file is a tabular list of the tests with relevant info and links. The
+ summary-issue.html and summary-devices.html files include data taken from
+ all tests on kernel issues and device performance. The folder looks like this:
+
+  suspend-xN-{date}-{time}:
+	summary.html
+	summary-issues.html
+	summary-devices.html
+	suspend-{date}-{time} (1)
+	suspend-{date}-{time} (2)
+	...
+
+ These are the relevant arguments to use for testing:
+
+  -m mode
+	Mode to initiate for suspend e.g. mem, freeze, standby (default: mem).
+
+  -rtcwake t
+	Use rtcwake to autoresume after t seconds (default: 15).
+
+  -gzip (optional)
+	Gzip the trace and dmesg logs to save space. The tool can also read in
+	gzipped logs for processing. This reduces the multitest folder size.
+
+  -dev (optional)
+	Add kernel source calls and threads to the timeline (default: disabled).
+
+  -multi n d
+	Execute n consecutive tests at d seconds intervals. The outputs will be
+	created in a new subdirectory: suspend-xN-{date}-{time}. When the multitest
+	run is done, the -summary command is called automatically to create summary
+	html files for all the data (unless you use -skiphtml). -skiphtml will
+	speed up the testing by not creating timelines or summary html files. You
+	can then run the tool again at a later time with -summary and -genhtml to
+	create the timelines.
+
+  -skiphtml (optional)
+	Run the test and capture the trace logs, but skip the timeline and summary
+	html generation. This can greatly speed up overall testing. You can then
+	copy the data to a faster host machine and run -summary -genhtml to
+	generate the timelines and summary.
+
+ These are the relevant commands to use after testing is complete:
+
+  -summary indir
+	Generate or regenerate the summary for a -multi test run. Creates three
+	files: summary.html, summary-issues.html, and summary-devices.html in the
+	current folder. summary.html is a table of tests with relevant info sorted
+	by kernel/host/mode, and links to the test html files. summary-issues.html
+	is a list of kernel issues found in dmesg from all the tests.
+	summary-devices.html is a list of devices and times from all the tests.
+
+  -genhtml
+	Used  with -summary to regenerate any missing html timelines from their
+	dmesg and ftrace logs. This will require a significant amount of time if
+	there are thousands of tests.
+
+Usage Examples
+_______________
+
+ A multitest is initiated like this:
+
+  %> sudo ./sleepgraph.py -m mem -rtcwake 10 -dev -gzip -multi 2000 0
+
+	or you can skip timeline generation in order to speed things up
+
+  %> sudo ./sleepgraph.py -m mem -rtcwake 10 -dev -gzip -multi 2000 0 -skiphtml
+
+ The tool will produce an output folder with all the test subfolders inside.
+ Each test subfolder contains the dmesg/ftrace logs and/or the html timeline
+ depending on whether you used the -skiphtml option. The root folder contains
+ the summary.html files.
+
+ The summary for an existing multitest is generated like this:
+
+  %> cd suspend-x2000-{date}-{time}
+  %> sleepgraph.py -summary .
+
+	or if you need to generate the html timelines you can use -genhtml
+
+  %> cd suspend-xN-{date}-{time}
+  %> sleepgraph.py -summary . -genhtml
 
 ------------------------------------------------------------------
 |                    CONFIGURATION FILES                         |
diff --git a/tools/power/pm-graph/bootgraph.py b/tools/power/pm-graph/bootgraph.py
index d3b99a1e92d6..2823cd3122f7 100755
--- a/tools/power/pm-graph/bootgraph.py
+++ b/tools/power/pm-graph/bootgraph.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0-only
 #
 # Tool for analyzing boot timing
diff --git a/tools/power/pm-graph/config/custom-timeline-functions.cfg b/tools/power/pm-graph/config/custom-timeline-functions.cfg
index 4f80ad7d7275..962e5768681c 100644
--- a/tools/power/pm-graph/config/custom-timeline-functions.cfg
+++ b/tools/power/pm-graph/config/custom-timeline-functions.cfg
@@ -125,7 +125,7 @@ acpi_suspend_begin:
 suspend_console:
 acpi_pm_prepare:
 syscore_suspend:
-arch_enable_nonboot_cpus_end:
+arch_thaw_secondary_cpus_end:
 syscore_resume:
 acpi_pm_finish:
 resume_console:
diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8
index 43aee64316df..5126271de98a 100644
--- a/tools/power/pm-graph/sleepgraph.8
+++ b/tools/power/pm-graph/sleepgraph.8
@@ -74,8 +74,10 @@ after the test is complete.
 Switch the display to the requested mode for the test using the xset command.
 This helps maintain the consistency of test data for better comparison.
 .TP
-\fB-skiphtml\fR
-Run the test and capture the trace logs, but skip the timeline generation.
+\fB-wifi\fR
+If a wifi connection is available, check that it reconnects after resume. Include
+the reconnect time in the total resume time calculation and treat wifi timeouts
+as resume failures.
 
 .SS "advanced"
 .TP
@@ -117,8 +119,24 @@ Include \fIt\fR ms delay before 1st suspend (default: 0 ms).
 Include \fIt\fR ms delay after last resume (default: 0 ms).
 .TP
 \fB-multi \fIn d\fR
-Execute \fIn\fR consecutive tests at \fId\fR seconds intervals. The outputs will
-be created in a new subdirectory with a summary page: suspend-xN-{date}-{time}.
+Used for endurance testing. If \fIn\fR is entirely numeric, it's treated as a count:
+Execute \fIn\fR consecutive tests at \fId\fR second intervals.
+If \fIn\fR is an integer followed by a "d", "h", or "m", it's treated as a duration:
+Execute tests continuously over \fIn\fR days, hours, or minutes at \fId\fR second intervals.
+The outputs will be created in a new subdirectory, for count: suspend-{date}-{time}-xN,
+for duration: suspend-{date}-{time}-Nm. When the multitest run is done, the \fI-summary\fR
+command is called automatically to create summary html files for all the data (unless you
+use \fI-skiphtml\fR). \fI-skiphtml\fR will speed up the testing by not creating timelines
+or summary html files. You can then run the tool again at a later time with \fI-summary\fR
+and \fI-genhtml\fR to create the timelines.
+.TP
+\fB-maxfail \fIn\fR
+Abort a -multi run after \fIn\fR consecutive fails. 0 means never abort (default = 0).
+.TP
+\fB-skiphtml\fR
+Run the test and capture the trace logs, but skip the timeline generation.
+You can generate the html timelines later with \fI-dmesg\fR & \fI-ftrace\fR, or
+by running \fI-summary\fR and \fI-genhtml\fR.
 
 .SS "ftrace debug"
 .TP
@@ -173,11 +191,20 @@ Set trace buffer size to N kilo-bytes (default: all of free memory up to 3GB)
 .SH COMMANDS
 .TP
 \fB-summary \fIindir\fR
-Create a summary page of all tests in \fIindir\fR. Creates summary.html
-in the current folder. The output page is a table of tests with
-suspend and resume values sorted by suspend mode, host, and kernel.
-Includes test averages by mode and links to the test html files.
-Use -genhtml to include tests with missing html.
+Create a set of summary pages for all tests in \fIindir\fR recursively.
+Creates summary.html, summary-issues.html, and summary-devices.html in the current folder.
+summary.html is a table of tests with relevant info sorted by kernel/host/mode,
+and links to the test html files. It identifies the minimum, maximum, and median
+suspend and resume times for you with highlights and links in the header.
+summary-issues.html is a list of kernel issues found in dmesg from all the tests.
+summary-devices.html is a list of devices and times from all the tests.
+
+Use \fI-genhtml\fR to regenerate any tests with missing html.
+.TP
+\fB-genhtml\fR
+Used with \fI-summary\fR to regenerate any missing html timelines from their
+dmesg and ftrace logs. This will require a significant amount of time if there
+are thousands of tests.
 .TP
 \fB-modes\fR
 List available suspend modes.
@@ -189,10 +216,7 @@ with any options you intend to use to see if they will work.
 \fB-fpdt\fR
 Print out the contents of the ACPI Firmware Performance Data Table.
 .TP
-\fB-battery\fR
-Print out battery status and current charge.
-.TP
-\fB-wifi\fR
+\fB-wificheck\fR
 Print out wifi status and connection details.
 .TP
 \fB-xon/-xoff/-xstandby/-xsuspend\fR
@@ -208,6 +232,9 @@ Print out system info extracted from BIOS. Reads /dev/mem directly instead of go
 \fB-devinfo\fR
 Print out the pm settings of all devices which support runtime suspend.
 .TP
+\fB-cmdinfo\fR
+Print out all the platform data collected from the system that makes it into the logs.
+.TP
 \fB-flist\fR
 Print the list of ftrace functions currently being captured. Functions
 that are not available as symbols in the current kernel are shown in red.
@@ -272,14 +299,20 @@ Run two suspends back to back, include a 500ms delay before, after, and in betwe
 .IP
 \f(CW$ sudo sleepgraph -m mem -rtcwake 15 -x2 -predelay 500 -x2delay 500 -postdelay 500\fR
 .PP
+Execute a suspend using a custom command.
+.IP
+\f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR
+.PP
+
+.SS "endurance testing using -multi"
+.PP
 Do a batch run of 10 freezes with 30 seconds delay between runs.
 .IP
 \f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 10 30\fR
 .PP
-Execute a suspend using a custom command.
+Do a batch run of freezes for 24 hours.
 .IP
-\f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR
-.PP
+\f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 24h 0\fR
 
 .SS "adding callgraph data"
 Add device callgraphs. Limit the trace depth and only show callgraphs 10ms or larger.
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index f7d1c1f62f86..602e64b68ba7 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0-only
 #
 # Tool for analyzing suspend/resume timing
@@ -58,7 +58,7 @@ import re
 import platform
 import signal
 import codecs
-from datetime import datetime
+from datetime import datetime, timedelta
 import struct
 import configparser
 import gzip
@@ -81,12 +81,13 @@ def ascii(text):
 #	 store system values and test parameters
 class SystemValues:
 	title = 'SleepGraph'
-	version = '5.5'
+	version = '5.6'
 	ansi = False
 	rs = 0
 	display = ''
 	gzip = False
 	sync = False
+	wifi = False
 	verbose = False
 	testlog = True
 	dmesglog = True
@@ -97,7 +98,8 @@ class SystemValues:
 	cgphase = ''
 	cgtest = -1
 	cgskip = ''
-	multitest = {'run': False, 'count': 0, 'delay': 0}
+	maxfail = 0
+	multitest = {'run': False, 'count': 1000000, 'delay': 0}
 	max_graph_depth = 0
 	callloopmaxgap = 0.0001
 	callloopmaxlen = 0.005
@@ -148,7 +150,7 @@ class SystemValues:
 	x2delay = 0
 	skiphtml = False
 	usecallgraph = False
-	ftopfunc = 'suspend_devices_and_enter'
+	ftopfunc = 'pm_suspend'
 	ftop = False
 	usetraceevents = False
 	usetracemarkers = True
@@ -164,6 +166,8 @@ class SystemValues:
 	predelay = 0
 	postdelay = 0
 	pmdebug = ''
+	tmstart = 'SUSPEND START %Y%m%d-%H:%M:%S.%f'
+	tmend = 'RESUME COMPLETE %Y%m%d-%H:%M:%S.%f'
 	tracefuncs = {
 		'sys_sync': {},
 		'ksys_sync': {},
@@ -183,16 +187,18 @@ class SystemValues:
 		'acpi_s2idle_sync': {},
 		'acpi_s2idle_begin': {},
 		'acpi_s2idle_prepare': {},
+		'acpi_s2idle_prepare_late': {},
 		'acpi_s2idle_wake': {},
 		'acpi_s2idle_wakeup': {},
 		'acpi_s2idle_restore': {},
+		'acpi_s2idle_restore_early': {},
 		'hibernate_preallocate_memory': {},
 		'create_basic_memory_bitmaps': {},
 		'swsusp_write': {},
 		'suspend_console': {},
 		'acpi_pm_prepare': {},
 		'syscore_suspend': {},
-		'arch_enable_nonboot_cpus_end': {},
+		'arch_thaw_secondary_cpus_end': {},
 		'syscore_resume': {},
 		'acpi_pm_finish': {},
 		'resume_console': {},
@@ -270,12 +276,23 @@ class SystemValues:
 		'intel_opregion_init': {},
 		'intel_fbdev_set_suspend': {},
 	}
+	infocmds = [
+		[0, 'kparams', 'cat', '/proc/cmdline'],
+		[0, 'mcelog', 'mcelog'],
+		[0, 'pcidevices', 'lspci', '-tv'],
+		[0, 'usbdevices', 'lsusb', '-t'],
+		[1, 'interrupts', 'cat', '/proc/interrupts'],
+		[1, 'wakeups', 'cat', '/sys/kernel/debug/wakeup_sources'],
+		[2, 'gpecounts', 'sh', '-c', 'grep -v invalid /sys/firmware/acpi/interrupts/*'],
+		[2, 'suspendstats', 'sh', '-c', 'grep -v invalid /sys/power/suspend_stats/*'],
+		[2, 'cpuidle', 'sh', '-c', 'grep -v invalid /sys/devices/system/cpu/cpu*/cpuidle/state*/s2idle/*'],
+		[2, 'battery', 'sh', '-c', 'grep -v invalid /sys/class/power_supply/*/*'],
+	]
 	cgblacklist = []
 	kprobes = dict()
 	timeformat = '%.3f'
 	cmdline = '%s %s' % \
 			(os.path.basename(sys.argv[0]), ' '.join(sys.argv[1:]))
-	kparams = ''
 	sudouser = ''
 	def __init__(self):
 		self.archargs = 'args_'+platform.machine()
@@ -295,6 +312,9 @@ class SystemValues:
 		if os.getuid() == 0 and 'SUDO_USER' in os.environ and \
 			os.environ['SUDO_USER']:
 			self.sudouser = os.environ['SUDO_USER']
+	def resetlog(self):
+		self.logmsg = ''
+		self.platinfo = []
 	def vprint(self, msg):
 		self.logmsg += msg+'\n'
 		if self.verbose or msg.startswith('WARNING:'):
@@ -304,11 +324,11 @@ class SystemValues:
 			return
 		signame = self.signames[signum] if signum in self.signames else 'UNKNOWN'
 		msg = 'Signal %s caused a tool exit, line %d' % (signame, frame.f_lineno)
-		sysvals.outputResult({'error':msg})
+		self.outputResult({'error':msg})
 		sys.exit(3)
 	def signalHandlerInit(self):
 		capture = ['BUS', 'SYS', 'XCPU', 'XFSZ', 'PWR', 'HUP', 'INT', 'QUIT',
-			'ILL', 'ABRT', 'FPE', 'SEGV', 'TERM', 'TSTP']
+			'ILL', 'ABRT', 'FPE', 'SEGV', 'TERM']
 		self.signames = dict()
 		for i in capture:
 			s = 'SIG'+i
@@ -336,6 +356,8 @@ class SystemValues:
 			self.outputResult({'error':msg})
 			sys.exit(1)
 		return False
+	def usable(self, file):
+		return (os.path.exists(file) and os.path.getsize(file) > 0)
 	def getExec(self, cmd):
 		try:
 			fp = Popen(['which', cmd], stdout=PIPE, stderr=PIPE).stdout
@@ -389,12 +411,6 @@ class SystemValues:
 		r = info['bios-release-date'] if 'bios-release-date' in info else ''
 		self.sysstamp = '# sysinfo | man:%s | plat:%s | cpu:%s | bios:%s | biosdate:%s | numcpu:%d | memsz:%d | memfr:%d' % \
 			(m, p, c, b, r, self.cpucount, self.memtotal, self.memfree)
-		try:
-			kcmd = open('/proc/cmdline', 'r').read().strip()
-		except:
-			kcmd = ''
-		if kcmd:
-			self.sysstamp += '\n# kparams | %s' % kcmd
 	def printSystemInfo(self, fatal=False):
 		self.rootCheck(True)
 		out = dmidecode(self.mempath, fatal)
@@ -441,6 +457,7 @@ class SystemValues:
 			self.testdir+'/'+self.prefix+'_'+self.suspendmode+'.html'
 		if not os.path.isdir(self.testdir):
 			os.makedirs(self.testdir)
+		self.sudoUserchown(self.testdir)
 	def getValueList(self, value):
 		out = []
 		for i in value.split(','):
@@ -486,7 +503,7 @@ class SystemValues:
 		fp.close()
 		self.dmesgstart = float(ktime)
 	def getdmesg(self, testdata):
-		op = self.writeDatafileHeader(sysvals.dmesgfile, testdata)
+		op = self.writeDatafileHeader(self.dmesgfile, testdata)
 		# store all new dmesg lines since initdmesg was called
 		fp = Popen('dmesg', stdout=PIPE).stdout
 		for line in fp:
@@ -716,9 +733,10 @@ class SystemValues:
 			if name == f:
 				return True
 		return False
-	def initFtrace(self):
-		self.printSystemInfo(False)
-		pprint('INITIALIZING FTRACE...')
+	def initFtrace(self, quiet=False):
+		if not quiet:
+			sysvals.printSystemInfo(False)
+			pprint('INITIALIZING FTRACE...')
 		# turn trace off
 		self.fsetVal('0', 'tracing_on')
 		self.cleanupFtrace()
@@ -746,7 +764,7 @@ class SystemValues:
 			if tgtsize < 65536:
 				tgtsize = int(self.fgetVal('buffer_size_kb')) * cpus
 				break
-		pprint('Setting trace buffers to %d kB (%d kB per cpu)' % (tgtsize, tgtsize/cpus))
+		self.vprint('Setting trace buffers to %d kB (%d kB per cpu)' % (tgtsize, tgtsize/cpus))
 		# initialize the callgraph trace
 		if(self.usecallgraph):
 			# set trace type
@@ -782,7 +800,8 @@ class SystemValues:
 			if self.usedevsrc:
 				for name in self.dev_tracefuncs:
 					self.defaultKprobe(name, self.dev_tracefuncs[name])
-			pprint('INITIALIZING KPROBES...')
+			if not quiet:
+				pprint('INITIALIZING KPROBES...')
 			self.addKprobes(self.verbose)
 		if(self.usetraceevents):
 			# turn trace events on
@@ -827,21 +846,10 @@ class SystemValues:
 				fw = test['fw']
 				if(fw):
 					fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1]))
-			if 'mcelog' in test:
-				fp.write('# mcelog %s\n' % test['mcelog'])
 			if 'turbo' in test:
 				fp.write('# turbostat %s\n' % test['turbo'])
-			if 'bat' in test:
-				(a1, c1), (a2, c2) = test['bat']
-				fp.write('# battery %s %d %s %d\n' % (a1, c1, a2, c2))
 			if 'wifi' in test:
-				wstr = []
-				for wifi in test['wifi']:
-					tmp = []
-					for key in sorted(wifi):
-						tmp.append('%s:%s' % (key, wifi[key]))
-					wstr.append('|'.join(tmp))
-				fp.write('# wifi %s\n' % (','.join(wstr)))
+				fp.write('# wifi %s\n' % test['wifi'])
 			if test['error'] or len(testdata) > 1:
 				fp.write('# enter_sleep_error %s\n' % test['error'])
 		return fp
@@ -901,23 +909,7 @@ class SystemValues:
 	def b64zip(self, data):
 		out = base64.b64encode(codecs.encode(data.encode(), 'zlib')).decode()
 		return out
-	def mcelog(self, clear=False):
-		cmd = self.getExec('mcelog')
-		if not cmd:
-			return ''
-		if clear:
-			call(cmd+' > /dev/null 2>&1', shell=True)
-			return ''
-		try:
-			fp = Popen([cmd], stdout=PIPE, stderr=PIPE).stdout
-			out = ascii(fp.read()).strip()
-			fp.close()
-		except:
-			return ''
-		if not out:
-			return ''
-		return self.b64zip(out)
-	def platforminfo(self):
+	def platforminfo(self, cmdafter):
 		# add platform info on to a completed ftrace file
 		if not os.path.exists(self.ftracefile):
 			return False
@@ -1001,31 +993,76 @@ class SystemValues:
 		footer += '# platform-devinfo: %s\n' % self.b64zip(out)
 
 		# add a line for each of these commands with their outputs
-		cmds = [
-			['pcidevices', 'lspci', '-tv'],
-			['interrupts', 'cat', '/proc/interrupts'],
-			['gpecounts', 'sh', '-c', 'grep -v invalid /sys/firmware/acpi/interrupts/gpe*'],
-		]
-		for cargs in cmds:
-			name = cargs[0]
-			cmdline = ' '.join(cargs[1:])
-			cmdpath = self.getExec(cargs[1])
-			if not cmdpath:
+		for name, cmdline, info in cmdafter:
+			footer += '# platform-%s: %s | %s\n' % (name, cmdline, self.b64zip(info))
+
+		with self.openlog(self.ftracefile, 'a') as fp:
+			fp.write(footer)
+		return True
+	def commonPrefix(self, list):
+		if len(list) < 2:
+			return ''
+		prefix = list[0]
+		for s in list[1:]:
+			while s[:len(prefix)] != prefix and prefix:
+				prefix = prefix[:len(prefix)-1]
+			if not prefix:
+				break
+		if '/' in prefix and prefix[-1] != '/':
+			prefix = prefix[0:prefix.rfind('/')+1]
+		return prefix
+	def dictify(self, text, format):
+		out = dict()
+		header = True if format == 1 else False
+		delim = ' ' if format == 1 else ':'
+		for line in text.split('\n'):
+			if header:
+				header, out['@'] = False, line
+				continue
+			line = line.strip()
+			if delim in line:
+				data = line.split(delim, 1)
+				num = re.search(r'[\d]+', data[1])
+				if format == 2 and num:
+					out[data[0].strip()] = num.group()
+				else:
+					out[data[0].strip()] = data[1]
+		return out
+	def cmdinfo(self, begin, debug=False):
+		out = []
+		if begin:
+			self.cmd1 = dict()
+		for cargs in self.infocmds:
+			delta, name = cargs[0], cargs[1]
+			cmdline, cmdpath = ' '.join(cargs[2:]), self.getExec(cargs[2])
+			if not cmdpath or (begin and not delta):
 				continue
-			cmd = [cmdpath] + cargs[2:]
 			try:
-				fp = Popen(cmd, stdout=PIPE, stderr=PIPE).stdout
+				fp = Popen([cmdpath]+cargs[3:], stdout=PIPE, stderr=PIPE).stdout
 				info = ascii(fp.read()).strip()
 				fp.close()
 			except:
 				continue
-			if not info:
-				continue
-			footer += '# platform-%s: %s | %s\n' % (name, cmdline, self.b64zip(info))
-
-		with self.openlog(self.ftracefile, 'a') as fp:
-			fp.write(footer)
-		return True
+			if not debug and begin:
+				self.cmd1[name] = self.dictify(info, delta)
+			elif not debug and delta and name in self.cmd1:
+				before, after = self.cmd1[name], self.dictify(info, delta)
+				dinfo = ('\t%s\n' % before['@']) if '@' in before else ''
+				prefix = self.commonPrefix(list(before.keys()))
+				for key in sorted(before):
+					if key in after and before[key] != after[key]:
+						title = key.replace(prefix, '')
+						if delta == 2:
+							dinfo += '\t%s : %s -> %s\n' % \
+								(title, before[key].strip(), after[key].strip())
+						else:
+							dinfo += '%10s (start) : %s\n%10s (after) : %s\n' % \
+								(title, before[key], title, after[key])
+				dinfo = '\tnothing changed' if not dinfo else dinfo.rstrip()
+				out.append((name, cmdline, dinfo))
+			else:
+				out.append((name, cmdline, '\tnothing' if not info else info))
+		return out
 	def haveTurbostat(self):
 		if not self.tstat:
 			return False
@@ -1035,8 +1072,8 @@ class SystemValues:
 		fp = Popen([cmd, '-v'], stdout=PIPE, stderr=PIPE).stderr
 		out = ascii(fp.read()).strip()
 		fp.close()
-		if re.match('turbostat version [0-9\.]* .*', out):
-			sysvals.vprint(out)
+		if re.match('turbostat version .*', out):
+			self.vprint(out)
 			return True
 		return False
 	def turbostat(self):
@@ -1056,11 +1093,11 @@ class SystemValues:
 		fp.close()
 		if not keyline or not valline or len(keyline) != len(valline):
 			errmsg = 'unrecognized turbostat output:\n'+rawout.strip()
-			sysvals.vprint(errmsg)
-			if not sysvals.verbose:
+			self.vprint(errmsg)
+			if not self.verbose:
 				pprint(errmsg)
 			return ''
-		if sysvals.verbose:
+		if self.verbose:
 			pprint(rawout.strip())
 		out = []
 		for key in keyline:
@@ -1068,30 +1105,36 @@ class SystemValues:
 			val = valline[idx]
 			out.append('%s=%s' % (key, val))
 		return '|'.join(out)
-	def checkWifi(self):
-		out = dict()
-		iwcmd, ifcmd = self.getExec('iwconfig'), self.getExec('ifconfig')
-		if not iwcmd or not ifcmd:
-			return out
-		fp = Popen(iwcmd, stdout=PIPE, stderr=PIPE).stdout
-		for line in fp:
-			m = re.match('(?P<dev>\S*) .* ESSID:(?P<ess>\S*)', ascii(line))
-			if not m:
+	def wifiDetails(self, dev):
+		try:
+			info = open('/sys/class/net/%s/device/uevent' % dev, 'r').read().strip()
+		except:
+			return dev
+		vals = [dev]
+		for prop in info.split('\n'):
+			if prop.startswith('DRIVER=') or prop.startswith('PCI_ID='):
+				vals.append(prop.split('=')[-1])
+		return ':'.join(vals)
+	def checkWifi(self, dev=''):
+		try:
+			w = open('/proc/net/wireless', 'r').read().strip()
+		except:
+			return ''
+		for line in reversed(w.split('\n')):
+			m = re.match(' *(?P<dev>.*): (?P<stat>[0-9a-f]*) .*', w.split('\n')[-1])
+			if not m or (dev and dev != m.group('dev')):
 				continue
-			out['device'] = m.group('dev')
-			if '"' in m.group('ess'):
-				out['essid'] = m.group('ess').strip('"')
-				break
-		fp.close()
-		if 'device' in out:
-			fp = Popen([ifcmd, out['device']], stdout=PIPE, stderr=PIPE).stdout
-			for line in fp:
-				m = re.match('.* inet (?P<ip>[0-9\.]*)', ascii(line))
-				if m:
-					out['ip'] = m.group('ip')
-					break
-			fp.close()
-		return out
+			return m.group('dev')
+		return ''
+	def pollWifi(self, dev, timeout=60):
+		start = time.time()
+		while (time.time() - start) < timeout:
+			w = self.checkWifi(dev)
+			if w:
+				return '%s reconnected %.2f' % \
+					(self.wifiDetails(dev), max(0, time.time() - start))
+			time.sleep(0.01)
+		return '%s timeout %d' % (self.wifiDetails(dev), timeout)
 	def errorSummary(self, errinfo, msg):
 		found = False
 		for entry in errinfo:
@@ -1113,8 +1156,9 @@ class SystemValues:
 				arr[j] = arr[j]\
 					.replace('\\', '\\\\').replace(']', '\]').replace('[', '\[')\
 					.replace('.', '\.').replace('+', '\+').replace('*', '\*')\
-					.replace('(', '\(').replace(')', '\)')
-		mstr = ' '.join(arr)
+					.replace('(', '\(').replace(')', '\)').replace('}', '\}')\
+					.replace('{', '\{')
+		mstr = ' *'.join(arr)
 		entry = {
 			'line': msg,
 			'match': mstr,
@@ -1122,6 +1166,44 @@ class SystemValues:
 			'urls': {self.hostname: [self.htmlfile]}
 		}
 		errinfo.append(entry)
+	def multistat(self, start, idx, finish):
+		if 'time' in self.multitest:
+			id = '%d Duration=%dmin' % (idx+1, self.multitest['time'])
+		else:
+			id = '%d/%d' % (idx+1, self.multitest['count'])
+		t = time.time()
+		if 'start' not in self.multitest:
+			self.multitest['start'] = self.multitest['last'] = t
+			self.multitest['total'] = 0.0
+			pprint('TEST (%s) START' % id)
+			return
+		dt = t - self.multitest['last']
+		if not start:
+			if idx == 0 and self.multitest['delay'] > 0:
+				self.multitest['total'] += self.multitest['delay']
+			pprint('TEST (%s) COMPLETE -- Duration %.1fs' % (id, dt))
+			return
+		self.multitest['total'] += dt
+		self.multitest['last'] = t
+		avg = self.multitest['total'] / idx
+		if 'time' in self.multitest:
+			left = finish - datetime.now()
+			left -= timedelta(microseconds=left.microseconds)
+		else:
+			left = timedelta(seconds=((self.multitest['count'] - idx) * int(avg)))
+		pprint('TEST (%s) START - Avg Duration %.1fs, Time left %s' % \
+			(id, avg, str(left)))
+	def multiinit(self, c, d):
+		sz, unit = 'count', 'm'
+		if c.endswith('d') or c.endswith('h') or c.endswith('m'):
+			sz, unit, c = 'time', c[-1], c[:-1]
+		self.multitest['run'] = True
+		self.multitest[sz] = getArgInt('multi: n d (exec count)', c, 1, 1000000, False)
+		self.multitest['delay'] = getArgInt('multi: n d (delay between tests)', d, 0, 3600, False)
+		if unit == 'd':
+			self.multitest[sz] *= 1440
+		elif unit == 'h':
+			self.multitest[sz] *= 60
 
 sysvals = SystemValues()
 switchvalues = ['enable', 'disable', 'on', 'off', 'true', 'false', '1', '0']
@@ -1210,25 +1292,30 @@ class Data:
 		'resume_complete': {'order': 9, 'color': '#FFFFCC'},
 	}
 	errlist = {
-		'HWERROR' : '.*\[ *Hardware Error *\].*',
-		'FWBUG'   : '.*\[ *Firmware Bug *\].*',
-		'BUG'     : '.*BUG.*',
-		'ERROR'   : '.*ERROR.*',
-		'WARNING' : '.*WARNING.*',
-		'IRQ'     : '.*genirq: .*',
-		'TASKFAIL': '.*Freezing of tasks *.*',
-		'ACPI'    : '.*ACPI *(?P<b>[A-Za-z]*) *Error[: ].*',
-		'DEVFAIL' : '.* failed to (?P<b>[a-z]*) async: .*',
-		'DISKFULL': '.*No space left on device.*',
-		'USBERR'  : '.*usb .*device .*, error [0-9-]*',
-		'ATAERR'  : ' *ata[0-9\.]*: .*failed.*',
-		'MEIERR'  : ' *mei.*: .*failed.*',
-		'TPMERR'  : '(?i) *tpm *tpm[0-9]*: .*error.*',
+		'HWERROR' : r'.*\[ *Hardware Error *\].*',
+		'FWBUG'   : r'.*\[ *Firmware Bug *\].*',
+		'BUG'     : r'(?i).*\bBUG\b.*',
+		'ERROR'   : r'(?i).*\bERROR\b.*',
+		'WARNING' : r'(?i).*\bWARNING\b.*',
+		'FAULT'   : r'(?i).*\bFAULT\b.*',
+		'FAIL'    : r'(?i).*\bFAILED\b.*',
+		'INVALID' : r'(?i).*\bINVALID\b.*',
+		'CRASH'   : r'(?i).*\bCRASHED\b.*',
+		'IRQ'     : r'.*\bgenirq: .*',
+		'TASKFAIL': r'.*Freezing of tasks *.*',
+		'ACPI'    : r'.*\bACPI *(?P<b>[A-Za-z]*) *Error[: ].*',
+		'DISKFULL': r'.*\bNo space left on device.*',
+		'USBERR'  : r'.*usb .*device .*, error [0-9-]*',
+		'ATAERR'  : r' *ata[0-9\.]*: .*failed.*',
+		'MEIERR'  : r' *mei.*: .*failed.*',
+		'TPMERR'  : r'(?i) *tpm *tpm[0-9]*: .*error.*',
 	}
 	def __init__(self, num):
 		idchar = 'abcdefghij'
 		self.start = 0.0 # test start
 		self.end = 0.0   # test end
+		self.hwstart = 0 # rtc test start
+		self.hwend = 0   # rtc test end
 		self.tSuspended = 0.0 # low-level suspend start
 		self.tResumed = 0.0   # low-level resume start
 		self.tKernSus = 0.0   # kernel level suspend start
@@ -1240,10 +1327,8 @@ class Data:
 		self.stamp = 0
 		self.outfile = ''
 		self.kerror = False
-		self.battery = 0
-		self.wifi = 0
+		self.wifi = dict()
 		self.turbostat = 0
-		self.mcelog = 0
 		self.enterfail = ''
 		self.currphase = ''
 		self.pstl = dict()    # process timeline
@@ -1308,6 +1393,8 @@ class Data:
 				continue
 			dir = 'suspend' if t < self.tSuspended else 'resume'
 			msg = m.group('msg')
+			if re.match('capability: warning: .*', msg):
+				continue
 			for err in self.errlist:
 				if re.match(self.errlist[err], msg):
 					list.append((msg, err, dir, t, i, i))
@@ -1316,17 +1403,26 @@ class Data:
 		msglist = []
 		for msg, type, dir, t, idx1, idx2 in list:
 			msglist.append(msg)
-			sysvals.vprint('kernel %s found in %s at %f' % (type, dir, t))
 			self.errorinfo[dir].append((type, t, idx1, idx2))
 		if self.kerror:
 			sysvals.dmesglog = True
 		if len(self.dmesgtext) < 1 and sysvals.dmesgfile:
 			lf.close()
 		return msglist
-	def setStart(self, time):
+	def setStart(self, time, msg=''):
 		self.start = time
-	def setEnd(self, time):
+		if msg:
+			try:
+				self.hwstart = datetime.strptime(msg, sysvals.tmstart)
+			except:
+				self.hwstart = 0
+	def setEnd(self, time, msg=''):
 		self.end = time
+		if msg:
+			try:
+				self.hwend = datetime.strptime(msg, sysvals.tmend)
+			except:
+				self.hwend = 0
 	def isTraceEventOutsideDeviceCalls(self, pid, time):
 		for phase in self.sortedPhases():
 			list = self.dmesg[phase]['list']
@@ -1546,6 +1642,14 @@ class Data:
 					self.trimTime(tS, tL, left)
 					self.tLow.append('%.0f'%(tL*1000))
 			lp = phase
+	def getMemTime(self):
+		if not self.hwstart or not self.hwend:
+			return
+		stime = (self.tSuspended - self.start) * 1000000
+		rtime = (self.end - self.tResumed) * 1000000
+		hws = self.hwstart + timedelta(microseconds=stime)
+		hwr = self.hwend - timedelta(microseconds=rtime)
+		self.tLow.append('%.0f'%((hwr - hws).total_seconds() * 1000))
 	def getTimeValues(self):
 		sktime = (self.tSuspended - self.tKernSus) * 1000
 		rktime = (self.tKernRes - self.tResumed) * 1000
@@ -1883,9 +1987,9 @@ class Data:
 			c = self.addProcessUsageEvent(ps, tres)
 			if c > 0:
 				sysvals.vprint('%25s (res): %d' % (ps, c))
-	def handleEndMarker(self, time):
+	def handleEndMarker(self, time, msg=''):
 		dm = self.dmesg
-		self.setEnd(time)
+		self.setEnd(time, msg)
 		self.initDevicegroups()
 		# give suspend_prepare an end if needed
 		if 'suspend_prepare' in dm and dm['suspend_prepare']['end'] < 0:
@@ -2071,7 +2175,7 @@ class FTraceLine:
 		if not self.fevent:
 			return False
 		if sysvals.usetracemarkers:
-			if(self.name == 'SUSPEND START'):
+			if(self.name.startswith('SUSPEND START')):
 				return True
 			return False
 		else:
@@ -2084,7 +2188,7 @@ class FTraceLine:
 		if not self.fevent:
 			return False
 		if sysvals.usetracemarkers:
-			if(self.name == 'RESUME COMPLETE'):
+			if(self.name.startswith('RESUME COMPLETE')):
 				return True
 			return False
 		else:
@@ -2444,7 +2548,7 @@ class Timeline:
 	def createHeader(self, sv, stamp):
 		if(not stamp['time']):
 			return
-		self.html += '<div class="version"><a href="https://01.org/suspendresume">%s v%s</a></div>' \
+		self.html += '<div class="version"><a href="https://01.org/pm-graph">%s v%s</a></div>' \
 			% (sv.title, sv.version)
 		if sv.logmsg and sv.testlog:
 			self.html += '<button id="showtest" class="logbtn btnfmt">log</button>'
@@ -2670,14 +2774,11 @@ class TestProps:
 	stampfmt = '# [a-z]*-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\
 				'(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\
 				' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$'
-	batteryfmt = '^# battery (?P<a1>\w*) (?P<c1>\d*) (?P<a2>\w*) (?P<c2>\d*)'
-	wififmt    = '^# wifi (?P<w>.*)'
+	wififmt    = '^# wifi *(?P<d>\S*) *(?P<s>\S*) *(?P<t>[0-9\.]+).*'
 	tstatfmt   = '^# turbostat (?P<t>\S*)'
-	mcelogfmt  = '^# mcelog (?P<m>\S*)'
 	testerrfmt = '^# enter_sleep_error (?P<e>.*)'
 	sysinfofmt = '^# sysinfo .*'
 	cmdlinefmt = '^# command \| (?P<cmd>.*)'
-	kparamsfmt = '^# kparams \| (?P<kp>.*)'
 	devpropfmt = '# Device Properties: .*'
 	pinfofmt   = '# platform-(?P<val>[a-z,A-Z,0-9]*): (?P<info>.*)'
 	tracertypefmt = '# tracer: (?P<t>.*)'
@@ -2695,11 +2796,8 @@ class TestProps:
 		self.stamp = ''
 		self.sysinfo = ''
 		self.cmdline = ''
-		self.kparams = ''
 		self.testerror = []
-		self.mcelog = []
 		self.turbostat = []
-		self.battery = []
 		self.wifi = []
 		self.fwdata = []
 		self.ftrace_line_fmt = self.ftrace_line_fmt_nop
@@ -2721,21 +2819,12 @@ class TestProps:
 		elif re.match(self.sysinfofmt, line):
 			self.sysinfo = line
 			return True
-		elif re.match(self.kparamsfmt, line):
-			self.kparams = line
-			return True
 		elif re.match(self.cmdlinefmt, line):
 			self.cmdline = line
 			return True
-		elif re.match(self.mcelogfmt, line):
-			self.mcelog.append(line)
-			return True
 		elif re.match(self.tstatfmt, line):
 			self.turbostat.append(line)
 			return True
-		elif re.match(self.batteryfmt, line):
-			self.battery.append(line)
-			return True
 		elif re.match(self.wififmt, line):
 			self.wifi.append(line)
 			return True
@@ -2749,6 +2838,8 @@ class TestProps:
 	def parseStamp(self, data, sv):
 		# global test data
 		m = re.match(self.stampfmt, self.stamp)
+		if not self.stamp or not m:
+			doError('data does not include the expected stamp')
 		data.stamp = {'time': '', 'host': '', 'mode': ''}
 		dt = datetime(int(m.group('y'))+2000, int(m.group('m')),
 			int(m.group('d')), int(m.group('H')), int(m.group('M')),
@@ -2780,10 +2871,6 @@ class TestProps:
 		m = re.match(self.cmdlinefmt, self.cmdline)
 		if m:
 			sv.cmdline = m.group('cmd')
-		if self.kparams:
-			m = re.match(self.kparamsfmt, self.kparams)
-			if m:
-				sv.kparams = m.group('kp')
 		if not sv.stamp:
 			sv.stamp = data.stamp
 		# firmware data
@@ -2793,26 +2880,18 @@ class TestProps:
 				data.fwSuspend, data.fwResume = int(m.group('s')), int(m.group('r'))
 				if(data.fwSuspend > 0 or data.fwResume > 0):
 					data.fwValid = True
-		# mcelog data
-		if len(self.mcelog) > data.testnumber:
-			m = re.match(self.mcelogfmt, self.mcelog[data.testnumber])
-			if m:
-				data.mcelog = sv.b64unzip(m.group('m'))
 		# turbostat data
 		if len(self.turbostat) > data.testnumber:
 			m = re.match(self.tstatfmt, self.turbostat[data.testnumber])
 			if m:
 				data.turbostat = m.group('t')
-		# battery data
-		if len(self.battery) > data.testnumber:
-			m = re.match(self.batteryfmt, self.battery[data.testnumber])
-			if m:
-				data.battery = m.groups()
 		# wifi data
 		if len(self.wifi) > data.testnumber:
 			m = re.match(self.wififmt, self.wifi[data.testnumber])
 			if m:
-				data.wifi = m.group('w')
+				data.wifi = {'dev': m.group('d'), 'stat': m.group('s'),
+					'time': float(m.group('t'))}
+				data.stamp['wifi'] = m.group('d')
 		# sleep mode enter errors
 		if len(self.testerror) > data.testnumber:
 			m = re.match(self.testerrfmt, self.testerror[data.testnumber])
@@ -3012,13 +3091,13 @@ def appendIncompleteTraceLog(testruns):
 		if(t.startMarker()):
 			data = testrun[testidx].data
 			tp.parseStamp(data, sysvals)
-			data.setStart(t.time)
+			data.setStart(t.time, t.name)
 			continue
 		if(not data):
 			continue
 		# find the end of resume
 		if(t.endMarker()):
-			data.setEnd(t.time)
+			data.setEnd(t.time, t.name)
 			testidx += 1
 			if(testidx >= testcnt):
 				break
@@ -3081,7 +3160,7 @@ def parseTraceLog(live=False):
 		doError('%s does not exist' % sysvals.ftracefile)
 	if not live:
 		sysvals.setupAllKprobes()
-	ksuscalls = ['pm_prepare_console']
+	ksuscalls = ['ksys_sync', 'pm_prepare_console']
 	krescalls = ['pm_restore_console']
 	tracewatch = ['irq_wakeup']
 	if sysvals.usekprobes:
@@ -3094,7 +3173,7 @@ def parseTraceLog(live=False):
 	testruns = []
 	testdata = []
 	testrun = 0
-	data = 0
+	data, limbo = 0, True
 	tf = sysvals.openlog(sysvals.ftracefile, 'r')
 	phase = 'suspend_prepare'
 	for line in tf:
@@ -3141,16 +3220,16 @@ def parseTraceLog(live=False):
 			continue
 		# find the start of suspend
 		if(t.startMarker()):
-			data = Data(len(testdata))
+			data, limbo = Data(len(testdata)), False
 			testdata.append(data)
 			testrun = TestRun(data)
 			testruns.append(testrun)
 			tp.parseStamp(data, sysvals)
-			data.setStart(t.time)
+			data.setStart(t.time, t.name)
 			data.first_suspend_prepare = True
 			phase = data.setPhase('suspend_prepare', t.time, True)
 			continue
-		if(not data):
+		if(not data or limbo):
 			continue
 		# process cpu exec line
 		if t.type == 'tracing_mark_write':
@@ -3167,14 +3246,16 @@ def parseTraceLog(live=False):
 				continue
 		# find the end of resume
 		if(t.endMarker()):
-			data.handleEndMarker(t.time)
+			if data.tKernRes == 0:
+				data.tKernRes = t.time
+			data.handleEndMarker(t.time, t.name)
 			if(not sysvals.usetracemarkers):
 				# no trace markers? then quit and be sure to finish recording
 				# the event we used to trigger resume end
 				if('thaw_processes' in testrun.ttemp and len(testrun.ttemp['thaw_processes']) > 0):
 					# if an entry exists, assume this is its end
 					testrun.ttemp['thaw_processes'][-1]['end'] = t.time
-				break
+			limbo = True
 			continue
 		# trace event processing
 		if(t.fevent):
@@ -3197,7 +3278,7 @@ def parseTraceLog(live=False):
 				# -- phase changes --
 				# start of kernel suspend
 				if(re.match('suspend_enter\[.*', t.name)):
-					if(isbegin):
+					if(isbegin and data.tKernSus == 0):
 						data.tKernSus = t.time
 					continue
 				# suspend_prepare start
@@ -3225,7 +3306,7 @@ def parseTraceLog(live=False):
 				elif(re.match('machine_suspend\[.*', t.name)):
 					if(isbegin):
 						lp = data.lastPhase()
-						if lp == 'resume_machine':
+						if lp.startswith('resume_machine'):
 							data.dmesg[lp]['end'] = t.time
 						phase = data.setPhase('suspend_machine', data.dmesg[lp]['end'], True)
 						data.setPhase(phase, t.time, False)
@@ -3320,7 +3401,8 @@ def parseTraceLog(live=False):
 					'proc': m_proc,
 				})
 				# start of kernel resume
-				if(phase == 'suspend_prepare' and kprobename in ksuscalls):
+				if(data.tKernSus == 0 and phase == 'suspend_prepare' \
+					and kprobename in ksuscalls):
 					data.tKernSus = t.time
 			elif(t.freturn):
 				if(key not in tp.ktemp) or len(tp.ktemp[key]) < 1:
@@ -3355,7 +3437,7 @@ def parseTraceLog(live=False):
 		sysvals.vprint('WARNING: ftrace start marker is missing')
 	if data and not data.devicegroups:
 		sysvals.vprint('WARNING: ftrace end marker is missing')
-		data.handleEndMarker(t.time)
+		data.handleEndMarker(t.time, t.name)
 
 	if sysvals.suspendmode == 'command':
 		for test in testruns:
@@ -3476,6 +3558,10 @@ def parseTraceLog(live=False):
 					data.fwValid = False
 				sysvals.vprint('WARNING: phase "%s" is missing!' % p)
 			lp = p
+		if not terr and 'dev' in data.wifi and data.wifi['stat'] == 'timeout':
+			terr = '%s%s failed in wifi_resume <i>(%s %.0fs timeout)</i>' % \
+				(sysvals.suspendmode, tn, data.wifi['dev'], data.wifi['time'])
+			error.append(terr)
 		if not terr and data.enterfail:
 			pprint('test%s FAILED: enter %s failed with %s' % (tn, sysvals.suspendmode, data.enterfail))
 			terr = 'test%s failed to enter %s mode' % (tn, sysvals.suspendmode)
@@ -3933,7 +4019,7 @@ def createHTMLSummarySimple(testruns, htmlfile, title):
 	tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [dict(), dict()]
 	iMin, iMed, iMax = [0, 0], [0, 0], [0, 0]
 	num = 0
-	useturbo = False
+	useturbo = usewifi = False
 	lastmode = ''
 	cnt = dict()
 	for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])):
@@ -3952,17 +4038,17 @@ def createHTMLSummarySimple(testruns, htmlfile, title):
 			tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [dict(), dict()]
 			iMin, iMed, iMax = [0, 0], [0, 0], [0, 0]
 			num = 0
-		pkgpc10 = syslpi = ''
+		pkgpc10 = syslpi = wifi = ''
 		if 'pkgpc10' in data and 'syslpi' in data:
-			pkgpc10 = data['pkgpc10']
-			syslpi = data['syslpi']
-			useturbo = True
+			pkgpc10, syslpi, useturbo = data['pkgpc10'], data['syslpi'], True
+		if 'wifi' in data:
+			wifi, usewifi = data['wifi'], True
 		res = data['result']
 		tVal = [float(data['suspend']), float(data['resume'])]
 		list[mode]['data'].append([data['host'], data['kernel'],
 			data['time'], tVal[0], tVal[1], data['url'], res,
 			data['issues'], data['sus_worst'], data['sus_worsttime'],
-			data['res_worst'], data['res_worsttime'], pkgpc10, syslpi])
+			data['res_worst'], data['res_worsttime'], pkgpc10, syslpi, wifi])
 		idx = len(list[mode]['data']) - 1
 		if res.startswith('fail in'):
 			res = 'fail'
@@ -4002,7 +4088,12 @@ def createHTMLSummarySimple(testruns, htmlfile, title):
 	td = '\t<td>{0}</td>\n'
 	tdh = '\t<td{1}>{0}</td>\n'
 	tdlink = '\t<td><a href="{0}">html</a></td>\n'
-	colspan = '14' if useturbo else '12'
+	cols = 12
+	if useturbo:
+		cols += 2
+	if usewifi:
+		cols += 1
+	colspan = '%d' % cols
 
 	# table header
 	html += '<table>\n<tr>\n' + th.format('#') +\
@@ -4013,6 +4104,8 @@ def createHTMLSummarySimple(testruns, htmlfile, title):
 		th.format('Worst Resume Device') + th.format('RD Time')
 	if useturbo:
 		html += th.format('PkgPC10') + th.format('SysLPI')
+	if usewifi:
+		html += th.format('Wifi')
 	html += th.format('Detail')+'</tr>\n'
 	# export list into html
 	head = '<tr class="head"><td>{0}</td><td>{1}</td>'+\
@@ -4076,6 +4169,8 @@ def createHTMLSummarySimple(testruns, htmlfile, title):
 			if useturbo:
 				html += td.format(d[12])								# pkg_pc10
 				html += td.format(d[13])								# syslpi
+			if usewifi:
+				html += td.format(d[14])								# wifi
 			html += tdlink.format(d[5]) if d[5] else td.format('')		# url
 			html += '</tr>\n'
 			num += 1
@@ -4224,6 +4319,8 @@ def createHTML(testruns, testfail):
 			kerror = True
 		if(sysvals.suspendmode in ['freeze', 'standby']):
 			data.trimFreezeTime(testruns[-1].tSuspended)
+		else:
+			data.getMemTime()
 
 	# html function templates
 	html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">{2}&rarr;</div>\n'
@@ -4242,13 +4339,10 @@ def createHTML(testruns, testfail):
 		'<td class="green">Execution Time: <b>{0} ms</b></td>'\
 		'<td class="yellow">Command: <b>{1}</b></td>'\
 		'</tr>\n</table>\n'
-	html_timegroups = '<table class="time2">\n<tr>'\
-		'<td class="green" title="time from kernel enter_state({5}) to firmware mode [kernel time only]">{4}Kernel Suspend: {0} ms</td>'\
-		'<td class="purple">{4}Firmware Suspend: {1} ms</td>'\
-		'<td class="purple">{4}Firmware Resume: {2} ms</td>'\
-		'<td class="yellow" title="time from firmware mode to return from kernel enter_state({5}) [kernel time only]">{4}Kernel Resume: {3} ms</td>'\
-		'</tr>\n</table>\n'
 	html_fail = '<table class="testfail"><tr><td>{0}</td></tr></table>\n'
+	html_kdesc = '<td class="{3}" title="time spent in kernel execution">{0}Kernel {2}: {1} ms</td>'
+	html_fwdesc = '<td class="{3}" title="time spent in firmware">{0}Firmware {2}: {1} ms</td>'
+	html_wifdesc = '<td class="yellow" title="time for wifi to reconnect after resume complete ({2})">{0}Wifi Resume: {1}</td>'
 
 	# html format variables
 	scaleH = 20
@@ -4264,13 +4358,10 @@ def createHTML(testruns, testfail):
 	# Generate the header for this timeline
 	for data in testruns:
 		tTotal = data.end - data.start
-		sktime, rktime = data.getTimeValues()
 		if(tTotal == 0):
 			doError('No timeline data')
-		if(len(data.tLow) > 0):
-			low_time = '+'.join(data.tLow)
 		if sysvals.suspendmode == 'command':
-			run_time = '%.0f'%((data.end-data.start)*1000)
+			run_time = '%.0f' % (tTotal * 1000)
 			if sysvals.testcommand:
 				testdesc = sysvals.testcommand
 			else:
@@ -4279,43 +4370,55 @@ def createHTML(testruns, testfail):
 				testdesc = ordinal(data.testnumber+1)+' '+testdesc
 			thtml = html_timetotal3.format(run_time, testdesc)
 			devtl.html += thtml
-		elif data.fwValid:
-			suspend_time = '%.0f'%(sktime + (data.fwSuspend/1000000.0))
-			resume_time = '%.0f'%(rktime + (data.fwResume/1000000.0))
-			testdesc1 = 'Total'
-			testdesc2 = ''
-			stitle = 'time from kernel enter_state(%s) to low-power mode [kernel & firmware time]' % sysvals.suspendmode
-			rtitle = 'time from low-power mode to return from kernel enter_state(%s) [firmware & kernel time]' % sysvals.suspendmode
-			if(len(testruns) > 1):
-				testdesc1 = testdesc2 = ordinal(data.testnumber+1)
-				testdesc2 += ' '
-			if(len(data.tLow) == 0):
-				thtml = html_timetotal.format(suspend_time, \
-					resume_time, testdesc1, stitle, rtitle)
-			else:
-				thtml = html_timetotal2.format(suspend_time, low_time, \
-					resume_time, testdesc1, stitle, rtitle)
-			devtl.html += thtml
+			continue
+		# typical full suspend/resume header
+		stot, rtot = sktime, rktime = data.getTimeValues()
+		ssrc, rsrc, testdesc, testdesc2 = ['kernel'], ['kernel'], 'Kernel', ''
+		if data.fwValid:
+			stot += (data.fwSuspend/1000000.0)
+			rtot += (data.fwResume/1000000.0)
+			ssrc.append('firmware')
+			rsrc.append('firmware')
+			testdesc = 'Total'
+		if 'time' in data.wifi and data.wifi['stat'] != 'timeout':
+			rtot += data.end - data.tKernRes + (data.wifi['time'] * 1000.0)
+			rsrc.append('wifi')
+			testdesc = 'Total'
+		suspend_time, resume_time = '%.3f' % stot, '%.3f' % rtot
+		stitle = 'time from kernel suspend start to %s mode [%s time]' % \
+			(sysvals.suspendmode, ' & '.join(ssrc))
+		rtitle = 'time from %s mode to kernel resume complete [%s time]' % \
+			(sysvals.suspendmode, ' & '.join(rsrc))
+		if(len(testruns) > 1):
+			testdesc = testdesc2 = ordinal(data.testnumber+1)
+			testdesc2 += ' '
+		if(len(data.tLow) == 0):
+			thtml = html_timetotal.format(suspend_time, \
+				resume_time, testdesc, stitle, rtitle)
+		else:
+			low_time = '+'.join(data.tLow)
+			thtml = html_timetotal2.format(suspend_time, low_time, \
+				resume_time, testdesc, stitle, rtitle)
+		devtl.html += thtml
+		if not data.fwValid and 'dev' not in data.wifi:
+			continue
+		# extra detail when the times come from multiple sources
+		thtml = '<table class="time2">\n<tr>'
+		thtml += html_kdesc.format(testdesc2, '%.3f'%sktime, 'Suspend', 'green')
+		if data.fwValid:
 			sftime = '%.3f'%(data.fwSuspend / 1000000.0)
 			rftime = '%.3f'%(data.fwResume / 1000000.0)
-			devtl.html += html_timegroups.format('%.3f'%sktime, \
-				sftime, rftime, '%.3f'%rktime, testdesc2, sysvals.suspendmode)
-		else:
-			suspend_time = '%.3f' % sktime
-			resume_time = '%.3f' % rktime
-			testdesc = 'Kernel'
-			stitle = 'time from kernel enter_state(%s) to firmware mode [kernel time only]' % sysvals.suspendmode
-			rtitle = 'time from firmware mode to return from kernel enter_state(%s) [kernel time only]' % sysvals.suspendmode
-			if(len(testruns) > 1):
-				testdesc = ordinal(data.testnumber+1)+' '+testdesc
-			if(len(data.tLow) == 0):
-				thtml = html_timetotal.format(suspend_time, \
-					resume_time, testdesc, stitle, rtitle)
+			thtml += html_fwdesc.format(testdesc2, sftime, 'Suspend', 'green')
+			thtml += html_fwdesc.format(testdesc2, rftime, 'Resume', 'yellow')
+		thtml += html_kdesc.format(testdesc2, '%.3f'%rktime, 'Resume', 'yellow')
+		if 'time' in data.wifi:
+			if data.wifi['stat'] != 'timeout':
+				wtime = '%.0f ms'%(data.end - data.tKernRes + (data.wifi['time'] * 1000.0))
 			else:
-				thtml = html_timetotal2.format(suspend_time, low_time, \
-					resume_time, testdesc, stitle, rtitle)
-			devtl.html += thtml
-
+				wtime = 'TIMEOUT'
+			thtml += html_wifdesc.format(testdesc2, wtime, data.wifi['dev'])
+		thtml += '</tr>\n</table>\n'
+		devtl.html += thtml
 	if testfail:
 		devtl.html += html_fail.format(testfail)
 
@@ -5082,28 +5185,32 @@ def setRuntimeSuspend(before=True):
 # Description:
 #	 Execute system suspend through the sysfs interface, then copy the output
 #	 dmesg and ftrace files to the test output directory.
-def executeSuspend():
+def executeSuspend(quiet=False):
 	pm = ProcessMonitor()
 	tp = sysvals.tpath
-	wifi = sysvals.checkWifi()
+	if sysvals.wifi:
+		wifi = sysvals.checkWifi()
 	testdata = []
-	battery = True if getBattery() else False
 	# run these commands to prepare the system for suspend
 	if sysvals.display:
-		pprint('SET DISPLAY TO %s' % sysvals.display.upper())
+		if not quiet:
+			pprint('SET DISPLAY TO %s' % sysvals.display.upper())
 		displayControl(sysvals.display)
 		time.sleep(1)
 	if sysvals.sync:
-		pprint('SYNCING FILESYSTEMS')
+		if not quiet:
+			pprint('SYNCING FILESYSTEMS')
 		call('sync', shell=True)
 	# mark the start point in the kernel ring buffer just as we start
 	sysvals.initdmesg()
 	# start ftrace
 	if(sysvals.usecallgraph or sysvals.usetraceevents):
-		pprint('START TRACING')
+		if not quiet:
+			pprint('START TRACING')
 		sysvals.fsetVal('1', 'tracing_on')
 		if sysvals.useprocmon:
 			pm.start()
+	sysvals.cmdinfo(True)
 	# execute however many s/r runs requested
 	for count in range(1,sysvals.execcount+1):
 		# x2delay in between test runs
@@ -5119,15 +5226,14 @@ def executeSuspend():
 				pprint('SUSPEND START')
 			else:
 				pprint('SUSPEND START (press a key to resume)')
-		sysvals.mcelog(True)
-		bat1 = getBattery() if battery else False
 		# set rtcwake
 		if(sysvals.rtcwake):
-			pprint('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime)
+			if not quiet:
+				pprint('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime)
 			sysvals.rtcWakeAlarmOn()
 		# start of suspend trace marker
 		if(sysvals.usecallgraph or sysvals.usetraceevents):
-			sysvals.fsetVal('SUSPEND START', 'trace_marker')
+			sysvals.fsetVal(datetime.now().strftime(sysvals.tmstart), 'trace_marker')
 		# predelay delay
 		if(count == 1 and sysvals.predelay > 0):
 			sysvals.fsetVal('WAIT %d' % sysvals.predelay, 'trace_marker')
@@ -5174,37 +5280,33 @@ def executeSuspend():
 		# return from suspend
 		pprint('RESUME COMPLETE')
 		if(sysvals.usecallgraph or sysvals.usetraceevents):
-			sysvals.fsetVal('RESUME COMPLETE', 'trace_marker')
+			sysvals.fsetVal(datetime.now().strftime(sysvals.tmend), 'trace_marker')
+		if sysvals.wifi and wifi:
+			tdata['wifi'] = sysvals.pollWifi(wifi)
 		if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'):
 			tdata['fw'] = getFPDT(False)
-		mcelog = sysvals.mcelog()
-		if mcelog:
-			tdata['mcelog'] = mcelog
-		bat2 = getBattery() if battery else False
-		if battery and bat1 and bat2:
-			tdata['bat'] = (bat1, bat2)
-		if 'device' in wifi and 'ip' in wifi:
-			tdata['wifi'] = (wifi, sysvals.checkWifi())
 		testdata.append(tdata)
+	cmdafter = sysvals.cmdinfo(False)
 	# stop ftrace
 	if(sysvals.usecallgraph or sysvals.usetraceevents):
 		if sysvals.useprocmon:
 			pm.stop()
 		sysvals.fsetVal('0', 'tracing_on')
 	# grab a copy of the dmesg output
-	pprint('CAPTURING DMESG')
+	if not quiet:
+		pprint('CAPTURING DMESG')
 	sysvals.getdmesg(testdata)
 	# grab a copy of the ftrace output
 	if(sysvals.usecallgraph or sysvals.usetraceevents):
-		pprint('CAPTURING TRACE')
+		if not quiet:
+			pprint('CAPTURING TRACE')
 		op = sysvals.writeDatafileHeader(sysvals.ftracefile, testdata)
 		fp = open(tp+'trace', 'r')
 		for line in fp:
 			op.write(line)
 		op.close()
 		sysvals.fsetVal('', 'trace')
-		sysvals.platforminfo()
-	return testdata
+		sysvals.platforminfo(cmdafter)
 
 def readFile(file):
 	if os.path.islink(file):
@@ -5447,25 +5549,6 @@ def dmidecode(mempath, fatal=False):
 		count += 1
 	return out
 
-def getBattery():
-	p, charge, bat = '/sys/class/power_supply', 0, {}
-	if not os.path.exists(p):
-		return False
-	for d in os.listdir(p):
-		type = sysvals.getVal(os.path.join(p, d, 'type')).strip().lower()
-		if type != 'battery':
-			continue
-		for v in ['status', 'energy_now', 'capacity_now']:
-			bat[v] = sysvals.getVal(os.path.join(p, d, v)).strip().lower()
-		break
-	if 'status' not in bat:
-		return False
-	ac = False if 'discharging' in bat['status'] else True
-	for v in ['energy_now', 'capacity_now']:
-		if v in bat and bat[v]:
-			charge = int(bat[v])
-	return (ac, charge)
-
 def displayControl(cmd):
 	xset, ret = 'timeout 10 xset -d :0.0 {0}', 0
 	if sysvals.sudouser:
@@ -5715,6 +5798,17 @@ def statusCheck(probecheck=False):
 		status = 'rtcwake is not properly supported'
 	pprint('    is rtcwake supported: %s' % res)
 
+	# check info commands
+	pprint('    optional commands this tool may use for info:')
+	no = sysvals.colorText('MISSING')
+	yes = sysvals.colorText('FOUND', 32)
+	for c in ['turbostat', 'mcelog', 'lspci', 'lsusb']:
+		if c == 'turbostat':
+			res = yes if sysvals.haveTurbostat() else no
+		else:
+			res = yes if sysvals.getExec(c) else no
+		pprint('        %s: %s' % (c, res))
+
 	if not probecheck:
 		return status
 
@@ -5780,8 +5874,9 @@ def getArgFloat(name, args, min, max, main=True):
 		doError(name+': value should be between %f and %f' % (min, max), True)
 	return val
 
-def processData(live=False):
-	pprint('PROCESSING DATA')
+def processData(live=False, quiet=False):
+	if not quiet:
+		pprint('PROCESSING DATA')
 	sysvals.vprint('usetraceevents=%s, usetracemarkers=%s, usekprobes=%s' % \
 		(sysvals.usetraceevents, sysvals.usetracemarkers, sysvals.usekprobes))
 	error = ''
@@ -5796,20 +5891,17 @@ def processData(live=False):
 			parseKernelLog(data)
 		if(sysvals.ftracefile and (sysvals.usecallgraph or sysvals.usetraceevents)):
 			appendIncompleteTraceLog(testruns)
+	if not sysvals.stamp:
+		pprint('ERROR: data does not include the expected stamp')
+		return (testruns, {'error': 'timeline generation failed'})
 	shown = ['bios', 'biosdate', 'cpu', 'host', 'kernel', 'man', 'memfr',
-			'memsz', 'mode', 'numcpu', 'plat', 'time']
+			'memsz', 'mode', 'numcpu', 'plat', 'time', 'wifi']
 	sysvals.vprint('System Info:')
 	for key in sorted(sysvals.stamp):
 		if key in shown:
 			sysvals.vprint('    %-8s : %s' % (key.upper(), sysvals.stamp[key]))
-	if sysvals.kparams:
-		sysvals.vprint('Kparams:\n    %s' % sysvals.kparams)
 	sysvals.vprint('Command:\n    %s' % sysvals.cmdline)
 	for data in testruns:
-		if data.mcelog:
-			sysvals.vprint('MCELOG Data:')
-			for line in data.mcelog.split('\n'):
-				sysvals.vprint('    %s' % line)
 		if data.turbostat:
 			idx, s = 0, 'Turbostat:\n    '
 			for val in data.turbostat.split('|'):
@@ -5819,23 +5911,13 @@ def processData(live=False):
 					s += '\n    '
 				s += val + ' '
 			sysvals.vprint(s)
-		if data.battery:
-			a1, c1, a2, c2 = data.battery
-			s = 'Battery:\n    Before - AC: %s, Charge: %d\n     After - AC: %s, Charge: %d' % \
-				(a1, int(c1), a2, int(c2))
-			sysvals.vprint(s)
-		if data.wifi:
-			w = data.wifi.replace('|', ' ').split(',')
-			s = 'Wifi:\n    Before %s\n     After %s' % \
-				(w[0], w[1])
-			sysvals.vprint(s)
 		data.printDetails()
-		if len(sysvals.platinfo) > 0:
-			sysvals.vprint('\nPlatform Info:')
-			for info in sysvals.platinfo:
-				sysvals.vprint(info[0]+' - '+info[1])
-				sysvals.vprint(info[2])
-			sysvals.vprint('')
+	if len(sysvals.platinfo) > 0:
+		sysvals.vprint('\nPlatform Info:')
+		for info in sysvals.platinfo:
+			sysvals.vprint('[%s - %s]' % (info[0], info[1]))
+			sysvals.vprint(info[2])
+		sysvals.vprint('')
 	if sysvals.cgdump:
 		for data in testruns:
 			data.debugPrint()
@@ -5845,7 +5927,8 @@ def processData(live=False):
 		return (testruns, {'error': 'timeline generation failed'})
 	sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile)
 	createHTML(testruns, error)
-	pprint('DONE')
+	if not quiet:
+		pprint('DONE')
 	data = testruns[0]
 	stamp = data.stamp
 	stamp['suspend'], stamp['resume'] = data.getTimeValues()
@@ -5872,31 +5955,28 @@ def rerunTest(htmlfile=''):
 			doError('a directory already exists with this name: %s' % sysvals.htmlfile)
 		elif not os.access(sysvals.htmlfile, os.W_OK):
 			doError('missing permission to write to %s' % sysvals.htmlfile)
-	testruns, stamp = processData(False)
-	sysvals.logmsg = ''
+	testruns, stamp = processData()
+	sysvals.resetlog()
 	return stamp
 
 # Function: runTest
 # Description:
 #	 execute a suspend/resume, gather the logs, and generate the output
-def runTest(n=0):
+def runTest(n=0, quiet=False):
 	# prepare for the test
-	sysvals.initFtrace()
+	sysvals.initFtrace(quiet)
 	sysvals.initTestOutput('suspend')
 
 	# execute the test
-	testdata = executeSuspend()
+	executeSuspend(quiet)
 	sysvals.cleanupFtrace()
 	if sysvals.skiphtml:
+		sysvals.outputResult({}, n)
 		sysvals.sudoUserchown(sysvals.testdir)
 		return
-	if not testdata[0]['error']:
-		testruns, stamp = processData(True)
-		for data in testruns:
-			del data
-	else:
-		stamp = testdata[0]
-
+	testruns, stamp = processData(True, quiet)
+	for data in testruns:
+		del data
 	sysvals.sudoUserchown(sysvals.testdir)
 	sysvals.outputResult(stamp, n)
 	if 'error' in stamp:
@@ -5904,13 +5984,14 @@ def runTest(n=0):
 	return 0
 
 def find_in_html(html, start, end, firstonly=True):
-	n, out = 0, []
-	while n < len(html):
-		m = re.search(start, html[n:])
+	n, cnt, out = 0, len(html), []
+	while n < cnt:
+		e = cnt if (n + 10000 > cnt or n == 0) else n + 10000
+		m = re.search(start, html[n:e])
 		if not m:
 			break
 		i = m.end()
-		m = re.search(end, html[n+i:])
+		m = re.search(end, html[n+i:e])
 		if not m:
 			break
 		j = m.start()
@@ -5945,7 +6026,7 @@ def data_from_html(file, outpath, issues, fulldetail=False):
 	tstr = dt.strftime('%Y/%m/%d %H:%M:%S')
 	error = find_in_html(html, '<table class="testfail"><tr><td>', '</td>')
 	if error:
-		m = re.match('[a-z]* failed in (?P<p>[a-z0-9_]*) phase', error)
+		m = re.match('[a-z0-9]* failed in (?P<p>\S*).*', error)
 		if m:
 			result = 'fail in %s' % m.group('p')
 		else:
@@ -5974,6 +6055,9 @@ def data_from_html(file, outpath, issues, fulldetail=False):
 				elist[err[0]] += 1
 		for i in elist:
 			ilist.append('%sx%d' % (i, elist[i]) if elist[i] > 1 else i)
+	wifi = find_in_html(html, 'Wifi Resume: ', '</td>')
+	if wifi:
+		extra['wifi'] = wifi
 	low = find_in_html(html, 'freeze time: <b>', ' ms</b>')
 	if low and '|' in low:
 		issue = 'FREEZEx%d' % len(low.split('|'))
@@ -6048,13 +6132,15 @@ def genHtml(subdir, force=False):
 	for dirname, dirnames, filenames in os.walk(subdir):
 		sysvals.dmesgfile = sysvals.ftracefile = sysvals.htmlfile = ''
 		for filename in filenames:
-			if(re.match('.*_dmesg.txt', filename)):
-				sysvals.dmesgfile = os.path.join(dirname, filename)
-			elif(re.match('.*_ftrace.txt', filename)):
-				sysvals.ftracefile = os.path.join(dirname, filename)
+			file = os.path.join(dirname, filename)
+			if sysvals.usable(file):
+				if(re.match('.*_dmesg.txt', filename)):
+					sysvals.dmesgfile = file
+				elif(re.match('.*_ftrace.txt', filename)):
+					sysvals.ftracefile = file
 		sysvals.setOutputFile()
-		if sysvals.ftracefile and sysvals.htmlfile and \
-			(force or not os.path.exists(sysvals.htmlfile)):
+		if (sysvals.dmesgfile or sysvals.ftracefile) and sysvals.htmlfile and \
+			(force or not sysvals.usable(sysvals.htmlfile)):
 			pprint('FTRACE: %s' % sysvals.ftracefile)
 			if sysvals.dmesgfile:
 				pprint('DMESG : %s' % sysvals.dmesgfile)
@@ -6169,9 +6255,9 @@ def configFromFile(file):
 				sysvals.cgtest = getArgInt('cgtest', value, 0, 1, False)
 			elif(option == 'cgphase'):
 				d = Data(0)
-				if value not in d.sortedPhases():
+				if value not in d.phasedef:
 					doError('invalid phase --> (%s: %s), valid phases are %s'\
-						% (option, value, d.sortedPhases()), True)
+						% (option, value, d.phasedef.keys()), True)
 				sysvals.cgphase = value
 			elif(option == 'fadd'):
 				file = sysvals.configFile(value)
@@ -6184,9 +6270,7 @@ def configFromFile(file):
 				nums = value.split()
 				if len(nums) != 2:
 					doError('multi requires 2 integers (exec_count and delay)', True)
-				sysvals.multitest['run'] = True
-				sysvals.multitest['count'] = getArgInt('multi: n d (exec count)', nums[0], 2, 1000000, False)
-				sysvals.multitest['delay'] = getArgInt('multi: n d (delay between tests)', nums[1], 0, 3600, False)
+				sysvals.multiinit(nums[0], nums[1])
 			elif(option == 'devicefilter'):
 				sysvals.setDeviceFilter(value)
 			elif(option == 'expandcg'):
@@ -6342,6 +6426,7 @@ def printHelp():
 	'   -srgap       Add a visible gap in the timeline between sus/res (default: disabled)\n'\
 	'   -skiphtml    Run the test and capture the trace logs, but skip the timeline (default: disabled)\n'\
 	'   -result fn   Export a results table to a text file for parsing.\n'\
+	'   -wifi        If a wifi connection is available, check that it reconnects after resume.\n'\
 	'  [testprep]\n'\
 	'   -sync        Sync the filesystems before starting the test\n'\
 	'   -rs on/off   Enable/disable runtime suspend for all devices, restore all after test\n'\
@@ -6356,8 +6441,10 @@ def printHelp():
 	'   -predelay t  Include t ms delay before 1st suspend (default: 0 ms)\n'\
 	'   -postdelay t Include t ms delay after last resume (default: 0 ms)\n'\
 	'   -mindev ms   Discard all device blocks shorter than ms milliseconds (e.g. 0.001 for us)\n'\
-	'   -multi n d   Execute <n> consecutive tests at <d> seconds intervals. The outputs will\n'\
-	'                be created in a new subdirectory with a summary page.\n'\
+	'   -multi n d   Execute <n> consecutive tests at <d> seconds intervals. If <n> is followed\n'\
+	'                by a "d", "h", or "m" execute for <n> days, hours, or mins instead.\n'\
+	'                The outputs will be created in a new subdirectory with a summary page.\n'\
+	'   -maxfail n   Abort a -multi run after n consecutive fails (default is 0 = never abort)\n'\
 	'  [debug]\n'\
 	'   -f           Use ftrace to create device callgraphs (default: disabled)\n'\
 	'   -ftop        Use ftrace on the top level call: "%s" (default: disabled)\n'\
@@ -6379,11 +6466,11 @@ def printHelp():
 	'   -modes       List available suspend modes\n'\
 	'   -status      Test to see if the system is enabled to run this tool\n'\
 	'   -fpdt        Print out the contents of the ACPI Firmware Performance Data Table\n'\
-	'   -battery     Print out battery info (if available)\n'\
-	'   -wifi        Print out wifi connection info (if wireless-tools and device exists)\n'\
+	'   -wificheck   Print out wifi connection info\n'\
 	'   -x<mode>     Test xset by toggling the given mode (on/off/standby/suspend)\n'\
 	'   -sysinfo     Print out system info extracted from BIOS\n'\
 	'   -devinfo     Print out the pm settings of all devices which support runtime suspend\n'\
+	'   -cmdinfo     Print out all the platform info collected before and after suspend/resume\n'\
 	'   -flist       Print the list of functions currently being captured in ftrace\n'\
 	'   -flistall    Print all functions capable of being captured in ftrace\n'\
 	'   -summary dir Create a summary of tests in this dir [-genhtml builds missing html]\n'\
@@ -6399,8 +6486,8 @@ if __name__ == '__main__':
 	genhtml = False
 	cmd = ''
 	simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall',
-		'-devinfo', '-status', '-battery', '-xon', '-xoff', '-xstandby',
-		'-xsuspend', '-xinit', '-xreset', '-xstat', '-wifi']
+		'-devinfo', '-status', '-xon', '-xoff', '-xstandby', '-xsuspend',
+		'-xinit', '-xreset', '-xstat', '-wificheck', '-cmdinfo']
 	if '-f' in sys.argv:
 		sysvals.cgskip = sysvals.configFile('cgskip.txt')
 	# loop through the command line arguments
@@ -6462,8 +6549,15 @@ if __name__ == '__main__':
 			sysvals.usedevsrc = True
 		elif(arg == '-sync'):
 			sysvals.sync = True
+		elif(arg == '-wifi'):
+			sysvals.wifi = True
 		elif(arg == '-gzip'):
 			sysvals.gzip = True
+		elif(arg == '-info'):
+			try:
+				val = next(args)
+			except:
+				doError('-info requires one string argument', True)
 		elif(arg == '-rs'):
 			try:
 				val = next(args)
@@ -6555,10 +6649,14 @@ if __name__ == '__main__':
 			sysvals.cgexp = True
 		elif(arg == '-srgap'):
 			sysvals.srgap = 5
+		elif(arg == '-maxfail'):
+			sysvals.maxfail = getArgInt('-maxfail', args, 0, 1000000)
 		elif(arg == '-multi'):
-			sysvals.multitest['run'] = True
-			sysvals.multitest['count'] = getArgInt('-multi n d (exec count)', args, 2, 1000000)
-			sysvals.multitest['delay'] = getArgInt('-multi n d (delay between tests)', args, 0, 3600)
+			try:
+				c, d = next(args), next(args)
+			except:
+				doError('-multi requires two values', True)
+			sysvals.multiinit(c, d)
 		elif(arg == '-o'):
 			try:
 				val = next(args)
@@ -6655,13 +6753,6 @@ if __name__ == '__main__':
 		elif(cmd == 'fpdt'):
 			if not getFPDT(True):
 				ret = 1
-		elif(cmd == 'battery'):
-			out = getBattery()
-			if out:
-				pprint('AC Connect    : %s\nBattery Charge: %d' % out)
-			else:
-				pprint('no battery found')
-				ret = 1
 		elif(cmd == 'sysinfo'):
 			sysvals.printSystemInfo(True)
 		elif(cmd == 'devinfo'):
@@ -6679,13 +6770,15 @@ if __name__ == '__main__':
 			ret = displayControl(cmd[1:])
 		elif(cmd == 'xstat'):
 			pprint('Display Status: %s' % displayControl('stat').upper())
-		elif(cmd == 'wifi'):
-			out = sysvals.checkWifi()
-			if 'device' not in out:
-				pprint('WIFI interface not found')
+		elif(cmd == 'wificheck'):
+			dev = sysvals.checkWifi()
+			if dev:
+				print('%s is connected' % sysvals.wifiDetails(dev))
 			else:
-				for key in sorted(out):
-					pprint('%6s: %s' % (key.upper(), out[key]))
+				print('No wifi connection found')
+		elif(cmd == 'cmdinfo'):
+			for out in sysvals.cmdinfo(False, True):
+				print('[%s - %s]\n%s\n' % out)
 		sys.exit(ret)
 
 	# if instructed, re-analyze existing data files
@@ -6720,24 +6813,38 @@ if __name__ == '__main__':
 	setRuntimeSuspend(True)
 	if sysvals.display:
 		displayControl('init')
-	ret = 0
+	failcnt, ret = 0, 0
 	if sysvals.multitest['run']:
 		# run multiple tests in a separate subdirectory
 		if not sysvals.outdir:
-			s = 'suspend-x%d' % sysvals.multitest['count']
-			sysvals.outdir = datetime.now().strftime(s+'-%y%m%d-%H%M%S')
+			if 'time' in sysvals.multitest:
+				s = '-%dm' % sysvals.multitest['time']
+			else:
+				s = '-x%d' % sysvals.multitest['count']
+			sysvals.outdir = datetime.now().strftime('suspend-%y%m%d-%H%M%S'+s)
 		if not os.path.isdir(sysvals.outdir):
 			os.makedirs(sysvals.outdir)
+		sysvals.sudoUserchown(sysvals.outdir)
+		finish = datetime.now()
+		if 'time' in sysvals.multitest:
+			finish += timedelta(minutes=sysvals.multitest['time'])
 		for i in range(sysvals.multitest['count']):
-			if(i != 0):
+			sysvals.multistat(True, i, finish)
+			if i != 0 and sysvals.multitest['delay'] > 0:
 				pprint('Waiting %d seconds...' % (sysvals.multitest['delay']))
 				time.sleep(sysvals.multitest['delay'])
-			pprint('TEST (%d/%d) START' % (i+1, sysvals.multitest['count']))
 			fmt = 'suspend-%y%m%d-%H%M%S'
 			sysvals.testdir = os.path.join(sysvals.outdir, datetime.now().strftime(fmt))
-			ret = runTest(i+1)
-			pprint('TEST (%d/%d) COMPLETE' % (i+1, sysvals.multitest['count']))
-			sysvals.logmsg = ''
+			ret = runTest(i+1, True)
+			failcnt = 0 if not ret else failcnt + 1
+			if sysvals.maxfail > 0 and failcnt >= sysvals.maxfail:
+				pprint('Maximum fail count of %d reached, aborting multitest' % (sysvals.maxfail))
+				break
+			time.sleep(5)
+			sysvals.resetlog()
+			sysvals.multistat(False, i, finish)
+			if 'time' in sysvals.multitest and datetime.now() >= finish:
+				break
 		if not sysvals.skiphtml:
 			runSummary(sysvals.outdir, False, False)
 		sysvals.sudoUserchown(sysvals.outdir)
diff --git a/tools/spi/Makefile b/tools/spi/Makefile
index 2249a1546cc1..ada881afb489 100644
--- a/tools/spi/Makefile
+++ b/tools/spi/Makefile
@@ -52,7 +52,9 @@ $(OUTPUT)spidev_fdx: $(SPIDEV_FDX_IN)
 clean:
 	rm -f $(ALL_PROGRAMS)
 	rm -rf $(OUTPUT)include/
-	find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
+	find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete
+	find $(if $(OUTPUT),$(OUTPUT),.) -name '\.*.o.d' -delete
+	find $(if $(OUTPUT),$(OUTPUT),.) -name '\.*.o.cmd' -delete
 
 install: $(ALL_PROGRAMS)
 	install -d -m 755 $(DESTDIR)$(bindir);		\
diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c
index 27967dd90f8f..eec23fa693bd 100644
--- a/tools/spi/spidev_test.c
+++ b/tools/spi/spidev_test.c
@@ -128,18 +128,22 @@ static void transfer(int fd, uint8_t const *tx, uint8_t const *rx, size_t len)
 		.bits_per_word = bits,
 	};
 
-	if (mode & SPI_TX_QUAD)
+	if (mode & SPI_TX_OCTAL)
+		tr.tx_nbits = 8;
+	else if (mode & SPI_TX_QUAD)
 		tr.tx_nbits = 4;
 	else if (mode & SPI_TX_DUAL)
 		tr.tx_nbits = 2;
-	if (mode & SPI_RX_QUAD)
+	if (mode & SPI_RX_OCTAL)
+		tr.rx_nbits = 8;
+	else if (mode & SPI_RX_QUAD)
 		tr.rx_nbits = 4;
 	else if (mode & SPI_RX_DUAL)
 		tr.rx_nbits = 2;
 	if (!(mode & SPI_LOOP)) {
-		if (mode & (SPI_TX_QUAD | SPI_TX_DUAL))
+		if (mode & (SPI_TX_OCTAL | SPI_TX_QUAD | SPI_TX_DUAL))
 			tr.rx_buf = 0;
-		else if (mode & (SPI_RX_QUAD | SPI_RX_DUAL))
+		else if (mode & (SPI_RX_OCTAL | SPI_RX_QUAD | SPI_RX_DUAL))
 			tr.tx_buf = 0;
 	}
 
@@ -187,6 +191,7 @@ static void print_usage(const char *prog)
 	     "  -R --ready    slave pulls low to pause\n"
 	     "  -2 --dual     dual transfer\n"
 	     "  -4 --quad     quad transfer\n"
+	     "  -8 --octal    octal transfer\n"
 	     "  -S --size     transfer size\n"
 	     "  -I --iter     iterations\n");
 	exit(1);
@@ -213,13 +218,14 @@ static void parse_opts(int argc, char *argv[])
 			{ "dual",    0, 0, '2' },
 			{ "verbose", 0, 0, 'v' },
 			{ "quad",    0, 0, '4' },
+			{ "octal",   0, 0, '8' },
 			{ "size",    1, 0, 'S' },
 			{ "iter",    1, 0, 'I' },
 			{ NULL, 0, 0, 0 },
 		};
 		int c;
 
-		c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3NR24p:vS:I:",
+		c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3NR248p:vS:I:",
 				lopts, NULL);
 
 		if (c == -1)
@@ -280,6 +286,9 @@ static void parse_opts(int argc, char *argv[])
 		case '4':
 			mode |= SPI_TX_QUAD;
 			break;
+		case '8':
+			mode |= SPI_TX_OCTAL;
+			break;
 		case 'S':
 			transfer_size = atoi(optarg);
 			break;
@@ -295,6 +304,8 @@ static void parse_opts(int argc, char *argv[])
 			mode |= SPI_RX_DUAL;
 		if (mode & SPI_TX_QUAD)
 			mode |= SPI_RX_QUAD;
+		if (mode & SPI_TX_OCTAL)
+			mode |= SPI_RX_OCTAL;
 	}
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index cde463af7071..c2642517e1d8 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -5,7 +5,8 @@
 static void test_fexit_bpf2bpf_common(const char *obj_file,
 				      const char *target_obj_file,
 				      int prog_cnt,
-				      const char **prog_name)
+				      const char **prog_name,
+				      bool run_prog)
 {
 	struct bpf_object *obj = NULL, *pkt_obj;
 	int err, pkt_fd, i;
@@ -18,7 +19,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 
 	err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC,
 			    &pkt_obj, &pkt_fd);
-	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
+	if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n",
+		  target_obj_file, err, errno))
 		return;
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
 			    .attach_prog_fd = pkt_fd,
@@ -33,7 +35,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 
 	obj = bpf_object__open_file(obj_file, &opts);
 	if (CHECK(IS_ERR_OR_NULL(obj), "obj_open",
-		  "failed to open fexit_bpf2bpf: %ld\n",
+		  "failed to open %s: %ld\n", obj_file,
 		  PTR_ERR(obj)))
 		goto close_prog;
 
@@ -49,6 +51,10 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
 			goto close_prog;
 	}
+
+	if (!run_prog)
+		goto close_prog;
+
 	data_map = bpf_object__find_map_by_name(obj, "fexit_bp.bss");
 	if (CHECK(!data_map, "find_data_map", "data map not found\n"))
 		goto close_prog;
@@ -89,7 +95,7 @@ static void test_target_no_callees(void)
 	test_fexit_bpf2bpf_common("./fexit_bpf2bpf_simple.o",
 				  "./test_pkt_md_access.o",
 				  ARRAY_SIZE(prog_name),
-				  prog_name);
+				  prog_name, true);
 }
 
 static void test_target_yes_callees(void)
@@ -103,7 +109,7 @@ static void test_target_yes_callees(void)
 	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
 				  "./test_pkt_access.o",
 				  ARRAY_SIZE(prog_name),
-				  prog_name);
+				  prog_name, true);
 }
 
 static void test_func_replace(void)
@@ -120,7 +126,18 @@ static void test_func_replace(void)
 	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
 				  "./test_pkt_access.o",
 				  ARRAY_SIZE(prog_name),
-				  prog_name);
+				  prog_name, true);
+}
+
+static void test_func_replace_verify(void)
+{
+	const char *prog_name[] = {
+		"freplace/do_bind",
+	};
+	test_fexit_bpf2bpf_common("./freplace_connect4.o",
+				  "./connect4_prog.o",
+				  ARRAY_SIZE(prog_name),
+				  prog_name, false);
 }
 
 void test_fexit_bpf2bpf(void)
@@ -128,4 +145,5 @@ void test_fexit_bpf2bpf(void)
 	test_target_no_callees();
 	test_target_yes_callees();
 	test_func_replace();
+	test_func_replace_verify();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
index 16a814eb4d64..43d0b5578f46 100644
--- a/tools/testing/selftests/bpf/prog_tests/mmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -19,15 +19,16 @@ void test_mmap(void)
 	const size_t map_sz = roundup_page(sizeof(struct map_data));
 	const int zero = 0, one = 1, two = 2, far = 1500;
 	const long page_size = sysconf(_SC_PAGE_SIZE);
-	int err, duration = 0, i, data_map_fd;
+	int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd, rdmap_fd;
 	struct bpf_map *data_map, *bss_map;
 	void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2;
 	struct test_mmap__bss *bss_data;
+	struct bpf_map_info map_info;
+	__u32 map_info_sz = sizeof(map_info);
 	struct map_data *map_data;
 	struct test_mmap *skel;
 	__u64 val = 0;
 
-
 	skel = test_mmap__open_and_load();
 	if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
 		return;
@@ -36,6 +37,25 @@ void test_mmap(void)
 	data_map = skel->maps.data_map;
 	data_map_fd = bpf_map__fd(data_map);
 
+	rdmap_fd = bpf_map__fd(skel->maps.rdonly_map);
+	tmp1 = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_SHARED, rdmap_fd, 0);
+	if (CHECK(tmp1 != MAP_FAILED, "rdonly_write_mmap", "unexpected success\n")) {
+		munmap(tmp1, 4096);
+		goto cleanup;
+	}
+	/* now double-check if it's mmap()'able at all */
+	tmp1 = mmap(NULL, 4096, PROT_READ, MAP_SHARED, rdmap_fd, 0);
+	if (CHECK(tmp1 == MAP_FAILED, "rdonly_read_mmap", "failed: %d\n", errno))
+		goto cleanup;
+
+	/* get map's ID */
+	memset(&map_info, 0, map_info_sz);
+	err = bpf_obj_get_info_by_fd(data_map_fd, &map_info, &map_info_sz);
+	if (CHECK(err, "map_get_info", "failed %d\n", errno))
+		goto cleanup;
+	data_map_id = map_info.id;
+
+	/* mmap BSS map */
 	bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
 			  bpf_map__fd(bss_map), 0);
 	if (CHECK(bss_mmaped == MAP_FAILED, "bss_mmap",
@@ -98,6 +118,10 @@ void test_mmap(void)
 		  "data_map freeze succeeded: err=%d, errno=%d\n", err, errno))
 		goto cleanup;
 
+	err = mprotect(map_mmaped, map_sz, PROT_READ);
+	if (CHECK(err, "mprotect_ro", "mprotect to r/o failed %d\n", errno))
+		goto cleanup;
+
 	/* unmap R/W mapping */
 	err = munmap(map_mmaped, map_sz);
 	map_mmaped = NULL;
@@ -111,6 +135,12 @@ void test_mmap(void)
 		map_mmaped = NULL;
 		goto cleanup;
 	}
+	err = mprotect(map_mmaped, map_sz, PROT_WRITE);
+	if (CHECK(!err, "mprotect_wr", "mprotect() succeeded unexpectedly!\n"))
+		goto cleanup;
+	err = mprotect(map_mmaped, map_sz, PROT_EXEC);
+	if (CHECK(!err, "mprotect_ex", "mprotect() succeeded unexpectedly!\n"))
+		goto cleanup;
 	map_data = map_mmaped;
 
 	/* map/unmap in a loop to test ref counting */
@@ -197,6 +227,53 @@ void test_mmap(void)
 	CHECK_FAIL(map_data->val[far] != 3 * 321);
 
 	munmap(tmp2, 4 * page_size);
+
+	/* map all 4 pages, but with pg_off=1 page, should fail */
+	tmp1 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED,
+		    data_map_fd, page_size /* initial page shift */);
+	if (CHECK(tmp1 != MAP_FAILED, "adv_mmap7", "unexpected success")) {
+		munmap(tmp1, 4 * page_size);
+		goto cleanup;
+	}
+
+	tmp1 = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0);
+	if (CHECK(tmp1 == MAP_FAILED, "last_mmap", "failed %d\n", errno))
+		goto cleanup;
+
+	test_mmap__destroy(skel);
+	skel = NULL;
+	CHECK_FAIL(munmap(bss_mmaped, bss_sz));
+	bss_mmaped = NULL;
+	CHECK_FAIL(munmap(map_mmaped, map_sz));
+	map_mmaped = NULL;
+
+	/* map should be still held by active mmap */
+	tmp_fd = bpf_map_get_fd_by_id(data_map_id);
+	if (CHECK(tmp_fd < 0, "get_map_by_id", "failed %d\n", errno)) {
+		munmap(tmp1, map_sz);
+		goto cleanup;
+	}
+	close(tmp_fd);
+
+	/* this should release data map finally */
+	munmap(tmp1, map_sz);
+
+	/* we need to wait for RCU grace period */
+	for (i = 0; i < 10000; i++) {
+		__u32 id = data_map_id - 1;
+		if (bpf_map_get_next_id(id, &id) || id > data_map_id)
+			break;
+		usleep(1);
+	}
+
+	/* should fail to get map FD by non-existing ID */
+	tmp_fd = bpf_map_get_fd_by_id(data_map_id);
+	if (CHECK(tmp_fd >= 0, "get_map_by_id_after",
+		  "unexpectedly succeeded %d\n", tmp_fd)) {
+		close(tmp_fd);
+		goto cleanup;
+	}
+
 cleanup:
 	if (bss_mmaped)
 		CHECK_FAIL(munmap(bss_mmaped, bss_sz));
diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c
index 9d9351dc2ded..713167449c98 100644
--- a/tools/testing/selftests/bpf/prog_tests/section_names.c
+++ b/tools/testing/selftests/bpf/prog_tests/section_names.c
@@ -43,18 +43,18 @@ static struct sec_name_test tests[] = {
 	{"lwt_seg6local", {0, BPF_PROG_TYPE_LWT_SEG6LOCAL, 0}, {-EINVAL, 0} },
 	{
 		"cgroup_skb/ingress",
-		{0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+		{0, BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_INGRESS},
 		{0, BPF_CGROUP_INET_INGRESS},
 	},
 	{
 		"cgroup_skb/egress",
-		{0, BPF_PROG_TYPE_CGROUP_SKB, 0},
+		{0, BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_EGRESS},
 		{0, BPF_CGROUP_INET_EGRESS},
 	},
 	{"cgroup/skb", {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, {-EINVAL, 0} },
 	{
 		"cgroup/sock",
-		{0, BPF_PROG_TYPE_CGROUP_SOCK, 0},
+		{0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE},
 		{0, BPF_CGROUP_INET_SOCK_CREATE},
 	},
 	{
@@ -69,26 +69,38 @@ static struct sec_name_test tests[] = {
 	},
 	{
 		"cgroup/dev",
-		{0, BPF_PROG_TYPE_CGROUP_DEVICE, 0},
+		{0, BPF_PROG_TYPE_CGROUP_DEVICE, BPF_CGROUP_DEVICE},
 		{0, BPF_CGROUP_DEVICE},
 	},
-	{"sockops", {0, BPF_PROG_TYPE_SOCK_OPS, 0}, {0, BPF_CGROUP_SOCK_OPS} },
+	{
+		"sockops",
+		{0, BPF_PROG_TYPE_SOCK_OPS, BPF_CGROUP_SOCK_OPS},
+		{0, BPF_CGROUP_SOCK_OPS},
+	},
 	{
 		"sk_skb/stream_parser",
-		{0, BPF_PROG_TYPE_SK_SKB, 0},
+		{0, BPF_PROG_TYPE_SK_SKB, BPF_SK_SKB_STREAM_PARSER},
 		{0, BPF_SK_SKB_STREAM_PARSER},
 	},
 	{
 		"sk_skb/stream_verdict",
-		{0, BPF_PROG_TYPE_SK_SKB, 0},
+		{0, BPF_PROG_TYPE_SK_SKB, BPF_SK_SKB_STREAM_VERDICT},
 		{0, BPF_SK_SKB_STREAM_VERDICT},
 	},
 	{"sk_skb", {0, BPF_PROG_TYPE_SK_SKB, 0}, {-EINVAL, 0} },
-	{"sk_msg", {0, BPF_PROG_TYPE_SK_MSG, 0}, {0, BPF_SK_MSG_VERDICT} },
-	{"lirc_mode2", {0, BPF_PROG_TYPE_LIRC_MODE2, 0}, {0, BPF_LIRC_MODE2} },
+	{
+		"sk_msg",
+		{0, BPF_PROG_TYPE_SK_MSG, BPF_SK_MSG_VERDICT},
+		{0, BPF_SK_MSG_VERDICT},
+	},
+	{
+		"lirc_mode2",
+		{0, BPF_PROG_TYPE_LIRC_MODE2, BPF_LIRC_MODE2},
+		{0, BPF_LIRC_MODE2},
+	},
 	{
 		"flow_dissector",
-		{0, BPF_PROG_TYPE_FLOW_DISSECTOR, 0},
+		{0, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_FLOW_DISSECTOR},
 		{0, BPF_FLOW_DISSECTOR},
 	},
 	{
@@ -158,17 +170,17 @@ static void test_prog_type_by_name(const struct sec_name_test *test)
 				      &expected_attach_type);
 
 	CHECK(rc != test->expected_load.rc, "check_code",
-	      "prog: unexpected rc=%d for %s", rc, test->sec_name);
+	      "prog: unexpected rc=%d for %s\n", rc, test->sec_name);
 
 	if (rc)
 		return;
 
 	CHECK(prog_type != test->expected_load.prog_type, "check_prog_type",
-	      "prog: unexpected prog_type=%d for %s",
+	      "prog: unexpected prog_type=%d for %s\n",
 	      prog_type, test->sec_name);
 
 	CHECK(expected_attach_type != test->expected_load.expected_attach_type,
-	      "check_attach_type", "prog: unexpected expected_attach_type=%d for %s",
+	      "check_attach_type", "prog: unexpected expected_attach_type=%d for %s\n",
 	      expected_attach_type, test->sec_name);
 }
 
@@ -180,13 +192,13 @@ static void test_attach_type_by_name(const struct sec_name_test *test)
 	rc = libbpf_attach_type_by_name(test->sec_name, &attach_type);
 
 	CHECK(rc != test->expected_attach.rc, "check_ret",
-	      "attach: unexpected rc=%d for %s", rc, test->sec_name);
+	      "attach: unexpected rc=%d for %s\n", rc, test->sec_name);
 
 	if (rc)
 		return;
 
 	CHECK(attach_type != test->expected_attach.attach_type,
-	      "check_attach_type", "attach: unexpected attach_type=%d for %s",
+	      "check_attach_type", "attach: unexpected attach_type=%d for %s\n",
 	      attach_type, test->sec_name);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
index 1e4c258de09d..b17eb2045c1d 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
@@ -15,7 +15,10 @@
 
 char *CMD_ARGS[] = {"true", NULL};
 
-int heap_mprotect(void)
+#define GET_PAGE_ADDR(ADDR, PAGE_SIZE)					\
+	(char *)(((unsigned long) (ADDR + PAGE_SIZE)) & ~(PAGE_SIZE-1))
+
+int stack_mprotect(void)
 {
 	void *buf;
 	long sz;
@@ -25,12 +28,9 @@ int heap_mprotect(void)
 	if (sz < 0)
 		return sz;
 
-	buf = memalign(sz, 2 * sz);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	ret = mprotect(buf, sz, PROT_READ | PROT_WRITE | PROT_EXEC);
-	free(buf);
+	buf = alloca(sz * 3);
+	ret = mprotect(GET_PAGE_ADDR(buf, sz), sz,
+		       PROT_READ | PROT_WRITE | PROT_EXEC);
 	return ret;
 }
 
@@ -73,8 +73,8 @@ void test_test_lsm(void)
 
 	skel->bss->monitored_pid = getpid();
 
-	err = heap_mprotect();
-	if (CHECK(errno != EPERM, "heap_mprotect", "want errno=EPERM, got %d\n",
+	err = stack_mprotect();
+	if (CHECK(errno != EPERM, "stack_mprotect", "want err=EPERM, got %d\n",
 		  errno))
 		goto close_prog;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
index 05b294d6b923..15ef3531483e 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
@@ -6,19 +6,34 @@
 
 void test_xdp_attach(void)
 {
+	__u32 duration = 0, id1, id2, id0 = 0, len;
 	struct bpf_object *obj1, *obj2, *obj3;
 	const char *file = "./test_xdp.o";
+	struct bpf_prog_info info = {};
 	int err, fd1, fd2, fd3;
-	__u32 duration = 0;
 	DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts,
 			    .old_fd = -1);
 
+	len = sizeof(info);
+
 	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1);
 	if (CHECK_FAIL(err))
 		return;
+	err = bpf_obj_get_info_by_fd(fd1, &info, &len);
+	if (CHECK_FAIL(err))
+		goto out_1;
+	id1 = info.id;
+
 	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj2, &fd2);
 	if (CHECK_FAIL(err))
 		goto out_1;
+
+	memset(&info, 0, sizeof(info));
+	err = bpf_obj_get_info_by_fd(fd2, &info, &len);
+	if (CHECK_FAIL(err))
+		goto out_2;
+	id2 = info.id;
+
 	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj3, &fd3);
 	if (CHECK_FAIL(err))
 		goto out_2;
@@ -28,6 +43,11 @@ void test_xdp_attach(void)
 	if (CHECK(err, "load_ok", "initial load failed"))
 		goto out_close;
 
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+	if (CHECK(err || id0 != id1, "id1_check",
+		  "loaded prog id %u != id1 %u, err %d", id0, id1, err))
+		goto out_close;
+
 	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE,
 				       &opts);
 	if (CHECK(!err, "load_fail", "load with expected id didn't fail"))
@@ -37,6 +57,10 @@ void test_xdp_attach(void)
 	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, 0, &opts);
 	if (CHECK(err, "replace_ok", "replace valid old_fd failed"))
 		goto out;
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+	if (CHECK(err || id0 != id2, "id2_check",
+		  "loaded prog id %u != id2 %u, err %d", id0, id2, err))
+		goto out_close;
 
 	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd3, 0, &opts);
 	if (CHECK(!err, "replace_fail", "replace invalid old_fd didn't fail"))
@@ -51,6 +75,10 @@ void test_xdp_attach(void)
 	if (CHECK(err, "remove_ok", "remove valid old_fd failed"))
 		goto out;
 
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+	if (CHECK(err || id0 != 0, "unload_check",
+		  "loaded prog id %u != 0, err %d", id0, err))
+		goto out_close;
 out:
 	bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
 out_close:
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
new file mode 100644
index 000000000000..d2d7a283d72f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/if_link.h>
+#include <test_progs.h>
+
+#define IFINDEX_LO 1
+
+void test_xdp_info(void)
+{
+	__u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id;
+	const char *file = "./xdp_dummy.o";
+	struct bpf_prog_info info = {};
+	struct bpf_object *obj;
+	int err, prog_fd;
+
+	/* Get prog_id for XDP_ATTACHED_NONE mode */
+
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0);
+	if (CHECK(err, "get_xdp_none", "errno=%d\n", errno))
+		return;
+	if (CHECK(prog_id, "prog_id_none", "unexpected prog_id=%u\n", prog_id))
+		return;
+
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE);
+	if (CHECK(err, "get_xdp_none_skb", "errno=%d\n", errno))
+		return;
+	if (CHECK(prog_id, "prog_id_none_skb", "unexpected prog_id=%u\n",
+		  prog_id))
+		return;
+
+	/* Setup prog */
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &len);
+	if (CHECK(err, "get_prog_info", "errno=%d\n", errno))
+		goto out_close;
+
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE);
+	if (CHECK(err, "set_xdp_skb", "errno=%d\n", errno))
+		goto out_close;
+
+	/* Get prog_id for single prog mode */
+
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0);
+	if (CHECK(err, "get_xdp", "errno=%d\n", errno))
+		goto out;
+	if (CHECK(prog_id != info.id, "prog_id", "prog_id not available\n"))
+		goto out;
+
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE);
+	if (CHECK(err, "get_xdp_skb", "errno=%d\n", errno))
+		goto out;
+	if (CHECK(prog_id != info.id, "prog_id_skb", "prog_id not available\n"))
+		goto out;
+
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_DRV_MODE);
+	if (CHECK(err, "get_xdp_drv", "errno=%d\n", errno))
+		goto out;
+	if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id))
+		goto out;
+
+out:
+	bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
+out_close:
+	bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index 75085119c5bb..ad3c498a8150 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -18,11 +18,25 @@
 
 int _version SEC("version") = 1;
 
+__attribute__ ((noinline))
+int do_bind(struct bpf_sock_addr *ctx)
+{
+	struct sockaddr_in sa = {};
+
+	sa.sin_family = AF_INET;
+	sa.sin_port = bpf_htons(0);
+	sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
+
+	if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+		return 0;
+
+	return 1;
+}
+
 SEC("cgroup/connect4")
 int connect_v4_prog(struct bpf_sock_addr *ctx)
 {
 	struct bpf_sock_tuple tuple = {};
-	struct sockaddr_in sa;
 	struct bpf_sock *sk;
 
 	/* Verify that new destination is available. */
@@ -56,17 +70,7 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
 	ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
 	ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
 
-	/* Rewrite source. */
-	memset(&sa, 0, sizeof(sa));
-
-	sa.sin_family = AF_INET;
-	sa.sin_port = bpf_htons(0);
-	sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
-
-	if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
-		return 0;
-
-	return 1;
+	return do_bind(ctx) ? 1 : 0;
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/freplace_connect4.c b/tools/testing/selftests/bpf/progs/freplace_connect4.c
new file mode 100644
index 000000000000..a0ae84230699
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_connect4.c
@@ -0,0 +1,18 @@
+#include <linux/stddef.h>
+#include <linux/ipv6.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <sys/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+SEC("freplace/do_bind")
+int new_do_bind(struct bpf_sock_addr *ctx)
+{
+  struct sockaddr_in sa = {};
+
+  bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa));
+  return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c
index a4e3c223028d..b4598d4bc4f7 100644
--- a/tools/testing/selftests/bpf/progs/lsm.c
+++ b/tools/testing/selftests/bpf/progs/lsm.c
@@ -23,12 +23,12 @@ int BPF_PROG(test_int_hook, struct vm_area_struct *vma,
 		return ret;
 
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
-	int is_heap = 0;
+	int is_stack = 0;
 
-	is_heap = (vma->vm_start >= vma->vm_mm->start_brk &&
-		   vma->vm_end <= vma->vm_mm->brk);
+	is_stack = (vma->vm_start <= vma->vm_mm->start_stack &&
+		    vma->vm_end >= vma->vm_mm->start_stack);
 
-	if (is_heap && monitored_pid == pid) {
+	if (is_stack && monitored_pid == pid) {
 		mprotect_count++;
 		ret = -EPERM;
 	}
diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
index 88b0566da13d..31538c9ed193 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
@@ -20,20 +20,12 @@ struct bpf_map_def SEC("maps") btf_map = {
 
 BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts);
 
-struct dummy_tracepoint_args {
-	unsigned long long pad;
-	struct sock *sock;
-};
-
 __attribute__((noinline))
-int test_long_fname_2(struct dummy_tracepoint_args *arg)
+int test_long_fname_2(void)
 {
 	struct ipv_counts *counts;
 	int key = 0;
 
-	if (!arg->sock)
-		return 0;
-
 	counts = bpf_map_lookup_elem(&btf_map, &key);
 	if (!counts)
 		return 0;
@@ -44,15 +36,15 @@ int test_long_fname_2(struct dummy_tracepoint_args *arg)
 }
 
 __attribute__((noinline))
-int test_long_fname_1(struct dummy_tracepoint_args *arg)
+int test_long_fname_1(void)
 {
-	return test_long_fname_2(arg);
+	return test_long_fname_2();
 }
 
 SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+int _dummy_tracepoint(void *arg)
 {
-	return test_long_fname_1(arg);
+	return test_long_fname_1();
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
index a924e53c8e9d..6c5560162746 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
@@ -28,20 +28,12 @@ struct {
 	__type(value, struct ipv_counts);
 } btf_map SEC(".maps");
 
-struct dummy_tracepoint_args {
-	unsigned long long pad;
-	struct sock *sock;
-};
-
 __attribute__((noinline))
-int test_long_fname_2(struct dummy_tracepoint_args *arg)
+int test_long_fname_2(void)
 {
 	struct ipv_counts *counts;
 	int key = 0;
 
-	if (!arg->sock)
-		return 0;
-
 	counts = bpf_map_lookup_elem(&btf_map, &key);
 	if (!counts)
 		return 0;
@@ -57,15 +49,15 @@ int test_long_fname_2(struct dummy_tracepoint_args *arg)
 }
 
 __attribute__((noinline))
-int test_long_fname_1(struct dummy_tracepoint_args *arg)
+int test_long_fname_1(void)
 {
-	return test_long_fname_2(arg);
+	return test_long_fname_2();
 }
 
 SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+int _dummy_tracepoint(void *arg)
 {
-	return test_long_fname_1(arg);
+	return test_long_fname_1();
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
index 983aedd1c072..506da7fd2da2 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
@@ -17,20 +17,12 @@ struct bpf_map_def SEC("maps") btf_map = {
 	.max_entries = 4,
 };
 
-struct dummy_tracepoint_args {
-	unsigned long long pad;
-	struct sock *sock;
-};
-
 __attribute__((noinline))
-int test_long_fname_2(struct dummy_tracepoint_args *arg)
+int test_long_fname_2(void)
 {
 	struct ipv_counts *counts;
 	int key = 0;
 
-	if (!arg->sock)
-		return 0;
-
 	counts = bpf_map_lookup_elem(&btf_map, &key);
 	if (!counts)
 		return 0;
@@ -41,15 +33,15 @@ int test_long_fname_2(struct dummy_tracepoint_args *arg)
 }
 
 __attribute__((noinline))
-int test_long_fname_1(struct dummy_tracepoint_args *arg)
+int test_long_fname_1(void)
 {
-	return test_long_fname_2(arg);
+	return test_long_fname_2();
 }
 
 SEC("dummy_tracepoint")
-int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+int _dummy_tracepoint(void *arg)
 {
-	return test_long_fname_1(arg);
+	return test_long_fname_1();
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c
index 6239596cd14e..4eb42cff5fe9 100644
--- a/tools/testing/selftests/bpf/progs/test_mmap.c
+++ b/tools/testing/selftests/bpf/progs/test_mmap.c
@@ -9,6 +9,14 @@ char _license[] SEC("license") = "GPL";
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 4096);
+	__uint(map_flags, BPF_F_MMAPABLE | BPF_F_RDONLY_PROG);
+	__type(key, __u32);
+	__type(value, char);
+} rdonly_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 512 * 4); /* at least 4 pages of data */
 	__uint(map_flags, BPF_F_MMAPABLE);
 	__type(key, __u32);
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index 56a50b25cd33..abb7344b531f 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -30,13 +30,13 @@ int prog3(struct bpf_raw_tracepoint_args *ctx)
 SEC("fentry/__set_task_comm")
 int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec)
 {
-	return !tsk;
+	return 0;
 }
 
 SEC("fexit/__set_task_comm")
 int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec)
 {
-	return !tsk;
+	return 0;
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 8da77cda5f4a..305fae8f80a9 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -2854,7 +2854,7 @@ static struct btf_raw_test raw_tests[] = {
 	.value_type_id = 1,
 	.max_entries = 4,
 	.btf_load_err = true,
-	.err_str = "vlen != 0",
+	.err_str = "Invalid func linkage",
 },
 
 {
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index 4d0d09574bf4..58f4aa593b1b 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -238,7 +238,7 @@
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
 	BPF_LD_MAP_FD(BPF_REG_1, 0),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
 	/* r1 = [0x00, 0xff] */
 	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
@@ -253,10 +253,6 @@
 	 *      [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
 	 */
 	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
-	/* r1 = 0 or
-	 *      [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff]
-	 */
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
 	/* error on OOB pointer computation */
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
 	/* exit */
@@ -265,8 +261,10 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	/* not actually fully unbounded, but the bound is very high */
-	.errstr = "value 72057594021150720 makes map_value pointer be out of bounds",
-	.result = REJECT
+	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
+	.result_unpriv = REJECT,
+	.errstr = "value -4294967168 makes map_value pointer be out of bounds",
+	.result = REJECT,
 },
 {
 	"bounds check after truncation of boundary-crossing range (2)",
@@ -276,7 +274,7 @@
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
 	BPF_LD_MAP_FD(BPF_REG_1, 0),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
 	/* r1 = [0x00, 0xff] */
 	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
@@ -293,10 +291,6 @@
 	 *      [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
 	 */
 	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
-	/* r1 = 0 or
-	 *      [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff]
-	 */
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
 	/* error on OOB pointer computation */
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
 	/* exit */
@@ -305,8 +299,10 @@
 	},
 	.fixup_map_hash_8b = { 3 },
 	/* not actually fully unbounded, but the bound is very high */
-	.errstr = "value 72057594021150720 makes map_value pointer be out of bounds",
-	.result = REJECT
+	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
+	.result_unpriv = REJECT,
+	.errstr = "value -4294967168 makes map_value pointer be out of bounds",
+	.result = REJECT,
 },
 {
 	"bounds check after wrapping 32-bit addition",
@@ -501,7 +497,7 @@
 	.result = REJECT
 },
 {
-	"bounds check mixed 32bit and 64bit arithmatic. test1",
+	"bounds check mixed 32bit and 64bit arithmetic. test1",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_MOV64_IMM(BPF_REG_1, -1),
@@ -520,7 +516,7 @@
 	.result = ACCEPT
 },
 {
-	"bounds check mixed 32bit and 64bit arithmatic. test2",
+	"bounds check mixed 32bit and 64bit arithmetic. test2",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_MOV64_IMM(BPF_REG_1, -1),
@@ -539,3 +535,25 @@
 	},
 	.result = ACCEPT
 },
+{
+	"assigning 32bit bounds to 64bit for wA = 0, wB = wA",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_MOV32_IMM(BPF_REG_9, 0),
+	BPF_MOV32_REG(BPF_REG_2, BPF_REG_9),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_2),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_8, 1),
+	BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_6, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c
index 7276620ef242..8bfeb77c60bd 100644
--- a/tools/testing/selftests/bpf/verifier/stack_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/stack_ptr.c
@@ -315,3 +315,43 @@
 	},
 	.result = ACCEPT,
 },
+{
+	"store PTR_TO_STACK in R10 to array map using BPF_B",
+	.insns = {
+	/* Load pointer to map. */
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 2),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	/* Copy R10 to R9. */
+	BPF_MOV64_REG(BPF_REG_9, BPF_REG_10),
+	/* Pollute other registers with unaligned values. */
+	BPF_MOV64_IMM(BPF_REG_2, -1),
+	BPF_MOV64_IMM(BPF_REG_3, -1),
+	BPF_MOV64_IMM(BPF_REG_4, -1),
+	BPF_MOV64_IMM(BPF_REG_5, -1),
+	BPF_MOV64_IMM(BPF_REG_6, -1),
+	BPF_MOV64_IMM(BPF_REG_7, -1),
+	BPF_MOV64_IMM(BPF_REG_8, -1),
+	/* Store both R9 and R10 with BPF_B and read back. */
+	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, 0),
+	BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_1, 0),
+	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_9, 0),
+	BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_1, 0),
+	/* Should read back as same value. */
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_3, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 42),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 3 },
+	.result = ACCEPT,
+	.retval = 42,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
diff --git a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c
index 7f6c232cd842..ed1c2cea1dea 100644
--- a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c
+++ b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c
@@ -88,6 +88,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
+	.errstr_unpriv = "leaking pointer from stack off -8",
 	.errstr = "R0 invalid mem access 'inv'",
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
index cd5e1f602ac9..909da9cdda97 100644
--- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
+++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
@@ -351,6 +351,7 @@ static int test_alloc_errors(char *heap_name)
 	}
 
 	printf("Expected error checking passed\n");
+	ret = 0;
 out:
 	if (dmabuf_fd >= 0)
 		close(dmabuf_fd);
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index 24dd8ed48580..b025daea062d 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -300,7 +300,7 @@ test_uc_aware()
 	local i
 
 	for ((i = 0; i < attempts; ++i)); do
-		if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 0.1; then
+		if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 1; then
 			((passes++))
 		fi
 
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
index dbd1e014ba17..da49ad2761b5 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
@@ -264,6 +264,8 @@ trap_policer_test()
 	local packets_t0
 	local packets_t1
 
+	RET=0
+
 	if [ $(devlink_trap_policers_num_get) -eq 0 ]; then
 		check_err 1 "Failed to dump policers"
 	fi
@@ -328,6 +330,8 @@ trap_group_check_policer()
 
 trap_policer_bind_test()
 {
+	RET=0
+
 	devlink trap group set $DEVLINK_DEV group l2_drops policer 1
 	check_err $? "Failed to bind a valid policer"
 	if [ $(devlink_trap_group_policer_get "l2_drops") -ne 1 ]; then
diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
index 11eee0b60040..d979ff14775a 100644
--- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
+++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
@@ -3,6 +3,7 @@
 #define _GNU_SOURCE
 #include <poll.h>
 #include <unistd.h>
+#include <assert.h>
 #include <signal.h>
 #include <pthread.h>
 #include <sys/epoll.h>
@@ -3136,4 +3137,149 @@ TEST(epoll59)
 	close(ctx.sfd[0]);
 }
 
+enum {
+	EPOLL60_EVENTS_NR = 10,
+};
+
+struct epoll60_ctx {
+	volatile int stopped;
+	int ready;
+	int waiters;
+	int epfd;
+	int evfd[EPOLL60_EVENTS_NR];
+};
+
+static void *epoll60_wait_thread(void *ctx_)
+{
+	struct epoll60_ctx *ctx = ctx_;
+	struct epoll_event e;
+	sigset_t sigmask;
+	uint64_t v;
+	int ret;
+
+	/* Block SIGUSR1 */
+	sigemptyset(&sigmask);
+	sigaddset(&sigmask, SIGUSR1);
+	sigprocmask(SIG_SETMASK, &sigmask, NULL);
+
+	/* Prepare empty mask for epoll_pwait() */
+	sigemptyset(&sigmask);
+
+	while (!ctx->stopped) {
+		/* Mark we are ready */
+		__atomic_fetch_add(&ctx->ready, 1, __ATOMIC_ACQUIRE);
+
+		/* Start when all are ready */
+		while (__atomic_load_n(&ctx->ready, __ATOMIC_ACQUIRE) &&
+		       !ctx->stopped);
+
+		/* Account this waiter */
+		__atomic_fetch_add(&ctx->waiters, 1, __ATOMIC_ACQUIRE);
+
+		ret = epoll_pwait(ctx->epfd, &e, 1, 2000, &sigmask);
+		if (ret != 1) {
+			/* We expect only signal delivery on stop */
+			assert(ret < 0 && errno == EINTR && "Lost wakeup!\n");
+			assert(ctx->stopped);
+			break;
+		}
+
+		ret = read(e.data.fd, &v, sizeof(v));
+		/* Since we are on ET mode, thus each thread gets its own fd. */
+		assert(ret == sizeof(v));
+
+		__atomic_fetch_sub(&ctx->waiters, 1, __ATOMIC_RELEASE);
+	}
+
+	return NULL;
+}
+
+static inline unsigned long long msecs(void)
+{
+	struct timespec ts;
+	unsigned long long msecs;
+
+	clock_gettime(CLOCK_REALTIME, &ts);
+	msecs = ts.tv_sec * 1000ull;
+	msecs += ts.tv_nsec / 1000000ull;
+
+	return msecs;
+}
+
+static inline int count_waiters(struct epoll60_ctx *ctx)
+{
+	return __atomic_load_n(&ctx->waiters, __ATOMIC_ACQUIRE);
+}
+
+TEST(epoll60)
+{
+	struct epoll60_ctx ctx = { 0 };
+	pthread_t waiters[ARRAY_SIZE(ctx.evfd)];
+	struct epoll_event e;
+	int i, n, ret;
+
+	signal(SIGUSR1, signal_handler);
+
+	ctx.epfd = epoll_create1(0);
+	ASSERT_GE(ctx.epfd, 0);
+
+	/* Create event fds */
+	for (i = 0; i < ARRAY_SIZE(ctx.evfd); i++) {
+		ctx.evfd[i] = eventfd(0, EFD_NONBLOCK);
+		ASSERT_GE(ctx.evfd[i], 0);
+
+		e.events = EPOLLIN | EPOLLET;
+		e.data.fd = ctx.evfd[i];
+		ASSERT_EQ(epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd[i], &e), 0);
+	}
+
+	/* Create waiter threads */
+	for (i = 0; i < ARRAY_SIZE(waiters); i++)
+		ASSERT_EQ(pthread_create(&waiters[i], NULL,
+					 epoll60_wait_thread, &ctx), 0);
+
+	for (i = 0; i < 300; i++) {
+		uint64_t v = 1, ms;
+
+		/* Wait for all to be ready */
+		while (__atomic_load_n(&ctx.ready, __ATOMIC_ACQUIRE) !=
+		       ARRAY_SIZE(ctx.evfd))
+			;
+
+		/* Steady, go */
+		__atomic_fetch_sub(&ctx.ready, ARRAY_SIZE(ctx.evfd),
+				   __ATOMIC_ACQUIRE);
+
+		/* Wait all have gone to kernel */
+		while (count_waiters(&ctx) != ARRAY_SIZE(ctx.evfd))
+			;
+
+		/* 1ms should be enough to schedule away */
+		usleep(1000);
+
+		/* Quickly signal all handles at once */
+		for (n = 0; n < ARRAY_SIZE(ctx.evfd); n++) {
+			ret = write(ctx.evfd[n], &v, sizeof(v));
+			ASSERT_EQ(ret, sizeof(v));
+		}
+
+		/* Busy loop for 1s and wait for all waiters to wake up */
+		ms = msecs();
+		while (count_waiters(&ctx) && msecs() < ms + 1000)
+			;
+
+		ASSERT_EQ(count_waiters(&ctx), 0);
+	}
+	ctx.stopped = 1;
+	/* Stop waiters */
+	for (i = 0; i < ARRAY_SIZE(waiters); i++)
+		ret = pthread_kill(waiters[i], SIGUSR1);
+	for (i = 0; i < ARRAY_SIZE(waiters); i++)
+		pthread_join(waiters[i], NULL);
+
+	for (i = 0; i < ARRAY_SIZE(waiters); i++)
+		close(ctx.evfd[i]);
+	close(ctx.epfd);
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config
index c2c8de4fafff..e59d985eeff0 100644
--- a/tools/testing/selftests/ftrace/config
+++ b/tools/testing/selftests/ftrace/config
@@ -11,5 +11,6 @@ CONFIG_PREEMPTIRQ_DELAY_TEST=m
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_SAMPLES=y
+CONFIG_SAMPLE_FTRACE_DIRECT=m
 CONFIG_SAMPLE_TRACE_PRINTK=m
 CONFIG_KALLSYMS_ALL=y
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 063ecb290a5a..a4605b5ee66d 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -17,6 +17,7 @@ echo "		-v|--verbose Increase verbosity of test messages"
 echo "		-vv        Alias of -v -v (Show all results in stdout)"
 echo "		-vvv       Alias of -v -v -v (Show all commands immediately)"
 echo "		--fail-unsupported Treat UNSUPPORTED as a failure"
+echo "		--fail-unresolved Treat UNRESOLVED as a failure"
 echo "		-d|--debug Debug mode (trace all shell commands)"
 echo "		-l|--logdir <dir> Save logs on the <dir>"
 echo "		            If <dir> is -, all logs output in console only"
@@ -29,8 +30,25 @@ err_ret=1
 # kselftest skip code is 4
 err_skip=4
 
+# cgroup RT scheduling prevents chrt commands from succeeding, which
+# induces failures in test wakeup tests.  Disable for the duration of
+# the tests.
+
+readonly sched_rt_runtime=/proc/sys/kernel/sched_rt_runtime_us
+
+sched_rt_runtime_orig=$(cat $sched_rt_runtime)
+
+setup() {
+  echo -1 > $sched_rt_runtime
+}
+
+cleanup() {
+  echo $sched_rt_runtime_orig > $sched_rt_runtime
+}
+
 errexit() { # message
   echo "Error: $1" 1>&2
+  cleanup
   exit $err_ret
 }
 
@@ -39,6 +57,8 @@ if [ `id -u` -ne 0 ]; then
   errexit "this must be run by root user"
 fi
 
+setup
+
 # Utilities
 absdir() { # file_path
   (cd `dirname $1`; pwd)
@@ -93,6 +113,10 @@ parse_opts() { # opts
       UNSUPPORTED_RESULT=1
       shift 1
     ;;
+    --fail-unresolved)
+      UNRESOLVED_RESULT=1
+      shift 1
+    ;;
     --logdir|-l)
       LOG_DIR=$2
       shift 2
@@ -157,6 +181,7 @@ KEEP_LOG=0
 DEBUG=0
 VERBOSE=0
 UNSUPPORTED_RESULT=0
+UNRESOLVED_RESULT=0
 STOP_FAILURE=0
 # Parse command-line options
 parse_opts $*
@@ -235,6 +260,7 @@ TOTAL_RESULT=0
 
 INSTANCE=
 CASENO=0
+
 testcase() { # testfile
   CASENO=$((CASENO+1))
   desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:`
@@ -260,7 +286,7 @@ eval_result() { # sigval
     $UNRESOLVED)
       prlog "	[${color_blue}UNRESOLVED${color_reset}]"
       UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO"
-      return 1 # this is a kind of bug.. something happened.
+      return $UNRESOLVED_RESULT # depends on use case
     ;;
     $UNTESTED)
       prlog "	[${color_blue}UNTESTED${color_reset}]"
@@ -273,7 +299,7 @@ eval_result() { # sigval
       return $UNSUPPORTED_RESULT # depends on use case
     ;;
     $XFAIL)
-      prlog "	[${color_red}XFAIL${color_reset}]"
+      prlog "	[${color_green}XFAIL${color_reset}]"
       XFAILED_CASES="$XFAILED_CASES $CASENO"
       return 0
     ;;
@@ -406,5 +432,7 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w`
 prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w`
 prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w`
 
+cleanup
+
 # if no error, return 0
 exit $TOTAL_RESULT
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
index aefab0c66d54..f59853857ad2 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc
@@ -10,10 +10,7 @@ if ! grep -q function_graph available_tracers; then
     exit_unsupported
 fi
 
-if [ ! -f set_ftrace_filter ]; then
-    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
-    exit_unsupported
-fi
+check_filter_file set_ftrace_filter
 
 do_reset() {
     if [ -e /proc/sys/kernel/stack_tracer_enabled ]; then
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
index c8a5209f2119..d610f47edd90 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc
@@ -9,6 +9,8 @@ if ! grep -q function_graph available_tracers; then
     exit_unsupported
 fi
 
+check_filter_file set_ftrace_filter
+
 fail() { # msg
     echo $1
     exit_fail
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
index f4e92afab14b..28936f434ee5 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc
@@ -9,6 +9,8 @@ if ! grep -q function available_tracers; then
     exit_unsupported
 fi
 
+check_filter_file set_ftrace_filter
+
 disable_tracing
 clear_trace
 
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
index 8aa46a2ea133..71db68a7975f 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
@@ -15,10 +15,7 @@ if [ ! -f set_ftrace_notrace_pid ]; then
     exit_unsupported
 fi
 
-if [ ! -f set_ftrace_filter ]; then
-    echo "set_ftrace_filter not found? Is function tracer not set?"
-    exit_unsupported
-fi
+check_filter_file set_ftrace_filter
 
 do_function_fork=1
 
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index f2ee1e889e13..d58403c4b7cd 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -16,10 +16,7 @@ if [ ! -f set_ftrace_pid ]; then
     exit_unsupported
 fi
 
-if [ ! -f set_ftrace_filter ]; then
-    echo "set_ftrace_filter not found? Is function tracer not set?"
-    exit_unsupported
-fi
+check_filter_file set_ftrace_filter
 
 do_function_fork=1
 
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
index 1a52f2883fe0..b2aff786c1a2 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
@@ -3,7 +3,7 @@
 # description: ftrace - stacktrace filter command
 # flags: instance
 
-[ ! -f set_ftrace_filter ] && exit_unsupported
+check_filter_file set_ftrace_filter
 
 echo _do_fork:stacktrace >> set_ftrace_filter
 
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
index ca2ffd7957f9..e9b1fd534e96 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc
@@ -11,10 +11,7 @@
 #
 
 # The triggers are set within the set_ftrace_filter file
-if [ ! -f set_ftrace_filter ]; then
-    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
-    exit_unsupported
-fi
+check_filter_file set_ftrace_filter
 
 do_reset() {
     reset_ftrace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
index 9330c873f9fe..1a4b4a442d33 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # description: ftrace - function trace on module
 
-[ ! -f set_ftrace_filter ] && exit_unsupported
+check_filter_file set_ftrace_filter
 
 : "mod: allows to filter a non exist function"
 echo 'non_exist_func:mod:non_exist_module' > set_ftrace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
index dfbae637c60c..a3dadb6b93b4 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc
@@ -18,10 +18,7 @@ if ! grep -q function_graph available_tracers; then
     exit_unsupported;
 fi
 
-if [ ! -f set_ftrace_filter ]; then
-    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
-    exit_unsupported
-fi
+check_filter_file set_ftrace_filter
 
 if [ ! -f function_profile_enabled ]; then
     echo "function_profile_enabled not found, function profiling enabled?"
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index 51f6e6146bd9..70bad441fa7d 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -10,10 +10,7 @@
 #
 
 # The triggers are set within the set_ftrace_filter file
-if [ ! -f set_ftrace_filter ]; then
-    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
-    exit_unsupported
-fi
+check_filter_file set_ftrace_filter
 
 fail() { # mesg
     echo $1
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
index b414f0e3c646..51e9e80bc0e6 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc
@@ -8,6 +8,8 @@ if [ ! -f stack_trace ]; then
   exit_unsupported
 fi
 
+check_filter_file stack_trace_filter
+
 echo > stack_trace_filter
 echo 0 > stack_max_size
 echo 1 > /proc/sys/kernel/stack_tracer_enabled
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
index 1947387fe976..3ed173f2944a 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc
@@ -11,10 +11,7 @@
 #
 
 # The triggers are set within the set_ftrace_filter file
-if [ ! -f set_ftrace_filter ]; then
-    echo "set_ftrace_filter not found? Is dynamic ftrace not set?"
-    exit_unsupported
-fi
+check_filter_file set_ftrace_filter
 
 fail() { # mesg
     echo $1
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index 5d4550591ff9..61a3c7e2634d 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -1,3 +1,9 @@
+check_filter_file() { # check filter file introduced by dynamic ftrace
+    if [ ! -f "$1" ]; then
+        echo "$1 not found? Is dynamic ftrace not set?"
+        exit_unsupported
+    fi
+}
 
 clear_trace() { # reset trace output
     echo > trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 1bcb67dcae26..81490ecaaa92 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -38,7 +38,7 @@ for width in 64 32 16 8; do
   echo 0 > events/kprobes/testprobe/enable
 
   : "Confirm the arguments is recorded in given types correctly"
-  ARGS=`grep "testprobe" trace | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
+  ARGS=`grep "testprobe" trace | head -n 1 | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'`
   check_types $ARGS $width
 
   : "Clear event for next loop"
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
index 7650a82db3f5..df5072815b87 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
@@ -5,6 +5,8 @@
 [ -f kprobe_events ] || exit_unsupported # this is configurable
 grep "function" available_tracers || exit_unsupported # this is configurable
 
+check_filter_file set_ftrace_filter
+
 # prepare
 echo nop > current_tracer
 echo _do_fork > set_ftrace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc
index cbd174334a48..2b82c80edf69 100644
--- a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc
+++ b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc
@@ -17,7 +17,14 @@ unsup() { #msg
     exit_unsupported
 }
 
-modprobe $MOD || unsup "$MOD module not available"
+unres() { #msg
+    reset_tracer
+    rmmod $MOD || true
+    echo $1
+    exit_unresolved
+}
+
+modprobe $MOD || unres "$MOD module not available"
 rmmod $MOD
 
 grep -q "preemptoff" available_tracers || unsup "preemptoff tracer not enabled"
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 0bb80619db58..32bdc978a711 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -1,13 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0
 
-MOUNT_CFLAGS := $(shell pkg-config --cflags mount 2>/dev/null)
-MOUNT_LDLIBS := $(shell pkg-config --libs mount 2>/dev/null)
-ifeq ($(MOUNT_LDLIBS),)
-MOUNT_LDLIBS := -lmount -I/usr/include/libmount
+VAR_CFLAGS := $(shell pkg-config --cflags mount 2>/dev/null)
+VAR_LDLIBS := $(shell pkg-config --libs mount 2>/dev/null)
+ifeq ($(VAR_LDLIBS),)
+VAR_LDLIBS := -lmount -I/usr/include/libmount
 endif
 
-CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ $(MOUNT_CFLAGS)
-LDLIBS += $(MOUNT_LDLIBS)
+CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ $(VAR_CFLAGS)
+LDLIBS += $(VAR_LDLIBS)
 
 TEST_PROGS := gpio-mockup.sh
 TEST_FILES := gpio-mockup-sysfs.sh
diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile
index 7340fd6a9a9f..39f0fa2a8fd6 100644
--- a/tools/testing/selftests/intel_pstate/Makefile
+++ b/tools/testing/selftests/intel_pstate/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE
-LDLIBS := $(LDLIBS) -lm
+LDLIBS += -lm
 
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index 4c156aeab6b8..5ec4d9e18806 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -137,7 +137,7 @@ int dump_queue(struct msgque_data *msgque)
 	for (kern_id = 0; kern_id < 256; kern_id++) {
 		ret = msgctl(kern_id, MSG_STAT, &ds);
 		if (ret < 0) {
-			if (errno == -EINVAL)
+			if (errno == EINVAL)
 				continue;
 			printf("Failed to get stats for IPC queue with id %d\n",
 					kern_id);
diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index e84d901f8567..676b3a8b114d 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -33,7 +33,7 @@ tap_timeout()
 {
 	# Make sure tests will time out if utility is available.
 	if [ -x /usr/bin/timeout ] ; then
-		/usr/bin/timeout "$kselftest_timeout" "$1"
+		/usr/bin/timeout --foreground "$kselftest_timeout" "$1"
 	else
 		"$1"
 	fi
diff --git a/tools/testing/selftests/kselftest_deps.sh b/tools/testing/selftests/kselftest_deps.sh
new file mode 100755
index 000000000000..bbc04646346b
--- /dev/null
+++ b/tools/testing/selftests/kselftest_deps.sh
@@ -0,0 +1,272 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# kselftest_deps.sh
+#
+# Checks for kselftest build dependencies on the build system.
+# Copyright (c) 2020 Shuah Khan <skhan@linuxfoundation.org>
+#
+#
+
+usage()
+{
+
+echo -e "Usage: $0 -[p] <compiler> [test_name]\n"
+echo -e "\tkselftest_deps.sh [-p] gcc"
+echo -e "\tkselftest_deps.sh [-p] gcc vm"
+echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc"
+echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc vm\n"
+echo "- Should be run in selftests directory in the kernel repo."
+echo "- Checks if Kselftests can be built/cross-built on a system."
+echo "- Parses all test/sub-test Makefile to find library dependencies."
+echo "- Runs compile test on a trivial C file with LDLIBS specified"
+echo "  in the test Makefiles to identify missing library dependencies."
+echo "- Prints suggested target list for a system filtering out tests"
+echo "  failed the build dependency check from the TARGETS in Selftests"
+echo "  main Makefile when optional -p is specified."
+echo "- Prints pass/fail dependency check for each tests/sub-test."
+echo "- Prints pass/fail targets and libraries."
+echo "- Default: runs dependency checks on all tests."
+echo "- Optional test name can be specified to check dependencies for it."
+exit 1
+
+}
+
+# Start main()
+main()
+{
+
+base_dir=`pwd`
+# Make sure we're in the selftests top-level directory.
+if [ $(basename "$base_dir") !=  "selftests" ]; then
+	echo -e "\tPlease run $0 in"
+	echo -e "\ttools/testing/selftests directory ..."
+	exit 1
+fi
+
+print_targets=0
+
+while getopts "p" arg; do
+    case $arg in
+        p)
+		print_targets=1
+	shift;;
+    esac
+done
+
+if [ $# -eq 0 ]
+then
+	usage
+fi
+
+# Compiler
+CC=$1
+
+tmp_file=$(mktemp).c
+trap "rm -f $tmp_file.o $tmp_file $tmp_file.bin" EXIT
+#echo $tmp_file
+
+pass=$(mktemp).out
+trap "rm -f $pass" EXIT
+#echo $pass
+
+fail=$(mktemp).out
+trap "rm -f $fail" EXIT
+#echo $fail
+
+# Generate tmp source fire for compile test
+cat << "EOF" > $tmp_file
+int main()
+{
+}
+EOF
+
+# Save results
+total_cnt=0
+fail_trgts=()
+fail_libs=()
+fail_cnt=0
+pass_trgts=()
+pass_libs=()
+pass_cnt=0
+
+# Get all TARGETS from selftests Makefile
+targets=$(egrep "^TARGETS +|^TARGETS =" Makefile | cut -d "=" -f2)
+
+# Single test case
+if [ $# -eq 2 ]
+then
+	test=$2/Makefile
+
+	l1_test $test
+	l2_test $test
+	l3_test $test
+
+	print_results $1 $2
+	exit $?
+fi
+
+# Level 1: LDLIBS set static.
+#
+# Find all LDLIBS set statically for all executables built by a Makefile
+# and filter out VAR_LDLIBS to discard the following:
+# 	gpio/Makefile:LDLIBS += $(VAR_LDLIBS)
+# Append space at the end of the list to append more tests.
+
+l1_tests=$(grep -r --include=Makefile "^LDLIBS" | \
+		grep -v "VAR_LDLIBS" | awk -F: '{print $1}')
+
+# Level 2: LDLIBS set dynamically.
+#
+# Level 2
+# Some tests have multiple valid LDLIBS lines for individual sub-tests
+# that need dependency checks. Find them and append them to the tests
+# e.g: vm/Makefile:$(OUTPUT)/userfaultfd: LDLIBS += -lpthread
+# Filter out VAR_LDLIBS to discard the following:
+# 	memfd/Makefile:$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS)
+# Append space at the end of the list to append more tests.
+
+l2_tests=$(grep -r --include=Makefile ": LDLIBS" | \
+		grep -v "VAR_LDLIBS" | awk -F: '{print $1}')
+
+# Level 3
+# gpio,  memfd and others use pkg-config to find mount and fuse libs
+# respectively and save it in VAR_LDLIBS. If pkg-config doesn't find
+# any, VAR_LDLIBS set to default.
+# Use the default value and filter out pkg-config for dependency check.
+# e.g:
+# gpio/Makefile
+#	VAR_LDLIBS := $(shell pkg-config --libs mount) 2>/dev/null)
+# memfd/Makefile
+#	VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null)
+
+l3_tests=$(grep -r --include=Makefile "^VAR_LDLIBS" | \
+		grep -v "pkg-config" | awk -F: '{print $1}')
+
+#echo $l1_tests
+#echo $l2_1_tests
+#echo $l3_tests
+
+all_tests
+print_results $1 $2
+
+exit $?
+}
+# end main()
+
+all_tests()
+{
+	for test in $l1_tests; do
+		l1_test $test
+	done
+
+	for test in $l2_tests; do
+		l2_test $test
+	done
+
+	for test in $l3_tests; do
+		l3_test $test
+	done
+}
+
+# Use same parsing used for l1_tests and pick libraries this time.
+l1_test()
+{
+	test_libs=$(grep --include=Makefile "^LDLIBS" $test | \
+			grep -v "VAR_LDLIBS" | \
+			sed -e 's/\:/ /' | \
+			sed -e 's/+/ /' | cut -d "=" -f 2)
+
+	check_libs $test $test_libs
+}
+
+# Use same parsing used for l2__tests and pick libraries this time.
+l2_test()
+{
+	test_libs=$(grep --include=Makefile ": LDLIBS" $test | \
+			grep -v "VAR_LDLIBS" | \
+			sed -e 's/\:/ /' | sed -e 's/+/ /' | \
+			cut -d "=" -f 2)
+
+	check_libs $test $test_libs
+}
+
+l3_test()
+{
+	test_libs=$(grep --include=Makefile "^VAR_LDLIBS" $test | \
+			grep -v "pkg-config" | sed -e 's/\:/ /' |
+			sed -e 's/+/ /' | cut -d "=" -f 2)
+
+	check_libs $test $test_libs
+}
+
+check_libs()
+{
+
+if [[ ! -z "${test_libs// }" ]]
+then
+
+	#echo $test_libs
+
+	for lib in $test_libs; do
+
+	let total_cnt+=1
+	$CC -o $tmp_file.bin $lib $tmp_file > /dev/null 2>&1
+	if [ $? -ne 0 ]; then
+		echo "FAIL: $test dependency check: $lib" >> $fail
+		let fail_cnt+=1
+		fail_libs+="$lib "
+		fail_target=$(echo "$test" | cut -d "/" -f1)
+		fail_trgts+="$fail_target "
+		targets=$(echo "$targets" | grep -v "$fail_target")
+	else
+		echo "PASS: $test dependency check passed $lib" >> $pass
+		let pass_cnt+=1
+		pass_libs+="$lib "
+		pass_trgts+="$(echo "$test" | cut -d "/" -f1) "
+	fi
+
+	done
+fi
+}
+
+print_results()
+{
+	echo -e "========================================================";
+	echo -e "Kselftest Dependency Check for [$0 $1 $2] results..."
+
+	if [ $print_targets -ne 0 ]
+	then
+	echo -e "Suggested Selftest Targets for your configuration:"
+	echo -e "$targets";
+	fi
+
+	echo -e "========================================================";
+	echo -e "Checked tests defining LDLIBS dependencies"
+	echo -e "--------------------------------------------------------";
+	echo -e "Total tests with Dependencies:"
+	echo -e "$total_cnt Pass: $pass_cnt Fail: $fail_cnt";
+
+	if [ $pass_cnt -ne 0 ]; then
+	echo -e "--------------------------------------------------------";
+	cat $pass
+	echo -e "--------------------------------------------------------";
+	echo -e "Targets passed build dependency check on system:"
+	echo -e "$(echo "$pass_trgts" | xargs -n1 | sort -u | xargs)"
+	fi
+
+	if [ $fail_cnt -ne 0 ]; then
+	echo -e "--------------------------------------------------------";
+	cat $fail
+	echo -e "--------------------------------------------------------";
+	echo -e "Targets failed build dependency check on system:"
+	echo -e "$(echo "$fail_trgts" | xargs -n1 | sort -u | xargs)"
+	echo -e "--------------------------------------------------------";
+	echo -e "Missing libraries system"
+	echo -e "$(echo "$fail_libs" | xargs -n1 | sort -u | xargs)"
+	fi
+
+	echo -e "--------------------------------------------------------";
+	echo -e "========================================================";
+}
+
+main "$@"
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 2902f6a78f8a..2bb8c81fc0b4 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -705,7 +705,7 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext)
 	/* Sanity check handler execution environment. */
 	if (!t) {
 		fprintf(TH_LOG_STREAM,
-			"no active test in SIGARLM handler!?\n");
+			"no active test in SIGALRM handler!?\n");
 		abort();
 	}
 	if (sig != SIGALRM || sig != info->si_signo) {
@@ -731,7 +731,7 @@ void __wait_for_test(struct __test_metadata *t)
 	if (sigaction(SIGALRM, &action, &saved_action)) {
 		t->passed = 0;
 		fprintf(TH_LOG_STREAM,
-			"%s: unable to install SIGARLM handler\n",
+			"%s: unable to install SIGALRM handler\n",
 			t->name);
 		return;
 	}
@@ -743,7 +743,7 @@ void __wait_for_test(struct __test_metadata *t)
 	if (sigaction(SIGALRM, &saved_action, NULL)) {
 		t->passed = 0;
 		fprintf(TH_LOG_STREAM,
-			"%s: unable to uninstall SIGARLM handler\n",
+			"%s: unable to uninstall SIGALRM handler\n",
 			t->name);
 		return;
 	}
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 712a2ddd2a27..42f4f49f2a48 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -5,8 +5,34 @@ all:
 
 top_srcdir = ../../../..
 KSFT_KHDR_INSTALL := 1
+
+# For cross-builds to work, UNAME_M has to map to ARCH and arch specific
+# directories and targets in this Makefile. "uname -m" doesn't map to
+# arch specific sub-directory names.
+#
+# UNAME_M variable to used to run the compiles pointing to the right arch
+# directories and build the right targets for these supported architectures.
+#
+# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable.
+# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable.
+#
+# x86_64 targets are named to include x86_64 as a suffix and directories
+# for includes are in x86_64 sub-directory. s390x and aarch64 follow the
+# same convention. "uname -m" doesn't result in the correct mapping for
+# s390x and aarch64.
+#
+# No change necessary for x86_64
 UNAME_M := $(shell uname -m)
 
+# Set UNAME_M for arm64 compile/install to work
+ifeq ($(ARCH),arm64)
+	UNAME_M := aarch64
+endif
+# Set UNAME_M s390x compile/install to work
+ifeq ($(ARCH),s390)
+	UNAME_M := s390x
+endif
+
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
 LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c
 LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
@@ -28,6 +54,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
+TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
 TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
@@ -53,7 +80,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M))
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
 LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
-LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include
+LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
 	-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
@@ -84,6 +111,7 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
 $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
 	$(AR) crs $@ $^
 
+x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
 all: $(STATIC_LIBS)
 $(TEST_GEN_PROGS): $(STATIC_LIBS)
 
diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h
index d8f4d6bfe05d..a034438b6266 100644
--- a/tools/testing/selftests/kvm/include/evmcs.h
+++ b/tools/testing/selftests/kvm/include/evmcs.h
@@ -219,8 +219,8 @@ struct hv_enlightened_vmcs {
 #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK	\
 		(~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
 
-struct hv_enlightened_vmcs *current_evmcs;
-struct hv_vp_assist_page *current_vp_assist;
+extern struct hv_enlightened_vmcs *current_evmcs;
+extern struct hv_vp_assist_page *current_vp_assist;
 
 int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id);
 
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index a99b875f50d2..92e184a422ee 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -143,6 +143,8 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
+			  struct kvm_guest_debug *debug);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);
 void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 8a3523d4434f..9622431069bc 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1201,6 +1201,15 @@ void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
 		    ret, errno);
 }
 
+void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
+			  struct kvm_guest_debug *debug)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int ret = ioctl(vcpu->fd, KVM_SET_GUEST_DEBUG, debug);
+
+	TEST_ASSERT(ret == 0, "KVM_SET_GUEST_DEBUG failed: %d", ret);
+}
+
 /*
  * VM VCPU Set MP State
  *
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 6f17f69394be..4ae104f6ce69 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -17,6 +17,9 @@
 
 bool enable_evmcs;
 
+struct hv_enlightened_vmcs *current_evmcs;
+struct hv_vp_assist_page *current_vp_assist;
+
 struct eptPageTableEntry {
 	uint64_t readable:1;
 	uint64_t writable:1;
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c
new file mode 100644
index 000000000000..8162c58a1234
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM guest debug register tests
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include <stdio.h>
+#include <string.h>
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+
+#define DR6_BD		(1 << 13)
+#define DR7_GD		(1 << 13)
+
+/* For testing data access debug BP */
+uint32_t guest_value;
+
+extern unsigned char sw_bp, hw_bp, write_data, ss_start, bd_start;
+
+static void guest_code(void)
+{
+	/*
+	 * Software BP tests.
+	 *
+	 * NOTE: sw_bp need to be before the cmd here, because int3 is an
+	 * exception rather than a normal trap for KVM_SET_GUEST_DEBUG (we
+	 * capture it using the vcpu exception bitmap).
+	 */
+	asm volatile("sw_bp: int3");
+
+	/* Hardware instruction BP test */
+	asm volatile("hw_bp: nop");
+
+	/* Hardware data BP test */
+	asm volatile("mov $1234,%%rax;\n\t"
+		     "mov %%rax,%0;\n\t write_data:"
+		     : "=m" (guest_value) : : "rax");
+
+	/* Single step test, covers 2 basic instructions and 2 emulated */
+	asm volatile("ss_start: "
+		     "xor %%rax,%%rax\n\t"
+		     "cpuid\n\t"
+		     "movl $0x1a0,%%ecx\n\t"
+		     "rdmsr\n\t"
+		     : : : "rax", "ecx");
+
+	/* DR6.BD test */
+	asm volatile("bd_start: mov %%dr0, %%rax" : : : "rax");
+	GUEST_DONE();
+}
+
+#define  CLEAR_DEBUG()  memset(&debug, 0, sizeof(debug))
+#define  APPLY_DEBUG()  vcpu_set_guest_debug(vm, VCPU_ID, &debug)
+#define  CAST_TO_RIP(v)  ((unsigned long long)&(v))
+#define  SET_RIP(v)  do {				\
+		vcpu_regs_get(vm, VCPU_ID, &regs);	\
+		regs.rip = (v);				\
+		vcpu_regs_set(vm, VCPU_ID, &regs);	\
+	} while (0)
+#define  MOVE_RIP(v)  SET_RIP(regs.rip + (v));
+
+int main(void)
+{
+	struct kvm_guest_debug debug;
+	unsigned long long target_dr6, target_rip;
+	struct kvm_regs regs;
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	uint64_t cmd;
+	int i;
+	/* Instruction lengths starting at ss_start */
+	int ss_size[4] = {
+		3,		/* xor */
+		2,		/* cpuid */
+		5,		/* mov */
+		2,		/* rdmsr */
+	};
+
+	if (!kvm_check_cap(KVM_CAP_SET_GUEST_DEBUG)) {
+		print_skip("KVM_CAP_SET_GUEST_DEBUG not supported");
+		return 0;
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+	run = vcpu_state(vm, VCPU_ID);
+
+	/* Test software BPs - int3 */
+	CLEAR_DEBUG();
+	debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP;
+	APPLY_DEBUG();
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+		    run->debug.arch.exception == BP_VECTOR &&
+		    run->debug.arch.pc == CAST_TO_RIP(sw_bp),
+		    "INT3: exit %d exception %d rip 0x%llx (should be 0x%llx)",
+		    run->exit_reason, run->debug.arch.exception,
+		    run->debug.arch.pc, CAST_TO_RIP(sw_bp));
+	MOVE_RIP(1);
+
+	/* Test instruction HW BP over DR[0-3] */
+	for (i = 0; i < 4; i++) {
+		CLEAR_DEBUG();
+		debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
+		debug.arch.debugreg[i] = CAST_TO_RIP(hw_bp);
+		debug.arch.debugreg[7] = 0x400 | (1UL << (2*i+1));
+		APPLY_DEBUG();
+		vcpu_run(vm, VCPU_ID);
+		target_dr6 = 0xffff0ff0 | (1UL << i);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+			    run->debug.arch.exception == DB_VECTOR &&
+			    run->debug.arch.pc == CAST_TO_RIP(hw_bp) &&
+			    run->debug.arch.dr6 == target_dr6,
+			    "INS_HW_BP (DR%d): exit %d exception %d rip 0x%llx "
+			    "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
+			    i, run->exit_reason, run->debug.arch.exception,
+			    run->debug.arch.pc, CAST_TO_RIP(hw_bp),
+			    run->debug.arch.dr6, target_dr6);
+	}
+	/* Skip "nop" */
+	MOVE_RIP(1);
+
+	/* Test data access HW BP over DR[0-3] */
+	for (i = 0; i < 4; i++) {
+		CLEAR_DEBUG();
+		debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
+		debug.arch.debugreg[i] = CAST_TO_RIP(guest_value);
+		debug.arch.debugreg[7] = 0x00000400 | (1UL << (2*i+1)) |
+		    (0x000d0000UL << (4*i));
+		APPLY_DEBUG();
+		vcpu_run(vm, VCPU_ID);
+		target_dr6 = 0xffff0ff0 | (1UL << i);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+			    run->debug.arch.exception == DB_VECTOR &&
+			    run->debug.arch.pc == CAST_TO_RIP(write_data) &&
+			    run->debug.arch.dr6 == target_dr6,
+			    "DATA_HW_BP (DR%d): exit %d exception %d rip 0x%llx "
+			    "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
+			    i, run->exit_reason, run->debug.arch.exception,
+			    run->debug.arch.pc, CAST_TO_RIP(write_data),
+			    run->debug.arch.dr6, target_dr6);
+		/* Rollback the 4-bytes "mov" */
+		MOVE_RIP(-7);
+	}
+	/* Skip the 4-bytes "mov" */
+	MOVE_RIP(7);
+
+	/* Test single step */
+	target_rip = CAST_TO_RIP(ss_start);
+	target_dr6 = 0xffff4ff0ULL;
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	for (i = 0; i < (sizeof(ss_size) / sizeof(ss_size[0])); i++) {
+		target_rip += ss_size[i];
+		CLEAR_DEBUG();
+		debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;
+		debug.arch.debugreg[7] = 0x00000400;
+		APPLY_DEBUG();
+		vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+			    run->debug.arch.exception == DB_VECTOR &&
+			    run->debug.arch.pc == target_rip &&
+			    run->debug.arch.dr6 == target_dr6,
+			    "SINGLE_STEP[%d]: exit %d exception %d rip 0x%llx "
+			    "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
+			    i, run->exit_reason, run->debug.arch.exception,
+			    run->debug.arch.pc, target_rip, run->debug.arch.dr6,
+			    target_dr6);
+	}
+
+	/* Finally test global disable */
+	CLEAR_DEBUG();
+	debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
+	debug.arch.debugreg[7] = 0x400 | DR7_GD;
+	APPLY_DEBUG();
+	vcpu_run(vm, VCPU_ID);
+	target_dr6 = 0xffff0ff0 | DR6_BD;
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
+		    run->debug.arch.exception == DB_VECTOR &&
+		    run->debug.arch.pc == CAST_TO_RIP(bd_start) &&
+		    run->debug.arch.dr6 == target_dr6,
+			    "DR7.GD: exit %d exception %d rip 0x%llx "
+			    "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
+			    run->exit_reason, run->debug.arch.exception,
+			    run->debug.arch.pc, target_rip, run->debug.arch.dr6,
+			    target_dr6);
+
+	/* Disable all debug controls, run to the end */
+	CLEAR_DEBUG();
+	APPLY_DEBUG();
+
+	vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "KVM_EXIT_IO");
+	cmd = get_ucall(vm, VCPU_ID, &uc);
+	TEST_ASSERT(cmd == UCALL_DONE, "UCALL_DONE");
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh
index dadf819148a4..ee64ff8df8f4 100755
--- a/tools/testing/selftests/lkdtm/run.sh
+++ b/tools/testing/selftests/lkdtm/run.sh
@@ -25,13 +25,13 @@ fi
 # Figure out which test to run from our script name.
 test=$(basename $0 .sh)
 # Look up details about the test from master list of LKDTM tests.
-line=$(egrep '^#?'"$test"'\b' tests.txt)
+line=$(grep -E '^#?'"$test"'\b' tests.txt)
 if [ -z "$line" ]; then
 	echo "Skipped: missing test '$test' in tests.txt"
 	exit $KSELFTEST_SKIP_TEST
 fi
 # Check that the test is known to LKDTM.
-if ! egrep -q '^'"$test"'$' "$TRIGGER" ; then
+if ! grep -E -q '^'"$test"'$' "$TRIGGER" ; then
 	echo "Skipped: test '$test' missing in $TRIGGER!"
 	exit $KSELFTEST_SKIP_TEST
 fi
@@ -59,30 +59,32 @@ if [ -z "$expect" ]; then
 	expect="call trace:"
 fi
 
-# Clear out dmesg for output reporting
-dmesg -c >/dev/null
-
 # Prepare log for report checking
-LOG=$(mktemp --tmpdir -t lkdtm-XXXXXX)
+LOG=$(mktemp --tmpdir -t lkdtm-log-XXXXXX)
+DMESG=$(mktemp --tmpdir -t lkdtm-dmesg-XXXXXX)
 cleanup() {
-	rm -f "$LOG"
+	rm -f "$LOG" "$DMESG"
 }
 trap cleanup EXIT
 
+# Save existing dmesg so we can detect new content below
+dmesg > "$DMESG"
+
 # Most shells yell about signals and we're expecting the "cat" process
 # to usually be killed by the kernel. So we have to run it in a sub-shell
 # and silence errors.
 ($SHELL -c 'cat <(echo '"$test"') >'"$TRIGGER" 2>/dev/null) || true
 
 # Record and dump the results
-dmesg -c >"$LOG"
+dmesg | diff --changed-group-format='%>' --unchanged-group-format='' "$DMESG" - > "$LOG" || true
+
 cat "$LOG"
 # Check for expected output
-if egrep -qi "$expect" "$LOG" ; then
+if grep -E -qi "$expect" "$LOG" ; then
 	echo "$test: saw '$expect': ok"
 	exit 0
 else
-	if egrep -qi XFAIL: "$LOG" ; then
+	if grep -E -qi XFAIL: "$LOG" ; then
 		echo "$test: saw 'XFAIL': [SKIP]"
 		exit $KSELFTEST_SKIP_TEST
 	else
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index 0a15f9e23431..4da8b565fa32 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -4,14 +4,25 @@ CFLAGS += -I../../../../include/uapi/
 CFLAGS += -I../../../../include/
 CFLAGS += -I../../../../usr/include/
 
-TEST_GEN_PROGS := memfd_test fuse_test fuse_mnt
+TEST_GEN_PROGS := memfd_test
 TEST_PROGS := run_fuse_test.sh run_hugetlbfs_test.sh
+TEST_GEN_FILES := fuse_test fuse_mnt
 
-fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags)
+VAR_CFLAGS := $(shell pkg-config fuse --cflags 2>/dev/null)
+ifeq ($(VAR_CFLAGS),)
+VAR_CFLAGS := -D_FILE_OFFSET_BITS=64 -I/usr/include/fuse
+endif
+
+VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null)
+ifeq ($(VAR_LDLIBS),)
+VAR_LDLIBS := -lfuse -pthread
+endif
+
+fuse_mnt.o: CFLAGS += $(VAR_CFLAGS)
 
 include ../lib.mk
 
-$(OUTPUT)/fuse_mnt: LDLIBS += $(shell pkg-config fuse --libs)
+$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS)
 
 $(OUTPUT)/memfd_test: memfd_test.c common.c
 $(OUTPUT)/fuse_test: fuse_test.c common.c
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 796670ebc65b..6560ed796ac4 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -749,6 +749,29 @@ ipv4_fcnal_runtime()
 	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
 	log_test $? 0 "Ping - multipath"
 
+	run_cmd "$IP ro delete 172.16.101.1/32 nhid 122"
+
+	#
+	# multiple default routes
+	# - tests fib_select_default
+	run_cmd "$IP nexthop add id 501 via 172.16.1.2 dev veth1"
+	run_cmd "$IP ro add default nhid 501"
+	run_cmd "$IP ro add default via 172.16.1.3 dev veth1 metric 20"
+	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+	log_test $? 0 "Ping - multiple default routes, nh first"
+
+	# flip the order
+	run_cmd "$IP ro del default nhid 501"
+	run_cmd "$IP ro del default via 172.16.1.3 dev veth1 metric 20"
+	run_cmd "$IP ro add default via 172.16.1.2 dev veth1 metric 20"
+	run_cmd "$IP nexthop replace id 501 via 172.16.1.3 dev veth1"
+	run_cmd "$IP ro add default nhid 501 metric 20"
+	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+	log_test $? 0 "Ping - multiple default routes, nh second"
+
+	run_cmd "$IP nexthop delete nhid 501"
+	run_cmd "$IP ro del default"
+
 	#
 	# IPv4 with blackhole nexthops
 	#
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index b7616704b55e..84205c3a55eb 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -618,16 +618,22 @@ fib_nexthop_test()
 
 fib_suppress_test()
 {
+	echo
+	echo "FIB rule with suppress_prefixlength"
+	setup
+
 	$IP link add dummy1 type dummy
 	$IP link set dummy1 up
 	$IP -6 route add default dev dummy1
 	$IP -6 rule add table main suppress_prefixlength 0
-	ping -f -c 1000 -W 1 1234::1 || true
+	ping -f -c 1000 -W 1 1234::1 >/dev/null 2>&1
 	$IP -6 rule del table main suppress_prefixlength 0
 	$IP link del dummy1
 
 	# If we got here without crashing, we're good.
-	return 0
+	log_test 0 0 "FIB rule suppress test"
+
+	cleanup
 }
 
 ################################################################################
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 9172746b6cf0..15f4f46ca3a9 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -30,7 +30,7 @@ ret=0
 
 cleanup()
 {
-	rm -f $out
+	rm -f $err
 	ip netns del $ns1
 }
 
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 35505b31e5cc..4555f88252ba 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -165,9 +165,10 @@ void *child_thread(void *arg)
 			socklen_t zc_len = sizeof(zc);
 			int res;
 
+			memset(&zc, 0, sizeof(zc));
 			zc.address = (__u64)((unsigned long)addr);
 			zc.length = chunk_size;
-			zc.recv_skip_hint = 0;
+
 			res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE,
 					 &zc, &zc_len);
 			if (res == -1)
@@ -281,12 +282,14 @@ static void setup_sockaddr(int domain, const char *str_addr,
 static void do_accept(int fdlisten)
 {
 	pthread_attr_t attr;
+	int rcvlowat;
 
 	pthread_attr_init(&attr);
 	pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
 
+	rcvlowat = chunk_size;
 	if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT,
-		       &chunk_size, sizeof(chunk_size)) == -1) {
+		       &rcvlowat, sizeof(rcvlowat)) == -1) {
 		perror("setsockopt SO_RCVLOWAT");
 	}
 
diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/nsfs/pidns.c
index e0d86e1668c0..e3c772c6a7c7 100644
--- a/tools/testing/selftests/nsfs/pidns.c
+++ b/tools/testing/selftests/nsfs/pidns.c
@@ -27,7 +27,7 @@
 #define __stack_aligned__	__attribute__((aligned(16)))
 struct cr_clone_arg {
 	char stack[128] __stack_aligned__;
-	char stack_ptr[0];
+	char stack_ptr[];
 };
 
 static int child(void *args)
diff --git a/tools/testing/selftests/pstore/pstore_tests b/tools/testing/selftests/pstore/pstore_tests
index 1cef54458aff..2aa9a3852a84 100755
--- a/tools/testing/selftests/pstore/pstore_tests
+++ b/tools/testing/selftests/pstore/pstore_tests
@@ -10,7 +10,7 @@
 . ./common_tests
 
 prlog -n "Checking pstore console is registered ... "
-dmesg | grep -q "console \[pstore"
+dmesg | grep -Eq "console \[(pstore|${backend})"
 show_result $?
 
 prlog -n "Checking /dev/pmsg0 exists ... "
diff --git a/tools/testing/selftests/rcutorture/bin/kcsan-collapse.sh b/tools/testing/selftests/rcutorture/bin/kcsan-collapse.sh
new file mode 100755
index 000000000000..e5cc6b2f195e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kcsan-collapse.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# If this was a KCSAN run, collapse the reports in the various console.log
+# files onto pairs of functions.
+#
+# Usage: kcsan-collapse.sh resultsdir
+#
+# Copyright (C) 2020 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+if test -z "$TORTURE_KCONFIG_KCSAN_ARG"
+then
+	exit 0
+fi
+cat $1/*/console.log |
+	grep "BUG: KCSAN: " |
+	sed -e 's/^\[[^]]*] //' |
+	sort |
+	uniq -c |
+	sort -k1nr > $1/kcsan.sum
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 9d9a41625dd9..1706cd4466b4 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -41,7 +41,21 @@ else
 		title="$title ($ngpsps/s)"
 	fi
 	echo $title $stopstate $fwdprog
-	nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
+	nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | \
+		awk -v sum=0 '
+		{
+			for (i = 0; i <= NF; i++) {
+				sum += $i;
+				if ($i ~ /Batch:/) {
+					sum = 0;
+					i = i + 2;
+				}
+			}
+		}
+
+		END {
+			print sum
+		}'`
 	if test -z "$nclosecalls"
 	then
 		exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 0326f4a5ff9c..736f04749b90 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -70,6 +70,15 @@ do
 			fi
 		fi
 	done
+	if test -f "$rd/kcsan.sum"
+	then
+		if test -s "$rd/kcsan.sum"
+		then
+			echo KCSAN summary in $rd/kcsan.sum
+		else
+			echo Clean KCSAN run in $rd
+		fi
+	fi
 done
 EDITOR=echo kvm-find-errors.sh "${@: -1}" > $T 2>&1
 ret=$?
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index e0352304b98b..6ff611c630d1 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -44,30 +44,32 @@ then
 fi
 echo ' ---' `date`: Starting build
 echo ' ---' Kconfig fragment at: $config_template >> $resdir/log
-touch $resdir/ConfigFragment.input $resdir/ConfigFragment
-if test -r "$config_dir/CFcommon"
-then
-	echo " --- $config_dir/CFcommon" >> $resdir/ConfigFragment.input
-	cat < $config_dir/CFcommon >> $resdir/ConfigFragment.input
-	config_override.sh $config_dir/CFcommon $config_template > $T/Kc1
-	grep '#CHECK#' $config_dir/CFcommon >> $resdir/ConfigFragment
-else
-	cp $config_template $T/Kc1
-fi
-echo " --- $config_template" >> $resdir/ConfigFragment.input
-cat $config_template >> $resdir/ConfigFragment.input
-grep '#CHECK#' $config_template >> $resdir/ConfigFragment
-if test -n "$TORTURE_KCONFIG_ARG"
-then
-	echo $TORTURE_KCONFIG_ARG | tr -s " " "\012" > $T/cmdline
-	echo " --- --kconfig argument" >> $resdir/ConfigFragment.input
-	cat $T/cmdline >> $resdir/ConfigFragment.input
-	config_override.sh $T/Kc1 $T/cmdline > $T/Kc2
-	# Note that "#CHECK#" is not permitted on commandline.
-else
-	cp $T/Kc1 $T/Kc2
-fi
-cat $T/Kc2 >> $resdir/ConfigFragment
+touch $resdir/ConfigFragment.input
+
+# Combine additional Kconfig options into an existing set such that
+# newer options win.  The first argument is the Kconfig source ID, the
+# second the to-be-updated file within $T, and the third and final the
+# list of additional Kconfig options.  Note that a $2.tmp file is
+# created when doing the update.
+config_override_param () {
+	if test -n "$3"
+	then
+		echo $3 | sed -e 's/^ *//' -e 's/ *$//' | tr -s " " "\012" > $T/Kconfig_args
+		echo " --- $1" >> $resdir/ConfigFragment.input
+		cat $T/Kconfig_args >> $resdir/ConfigFragment.input
+		config_override.sh $T/$2 $T/Kconfig_args > $T/$2.tmp
+		mv $T/$2.tmp $T/$2
+		# Note that "#CHECK#" is not permitted on commandline.
+	fi
+}
+
+echo > $T/KcList
+config_override_param "$config_dir/CFcommon" KcList "`cat $config_dir/CFcommon 2> /dev/null`"
+config_override_param "$config_template" KcList "`cat $config_template 2> /dev/null`"
+config_override_param "--kasan options" KcList "$TORTURE_KCONFIG_KASAN_ARG"
+config_override_param "--kcsan options" KcList "$TORTURE_KCONFIG_KCSAN_ARG"
+config_override_param "--kconfig argument" KcList "$TORTURE_KCONFIG_ARG"
+cp $T/KcList $resdir/ConfigFragment
 
 base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'`
 if test "$base_resdir" != "$resdir" -a -f $base_resdir/bzImage -a -f $base_resdir/vmlinux
@@ -80,7 +82,7 @@ then
 	ln -s $base_resdir/.config $resdir  # for kvm-recheck.sh
 	# Arch-independent indicator
 	touch $resdir/builtkernel
-elif kvm-build.sh $T/Kc2 $resdir
+elif kvm-build.sh $T/KcList $resdir
 then
 	# Had to build a kernel for this test.
 	QEMU="`identify_qemu vmlinux`"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 2315e2ec12d6..c279cf9cb010 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -31,6 +31,8 @@ TORTURE_DEFCONFIG=defconfig
 TORTURE_BOOT_IMAGE=""
 TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
 TORTURE_KCONFIG_ARG=""
+TORTURE_KCONFIG_KASAN_ARG=""
+TORTURE_KCONFIG_KCSAN_ARG=""
 TORTURE_KMAKE_ARG=""
 TORTURE_QEMU_MEM=512
 TORTURE_SHUTDOWN_GRACE=180
@@ -133,6 +135,12 @@ do
 		TORTURE_KCONFIG_ARG="$2"
 		shift
 		;;
+	--kasan)
+		TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
+		;;
+	--kcsan)
+		TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_KCSAN_INTERRUPT_WATCHER=y"; export TORTURE_KCONFIG_KCSAN_ARG
+		;;
 	--kmake-arg)
 		checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
 		TORTURE_KMAKE_ARG="$2"
@@ -310,6 +318,8 @@ TORTURE_BUILDONLY="$TORTURE_BUILDONLY"; export TORTURE_BUILDONLY
 TORTURE_DEFCONFIG="$TORTURE_DEFCONFIG"; export TORTURE_DEFCONFIG
 TORTURE_INITRD="$TORTURE_INITRD"; export TORTURE_INITRD
 TORTURE_KCONFIG_ARG="$TORTURE_KCONFIG_ARG"; export TORTURE_KCONFIG_ARG
+TORTURE_KCONFIG_KASAN_ARG="$TORTURE_KCONFIG_KASAN_ARG"; export TORTURE_KCONFIG_KASAN_ARG
+TORTURE_KCONFIG_KCSAN_ARG="$TORTURE_KCONFIG_KCSAN_ARG"; export TORTURE_KCONFIG_KCSAN_ARG
 TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG
 TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD
 TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE
@@ -464,6 +474,7 @@ echo
 echo
 echo " --- `date` Test summary:"
 echo Results directory: $resdir/$ds
+kcsan-collapse.sh $resdir/$ds
 kvm-recheck.sh $resdir/$ds
 ___EOF___
 
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
index c3c1fb5a9e1f..f2b20db9e296 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
@@ -14,3 +14,6 @@ TINY02
 TASKS01
 TASKS02
 TASKS03
+RUDE01
+TRACE01
+TRACE02
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
new file mode 100644
index 000000000000..bafe94cbd739
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
@@ -0,0 +1,10 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+#CHECK#CONFIG_PROVE_RCU=y
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01.boot
new file mode 100644
index 000000000000..9363708c9075
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks-rude
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
new file mode 100644
index 000000000000..12e7661b86f5
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
@@ -0,0 +1,11 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+#CHECK#CONFIG_PROVE_RCU=y
+CONFIG_TASKS_TRACE_RCU_READ_MB=y
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot
new file mode 100644
index 000000000000..9675ad632dcc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks-tracing
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
new file mode 100644
index 000000000000..b69ed6673c41
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
@@ -0,0 +1,11 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_LOCKING=n
+#CHECK#CONFIG_PROVE_RCU=n
+CONFIG_TASKS_TRACE_RCU_READ_MB=n
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot
new file mode 100644
index 000000000000..9675ad632dcc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks-tracing
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
index 2debe7891aeb..7311f84a5876 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
@@ -1,5 +1,5 @@
 CONFIG_SMP=y
-CONFIG_NR_CPUS=100
+CONFIG_NR_CPUS=56
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 89fb3e0b552e..c0aa46ce14f6 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -2803,12 +2803,13 @@ TEST(syscall_restart)
 			 offsetof(struct seccomp_data, nr)),
 
 #ifdef __NR_sigreturn
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_sigreturn, 6, 0),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_sigreturn, 7, 0),
 #endif
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 5, 0),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit, 4, 0),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_rt_sigreturn, 3, 0),
-		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_nanosleep, 4, 0),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 6, 0),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit, 5, 0),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_rt_sigreturn, 4, 0),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_nanosleep, 5, 0),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_clock_nanosleep, 4, 0),
 		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_restart_syscall, 4, 0),
 
 		/* Allow __NR_write for easy logging. */
@@ -2895,7 +2896,8 @@ TEST(syscall_restart)
 	ASSERT_EQ(PTRACE_EVENT_SECCOMP, (status >> 16));
 	ASSERT_EQ(0, ptrace(PTRACE_GETEVENTMSG, child_pid, NULL, &msg));
 	ASSERT_EQ(0x100, msg);
-	EXPECT_EQ(__NR_nanosleep, get_syscall(_metadata, child_pid));
+	ret = get_syscall(_metadata, child_pid);
+	EXPECT_TRUE(ret == __NR_nanosleep || ret == __NR_clock_nanosleep);
 
 	/* Might as well check siginfo for sanity while we're here. */
 	ASSERT_EQ(0, ptrace(PTRACE_GETSIGINFO, child_pid, NULL, &info));
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
new file mode 100644
index 000000000000..1cda2e11b3ad
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
@@ -0,0 +1,21 @@
+[
+    {
+        "id": "83be",
+        "name": "Create FQ-PIE with invalid number of flows",
+        "category": [
+            "qdisc",
+            "fq_pie"
+        ],
+        "setup": [
+            "$IP link add dev $DUMMY type dummy || /bin/true"
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY root fq_pie flows 65536",
+        "expExitCode": "2",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc",
+        "matchCount": "0",
+        "teardown": [
+            "$IP link del dev $DUMMY"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index e566c70e64a1..a3e43189d940 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -713,9 +713,8 @@ def set_operation_mode(pm, parser, args, remaining):
         exit(0)
 
     if args.list:
-        if args.list:
-            list_test_cases(alltests)
-            exit(0)
+        list_test_cases(alltests)
+        exit(0)
 
     if len(alltests):
         req_plugins = pm.get_required_plugins(alltests)
diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh
index b630c7b5950a..8155c2ea7ccb 100755
--- a/tools/testing/selftests/tpm2/test_smoke.sh
+++ b/tools/testing/selftests/tpm2/test_smoke.sh
@@ -1,17 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
-self.flags = flags
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-
-if [ -f /dev/tpm0 ] ; then
-	python -m unittest -v tpm2_tests.SmokeTest
-	python -m unittest -v tpm2_tests.AsyncTest
-else
-	exit $ksft_skip
-fi
+python -m unittest -v tpm2_tests.SmokeTest
+python -m unittest -v tpm2_tests.AsyncTest
 
 CLEAR_CMD=$(which tpm2_clear)
 if [ -n $CLEAR_CMD ]; then
diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh
index 180b469c53b4..a6f5e346635e 100755
--- a/tools/testing/selftests/tpm2/test_space.sh
+++ b/tools/testing/selftests/tpm2/test_space.sh
@@ -1,11 +1,4 @@
 #!/bin/bash
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-if [ -f /dev/tpmrm0 ] ; then
-	python -m unittest -v tpm2_tests.SpaceTest
-else
-	exit $ksft_skip
-fi
+python -m unittest -v tpm2_tests.SpaceTest
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 0edb6d900e8d..ca17fe0c3280 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -6,6 +6,7 @@ map_populate
 thuge-gen
 compaction_test
 mlock2-tests
+mremap_dontunmap
 on-fault-limit
 transhuge-stress
 userfaultfd
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d31db052dff6..6998877f707e 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for vm selftests
 uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
+MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
 
 CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
 LDLIBS = -lrt
@@ -20,7 +20,7 @@ TEST_GEN_FILES += thuge-gen
 TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += userfaultfd
 
-ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64))
+ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64))
 TEST_GEN_FILES += va_128TBswitch
 TEST_GEN_FILES += virtual_address_range
 TEST_GEN_FILES += write_to_hugetlbfs
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 665009ebfba4..76ca5e7a3951 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -59,7 +59,7 @@ else
 fi
 
 #filter 64bit architectures
-ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64"
+ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64"
 if [ -z $ARCH ]; then
   ARCH=`uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/'`
 fi
diff --git a/tools/testing/selftests/vm/write_to_hugetlbfs.c b/tools/testing/selftests/vm/write_to_hugetlbfs.c
index 110bc4e4015d..6a2caba19ee1 100644
--- a/tools/testing/selftests/vm/write_to_hugetlbfs.c
+++ b/tools/testing/selftests/vm/write_to_hugetlbfs.c
@@ -74,8 +74,6 @@ int main(int argc, char **argv)
 	int write = 0;
 	int reserve = 1;
 
-	unsigned long i;
-
 	if (signal(SIGINT, sig_handler) == SIG_ERR)
 		err(1, "\ncan't catch SIGINT\n");
 
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 936e1ca9410e..17a1f53ceba0 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -48,8 +48,11 @@ cleanup() {
 	exec 2>/dev/null
 	printf "$orig_message_cost" > /proc/sys/net/core/message_cost
 	ip0 link del dev wg0
+	ip0 link del dev wg1
 	ip1 link del dev wg0
+	ip1 link del dev wg1
 	ip2 link del dev wg0
+	ip2 link del dev wg1
 	local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)"
 	[[ -n $to_kill ]] && kill $to_kill
 	pp ip netns del $netns1
@@ -77,18 +80,20 @@ ip0 link set wg0 netns $netns2
 key1="$(pp wg genkey)"
 key2="$(pp wg genkey)"
 key3="$(pp wg genkey)"
+key4="$(pp wg genkey)"
 pub1="$(pp wg pubkey <<<"$key1")"
 pub2="$(pp wg pubkey <<<"$key2")"
 pub3="$(pp wg pubkey <<<"$key3")"
+pub4="$(pp wg pubkey <<<"$key4")"
 psk="$(pp wg genpsk)"
 [[ -n $key1 && -n $key2 && -n $psk ]]
 
 configure_peers() {
 	ip1 addr add 192.168.241.1/24 dev wg0
-	ip1 addr add fd00::1/24 dev wg0
+	ip1 addr add fd00::1/112 dev wg0
 
 	ip2 addr add 192.168.241.2/24 dev wg0
-	ip2 addr add fd00::2/24 dev wg0
+	ip2 addr add fd00::2/112 dev wg0
 
 	n1 wg set wg0 \
 		private-key <(echo "$key1") \
@@ -230,9 +235,38 @@ n1 ping -W 1 -c 1 192.168.241.2
 n1 wg set wg0 private-key <(echo "$key3")
 n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove
 n1 ping -W 1 -c 1 192.168.241.2
+n2 wg set wg0 peer "$pub3" remove
+
+# Test that we can route wg through wg
+ip1 addr flush dev wg0
+ip2 addr flush dev wg0
+ip1 addr add fd00::5:1/112 dev wg0
+ip2 addr add fd00::5:2/112 dev wg0
+n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips fd00::5:2/128 endpoint 127.0.0.1:2
+n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips fd00::5:1/128 endpoint 127.212.121.99:9998
+ip1 link add wg1 type wireguard
+ip2 link add wg1 type wireguard
+ip1 addr add 192.168.241.1/24 dev wg1
+ip1 addr add fd00::1/112 dev wg1
+ip2 addr add 192.168.241.2/24 dev wg1
+ip2 addr add fd00::2/112 dev wg1
+ip1 link set mtu 1340 up dev wg1
+ip2 link set mtu 1340 up dev wg1
+n1 wg set wg1 listen-port 5 private-key <(echo "$key3") peer "$pub4" allowed-ips 192.168.241.2/32,fd00::2/128 endpoint [fd00::5:2]:5
+n2 wg set wg1 listen-port 5 private-key <(echo "$key4") peer "$pub3" allowed-ips 192.168.241.1/32,fd00::1/128 endpoint [fd00::5:1]:5
+tests
+# Try to set up a routing loop between the two namespaces
+ip1 link set netns $netns0 dev wg1
+ip0 addr add 192.168.241.1/24 dev wg1
+ip0 link set up dev wg1
+n0 ping -W 1 -c 1 192.168.241.2
+n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7
+ip2 link del wg0
+ip2 link del wg1
+! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel
 
+ip0 link del wg1
 ip1 link del wg0
-ip2 link del wg0
 
 # Test using NAT. We now change the topology to this:
 # ┌────────────────────────────────────────┐    ┌────────────────────────────────────────────────┐     ┌────────────────────────────────────────┐
@@ -282,6 +316,20 @@ pp sleep 3
 n2 ping -W 1 -c 1 192.168.241.1
 n1 wg set wg0 peer "$pub2" persistent-keepalive 0
 
+# Test that onion routing works, even when it loops
+n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
+ip1 addr add 192.168.242.1/24 dev wg0
+ip2 link add wg1 type wireguard
+ip2 addr add 192.168.242.2/24 dev wg1
+n2 wg set wg1 private-key <(echo "$key3") listen-port 5 peer "$pub1" allowed-ips 192.168.242.1/32
+ip2 link set wg1 up
+n1 ping -W 1 -c 1 192.168.242.2
+ip2 link del wg1
+n1 wg set wg0 peer "$pub3" endpoint 192.168.242.2:5
+! n1 ping -W 1 -c 1 192.168.242.2 || false # Should not crash kernel
+n1 wg set wg0 peer "$pub3" remove
+ip1 addr del 192.168.242.1/24 dev wg0
+
 # Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs.
 ip1 -6 addr add fc00::9/96 dev vethc
 ip1 -6 route add default via fc00::1
diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile
index 90598a425c18..4bdd6c1a19d3 100644
--- a/tools/testing/selftests/wireguard/qemu/Makefile
+++ b/tools/testing/selftests/wireguard/qemu/Makefile
@@ -44,7 +44,7 @@ endef
 $(eval $(call tar_download,MUSL,musl,1.2.0,.tar.gz,https://musl.libc.org/releases/,c6de7b191139142d3f9a7b5b702c9cae1b5ee6e7f57e582da9328629408fd4e8))
 $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
 $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
-$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
+$(eval $(call tar_download,IPROUTE2,iproute2,5.6.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,1b5b0e25ce6e23da7526ea1da044e814ad85ba761b10dd29c2b027c056b04692))
 $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
 $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
 $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
index 990c510a9cfa..f52f1e2bc7f6 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
@@ -10,3 +10,4 @@ CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="console=hvc0 wg.success=hvc1"
 CONFIG_SECTION_MISMATCH_WARN_ONLY=y
 CONFIG_FRAME_WARN=1280
+CONFIG_THREAD_SHIFT=14
diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index 5909e7ef2a5c..b50c2085c1ac 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -25,7 +25,6 @@ CONFIG_KASAN=y
 CONFIG_KASAN_INLINE=y
 CONFIG_UBSAN=y
 CONFIG_UBSAN_SANITIZE_ALL=y
-CONFIG_UBSAN_NO_ALIGNMENT=y
 CONFIG_UBSAN_NULL=y
 CONFIG_DEBUG_KMEMLEAK=y
 CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192
@@ -58,7 +57,6 @@ CONFIG_RCU_EQS_DEBUG=y
 CONFIG_USER_STACKTRACE_SUPPORT=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_DOUBLEFAULT=y
 CONFIG_X86_DEBUG_FPU=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_DEBUG_PAGEALLOC=y
diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile
index f33f32f1d208..b587b9a7a124 100644
--- a/tools/virtio/Makefile
+++ b/tools/virtio/Makefile
@@ -4,7 +4,7 @@ test: virtio_test vringh_test
 virtio_test: virtio_ring.o virtio_test.o
 vringh_test: vringh_test.o vringh.o virtio_ring.o
 
-CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE
+CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h
 vpath %.c ../../drivers/virtio ../../drivers/vhost
 mod:
 	${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test V=${V}
@@ -22,7 +22,8 @@ OOT_CONFIGS=\
 	CONFIG_VHOST=m \
 	CONFIG_VHOST_NET=n \
 	CONFIG_VHOST_SCSI=n \
-	CONFIG_VHOST_VSOCK=n
+	CONFIG_VHOST_VSOCK=n \
+	CONFIG_VHOST_RING=n
 OOT_BUILD=KCFLAGS="-I "${OOT_VHOST} ${MAKE} -C ${OOT_KSRC} V=${V}
 oot-build:
 	echo "UNSUPPORTED! Don't use the resulting modules in production!"
diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h
index d0351f83aebe..04d563fc9b95 100644
--- a/tools/virtio/asm/barrier.h
+++ b/tools/virtio/asm/barrier.h
@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
 #if defined(__i386__) || defined(__x86_64__)
 #define barrier() asm volatile("" ::: "memory")
 #define virt_mb() __sync_synchronize()
diff --git a/tools/virtio/generated/autoconf.h b/tools/virtio/generated/autoconf.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/virtio/generated/autoconf.h
diff --git a/tools/virtio/linux/compiler.h b/tools/virtio/linux/compiler.h
index 903dc9c4bd11..2c51bccb97bb 100644
--- a/tools/virtio/linux/compiler.h
+++ b/tools/virtio/linux/compiler.h
@@ -7,4 +7,5 @@
 
 #define READ_ONCE(var) (*((volatile typeof(var) *)(&(var))))
 
+#define __aligned(x) __attribute((__aligned__(x)))
 #endif
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 20f6cf04377f..9860622cbb15 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for vm tools
 #
+include ../scripts/Makefile.include
+
 TARGETS=page-types slabinfo page_owner_sort
 
 LIB_DIR = ../lib/api
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 48d0ec44ad77..53b3ba9173ba 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -1387,9 +1387,7 @@ static inline void hyp_cpu_pm_exit(void)
 
 static int init_common_resources(void)
 {
-	kvm_set_ipa_limit();
-
-	return 0;
+	return kvm_set_ipa_limit();
 }
 
 static int init_subsystems(void)
diff --git a/virt/kvm/arm/hyp/aarch32.c b/virt/kvm/arm/hyp/aarch32.c
index d31f267961e7..25c0e47d57cb 100644
--- a/virt/kvm/arm/hyp/aarch32.c
+++ b/virt/kvm/arm/hyp/aarch32.c
@@ -125,12 +125,16 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
  */
 void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
+	u32 pc = *vcpu_pc(vcpu);
 	bool is_thumb;
 
 	is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT);
 	if (is_thumb && !is_wide_instr)
-		*vcpu_pc(vcpu) += 2;
+		pc += 2;
 	else
-		*vcpu_pc(vcpu) += 4;
+		pc += 4;
+
+	*vcpu_pc(vcpu) = pc;
+
 	kvm_adjust_itstate(vcpu);
 }
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index 14a162e295a9..ae364716ee40 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -186,6 +186,33 @@ static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
 	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
 }
 
+static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu)
+{
+	int i;
+
+	/*
+	 * Zero the input registers' upper 32 bits. They will be fully
+	 * zeroed on exit, so we're fine changing them in place.
+	 */
+	for (i = 1; i < 4; i++)
+		vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i)));
+}
+
+static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn)
+{
+	switch(fn) {
+	case PSCI_0_2_FN64_CPU_SUSPEND:
+	case PSCI_0_2_FN64_CPU_ON:
+	case PSCI_0_2_FN64_AFFINITY_INFO:
+		/* Disallow these functions for 32bit guests */
+		if (vcpu_mode_is_32bit(vcpu))
+			return PSCI_RET_NOT_SUPPORTED;
+		break;
+	}
+
+	return 0;
+}
+
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -193,6 +220,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 	unsigned long val;
 	int ret = 1;
 
+	val = kvm_psci_check_allowed_function(vcpu, psci_fn);
+	if (val)
+		goto out;
+
 	switch (psci_fn) {
 	case PSCI_0_2_FN_PSCI_VERSION:
 		/*
@@ -210,12 +241,16 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		val = PSCI_RET_SUCCESS;
 		break;
 	case PSCI_0_2_FN_CPU_ON:
+		kvm_psci_narrow_to_32bit(vcpu);
+		fallthrough;
 	case PSCI_0_2_FN64_CPU_ON:
 		mutex_lock(&kvm->lock);
 		val = kvm_psci_vcpu_on(vcpu);
 		mutex_unlock(&kvm->lock);
 		break;
 	case PSCI_0_2_FN_AFFINITY_INFO:
+		kvm_psci_narrow_to_32bit(vcpu);
+		fallthrough;
 	case PSCI_0_2_FN64_AFFINITY_INFO:
 		val = kvm_psci_vcpu_affinity_info(vcpu);
 		break;
@@ -256,6 +291,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		break;
 	}
 
+out:
 	smccc_set_retval(vcpu, val, 0, 0, 0);
 	return ret;
 }
@@ -273,6 +309,10 @@ static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu)
 		break;
 	case PSCI_1_0_FN_PSCI_FEATURES:
 		feature = smccc_get_arg1(vcpu);
+		val = kvm_psci_check_allowed_function(vcpu, feature);
+		if (val)
+			break;
+
 		switch(feature) {
 		case PSCI_0_2_FN_PSCI_VERSION:
 		case PSCI_0_2_FN_CPU_SUSPEND:
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index a963b9d766b7..32e32d67a127 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -294,8 +294,15 @@ int vgic_init(struct kvm *kvm)
 		}
 	}
 
-	if (vgic_has_its(kvm)) {
+	if (vgic_has_its(kvm))
 		vgic_lpi_translation_cache_init(kvm);
+
+	/*
+	 * If we have GICv4.1 enabled, unconditionnaly request enable the
+	 * v4 support so that we get HW-accelerated vSGIs. Otherwise, only
+	 * enable it if we present a virtual ITS to the guest.
+	 */
+	if (vgic_supports_direct_msis(kvm)) {
 		ret = vgic_v4_init(kvm);
 		if (ret)
 			goto out;
@@ -348,6 +355,12 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
+	/*
+	 * Retire all pending LPIs on this vcpu anyway as we're
+	 * going to destroy it.
+	 */
+	vgic_flush_pending_lpis(vcpu);
+
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
 }
 
@@ -359,10 +372,10 @@ static void __kvm_vgic_destroy(struct kvm *kvm)
 
 	vgic_debug_destroy(kvm);
 
-	kvm_vgic_dist_destroy(kvm);
-
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_vgic_vcpu_destroy(vcpu);
+
+	kvm_vgic_dist_destroy(kvm);
 }
 
 void kvm_vgic_destroy(struct kvm *kvm)
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index d53d34a33e35..c012a52b19f5 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -96,14 +96,21 @@ out_unlock:
 	 * We "cache" the configuration table entries in our struct vgic_irq's.
 	 * However we only have those structs for mapped IRQs, so we read in
 	 * the respective config data from memory here upon mapping the LPI.
+	 *
+	 * Should any of these fail, behave as if we couldn't create the LPI
+	 * by dropping the refcount and returning the error.
 	 */
 	ret = update_lpi_config(kvm, irq, NULL, false);
-	if (ret)
+	if (ret) {
+		vgic_put_irq(kvm, irq);
 		return ERR_PTR(ret);
+	}
 
 	ret = vgic_v3_lpi_sync_pending_status(kvm, irq);
-	if (ret)
+	if (ret) {
+		vgic_put_irq(kvm, irq);
 		return ERR_PTR(ret);
+	}
 
 	return irq;
 }
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c
index 5945f062d749..a016f07adc28 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v2.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c
@@ -409,24 +409,28 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = {
 		NULL, vgic_mmio_uaccess_write_v2_group, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_SET,
-		vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1,
+		vgic_mmio_read_enable, vgic_mmio_write_senable,
+		NULL, vgic_uaccess_write_senable, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_CLEAR,
-		vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1,
+		vgic_mmio_read_enable, vgic_mmio_write_cenable,
+		NULL, vgic_uaccess_write_cenable, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET,
-		vgic_mmio_read_pending, vgic_mmio_write_spending, NULL, NULL, 1,
+		vgic_mmio_read_pending, vgic_mmio_write_spending,
+		NULL, vgic_uaccess_write_spending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR,
-		vgic_mmio_read_pending, vgic_mmio_write_cpending, NULL, NULL, 1,
+		vgic_mmio_read_pending, vgic_mmio_write_cpending,
+		NULL, vgic_uaccess_write_cpending, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET,
 		vgic_mmio_read_active, vgic_mmio_write_sactive,
-		NULL, vgic_mmio_uaccess_write_sactive, 1,
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR,
 		vgic_mmio_read_active, vgic_mmio_write_cactive,
-		NULL, vgic_mmio_uaccess_write_cactive, 1,
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI,
 		vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL,
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index 859464fd413f..d2339a2b9fb9 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -50,7 +50,8 @@ bool vgic_has_its(struct kvm *kvm)
 
 bool vgic_supports_direct_msis(struct kvm *kvm)
 {
-	return kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm);
+	return (kvm_vgic_global_state.has_gicv4_1 ||
+		(kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm)));
 }
 
 /*
@@ -538,10 +539,12 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = {
 		vgic_mmio_read_group, vgic_mmio_write_group, NULL, NULL, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER,
-		vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1,
+		vgic_mmio_read_enable, vgic_mmio_write_senable,
+		NULL, vgic_uaccess_write_senable, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER,
-		vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1,
+		vgic_mmio_read_enable, vgic_mmio_write_cenable,
+	       NULL, vgic_uaccess_write_cenable, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR,
 		vgic_mmio_read_pending, vgic_mmio_write_spending,
@@ -553,11 +556,11 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER,
 		vgic_mmio_read_active, vgic_mmio_write_sactive,
-		NULL, vgic_mmio_uaccess_write_sactive, 1,
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER,
 		vgic_mmio_read_active, vgic_mmio_write_cactive,
-		NULL, vgic_mmio_uaccess_write_cactive,
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive,
 		1, VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR,
 		vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL,
@@ -609,11 +612,13 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = {
 	REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0,
 		vgic_mmio_read_group, vgic_mmio_write_group, 4,
 		VGIC_ACCESS_32bit),
-	REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ISENABLER0,
-		vgic_mmio_read_enable, vgic_mmio_write_senable, 4,
+	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISENABLER0,
+		vgic_mmio_read_enable, vgic_mmio_write_senable,
+		NULL, vgic_uaccess_write_senable, 4,
 		VGIC_ACCESS_32bit),
-	REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICENABLER0,
-		vgic_mmio_read_enable, vgic_mmio_write_cenable, 4,
+	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICENABLER0,
+		vgic_mmio_read_enable, vgic_mmio_write_cenable,
+		NULL, vgic_uaccess_write_cenable, 4,
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0,
 		vgic_mmio_read_pending, vgic_mmio_write_spending,
@@ -625,12 +630,12 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = {
 		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0,
 		vgic_mmio_read_active, vgic_mmio_write_sactive,
-		NULL, vgic_mmio_uaccess_write_sactive,
-		4, VGIC_ACCESS_32bit),
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4,
+		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0,
 		vgic_mmio_read_active, vgic_mmio_write_cactive,
-		NULL, vgic_mmio_uaccess_write_cactive,
-		4, VGIC_ACCESS_32bit),
+		vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4,
+		VGIC_ACCESS_32bit),
 	REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0,
 		vgic_mmio_read_priority, vgic_mmio_write_priority, 32,
 		VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 2199302597fa..b2d73fc0d1ef 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -184,6 +184,48 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu,
 	}
 }
 
+int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu,
+			       gpa_t addr, unsigned int len,
+			       unsigned long val)
+{
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+	int i;
+	unsigned long flags;
+
+	for_each_set_bit(i, &val, len * 8) {
+		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+		irq->enabled = true;
+		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
+
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+
+	return 0;
+}
+
+int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
+			       gpa_t addr, unsigned int len,
+			       unsigned long val)
+{
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+	int i;
+	unsigned long flags;
+
+	for_each_set_bit(i, &val, len * 8) {
+		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+		irq->enabled = false;
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+
+	return 0;
+}
+
 unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 				     gpa_t addr, unsigned int len)
 {
@@ -219,17 +261,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 	return value;
 }
 
-/* Must be called with irq->irq_lock held */
-static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
-				 bool is_uaccess)
-{
-	if (is_uaccess)
-		return;
-
-	irq->pending_latch = true;
-	vgic_irq_set_phys_active(irq, true);
-}
-
 static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 {
 	return (vgic_irq_is_sgi(irq->intid) &&
@@ -240,7 +271,6 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val)
 {
-	bool is_uaccess = !kvm_get_running_vcpu();
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
 	unsigned long flags;
@@ -270,22 +300,48 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 			continue;
 		}
 
+		irq->pending_latch = true;
 		if (irq->hw)
-			vgic_hw_irq_spending(vcpu, irq, is_uaccess);
-		else
-			irq->pending_latch = true;
+			vgic_irq_set_phys_active(irq, true);
+
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
 		vgic_put_irq(vcpu->kvm, irq);
 	}
 }
 
-/* Must be called with irq->irq_lock held */
-static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
-				 bool is_uaccess)
+int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu,
+				gpa_t addr, unsigned int len,
+				unsigned long val)
 {
-	if (is_uaccess)
-		return;
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+	int i;
+	unsigned long flags;
+
+	for_each_set_bit(i, &val, len * 8) {
+		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+		irq->pending_latch = true;
 
+		/*
+		 * GICv2 SGIs are terribly broken. We can't restore
+		 * the source of the interrupt, so just pick the vcpu
+		 * itself as the source...
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source |= BIT(vcpu->vcpu_id);
+
+		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
+
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+
+	return 0;
+}
+
+/* Must be called with irq->irq_lock held */
+static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
+{
 	irq->pending_latch = false;
 
 	/*
@@ -308,7 +364,6 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val)
 {
-	bool is_uaccess = !kvm_get_running_vcpu();
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
 	unsigned long flags;
@@ -339,7 +394,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 		}
 
 		if (irq->hw)
-			vgic_hw_irq_cpending(vcpu, irq, is_uaccess);
+			vgic_hw_irq_cpending(vcpu, irq);
 		else
 			irq->pending_latch = false;
 
@@ -348,8 +403,68 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 	}
 }
 
-unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
-				    gpa_t addr, unsigned int len)
+int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu,
+				gpa_t addr, unsigned int len,
+				unsigned long val)
+{
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+	int i;
+	unsigned long flags;
+
+	for_each_set_bit(i, &val, len * 8) {
+		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+
+		raw_spin_lock_irqsave(&irq->irq_lock, flags);
+		/*
+		 * More fun with GICv2 SGIs! If we're clearing one of them
+		 * from userspace, which source vcpu to clear? Let's not
+		 * even think of it, and blow the whole set.
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source = 0;
+
+		irq->pending_latch = false;
+
+		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+
+	return 0;
+}
+
+/*
+ * If we are fiddling with an IRQ's active state, we have to make sure the IRQ
+ * is not queued on some running VCPU's LRs, because then the change to the
+ * active state can be overwritten when the VCPU's state is synced coming back
+ * from the guest.
+ *
+ * For shared interrupts as well as GICv3 private interrupts, we have to
+ * stop all the VCPUs because interrupts can be migrated while we don't hold
+ * the IRQ locks and we don't want to be chasing moving targets.
+ *
+ * For GICv2 private interrupts we don't have to do anything because
+ * userspace accesses to the VGIC state already require all VCPUs to be
+ * stopped, and only the VCPU itself can modify its private interrupts
+ * active state, which guarantees that the VCPU is not running.
+ */
+static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid)
+{
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
+	    intid >= VGIC_NR_PRIVATE_IRQS)
+		kvm_arm_halt_guest(vcpu->kvm);
+}
+
+/* See vgic_access_active_prepare */
+static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid)
+{
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
+	    intid >= VGIC_NR_PRIVATE_IRQS)
+		kvm_arm_resume_guest(vcpu->kvm);
+}
+
+static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu,
+					     gpa_t addr, unsigned int len)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	u32 value = 0;
@@ -359,6 +474,10 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 	for (i = 0; i < len * 8; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
+		/*
+		 * Even for HW interrupts, don't evaluate the HW state as
+		 * all the guest is interested in is the virtual state.
+		 */
 		if (irq->active)
 			value |= (1U << i);
 
@@ -368,6 +487,29 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 	return value;
 }
 
+unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
+				    gpa_t addr, unsigned int len)
+{
+	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
+	u32 val;
+
+	mutex_lock(&vcpu->kvm->lock);
+	vgic_access_active_prepare(vcpu, intid);
+
+	val = __vgic_mmio_read_active(vcpu, addr, len);
+
+	vgic_access_active_finish(vcpu, intid);
+	mutex_unlock(&vcpu->kvm->lock);
+
+	return val;
+}
+
+unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu,
+				    gpa_t addr, unsigned int len)
+{
+	return __vgic_mmio_read_active(vcpu, addr, len);
+}
+
 /* Must be called with irq->irq_lock held */
 static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 				      bool active, bool is_uaccess)
@@ -426,36 +568,6 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 }
 
-/*
- * If we are fiddling with an IRQ's active state, we have to make sure the IRQ
- * is not queued on some running VCPU's LRs, because then the change to the
- * active state can be overwritten when the VCPU's state is synced coming back
- * from the guest.
- *
- * For shared interrupts, we have to stop all the VCPUs because interrupts can
- * be migrated while we don't hold the IRQ locks and we don't want to be
- * chasing moving targets.
- *
- * For private interrupts we don't have to do anything because userspace
- * accesses to the VGIC state already require all VCPUs to be stopped, and
- * only the VCPU itself can modify its private interrupts active state, which
- * guarantees that the VCPU is not running.
- */
-static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid)
-{
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
-	    intid > VGIC_NR_PRIVATE_IRQS)
-		kvm_arm_halt_guest(vcpu->kvm);
-}
-
-/* See vgic_change_active_prepare */
-static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid)
-{
-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
-	    intid > VGIC_NR_PRIVATE_IRQS)
-		kvm_arm_resume_guest(vcpu->kvm);
-}
-
 static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
 				      gpa_t addr, unsigned int len,
 				      unsigned long val)
@@ -477,11 +589,11 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 
 	mutex_lock(&vcpu->kvm->lock);
-	vgic_change_active_prepare(vcpu, intid);
+	vgic_access_active_prepare(vcpu, intid);
 
 	__vgic_mmio_write_cactive(vcpu, addr, len, val);
 
-	vgic_change_active_finish(vcpu, intid);
+	vgic_access_active_finish(vcpu, intid);
 	mutex_unlock(&vcpu->kvm->lock);
 }
 
@@ -514,11 +626,11 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 
 	mutex_lock(&vcpu->kvm->lock);
-	vgic_change_active_prepare(vcpu, intid);
+	vgic_access_active_prepare(vcpu, intid);
 
 	__vgic_mmio_write_sactive(vcpu, addr, len, val);
 
-	vgic_change_active_finish(vcpu, intid);
+	vgic_access_active_finish(vcpu, intid);
 	mutex_unlock(&vcpu->kvm->lock);
 }
 
diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h
index 5af2aefad435..fefcca2b14dc 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.h
+++ b/virt/kvm/arm/vgic/vgic-mmio.h
@@ -138,6 +138,14 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu,
 			     gpa_t addr, unsigned int len,
 			     unsigned long val);
 
+int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu,
+			       gpa_t addr, unsigned int len,
+			       unsigned long val);
+
+int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
+			       gpa_t addr, unsigned int len,
+			       unsigned long val);
+
 unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 				     gpa_t addr, unsigned int len);
 
@@ -149,9 +157,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val);
 
+int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu,
+				gpa_t addr, unsigned int len,
+				unsigned long val);
+
+int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu,
+				gpa_t addr, unsigned int len,
+				unsigned long val);
+
 unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
 				    gpa_t addr, unsigned int len);
 
+unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu,
+				    gpa_t addr, unsigned int len);
+
 void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
 			     gpa_t addr, unsigned int len,
 			     unsigned long val);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 74bdb7bf3295..731c1e517716 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -259,6 +259,7 @@ static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait)
 }
 
 bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
+				 struct kvm_vcpu *except,
 				 unsigned long *vcpu_bitmap, cpumask_var_t tmp)
 {
 	int i, cpu, me;
@@ -268,7 +269,8 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 	me = get_cpu();
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
+		if ((vcpu_bitmap && !test_bit(i, vcpu_bitmap)) ||
+		    vcpu == except)
 			continue;
 
 		kvm_make_request(req, vcpu);
@@ -288,19 +290,25 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 	return called;
 }
 
-bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
+bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
+				      struct kvm_vcpu *except)
 {
 	cpumask_var_t cpus;
 	bool called;
 
 	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
 
-	called = kvm_make_vcpus_request_mask(kvm, req, NULL, cpus);
+	called = kvm_make_vcpus_request_mask(kvm, req, except, NULL, cpus);
 
 	free_cpumask_var(cpus);
 	return called;
 }
 
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
+{
+	return kvm_make_all_cpus_request_except(kvm, req, NULL);
+}
+
 #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {